1
|
Stefano A. Challenges and limitations in applying radiomics to PET imaging: Possible opportunities and avenues for research. Comput Biol Med 2024; 179:108827. [PMID: 38964244 DOI: 10.1016/j.compbiomed.2024.108827] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2024] [Revised: 06/05/2024] [Accepted: 06/29/2024] [Indexed: 07/06/2024]
Abstract
Radiomics, the high-throughput extraction of quantitative imaging features from medical images, holds immense potential for advancing precision medicine in oncology and beyond. While radiomics applied to positron emission tomography (PET) imaging offers unique insights into tumor biology and treatment response, it is imperative to elucidate the challenges and constraints inherent in this domain to facilitate their translation into clinical practice. This review examines the challenges and limitations of applying radiomics to PET imaging, synthesizing findings from the last five years (2019-2023) and highlights the significance of addressing these challenges to realize the full clinical potential of radiomics in oncology and molecular imaging. A comprehensive search was conducted across multiple electronic databases, including PubMed, Scopus, and Web of Science, using keywords relevant to radiomics issues in PET imaging. Only studies published in peer-reviewed journals were eligible for inclusion in this review. Although many studies have highlighted the potential of radiomics in predicting treatment response, assessing tumor heterogeneity, enabling risk stratification, and personalized therapy selection, various challenges regarding the practical implementation of the proposed models still need to be addressed. This review illustrates the challenges and limitations of radiomics in PET imaging across various cancer types, encompassing both phantom and clinical investigations. The analyzed studies highlight the importance of reproducible segmentation methods, standardized pre-processing and post-processing methodologies, and the need to create large multicenter studies registered in a centralized database to promote the continuous validation and clinical integration of radiomics into PET imaging.
Collapse
Affiliation(s)
- Alessandro Stefano
- Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), Cefalù, Italy.
| |
Collapse
|
2
|
Da-Ano R, Andrade-Miranda G, Tankyevych O, Visvikis D, Conze PH, Rest CCL. Automated PD-L1 status prediction in lung cancer with multi-modal PET/CT fusion. Sci Rep 2024; 14:16720. [PMID: 39030240 PMCID: PMC11271510 DOI: 10.1038/s41598-024-66487-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2024] [Accepted: 07/01/2024] [Indexed: 07/21/2024] Open
Abstract
Programmed death-ligand 1 (PD-L1) expressions play a crucial role in guiding therapeutic interventions such as the use of tyrosine kinase inhibitors (TKIs) and immune checkpoint inhibitors (ICIs) in lung cancer. Conventional determination of PD-L1 status includes careful surgical or biopsied tumor specimens. These specimens are gathered through invasive procedures, representing a risk of difficulties and potential challenges in getting reliable and representative tissue samples. Using a single center cohort of 189 patients, our objective was to evaluate various fusion methods that used non-invasive computed tomography (CT) and18 F-FDG positron emission tomography (PET) images as inputs to various deep learning models to automatically predict PD-L1 in non-small cell lung cancer (NSCLC). We compared three different architectures (ResNet, DenseNet, and EfficientNet) and considered different input data (CT only, PET only, PET/CT early fusion, PET/CT late fusion without as well as with partially and fully shared weights to determine the best model performance. Models were assessed utilizing areas under the receiver operating characteristic curves (AUCs) considering their 95% confidence intervals (CI). The fusion of PET and CT images as input yielded better performance for PD-L1 classification. The different data fusion schemes systematically outperformed their individual counterparts when used as input of the various deep models. Furthermore, early fusion consistently outperformed late fusion, probably as a result of its capacity to capture more complicated patterns by merging PET and CT derived content at a lower level. When we looked more closely at the effects of weight sharing in late fusion architectures, we discovered that while it might boost model stability, it did not always result in better results. This suggests that although weight sharing could be beneficial when modality parameters are similar, the anatomical and metabolic information provided by CT and PET scans are too dissimilar to consistently lead to improved PD-L1 status predictions.
Collapse
Affiliation(s)
- Ronrick Da-Ano
- LaTIM, UMR 1101, Inserm, University of Brest, Brest, France
| | | | - Olena Tankyevych
- LaTIM, UMR 1101, Inserm, University of Brest, Brest, France
- Nuclear Medicine, University of Poitiers, Poitiers, France
| | | | - Pierre-Henri Conze
- LaTIM, UMR 1101, Inserm, University of Brest, Brest, France
- IMT Atlantique, Brest, France
| | - Catherine Cheze Le Rest
- LaTIM, UMR 1101, Inserm, University of Brest, Brest, France
- Nuclear Medicine, University of Poitiers, Poitiers, France
| |
Collapse
|
3
|
Jang SI, Pan T, Li Y, Heidari P, Chen J, Li Q, Gong K. Spach Transformer: Spatial and Channel-Wise Transformer Based on Local and Global Self-Attentions for PET Image Denoising. IEEE TRANSACTIONS ON MEDICAL IMAGING 2024; 43:2036-2049. [PMID: 37995174 PMCID: PMC11111593 DOI: 10.1109/tmi.2023.3336237] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/25/2023]
Abstract
Position emission tomography (PET) is widely used in clinics and research due to its quantitative merits and high sensitivity, but suffers from low signal-to-noise ratio (SNR). Recently convolutional neural networks (CNNs) have been widely used to improve PET image quality. Though successful and efficient in local feature extraction, CNN cannot capture long-range dependencies well due to its limited receptive field. Global multi-head self-attention (MSA) is a popular approach to capture long-range information. However, the calculation of global MSA for 3D images has high computational costs. In this work, we proposed an efficient spatial and channel-wise encoder-decoder transformer, Spach Transformer, that can leverage spatial and channel information based on local and global MSAs. Experiments based on datasets of different PET tracers, i.e., 18F-FDG, 18F-ACBC, 18F-DCFPyL, and 68Ga-DOTATATE, were conducted to evaluate the proposed framework. Quantitative results show that the proposed Spach Transformer framework outperforms state-of-the-art deep learning architectures.
Collapse
|
4
|
Xu K, Kang H. A Review of Machine Learning Approaches for Brain Positron Emission Tomography Data Analysis. Nucl Med Mol Imaging 2024; 58:203-212. [PMID: 38932757 PMCID: PMC11196571 DOI: 10.1007/s13139-024-00845-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2023] [Revised: 01/19/2024] [Accepted: 01/25/2024] [Indexed: 06/28/2024] Open
Abstract
Positron emission tomography (PET) imaging has moved forward the development of medical diagnostics and research across various domains, including cardiology, neurology, infection detection, and oncology. The integration of machine learning (ML) algorithms into PET data analysis has further enhanced their capabilities of including disease diagnosis and classification, image segmentation, and quantitative analysis. ML algorithms empower researchers and clinicians to extract valuable insights from complex big PET datasets, which enabling automated pattern recognition, predictive health outcome modeling, and more efficient data analysis. This review explains the basic knowledge of PET imaging, statistical methods for PET image analysis, and challenges of PET data analysis. We also discussed the improvement of analysis capabilities by combining PET data with machine learning algorithms and the application of this combination in various aspects of PET image research. This review also highlights current trends and future directions in PET imaging, emphasizing the driving and critical role of machine learning and big PET image data analytics in improving diagnostic accuracy and personalized medical approaches. Integration between PET imaging will shape the future of medical diagnosis and research.
Collapse
Affiliation(s)
- Ke Xu
- Department of Biostatistics, Vanderbilt University Medical Center, 2525 West End Avenue, Suite 1100, Nashville, TN 37203 USA
| | - Hakmook Kang
- Department of Biostatistics, Vanderbilt University Medical Center, 2525 West End Avenue, Suite 1100, Nashville, TN 37203 USA
| |
Collapse
|
5
|
Schaefer-Schuler A, Burgard C, Blickle A, Maus S, Petrescu C, Petto S, Bartholomä M, Stemler T, Ezziddin S, Rosar F. [ 161Tb]Tb-PSMA-617 radioligand therapy in patients with mCRPC: preliminary dosimetry results and intra-individual head-to-head comparison to [ 177Lu]Lu-PSMA-617. Theranostics 2024; 14:1829-1840. [PMID: 38505615 PMCID: PMC10945337 DOI: 10.7150/thno.92273] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2023] [Accepted: 01/19/2024] [Indexed: 03/21/2024] Open
Abstract
Rationale: Evaluation of alternative radionuclides for use in prostate-specific membrane antigen (PSMA)-targeted radioligand therapy (RLT) is currently focusing on 161Tb, which may provide advantages by emitting additional Auger and conversion electrons. In this pilot study, we present preliminary dosimetry data for [161Tb]Tb-PSMA-617 RLT in a direct comparison with [177Lu]Lu-PSMA-617. Method: Six patients with metastatic castration-resistant prostate cancer (mCRPC) underwent treatment with [177Lu]Lu-PSMA-617 and subsequently - after inadequate response - with [161Tb]Tb-PSMA-617. Whole-body planar and SPECT imaging-based dosimetry of organs at risk (kidneys and salivary glands) and tumor lesions were calculated using IDAC for 177Lu and OLINDA/EXM for 161Tb. The therapeutic index (TI) of mean tumor-absorbed doses over relevant organs at risk was calculated. Results: Mean absorbed doses to organs at risk of PSMA-RLT were slightly higher for [161Tb]Tb-PSMA-617 compared to [177Lu]Lu-PSMA-617 (kidneys: 0.643 ± 0.247 vs. 0.545 ± 0.231 Gy/GBq, factor 1.18; parotid gland: 0.367 ± 0.198 vs. 0.329 ± 0.180 Gy/GBq, factor 1.10), but markedly higher regarding tumor lesions (6.10 ± 6.59 vs 2.59 ± 3.30 Gy/GBq, factor 2.40, p < 0.001). Consequently, the mean TI was higher for [161Tb]Tb-PSMA-617 compared to [177Lu]Lu-PSMA-617 for both, the kidneys (11.54 ± 9.74 vs. 5.28 ± 5.13, p = 0.002) and the parotid gland (16.77 ± 13.10 vs. 12.51 ± 18.09, p = 0.008). Conclusion: In this intra-individual head-to-head pilot study, [161Tb]Tb-PSMA-617 delivered higher tumor-absorbed doses and resulted in superior TI compared to [177Lu]Lu-PSMA-617. This preliminary data support 161Tb as a promising radionuclide for PSMA-RLT in mCRPC.
Collapse
Affiliation(s)
| | | | | | | | | | | | | | | | | | - Florian Rosar
- Department of Nuclear Medicine, Saarland University, Medical Center, Homburg, Germany
| |
Collapse
|
6
|
Maino C, Vernuccio F, Cannella R, Franco PN, Giannini V, Dezio M, Pisani AR, Blandino AA, Faletti R, De Bernardi E, Ippolito D, Gatti M, Inchingolo R. Radiomics and liver: Where we are and where we are headed? Eur J Radiol 2024; 171:111297. [PMID: 38237517 DOI: 10.1016/j.ejrad.2024.111297] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2023] [Revised: 01/03/2024] [Accepted: 01/07/2024] [Indexed: 02/10/2024]
Abstract
Hepatic diffuse conditions and focal liver lesions represent two of the most common scenarios to face in everyday radiological clinical practice. Thanks to the advances in technology, radiology has gained a central role in the management of patients with liver disease, especially due to its high sensitivity and specificity. Since the introduction of computed tomography (CT) and magnetic resonance imaging (MRI), radiology has been considered the non-invasive reference modality to assess and characterize liver pathologies. In recent years, clinical practice has moved forward to a quantitative approach to better evaluate and manage each patient with a more fitted approach. In this setting, radiomics has gained an important role in helping radiologists and clinicians characterize hepatic pathological entities, in managing patients, and in determining prognosis. Radiomics can extract a large amount of data from radiological images, which can be associated with different liver scenarios. Thanks to its wide applications in ultrasonography (US), CT, and MRI, different studies were focused on specific aspects related to liver diseases. Even if broadly applied, radiomics has some advantages and different pitfalls. This review aims to summarize the most important and robust studies published in the field of liver radiomics, underlying their main limitations and issues, and what they can add to the current and future clinical practice and literature.
Collapse
Affiliation(s)
- Cesare Maino
- Department of Radiology, Fondazione IRCCS San Gerardo dei Tintori, Monza 20900, Italy.
| | - Federica Vernuccio
- Institute of Radiology, University Hospital of Padova, Padova 35128, Italy
| | - Roberto Cannella
- Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo 90127, Italy
| | - Paolo Niccolò Franco
- Department of Radiology, Fondazione IRCCS San Gerardo dei Tintori, Monza 20900, Italy
| | - Valentina Giannini
- Department of Surgical Sciences, University of Turin, Turin 10126, Italy
| | - Michele Dezio
- Department of Radiology, Miulli Hospital, Acquaviva delle Fonti 70021, Bari, Italy
| | - Antonio Rosario Pisani
- Nuclear Medicine Unit, Interdisciplinary Department of Medicine, University of Bari, Bari 70121, Italy
| | - Antonino Andrea Blandino
- Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo 90127, Italy
| | - Riccardo Faletti
- Department of Surgical Sciences, University of Turin, Turin 10126, Italy
| | - Elisabetta De Bernardi
- Bicocca Bioinformatics Biostatistics and Bioimaging Centre - B4, University of Milano Bicocca, Milano 20100, Italy; School of Medicine, University of Milano Bicocca, Milano 20100, Italy
| | - Davide Ippolito
- Department of Radiology, Fondazione IRCCS San Gerardo dei Tintori, Monza 20900, Italy; School of Medicine, University of Milano Bicocca, Milano 20100, Italy
| | - Marco Gatti
- Department of Surgical Sciences, University of Turin, Turin 10126, Italy
| | - Riccardo Inchingolo
- Unit of Interventional Radiology, F. Miulli Hospital, Acquaviva delle Fonti 70021, Italy
| |
Collapse
|
7
|
Andrearczyk V, Oreiller V, Boughdad S, Le Rest CC, Tankyevych O, Elhalawani H, Jreige M, Prior JO, Vallières M, Visvikis D, Hatt M, Depeursinge A. Automatic Head and Neck Tumor segmentation and outcome prediction relying on FDG-PET/CT images: Findings from the second edition of the HECKTOR challenge. Med Image Anal 2023; 90:102972. [PMID: 37742374 DOI: 10.1016/j.media.2023.102972] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2022] [Revised: 07/27/2023] [Accepted: 09/14/2023] [Indexed: 09/26/2023]
Abstract
By focusing on metabolic and morphological tissue properties respectively, FluoroDeoxyGlucose (FDG)-Positron Emission Tomography (PET) and Computed Tomography (CT) modalities include complementary and synergistic information for cancerous lesion delineation and characterization (e.g. for outcome prediction), in addition to usual clinical variables. This is especially true in Head and Neck Cancer (HNC). The goal of the HEad and neCK TumOR segmentation and outcome prediction (HECKTOR) challenge was to develop and compare modern image analysis methods to best extract and leverage this information automatically. We present here the post-analysis of HECKTOR 2nd edition, at the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2021. The scope of the challenge was substantially expanded compared to the first edition, by providing a larger population (adding patients from a new clinical center) and proposing an additional task to the challengers, namely the prediction of Progression-Free Survival (PFS). To this end, the participants were given access to a training set of 224 cases from 5 different centers, each with a pre-treatment FDG-PET/CT scan and clinical variables. Their methods were subsequently evaluated on a held-out test set of 101 cases from two centers. For the segmentation task (Task 1), the ranking was based on a Borda counting of their ranks according to two metrics: mean Dice Similarity Coefficient (DSC) and median Hausdorff Distance at 95th percentile (HD95). For the PFS prediction task, challengers could use the tumor contours provided by experts (Task 3) or rely on their own (Task 2). The ranking was obtained according to the Concordance index (C-index) calculated on the predicted risk scores. A total of 103 teams registered for the challenge, for a total of 448 submissions and 29 papers. The best method in the segmentation task obtained an average DSC of 0.759, and the best predictions of PFS obtained a C-index of 0.717 (without relying on the provided contours) and 0.698 (using the expert contours). An interesting finding was that best PFS predictions were reached by relying on DL approaches (with or without explicit tumor segmentation, 4 out of the 5 best ranked) compared to standard radiomics methods using handcrafted features extracted from delineated tumors, and by exploiting alternative tumor contours (automated and/or larger volumes encompassing surrounding tissues) rather than relying on the expert contours. This second edition of the challenge confirmed the promising performance of fully automated primary tumor delineation in PET/CT images of HNC patients, although there is still a margin for improvement in some difficult cases. For the first time, the prediction of outcome was also addressed and the best methods reached relatively good performance (C-index above 0.7). Both results constitute another step forward toward large-scale outcome prediction studies in HNC.
Collapse
Affiliation(s)
- Vincent Andrearczyk
- Institute of Informatics, University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland.
| | - Valentin Oreiller
- Institute of Informatics, University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland; Department of Nuclear Medicine and Molecular Imaging, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland; Faculty of Biology and Medicine, University of Lausanne, Lausanne, Switzerland
| | - Sarah Boughdad
- Department of Nuclear Medicine and Molecular Imaging, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
| | - Catherine Cheze Le Rest
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France; Poitiers University Hospital, nuclear medicine, Poitiers, France
| | - Olena Tankyevych
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France; Poitiers University Hospital, nuclear medicine, Poitiers, France
| | - Hesham Elhalawani
- Cleveland Clinic Foundation, Department of Radiation Oncology, Cleveland, OH, United States of America
| | - Mario Jreige
- Department of Nuclear Medicine and Molecular Imaging, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
| | - John O Prior
- Department of Nuclear Medicine and Molecular Imaging, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland; Faculty of Biology and Medicine, University of Lausanne, Lausanne, Switzerland
| | - Martin Vallières
- Department of Computer Science, Université de Sherbrooke, Sherbrooke, Québec, Canada
| | | | - Mathieu Hatt
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France
| | - Adrien Depeursinge
- Institute of Informatics, University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland; Department of Nuclear Medicine and Molecular Imaging, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
| |
Collapse
|
8
|
Bodet-Milin C, Morvant C, Carlier T, Frecon G, Tournilhac O, Safar V, Kraeber-Bodere F, Le Gouill S, Macintyre E, Bailly C. Performance of baseline FDG-PET/CT radiomics for prediction of bone marrow minimal residual disease status in the LyMa-101 trial. Sci Rep 2023; 13:18177. [PMID: 37875524 PMCID: PMC10598231 DOI: 10.1038/s41598-023-45215-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2023] [Accepted: 10/17/2023] [Indexed: 10/26/2023] Open
Abstract
The prognostic value of 18F-Fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) at baseline or the predictive value of minimal residual disease (MRD) detection appear as potential tools to improve mantle cell lymphoma (MCL) patients' management. The LyMa-101, a phase 2 trial of the LYSA group (ClinicalTrials.gov:NCT02896582) reported induction therapy with obinutuzumab, a CD20 monoclonal antibody. Herein, we investigated the added prognostic value of radiomic features (RF) derived from FDG-PET/CT at diagnosis for MRD value prediction. FDG-PET/CT of 59 MCL patients included in the LyMa-101 trial have been independently, blindly and centrally reviewed. RF were extracted from the disease area with the highest uptake and from the total metabolic tumor volume (TMTV). Two models of machine learning were used to compare several combinations for prediction of MRD before autologous stem cell transplant consolidation (ASCT). Each algorithm was generated with or without constrained feature selections for clinical and laboratory parameters. Both algorithms showed better discrimination performances for negative vs positive MRD in the lesion with the highest uptake than in the TMTV. The constrained use of clinical and biological features showed a clear loss in sensitivity for the prediction of MRD status before ASCT, regardless of the machine learning model. These data plead for the importance of FDG-PET/CT RF compared to clinical and laboratory parameters and also reinforced the previously made hypothesis that the prognosis of the disease in MCL patients is linked to the most aggressive contingent, within the lesion with the highest uptake.
Collapse
Affiliation(s)
- Caroline Bodet-Milin
- Université de Nantes, CHU Nantes, CNRS, Inserm, CRCINA, 44000, Nantes, France
- Nuclear Medicine Unit, University Hospital, 44093, Nantes, France
| | - Cyrille Morvant
- Université de Nantes, CHU Nantes, CNRS, Inserm, CRCINA, 44000, Nantes, France
- Nuclear Medicine Unit, University Hospital, 44093, Nantes, France
| | - Thomas Carlier
- Université de Nantes, CHU Nantes, CNRS, Inserm, CRCINA, 44000, Nantes, France
- Nuclear Medicine Unit, University Hospital, 44093, Nantes, France
| | - Gauthier Frecon
- Nuclear Medicine Unit, University Hospital, 44093, Nantes, France
| | - Olivier Tournilhac
- Haematology and Cell Therapy Department, Hôpital Estaing, CHU de Clermont-Ferrand, Clermont-Ferrand, France
| | - Violaine Safar
- Department of Hematology, Hospices Civils de Lyon, Lyon Sud Hospital, Pierre-Bénite, France
| | - Françoise Kraeber-Bodere
- Université de Nantes, CHU Nantes, CNRS, Inserm, CRCINA, 44000, Nantes, France
- Nuclear Medicine Unit, University Hospital, 44093, Nantes, France
| | - Steven Le Gouill
- Université de Nantes, CHU Nantes, CNRS, Inserm, CRCINA, 44000, Nantes, France
- Institut Curie, Paris and Saint-Cloud, Université Versailles-Saint Quentin, Saint-Cloud, France
| | - Elizabeth Macintyre
- Onco-Haematology, Université de Paris, Hôpital and Institut Necker-Enfants Malades, Assistance-Publique-Hôpitaux de Paris, INSERM U1151, Paris, France
| | - Clément Bailly
- Université de Nantes, CHU Nantes, CNRS, Inserm, CRCINA, 44000, Nantes, France.
- Nuclear Medicine Unit, University Hospital, 44093, Nantes, France.
| |
Collapse
|
9
|
Zhang W, Ray S. From coarse to fine: a deep 3D probability volume contours framework for tumour segmentation and dose painting in PET images. FRONTIERS IN RADIOLOGY 2023; 3:1225215. [PMID: 37745205 PMCID: PMC10512384 DOI: 10.3389/fradi.2023.1225215] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/18/2023] [Accepted: 08/21/2023] [Indexed: 09/26/2023]
Abstract
With the increasing integration of functional imaging techniques like Positron Emission Tomography (PET) into radiotherapy (RT) practices, a paradigm shift in cancer treatment methodologies is underway. A fundamental step in RT planning is the accurate segmentation of tumours based on clinical diagnosis. Furthermore, novel tumour control methods, such as intensity modulated radiation therapy (IMRT) dose painting, demand the precise delineation of multiple intensity value contours to ensure optimal tumour dose distribution. Recently, convolutional neural networks (CNNs) have made significant strides in 3D image segmentation tasks, most of which present the output map at a voxel-wise level. However, because of information loss in subsequent downsampling layers, they frequently fail to precisely identify precise object boundaries. Moreover, in the context of dose painting strategies, there is an imperative need for reliable and precise image segmentation techniques to delineate high recurrence-risk contours. To address these challenges, we introduce a 3D coarse-to-fine framework, integrating a CNN with a kernel smoothing-based probability volume contour approach (KsPC). This integrated approach generates contour-based segmentation volumes, mimicking expert-level precision and providing accurate probability contours crucial for optimizing dose painting/IMRT strategies. Our final model, named KsPC-Net, leverages a CNN backbone to automatically learn parameters in the kernel smoothing process, thereby obviating the need for user-supplied tuning parameters. The 3D KsPC-Net exploits the strength of KsPC to simultaneously identify object boundaries and generate corresponding probability volume contours, which can be trained within an end-to-end framework. The proposed model has demonstrated promising performance, surpassing state-of-the-art models when tested against the MICCAI 2021 challenge dataset (HECKTOR).
Collapse
Affiliation(s)
- Wenhui Zhang
- School of Mathematics and Statistics, University of Glasgow, Glasgow, United Kingdom
| | | |
Collapse
|
10
|
Constantino CS, Leocádio S, Oliveira FPM, Silva M, Oliveira C, Castanheira JC, Silva Â, Vaz S, Teixeira R, Neves M, Lúcio P, João C, Costa DC. Evaluation of Semiautomatic and Deep Learning-Based Fully Automatic Segmentation Methods on [ 18F]FDG PET/CT Images from Patients with Lymphoma: Influence on Tumor Characterization. J Digit Imaging 2023; 36:1864-1876. [PMID: 37059891 PMCID: PMC10407010 DOI: 10.1007/s10278-023-00823-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2023] [Revised: 03/14/2023] [Accepted: 03/27/2023] [Indexed: 04/16/2023] Open
Abstract
The objective is to assess the performance of seven semiautomatic and two fully automatic segmentation methods on [18F]FDG PET/CT lymphoma images and evaluate their influence on tumor quantification. All lymphoma lesions identified in 65 whole-body [18F]FDG PET/CT staging images were segmented by two experienced observers using manual and semiautomatic methods. Semiautomatic segmentation using absolute and relative thresholds, k-means and Bayesian clustering, and a self-adaptive configuration (SAC) of k-means and Bayesian was applied. Three state-of-the-art deep learning-based segmentations methods using a 3D U-Net architecture were also applied. One was semiautomatic and two were fully automatic, of which one is publicly available. Dice coefficient (DC) measured segmentation overlap, considering manual segmentation the ground truth. Lymphoma lesions were characterized by 31 features. Intraclass correlation coefficient (ICC) assessed features agreement between different segmentation methods. Nine hundred twenty [18F]FDG-avid lesions were identified. The SAC Bayesian method achieved the highest median intra-observer DC (0.87). Inter-observers' DC was higher for SAC Bayesian than manual segmentation (0.94 vs 0.84, p < 0.001). Semiautomatic deep learning-based median DC was promising (0.83 (Obs1), 0.79 (Obs2)). Threshold-based methods and publicly available 3D U-Net gave poorer results (0.56 ≤ DC ≤ 0.68). Maximum, mean, and peak standardized uptake values, metabolic tumor volume, and total lesion glycolysis showed excellent agreement (ICC ≥ 0.92) between manual and SAC Bayesian segmentation methods. The SAC Bayesian classifier is more reproducible and produces similar lesion features compared to manual segmentation, giving the best concordant results of all other methods. Deep learning-based segmentation can achieve overall good segmentation results but failed in few patients impacting patients' clinical evaluation.
Collapse
Affiliation(s)
- Cláudia S Constantino
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal.
| | - Sónia Leocádio
- Hematology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Francisco P M Oliveira
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Mariana Silva
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Carla Oliveira
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Joana C Castanheira
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Ângelo Silva
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Sofia Vaz
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Ricardo Teixeira
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Manuel Neves
- Hematology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Paulo Lúcio
- Hematology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Cristina João
- Hematology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| | - Durval C Costa
- Nuclear Medicine - Radiopharmacology Department, Champalimaud Foundation, Av. Brasília, 1400-038, Lisbon, Portugal
| |
Collapse
|
11
|
Li L, Jiang C, Wang PSP, Zheng S. 3D PET/CT Tumor Co-Segmentation Based on Background Subtraction Hybrid Active Contour Model. INT J PATTERN RECOGN 2023; 37. [DOI: 10.1142/s0218001423570069] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/15/2024]
Abstract
Accurate tumor segmentation in medical images plays an important role in clinical diagnosis and disease analysis. However, medical images usually have great complexity, such as low contrast of computed tomography (CT) or low spatial resolution of positron emission tomography (PET). In the actual radiotherapy plan, multimodal imaging technology, such as PET/CT, is often used. PET images provide basic metabolic information and CT images provide anatomical details. In this paper, we propose a 3D PET/CT tumor co-segmentation framework based on active contour model. First, a new edge stop function (ESF) based on PET image and CT image is defined, which combines the grayscale standard deviation information of the image and is more effective for blurry medical image edges. Second, we propose a background subtraction model to solve the problem of uneven grayscale level in medical images. Apart from that, the calculation format adopts the level set algorithm based on the additive operator splitting (AOS) format. The solution is unconditionally stable and eliminates the dependence on time step size. Experimental results on a dataset of 50 pairs of PET/CT images of non-small cell lung cancer patients show that the proposed method has a good performance for tumor segmentation.
Collapse
Affiliation(s)
- Laquan Li
- School of Science, Chongqing University of Posts and Telecommunications, Chongqing 400065, P. R. China
- College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, P. R. China
| | - Chuangbo Jiang
- School of Science, Chongqing University of Posts and Telecommunications, Chongqing 400065, P. R. China
| | - Patrick Shen-Pei Wang
- College of Computer and Information Science, Northeastern University, Boston 02115, USA
| | - Shenhai Zheng
- College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, P. R. China
- College of Computer Science, Chongqing University, Chongqing 400044, P. R. China
| |
Collapse
|
12
|
Horvat N, Miranda J, El Homsi M, Peoples JJ, Long NM, Simpson AL, Do RKG. A primer on texture analysis in abdominal radiology. Abdom Radiol (NY) 2022; 47:2972-2985. [PMID: 34825946 DOI: 10.1007/s00261-021-03359-3] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/20/2021] [Revised: 11/16/2021] [Accepted: 11/17/2021] [Indexed: 01/18/2023]
Abstract
The number of publications on texture analysis (TA), radiomics, and radiogenomics has been growing exponentially, with abdominal radiologists aiming to build new prognostic or predictive biomarkers for a wide range of clinical applications including the use of oncological imaging to advance the field of precision medicine. TA is specifically concerned with the study of the variation of pixel intensity values in radiological images. Radiologists aim to capture pixel variation in radiological images to deliver new insights into tumor biology that cannot be derived from visual inspection alone. TA remains an active area of investigation and requires further standardization prior to its clinical acceptance and applicability. This review is for radiologists interested in this rapidly evolving field, who are thinking of performing research or want to better interpret results in this arena. We will review the main concepts in TA, workflow processes, and existing challenges and steps to overcome them, as well as look at publications in body imaging with external validation.
Collapse
Affiliation(s)
- Natally Horvat
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY, 10065, USA
| | - Joao Miranda
- Department of Radiology, University of Sao Paulo, Sao Paulo, SP, Brazil
| | - Maria El Homsi
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY, 10065, USA
| | - Jacob J Peoples
- School of Computing, Queen's University, Kingston, ON, Canada
| | - Niamh M Long
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY, 10065, USA
| | - Amber L Simpson
- School of Computing, Queen's University, Kingston, ON, Canada.,Department of Biomedical and Molecular Sciences, Queen's University, Kingston, ON, Canada
| | - Richard K G Do
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY, 10065, USA.
| |
Collapse
|
13
|
[ 89Zr]Zr-PSMA-617 PET/CT in biochemical recurrence of prostate cancer: first clinical experience from a pilot study including biodistribution and dose estimates. Eur J Nucl Med Mol Imaging 2022; 49:4736-4747. [PMID: 35930033 PMCID: PMC9606102 DOI: 10.1007/s00259-022-05925-3] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2022] [Accepted: 07/22/2022] [Indexed: 11/14/2022]
Abstract
Purpose Prostate-specific membrane antigen (PSMA)-targeted PET/CT has become increasingly important in the management of prostate cancer, especially in localization of biochemical recurrence (BCR). PSMA-targeted PET/CT imaging with long-lived radionuclides as 89Zr (T1/2 = 78.4 h) may improve diagnostics by allowing data acquisition on later time points. In this study, we present our first clinical experience including preliminary biodistribution and dosimetry data of [89Zr]Zr-PSMA-617 PET/CT in patients with BCR of prostate cancer. Methods Seven patients with BCR of prostate cancer who revealed no (n = 4) or undetermined (n = 3) findings on [68Ga]Ga-PSMA-11 PET/CT imaging were referred to [89Zr]Zr-PSMA-617 PET/CT. PET/CT imaging was performed 1 h, 24 h, 48 h, and 72 h post injection (p.i.) of 111 ± 11 MBq [89Zr]Zr-PSMA-617 (mean ± standard deviation). Normal organ distribution and dosimetry were determined. Lesions visually considered as suggestive of prostate cancer were quantitatively analyzed. Results Intense physiological uptake was observed in the salivary and lacrimal glands, liver, spleen, kidneys, intestine and urinary tract. The parotid gland received the highest absorbed dose (0.601 ± 0.185 mGy/MBq), followed by the kidneys (0.517 ± 0.125 mGy/MBq). The estimated overall effective dose for the administration of 111 MBq was 10.1 mSv (0.0913 ± 0.0118 mSv/MBq). In 6 patients, and in particular in 3 of 4 patients with negative [68Ga]Ga-PSMA-11 PET/CT, at least one prostate cancer lesion was detected in [89Zr]Zr-PSMA-617 PET/CT imaging at later time points. The majority of tumor lesions were first visible at 24 h p.i. with continuously increasing tumor-to-background ratio over time. All tumor lesions were detectable at 48 h and 72 h p.i. Conclusion [89Zr]Zr-PSMA-617 PET/CT imaging is a promising new diagnostic tool with acceptable radiation exposure for patients with prostate cancer especially when [68Ga]Ga-PSMA-11 PET/CT imaging fails detecting recurrent disease. The long half-life of 89Zr enables late time point imaging (up to 72 h in our study) with increased tracer uptake in tumor lesions and higher tumor-to-background ratios allowing identification of lesions non-visible on [68Ga]Ga-PSMA-11 PET/CT imaging.
Collapse
|
14
|
Bamneshin K, Rabi Mahdavi S, Bitarafan-Rajabi A, Geramifar P, Hejazi P, Koosha F, Jadidi M. Evaluation of Dose-Painting in the Dominant Intraprostatic Lesions by Radiobiological Parameters using 68Ga- PSMA PET/CT. J Biomed Phys Eng 2022; 12:369-376. [PMID: 36059285 PMCID: PMC9395631 DOI: 10.31661/jbpe.v0i0.1912-1006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2019] [Accepted: 02/03/2020] [Indexed: 06/15/2023]
Abstract
BACKGROUND Patients diagnosed with dominant intraprostatic lesions (DIL) may need radiation doses over than 80 Gy. Dose-painting by contours (DPC) is a useful technique which helps the patients. Dose-painting approach need to be evaluated. OBJECTIVE To evaluate the DCP technique in the case of boosting the DILs by radiobiological parameters, tumor control probability (TCP), and normal tissue complication probability (NTCP) via PET/CT images traced by 68Ga-PSMA. MATERIAL AND METHODS In this analytical study, 68Ga-PSMA PET/CT images were obtained from patients with DILs that were delineated using the Fuzzy c-mean (FCM) algorithm and thresholding methods. The protocol of therapy included two phases; at the first phase (ph1), a total dose of 72 Gy in 36 fractions were delivered to the planning target volume (PTV1); the seconds phase consisted of the application of variable doses to the PTV2. Moreover, two concepts were also considered to calculate the TCP using the Zaider-Minerbo model. RESULTS The lowest volume in DILs belonged to the DIL1 extracted by the FCM method. According to dose-volume parameters of the rectum and bladder, by the increase in the PTV dose higher than 92 Gy, the amounts of rectum and bladder doses are increased. There was no difference between the TCPs of DILs at doses higher than 86 Gy and 100 Gy for ordinary and high clone density, respectively. CONCLUSION Consequently, our dose-painting approach for DILs, extracted by the FCM method via PET/CT images, can reduce the total dose for prostate radiation with 100% tumor control and less normal tissue complications.
Collapse
Affiliation(s)
- Khadijeh Bamneshin
- PhD, Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
- PhD, Student Research Committee, Iran University of Medical Sciences, Tehran, Iran
| | - Seied Rabi Mahdavi
- PhD, Radiation Biology Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Ahmad Bitarafan-Rajabi
- PhD, Echocardiography Research Center, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Parham Geramifar
- PhD, Department of Nuclear Medicine, Shariati Hospital Tehran University of Medical Sciences, Tehran, Iran
| | - Payman Hejazi
- PhD, Department of Medical Physics, Faculty of Medicine, Semnan University of Medical Sciences, Semnan, Iran
| | - Fereshteh Koosha
- PhD, Department of Radiology Technology, Faculty of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Majid Jadidi
- PhD, Department of Medical Physics, Faculty of Medicine, Semnan University of Medical Sciences, Semnan, Iran
| |
Collapse
|
15
|
Positron Emission Tomography Image Segmentation Based on Atanassov’s Intuitionistic Fuzzy Sets. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12104865] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/10/2022]
Abstract
In this paper, we present an approach to fully automate tumor delineation in positron emission tomography (PET) images. PET images play a major role in medicine for in vivo imaging in oncology (PET images are used to evaluate oncology patients, detecting emitted photons from a radiotracer localized in abnormal cells). PET image tumor delineation plays a vital role both in pre- and post-treatment stages. The low spatial resolution and high noise characteristics of PET images increase the challenge in PET image segmentation. Despite the difficulties and known limitations, several image segmentation approaches have been proposed. This paper introduces a new unsupervised approach to perform tumor delineation in PET images using Atanassov’s intuitionistic fuzzy sets (A-IFSs) and restricted dissimilarity functions. Moreover, the implementation of this methodology is presented and tested against other existing methodologies. The proposed algorithm increases the accuracy of tumor delineation in PET images, and the experimental results show that the proposed method outperformed all methods tested.
Collapse
|
16
|
Decentralized Distributed Multi-institutional PET Image Segmentation Using a Federated Deep Learning Framework. Clin Nucl Med 2022; 47:606-617. [PMID: 35442222 DOI: 10.1097/rlu.0000000000004194] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
PURPOSE The generalizability and trustworthiness of deep learning (DL)-based algorithms depend on the size and heterogeneity of training datasets. However, because of patient privacy concerns and ethical and legal issues, sharing medical images between different centers is restricted. Our objective is to build a federated DL-based framework for PET image segmentation utilizing a multicentric dataset and to compare its performance with the centralized DL approach. METHODS PET images from 405 head and neck cancer patients from 9 different centers formed the basis of this study. All tumors were segmented manually. PET images converted to SUV maps were resampled to isotropic voxels (3 × 3 × 3 mm3) and then normalized. PET image subvolumes (12 × 12 × 12 cm3) consisting of whole tumors and background were analyzed. Data from each center were divided into train/validation (80% of patients) and test sets (20% of patients). The modified R2U-Net was used as core DL model. A parallel federated DL model was developed and compared with the centralized approach where the data sets are pooled to one server. Segmentation metrics, including Dice similarity and Jaccard coefficients, percent relative errors (RE%) of SUVpeak, SUVmean, SUVmedian, SUVmax, metabolic tumor volume, and total lesion glycolysis were computed and compared with manual delineations. RESULTS The performance of the centralized versus federated DL methods was nearly identical for segmentation metrics: Dice (0.84 ± 0.06 vs 0.84 ± 0.05) and Jaccard (0.73 ± 0.08 vs 0.73 ± 0.07). For quantitative PET parameters, we obtained comparable RE% for SUVmean (6.43% ± 4.72% vs 6.61% ± 5.42%), metabolic tumor volume (12.2% ± 16.2% vs 12.1% ± 15.89%), and total lesion glycolysis (6.93% ± 9.6% vs 7.07% ± 9.85%) and negligible RE% for SUVmax and SUVpeak. No significant differences in performance (P > 0.05) between the 2 frameworks (centralized vs federated) were observed. CONCLUSION The developed federated DL model achieved comparable quantitative performance with respect to the centralized DL model. Federated DL models could provide robust and generalizable segmentation, while addressing patient privacy and legal and ethical issues in clinical data sharing.
Collapse
|
17
|
Solari EL, Gafita A, Schachoff S, Bogdanović B, Villagrán Asiares A, Amiel T, Hui W, Rauscher I, Visvikis D, Maurer T, Schwamborn K, Mustafa M, Weber W, Navab N, Eiber M, Hatt M, Nekolla SG. The added value of PSMA PET/MR radiomics for prostate cancer staging. Eur J Nucl Med Mol Imaging 2022; 49:527-538. [PMID: 34255130 PMCID: PMC8803696 DOI: 10.1007/s00259-021-05430-z] [Citation(s) in RCA: 36] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2021] [Accepted: 05/24/2021] [Indexed: 12/24/2022]
Abstract
PURPOSE To evaluate the performance of combined PET and multiparametric MRI (mpMRI) radiomics for the group-wise prediction of postsurgical Gleason scores (psGSs) in primary prostate cancer (PCa) patients. METHODS Patients with PCa, who underwent [68 Ga]Ga-PSMA-11 PET/MRI followed by radical prostatectomy, were included in this retrospective analysis (n = 101). Patients were grouped by psGS in three categories: ISUP grades 1-3, ISUP grade 4, and ISUP grade 5. mpMRI images included T1-weighted, T2-weighted, and apparent diffusion coefficient (ADC) map. Whole-prostate segmentations were performed on each modality, and image biomarker standardization initiative (IBSI)-compliant radiomic features were extracted. Nine support vector machine (SVM) models were trained: four single-modality radiomic models (PET, T1w, T2w, ADC); three PET + MRI double-modality models (PET + T1w, PET + T2w, PET + ADC), and two baseline models (one with patient data, one image-based) for comparison. A sixfold stratified cross-validation was performed, and balanced accuracies (bAcc) of the predictions of the best-performing models were reported and compared through Student's t-tests. The predictions of the best-performing model were compared against biopsy GS (bGS). RESULTS All radiomic models outperformed the baseline models. The best-performing (mean ± stdv [%]) single-modality model was the ADC model (76 ± 6%), although not significantly better (p > 0.05) than other single-modality models (T1w: 72 ± 3%, T2w: 73 ± 2%; PET: 75 ± 5%). The overall best-performing model combined PET + ADC radiomics (82 ± 5%). It significantly outperformed most other double-modality (PET + T1w: 74 ± 5%, p = 0.026; PET + T2w: 71 ± 4%, p = 0.003) and single-modality models (PET: p = 0.042; T1w: p = 0.002; T2w: p = 0.003), except the ADC-only model (p = 0.138). In this initial cohort, the PET + ADC model outperformed bGS overall (82.5% vs 72.4%) in the prediction of psGS. CONCLUSION All single- and double-modality models outperformed the baseline models, showing their potential in the prediction of GS, even with an unbalanced cohort. The best-performing model included PET + ADC radiomics, suggesting a complementary value of PSMA-PET and ADC radiomics.
Collapse
Affiliation(s)
- Esteban Lucas Solari
- School of Medicine, Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University Munich, Munich, Germany.
| | - Andrei Gafita
- School of Medicine, Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University Munich, Munich, Germany
| | - Sylvia Schachoff
- School of Medicine, Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University Munich, Munich, Germany
| | - Borjana Bogdanović
- School of Medicine, Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University Munich, Munich, Germany
| | - Alberto Villagrán Asiares
- School of Medicine, Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University Munich, Munich, Germany
| | - Thomas Amiel
- School of Medicine, Department of Urology, Klinikum rechts der Isar, Technical University Munich, Munich, Germany
| | - Wang Hui
- School of Medicine, Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University Munich, Munich, Germany
| | - Isabel Rauscher
- School of Medicine, Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University Munich, Munich, Germany
| | | | - Tobias Maurer
- Department of Urology and Martini-Klinik Prostate Cancer Center, University Hospital Hamburg-Eppendorf, Hamburg, Germany
| | - Kristina Schwamborn
- School of Medicine, Institute of Pathology, Klinikum rechts der Isar, Technical University Munich, Munich, Germany
| | - Mona Mustafa
- School of Medicine, Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University Munich, Munich, Germany
| | - Wolfgang Weber
- School of Medicine, Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University Munich, Munich, Germany
| | - Nassir Navab
- School of Computer Science, Computer Aided Medical Procedures and Augmented Reality, Technical University Munich, Munich, Germany
| | - Matthias Eiber
- School of Medicine, Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University Munich, Munich, Germany
| | - Mathieu Hatt
- INSERM, UMR 1101, LaTIM, Univ Brest, Brest, France
| | - Stephan G Nekolla
- School of Medicine, Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University Munich, Munich, Germany
| |
Collapse
|
18
|
Yassin MA, Nehmeh SA, Nashwan AJ, Kohla SA, Mohamed SF, Ismail OM, Al Sabbagh A, Soliman DS, Szabados L, Fayad H. Assessing Bone Marrow Activity with [ 18F]FLT PET in Patients with Essential Thrombocythemia and Prefibrotic Myelofibrosis: A Proof of Concept. Technol Cancer Res Treat 2022; 21:15330338221086396. [PMID: 35341409 PMCID: PMC8966096 DOI: 10.1177/15330338221086396] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2021] [Revised: 02/20/2022] [Accepted: 02/22/2022] [Indexed: 12/02/2022] Open
Abstract
Objectives: This study aims to assess the value of FLT-PET as a non-invasive tool to differentiate between patients with ET and Pre-PMF. This study is a pilot study to have a proof of concept only. Methods: This is a prospective, interventional study where a total of 12 patients were included. Each patient underwent FLT PET imaging as well as bone marrow examination (gold standard). In addition, semi-quantitative (SUVmax and SUVmean) measurements of FLT uptake in the liver, spleen, and Lspine, SUVmean, as well as the Total Lesion Glycolysis (TLG) of the Lspine were performed. Results from the two patient cohorts were compared using = Kruskal-Wallis statistical test. A P-value of <.05 is considered to be statistically significant. Results: The differences in FLT SUVmax and SUVmean measurements in the three organs (liver, spleen, and LSpine) between the ET and Pre-PMF patients were not statistically significant (P > .05). In contrast, TLG measurements in the LSpine were statistically different (P = .013), and therefore, compared to gold standard bone marrow results, TLG can separate ET and Pre-PMF patients. Conclusion: This study is a proof of concept about the potential to discriminate between ET and pre-PMF patients in a non-invasive way. TLG of the LSpine in FLT PET images is a potential quantitative parameter to distinguish between ET and pre-PMF patients.
Collapse
Affiliation(s)
- Mohamed A. Yassin
- Department of Medical Oncology/Hematology, National Centre for Cancer Care and Research, Hamad Medical Corporation, Doha, Qatar
| | - Sadek A. Nehmeh
- Department of Radiology, Weill Cornell Medicine, New York, USA
| | - Abdulqadir J. Nashwan
- Department of Education & Practice Development, Hazm Mebaireek General Hospital, Doha, Qatar
| | - Samah A. Kohla
- Department of Laboratory Medicine and Pathology, Hematopathology Section, Hamad Medical Corporation, Doha, Qatar
| | - Shehab F. Mohamed
- Department of Medical Oncology/Hematology, National Centre for Cancer Care and Research, Hamad Medical Corporation, Doha, Qatar
| | - Omar M. Ismail
- Department of Medical Oncology/Hematology, National Centre for Cancer Care and Research, Hamad Medical Corporation, Doha, Qatar
| | - Ahmad Al Sabbagh
- Department of Laboratory Medicine and Pathology, Hematopathology Section, Hamad Medical Corporation, Doha, Qatar
| | - Dina S. Soliman
- Department of Laboratory Medicine and Pathology, Hematopathology Section, Hamad Medical Corporation, Doha, Qatar
| | - Lajos Szabados
- Clinical Imaging Department, Hamad Medical Corporation, Doha, Qatar
| | - Hadi Fayad
- Occupational Health and Safety Department, Hamad Medical Corporation, Doha, Qatar
| |
Collapse
|
19
|
Oreiller V, Andrearczyk V, Jreige M, Boughdad S, Elhalawani H, Castelli J, Vallières M, Zhu S, Xie J, Peng Y, Iantsen A, Hatt M, Yuan Y, Ma J, Yang X, Rao C, Pai S, Ghimire K, Feng X, Naser MA, Fuller CD, Yousefirizi F, Rahmim A, Chen H, Wang L, Prior JO, Depeursinge A. Head and neck tumor segmentation in PET/CT: The HECKTOR challenge. Med Image Anal 2021; 77:102336. [PMID: 35016077 DOI: 10.1016/j.media.2021.102336] [Citation(s) in RCA: 58] [Impact Index Per Article: 19.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2021] [Revised: 10/13/2021] [Accepted: 12/14/2021] [Indexed: 12/23/2022]
Abstract
This paper relates the post-analysis of the first edition of the HEad and neCK TumOR (HECKTOR) challenge. This challenge was held as a satellite event of the 23rd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2020, and was the first of its kind focusing on lesion segmentation in combined FDG-PET and CT image modalities. The challenge's task is the automatic segmentation of the Gross Tumor Volume (GTV) of Head and Neck (H&N) oropharyngeal primary tumors in FDG-PET/CT images. To this end, the participants were given a training set of 201 cases from four different centers and their methods were tested on a held-out set of 53 cases from a fifth center. The methods were ranked according to the Dice Score Coefficient (DSC) averaged across all test cases. An additional inter-observer agreement study was organized to assess the difficulty of the task from a human perspective. 64 teams registered to the challenge, among which 10 provided a paper detailing their approach. The best method obtained an average DSC of 0.7591, showing a large improvement over our proposed baseline method and the inter-observer agreement, associated with DSCs of 0.6610 and 0.61, respectively. The automatic methods proved to successfully leverage the wealth of metabolic and structural properties of combined PET and CT modalities, significantly outperforming human inter-observer agreement level, semi-automatic thresholding based on PET images as well as other single modality-based methods. This promising performance is one step forward towards large-scale radiomics studies in H&N cancer, obviating the need for error-prone and time-consuming manual delineation of GTVs.
Collapse
Affiliation(s)
- Valentin Oreiller
- Institute of Information Systems, University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland; Department of Nuclear Medicine and Molecular Imaging, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland.
| | - Vincent Andrearczyk
- Institute of Information Systems, University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland
| | - Mario Jreige
- Department of Nuclear Medicine and Molecular Imaging, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
| | - Sarah Boughdad
- Department of Nuclear Medicine and Molecular Imaging, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
| | - Hesham Elhalawani
- Department of Radiation Oncology, Brigham and Women's Hospital and Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA, USA
| | - Joel Castelli
- Radiotherapy Department, Cancer Institute Eugène Marquis, Rennes, France
| | - Martin Vallières
- Department of Computer Science, Université de Sherbrooke, Sherbrooke, Québec, Canada
| | - Simeng Zhu
- Department of Radiation Oncology, Henry Ford Cancer Institute, Detroit, MI, USA
| | - Juanying Xie
- School of Computer Science, Shaanxi Normal University, Xi'an 710119, PR China
| | - Ying Peng
- School of Computer Science, Shaanxi Normal University, Xi'an 710119, PR China
| | - Andrei Iantsen
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France
| | - Mathieu Hatt
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France
| | - Yading Yuan
- Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Jun Ma
- Department of Mathematics, Nanjing University of Science and Technology, Jiangsu, China
| | - Xiaoping Yang
- Department of Mathematics, Nanjing University, Jiangsu, China
| | - Chinmay Rao
- Department of Radiation Oncology (Maastro), GROW School for Oncology, Maastricht University Medical Centre+, Maastricht, The Netherlands
| | - Suraj Pai
- Department of Radiation Oncology (Maastro), GROW School for Oncology, Maastricht University Medical Centre+, Maastricht, The Netherlands
| | | | - Xue Feng
- Carina Medical, Lexington, KY, 40513, USA; Department of Biomedical Engineering, University of Virginia, Charlottesville VA 22903, USA
| | - Mohamed A Naser
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas 77030, USA
| | - Clifton D Fuller
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas 77030, USA
| | - Fereshteh Yousefirizi
- Department of Integrative Oncology, BC Cancer Research Institute, Vancouver BC, Canada
| | - Arman Rahmim
- Department of Integrative Oncology, BC Cancer Research Institute, Vancouver BC, Canada
| | - Huai Chen
- Department of Automation, Institute of Image Processing and Pattern Recognition, Shangai Jiao Tong University, Shanghai 200240, People's Republic of China
| | - Lisheng Wang
- Department of Automation, Institute of Image Processing and Pattern Recognition, Shangai Jiao Tong University, Shanghai 200240, People's Republic of China
| | - John O Prior
- Department of Nuclear Medicine and Molecular Imaging, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
| | - Adrien Depeursinge
- Institute of Information Systems, University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland; Department of Nuclear Medicine and Molecular Imaging, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
| |
Collapse
|
20
|
Sepehri S, Tankyevych O, Iantsen A, Visvikis D, Hatt M, Cheze Le Rest C. Accurate Tumor Delineation vs. Rough Volume of Interest Analysis for 18F-FDG PET/CT Radiomics-Based Prognostic Modeling inNon-Small Cell Lung Cancer. Front Oncol 2021; 11:726865. [PMID: 34733779 PMCID: PMC8560021 DOI: 10.3389/fonc.2021.726865] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/17/2021] [Accepted: 09/20/2021] [Indexed: 12/24/2022] Open
Abstract
Background The aim of this work was to investigate the ability of building prognostic models in non-small cell lung cancer (NSCLC) using radiomic features from positron emission tomography and computed tomography with 2-deoxy-2-[fluorine-18]fluoro-d-glucose (18F-FDG PET/CT) images based on a "rough" volume of interest (VOI) containing the tumor instead of its accurate delineation, which is a significant time-consuming bottleneck of radiomics analyses. Methods A cohort of 138 patients with stage II-III NSCLC treated with radiochemotherapy recruited retrospectively (n = 87) and prospectively (n = 51) was used. Two approaches were compared: firstly, the radiomic features were extracted from the delineated primary tumor volumes in both PET (using the automated fuzzy locally adaptive Bayesian, FLAB) and CT (using a semi-automated approach with 3D Slicer™) components. Both delineations were carried out within previously manually defined "rough" VOIs containing the tumor and the surrounding tissues, which were exploited for the second approach: the same features were extracted from this alternative VOI. Both sets for features were then combined with the clinical variables and processed through the same machine learning (ML) pipelines using the retrospectively recruited patients as the training set and the prospectively recruited patients as the testing set. Logistic regression (LR), random forest (RF), and support vector machine (SVM), as well as their consensus through averaging the output probabilities, were considered for feature selection and modeling for overall survival (OS) prediction as a binary classification (either median OS or 6 months OS). The resulting models were compared in terms of balanced accuracy, sensitivity, and specificity. Results Overall, better performance was achieved using the features from delineated tumor volumes. This was observed consistently across ML algorithms and for the two clinical endpoints. However, the loss of performance was not significant, especially when a consensus of the three ML algorithms was considered (0.89 vs. 0.88 and 0.78 vs. 0.77). Conclusion Our findings suggest that it is feasible to achieve similar levels of prognostic accuracy in radiomics-based modeling by relying on a faster and easier VOI definition, skipping a time-consuming tumor delineation step, thus facilitating automation of the whole radiomics workflow. The associated cost is a loss of performance in the resulting models, although this loss can be greatly mitigated when a consensus of several models is relied upon.
Collapse
Affiliation(s)
| | - Olena Tankyevych
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France.,University Hospital Poitiers, Nuclear Medicine Department, Poitiers, France
| | | | | | - Mathieu Hatt
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | - Catherine Cheze Le Rest
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France.,University Hospital Poitiers, Nuclear Medicine Department, Poitiers, France
| |
Collapse
|
21
|
Shiri I, Arabi H, Sanaat A, Jenabi E, Becker M, Zaidi H. Fully Automated Gross Tumor Volume Delineation From PET in Head and Neck Cancer Using Deep Learning Algorithms. Clin Nucl Med 2021; 46:872-883. [PMID: 34238799 DOI: 10.1097/rlu.0000000000003789] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
PURPOSE The availability of automated, accurate, and robust gross tumor volume (GTV) segmentation algorithms is critical for the management of head and neck cancer (HNC) patients. In this work, we evaluated 3 state-of-the-art deep learning algorithms combined with 8 different loss functions for PET image segmentation using a comprehensive training set and evaluated its performance on an external validation set of HNC patients. PATIENTS AND METHODS 18F-FDG PET/CT images of 470 patients presenting with HNC on which manually defined GTVs serving as standard of reference were used for training (340 patients), evaluation (30 patients), and testing (100 patients from different centers) of these algorithms. PET image intensity was converted to SUVs and normalized in the range (0-1) using the SUVmax of the whole data set. PET images were cropped to 12 × 12 × 12 cm3 subvolumes using isotropic voxel spacing of 3 × 3 × 3 mm3 containing the whole tumor and neighboring background including lymph nodes. We used different approaches for data augmentation, including rotation (-15 degrees, +15 degrees), scaling (-20%, 20%), random flipping (3 axes), and elastic deformation (sigma = 1 and proportion to deform = 0.7) to increase the number of training sets. Three state-of-the-art networks, including Dense-VNet, NN-UNet, and Res-Net, with 8 different loss functions, including Dice, generalized Wasserstein Dice loss, Dice plus XEnt loss, generalized Dice loss, cross-entropy, sensitivity-specificity, and Tversky, were used. Overall, 28 different networks were built. Standard image segmentation metrics, including Dice similarity, image-derived PET metrics, first-order, and shape radiomic features, were used for performance assessment of these algorithms. RESULTS The best results in terms of Dice coefficient (mean ± SD) were achieved by cross-entropy for Res-Net (0.86 ± 0.05; 95% confidence interval [CI], 0.85-0.87), Dense-VNet (0.85 ± 0.058; 95% CI, 0.84-0.86), and Dice plus XEnt for NN-UNet (0.87 ± 0.05; 95% CI, 0.86-0.88). The difference between the 3 networks was not statistically significant (P > 0.05). The percent relative error (RE%) of SUVmax quantification was less than 5% in networks with a Dice coefficient more than 0.84, whereas a lower RE% (0.41%) was achieved by Res-Net with cross-entropy loss. For maximum 3-dimensional diameter and sphericity shape features, all networks achieved a RE ≤ 5% and ≤10%, respectively, reflecting a small variability. CONCLUSIONS Deep learning algorithms exhibited promising performance for automated GTV delineation on HNC PET images. Different loss functions performed competitively when using different networks and cross-entropy for Res-Net, Dense-VNet, and Dice plus XEnt for NN-UNet emerged as reliable networks for GTV delineation. Caution should be exercised for clinical deployment owing to the occurrence of outliers in deep learning-based algorithms.
Collapse
Affiliation(s)
- Isaac Shiri
- From the Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland
| | - Hossein Arabi
- From the Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland
| | - Amirhossein Sanaat
- From the Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland
| | - Elnaz Jenabi
- Research Centre for Nuclear Medicine, Shariati Hospital, Tehran University of Medical Sciences, Tehran, Iran
| | | | | |
Collapse
|
22
|
Collet S, Guillamo JS, Berro DH, Chakhoyan A, Constans JM, Lechapt-Zalcman E, Derlon JM, Hatt M, Visvikis D, Guillouet S, Perrio C, Bernaudin M, Valable S. Simultaneous Mapping of Vasculature, Hypoxia, and Proliferation Using Dynamic Susceptibility Contrast MRI, 18F-FMISO PET, and 18F-FLT PET in Relation to Contrast Enhancement in Newly Diagnosed Glioblastoma. J Nucl Med 2021; 62:1349-1356. [PMID: 34016725 PMCID: PMC8724903 DOI: 10.2967/jnumed.120.249524] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2020] [Accepted: 01/14/2021] [Indexed: 11/16/2022] Open
Abstract
Conventional MRI plays a key role in the management of patients with high-grade glioma, but multiparametric MRI and PET tracers could provide further information to better characterize tumor metabolism and heterogeneity by identifying regions having a high risk of recurrence. In this study, we focused on proliferation, hypervascularization, and hypoxia, all factors considered indicative of poor prognosis. They were assessed by measuring uptake of 18F-3'-deoxy-3'-18F-fluorothymidine (18F-FLT), relative cerebral blood volume (rCBV) maps, and uptake of 18F-fluoromisonidazole (18F-FMISO), respectively. For each modality, the volumes and high-uptake subvolumes (hot spots) were semiautomatically segmented and compared with the contrast enhancement (CE) volume on T1-weighted gadolinium-enhanced (T1w-Gd) images, commonly used in the management of patients with glioblastoma. Methods: Dynamic susceptibility contrast-enhanced MRI (31 patients), 18F-FLT PET (20 patients), or 18F-FMISO PET (20 patients), for a total of 31 patients, was performed on preoperative glioblastoma patients. Volumes and hot spots were segmented on SUV maps for 18F-FLT PET (using the fuzzy locally adaptive bayesian algorithm) and 18F-FMISO PET (using a mean contralateral image + 3.3 SDs) and on rCBV maps (using a mean contralateral image + 1.96 SDs) for dynamic susceptibility contrast-enhanced MRI and overlaid on T1w-Gd images. For each modality, the percentages of the peripheral volumes and the peripheral hot spots outside the CE volume were calculated. Results: All tumors showed highly proliferated, hypervascularized, and hypoxic regions. The images also showed pronounced heterogeneity of both tracers regarding their uptake and rCBV maps, within each individual patient. Overlaid volumes on T1w-Gd images showed that some proliferative, hypervascularized, and hypoxic regions extended beyond the CE volume but with marked differences between patients. The ranges of peripheral volume outside the CE volume were 1.6%-155.5%, 1.5%-89.5%, and 3.1%-78.0% for 18F-FLT, rCBV, and 18F-FMISO, respectively. All patients had hyperproliferative hot spots outside the CE volume, whereas hypervascularized and hypoxic hot spots were detected mainly within the enhancing region. Conclusion: Spatial analysis of multiparametric maps with segmented volumes and hot spots provides valuable information to optimize the management and treatment of patients with glioblastoma.
Collapse
Affiliation(s)
- Solène Collet
- Normandie University, UNICAEN, CEA, CNRS, ISTCT/CERVOxy Group, GIP Cyceron, Caen, France
- Radiophysics Department, Centre François Baclesse, Caen, France
| | - Jean-Sébastien Guillamo
- Normandie University, UNICAEN, CEA, CNRS, ISTCT/CERVOxy Group, GIP Cyceron, Caen, France
- Department of Neurology, CHU de Caen, Caen, France
- Department of Neurology, CHU de Nimes, Nimes, France
| | - David Hassanein Berro
- Normandie University, UNICAEN, CEA, CNRS, ISTCT/CERVOxy Group, GIP Cyceron, Caen, France
- Department of Neurosurgery, CHU de Caen, Caen, France
| | - Ararat Chakhoyan
- Normandie University, UNICAEN, CEA, CNRS, ISTCT/CERVOxy Group, GIP Cyceron, Caen, France
| | - Jean-Marc Constans
- Normandie University, UNICAEN, CEA, CNRS, ISTCT/CERVOxy Group, GIP Cyceron, Caen, France
- Department of Neuroradiology, CHU de Caen, Caen, France
| | - Emmanuèle Lechapt-Zalcman
- Normandie University, UNICAEN, CEA, CNRS, ISTCT/CERVOxy Group, GIP Cyceron, Caen, France
- Department of Pathology, CHU de Caen, Caen, France
- Department of Neuropathology, GHU Paris Psychiatry and Neuroscience, Paris, France
| | - Jean-Michel Derlon
- Normandie University, UNICAEN, CEA, CNRS, ISTCT/CERVOxy Group, GIP Cyceron, Caen, France
| | - Mathieu Hatt
- LaTIM, INSERM, UMR 1101, University of Brest, Brest, France; and
| | | | - Stéphane Guillouet
- Normandie University, UNICAEN, CEA, CNRS, ISTCT/LDM-TEP Group, GIP Cyceron, Caen, France
| | - Cécile Perrio
- Normandie University, UNICAEN, CEA, CNRS, ISTCT/LDM-TEP Group, GIP Cyceron, Caen, France
| | - Myriam Bernaudin
- Normandie University, UNICAEN, CEA, CNRS, ISTCT/CERVOxy Group, GIP Cyceron, Caen, France
| | - Samuel Valable
- Normandie University, UNICAEN, CEA, CNRS, ISTCT/CERVOxy Group, GIP Cyceron, Caen, France;
| |
Collapse
|
23
|
Ferreira M, Lovinfosse P, Hermesse J, Decuypere M, Rousseau C, Lucia F, Schick U, Reinhold C, Robin P, Hatt M, Visvikis D, Bernard C, Leijenaar RTH, Kridelka F, Lambin P, Meyer PE, Hustinx R. [ 18F]FDG PET radiomics to predict disease-free survival in cervical cancer: a multi-scanner/center study with external validation. Eur J Nucl Med Mol Imaging 2021; 48:3432-3443. [PMID: 33772334 PMCID: PMC8440288 DOI: 10.1007/s00259-021-05303-5] [Citation(s) in RCA: 31] [Impact Index Per Article: 10.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/12/2020] [Accepted: 03/07/2021] [Indexed: 02/07/2023]
Abstract
PURPOSE To test the performances of native and tumour to liver ratio (TLR) radiomic features extracted from pre-treatment 2-[18F] fluoro-2-deoxy-D-glucose ([18F]FDG) PET/CT and combined with machine learning (ML) for predicting cancer recurrence in patients with locally advanced cervical cancer (LACC). METHODS One hundred fifty-eight patients with LACC from multiple centers were retrospectively included in the study. Tumours were segmented using the Fuzzy Local Adaptive Bayesian (FLAB) algorithm. Radiomic features were extracted from the tumours and from regions drawn over the normal liver. Cox proportional hazard model was used to test statistical significance of clinical and radiomic features. Fivefold cross validation was used to tune the number of features. Seven different feature selection methods and four classifiers were tested. The models with the selected features were trained using bootstrapping and tested in data from each scanner independently. Reproducibility of radiomics features, clinical data added value and effect of ComBat-based harmonisation were evaluated across scanners. RESULTS After a median follow-up of 23 months, 29% of the patients recurred. No individual radiomic or clinical features were significantly associated with cancer recurrence. The best model was obtained using 10 TLR features combined with clinical information. The area under the curve (AUC), F1-score, precision and recall were respectively 0.78 (0.67-0.88), 0.49 (0.25-0.67), 0.42 (0.25-0.60) and 0.63 (0.20-0.80). ComBat did not improve the predictive performance of the best models. Both the TLR and the native models performance varied across scanners used in the test set. CONCLUSION [18F]FDG PET radiomic features combined with ML add relevant information to the standard clinical parameters in terms of LACC patient's outcome but remain subject to variability across PET/CT devices.
Collapse
Affiliation(s)
- Marta Ferreira
- GIGA-CRC in vivo Imaging, University of Liège, GIGA, Avenue de l'Hôpital 11, 4000, Liege, Belgium.
| | - Pierre Lovinfosse
- Division of Nuclear Medicine and Oncological Imaging, University Hospital of Liège, Liège, Belgium
| | - Johanne Hermesse
- Department of Radiation Oncology, Liège University Hospital, Liège, Belgium
| | - Marjolein Decuypere
- Division of Oncological Gynecology, University Hospital of Liège, Liège, Belgium
| | - Caroline Rousseau
- Université de Nantes, CNRS, Inserm, CRCINA, F-44000, Nantes, France
- ICO René Gauducheau, F-44800, Saint-Herblain, France
| | - François Lucia
- Radiation Oncology Department, University Hospital, Brest, France
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | - Ulrike Schick
- Radiation Oncology Department, University Hospital, Brest, France
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | - Caroline Reinhold
- Department of Radiology, McGill University Health Centre (MUHC), Montreal, Canada
| | - Philippe Robin
- Department of Nuclear Medicine and EA3878, Brest University Hospital, University of Brest, Brest, France
| | - Mathieu Hatt
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | | | - Claire Bernard
- Division of Nuclear Medicine and Oncological Imaging, University Hospital of Liège, Liège, Belgium
| | - Ralph T H Leijenaar
- Oncoradiomics SA, Clos Chanmurly 13, 4000, Liège, Belgium
- The-D Lab, Precision Medicine, GROW-School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, Netherlands
| | - Frédéric Kridelka
- Division of Oncological Gynecology, University Hospital of Liège, Liège, Belgium
| | - Philippe Lambin
- The-D Lab, Precision Medicine, GROW-School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, Netherlands
- Department of Radiology and Nuclear Medicine, Maastricht University Medical Centre, Maastricht, The Netherlands
| | - Patrick E Meyer
- Bioinformatics and Systems Biology Lab, University of Liège, Liège, Belgium
| | - Roland Hustinx
- GIGA-CRC in vivo Imaging, University of Liège, GIGA, Avenue de l'Hôpital 11, 4000, Liege, Belgium
| |
Collapse
|
24
|
Yousefirizi F, Jha AK, Brosch-Lenz J, Saboury B, Rahmim A. Toward High-Throughput Artificial Intelligence-Based Segmentation in Oncological PET Imaging. PET Clin 2021; 16:577-596. [PMID: 34537131 DOI: 10.1016/j.cpet.2021.06.001] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
Artificial intelligence (AI) techniques for image-based segmentation have garnered much attention in recent years. Convolutional neural networks have shown impressive results and potential toward fully automated segmentation in medical imaging, and particularly PET imaging. To cope with the limited access to annotated data needed in supervised AI methods, given tedious and prone-to-error manual delineations, semi-supervised and unsupervised AI techniques have also been explored for segmentation of tumors or normal organs in single- and bimodality scans. This work reviews existing AI techniques for segmentation tasks and the evaluation criteria for translational AI-based segmentation efforts toward routine adoption in clinical workflows.
Collapse
Affiliation(s)
- Fereshteh Yousefirizi
- Department of Integrative Oncology, BC Cancer Research Institute, 675 West 10th Avenue, Vancouver, British Columbia V5Z 1L3, Canada.
| | - Abhinav K Jha
- Department of Biomedical Engineering, Washington University in St. Louis, St Louis, MO 63130, USA; Mallinckrodt Institute of Radiology, Washington University School of Medicine, St Louis, MO 63110, USA
| | - Julia Brosch-Lenz
- Department of Integrative Oncology, BC Cancer Research Institute, 675 West 10th Avenue, Vancouver, British Columbia V5Z 1L3, Canada
| | - Babak Saboury
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Bethesda, MD 20892, USA; Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County, Baltimore, MD, USA; Department of Radiology, Hospital of the University of Pennsylvania, 3400 Spruce Street, Philadelphia, PA 19104, USA
| | - Arman Rahmim
- Department of Radiology, University of British Columbia, BC Cancer, BC Cancer Research Institute, 675 West 10th Avenue, Office 6-112, Vancouver, British Columbia V5Z 1L3, Canada; Department of Physics, University of British Columbia, Senior Scientist & Provincial Medical Imaging Physicist, BC Cancer, BC Cancer Research Institute, 675 West 10th Avenue, Office 6-112, Vancouver, British Columbia V5Z 1L3, Canada
| |
Collapse
|
25
|
Parkinson C, Matthams C, Foley K, Spezi E. Artificial intelligence in radiation oncology: A review of its current status and potential application for the radiotherapy workforce. Radiography (Lond) 2021; 27 Suppl 1:S63-S68. [PMID: 34493445 DOI: 10.1016/j.radi.2021.07.012] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2021] [Revised: 07/05/2021] [Accepted: 07/20/2021] [Indexed: 12/15/2022]
Abstract
OBJECTIVE Radiation oncology is a continually evolving speciality. With the development of new imaging modalities and advanced imaging processing techniques, there is an increasing amount of data available to practitioners. In this narrative review, Artificial Intelligence (AI) is used as a reference to machine learning, and its potential, along with current problems in the field of radiation oncology, are considered from a technical position. KEY FINDINGS AI has the potential to harness the availability of data for improving patient outcomes, reducing toxicity, and easing clinical burdens. However, problems including the requirement of complexity of data, undefined core outcomes and limited generalisability are apparent. CONCLUSION This original review highlights considerations for the radiotherapy workforce, particularly therapeutic radiographers, as there will be an increasing requirement for their familiarity with AI due to their unique position as the interface between imaging technology and patients. IMPLICATIONS FOR PRACTICE Collaboration between AI experts and the radiotherapy workforce are required to overcome current issues before clinical adoption. The development of educational resources and standardised reporting of AI studies may help facilitate this.
Collapse
Affiliation(s)
- C Parkinson
- School of Engineering, Cardiff University, UK.
| | | | | | - E Spezi
- School of Engineering, Cardiff University, UK
| |
Collapse
|
26
|
Li K, Zhang R, Cai W. Deep learning convolutional neural network (DLCNN): unleashing the potential of 18F-FDG PET/CT in lymphoma. AMERICAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING 2021; 11:327-331. [PMID: 34513286 PMCID: PMC8414402] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Subscribe] [Scholar Register] [Received: 06/03/2021] [Accepted: 06/07/2021] [Indexed: 06/13/2023]
Abstract
This perspective briefly reviewed the applications of 18F-FDG PET/CT in the clinical management of lymphoma and the need for lesion segmentation in those applications. It discussed the limitations of existing segmentation technologies and the great potential of using deep learning convolutional neural network (DLCNN) to accomplish automatic lymphoma segmentation and characterizations. Finally, the authors shared perspectives on the technical challenges that need to be addressed to fully unleash the potential of DLCNN and 18F-FDG PET/CT in the diagnosis, prognosis, and treatment of lymphoma.
Collapse
Affiliation(s)
- Ke Li
- Department of Medical Physics, University of Wisconsin-Madison1111 Highland Avenue, Madison, WI, USA
- Department of Radiology, University of Wisconsin-Madison600 Highland Avenue, Madison, WI, USA
- University of Wisconsin Carbone Cancer Center600 Highland Avenue, Madison, WI, USA
| | - Ran Zhang
- Department of Medical Physics, University of Wisconsin-Madison1111 Highland Avenue, Madison, WI, USA
| | - Weibo Cai
- Department of Medical Physics, University of Wisconsin-Madison1111 Highland Avenue, Madison, WI, USA
- Department of Radiology, University of Wisconsin-Madison600 Highland Avenue, Madison, WI, USA
- University of Wisconsin Carbone Cancer Center600 Highland Avenue, Madison, WI, USA
| |
Collapse
|
27
|
Da-ano R, Lucia F, Masson I, Abgral R, Alfieri J, Rousseau C, Mervoyer A, Reinhold C, Pradier O, Schick U, Visvikis D, Hatt M. A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets. PLoS One 2021; 16:e0253653. [PMID: 34197503 PMCID: PMC8248970 DOI: 10.1371/journal.pone.0253653] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2021] [Accepted: 06/09/2021] [Indexed: 12/15/2022] Open
Abstract
PURPOSE To facilitate the demonstration of the prognostic value of radiomics, multicenter radiomics studies are needed. Pooling radiomic features of such data in a statistical analysis is however challenging, as they are sensitive to the variability in scanner models, acquisition protocols and reconstruction settings, which is often unavoidable in a multicentre retrospective analysis. A statistical harmonization strategy called ComBat was utilized in radiomics studies to deal with the "center-effect". The goal of the present work was to integrate a transfer learning (TL) technique within ComBat-and recently developed alternate versions of ComBat with improved flexibility (M-ComBat) and robustness (B-ComBat)-to allow the use of a previously determined harmonization transform to the radiomic feature values of new patients from an already known center. MATERIAL AND METHODS The proposed TL approach were incorporated in the four versions of ComBat (standard, B, M, and B-M ComBat). The proposed approach was evaluated using a dataset of 189 locally advanced cervical cancer patients from 3 centers, with magnetic resonance imaging (MRI) and positron emission tomography (PET) images, with the clinical endpoint of predicting local failure. The impact performance of the TL approach was evaluated by comparing the harmonization achieved using only parts of the data to the reference (harmonization achieved using all the available data). It was performed through three different machine learning pipelines. RESULTS The proposed TL technique was successful in harmonizing features of new patients from a known center in all versions of ComBat, leading to predictive models reaching similar performance as the ones developed using the features harmonized with all the data available. CONCLUSION The proposed TL approach enables applying a previously determined ComBat transform to new, previously unseen data.
Collapse
Affiliation(s)
- Ronrick Da-ano
- INSERM, UMR 1101, LaTIM, University of Brest, Brest, France
- * E-mail:
| | - François Lucia
- INSERM, UMR 1101, LaTIM, University of Brest, Brest, France
- Radiation Oncology Department, University Hospital, Brest, France
| | - Ingrid Masson
- INSERM, UMR 1101, LaTIM, University of Brest, Brest, France
- Department of Radiation Oncology, Institut de cancérologie de l’Ouest René-Gauducheau, Saint-Herblain, France
| | - Ronan Abgral
- Department of Nuclear Medicine, University of Brest, Brest, France
| | - Joanne Alfieri
- Department of Radiation Oncology, McGill University Health Centre, Montreal, Quebec
| | - Caroline Rousseau
- Department of Nuclear Medicine, Institut de cancérologie de l’Ouest René-Gauducheau, Saint-Herblain, France
| | - Augustin Mervoyer
- Department of Radiation Oncology, Institut de cancérologie de l’Ouest René-Gauducheau, Saint-Herblain, France
| | - Caroline Reinhold
- Department of Radiology, McGill University Health Centre, Montreal, Canada
- Augmented Intelligence & Precision Health Laboratory of the Research Institute of McGill University Health Centre, Montreal, Canada
| | - Olivier Pradier
- INSERM, UMR 1101, LaTIM, University of Brest, Brest, France
- Radiation Oncology Department, University Hospital, Brest, France
| | - Ulrike Schick
- INSERM, UMR 1101, LaTIM, University of Brest, Brest, France
- Radiation Oncology Department, University Hospital, Brest, France
| | | | - Mathieu Hatt
- INSERM, UMR 1101, LaTIM, University of Brest, Brest, France
| |
Collapse
|
28
|
Lin M, Wynne JF, Zhou B, Wang T, Lei Y, Curran WJ, Liu T, Yang X. Artificial intelligence in tumor subregion analysis based on medical imaging: A review. J Appl Clin Med Phys 2021; 22:10-26. [PMID: 34164913 PMCID: PMC8292694 DOI: 10.1002/acm2.13321] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2020] [Revised: 04/17/2021] [Accepted: 05/22/2021] [Indexed: 12/20/2022] Open
Abstract
Medical imaging is widely used in the diagnosis and treatment of cancer, and artificial intelligence (AI) has achieved tremendous success in medical image analysis. This paper reviews AI-based tumor subregion analysis in medical imaging. We summarize the latest AI-based methods for tumor subregion analysis and their applications. Specifically, we categorize the AI-based methods by training strategy: supervised and unsupervised. A detailed review of each category is presented, highlighting important contributions and achievements. Specific challenges and potential applications of AI in tumor subregion analysis are discussed.
Collapse
Affiliation(s)
- Mingquan Lin
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
| | - Jacob F. Wynne
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
| | - Boran Zhou
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
| | - Tonghe Wang
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
| | - Yang Lei
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
| | - Walter J. Curran
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
| | - Tian Liu
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
| | - Xiaofeng Yang
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
| |
Collapse
|
29
|
Brady L, Wang YN, Rombokas E, Ledoux WR. Comparison of texture-based classification and deep learning for plantar soft tissue histology segmentation. Comput Biol Med 2021; 134:104491. [PMID: 34090017 PMCID: PMC8263502 DOI: 10.1016/j.compbiomed.2021.104491] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2021] [Revised: 05/10/2021] [Accepted: 05/10/2021] [Indexed: 11/22/2022]
Abstract
Histomorphological measurements can be used to identify microstructural changes related to disease pathomechanics, in particular, plantar soft tissue changes with diabetes. However, these measurements are time-consuming and susceptible to sampling and human measurement error. We investigated two approaches to automate segmentation of plantar soft tissue stained with modified Hart's stain for elastin with the eventual goal of subsequent morphological analysis. The first approach used multiple texture- and color-based features with tile-wise classification. The second approach used a convolutional neural network modified from the U-Net architecture with fewer channel dimensions and additional downsampling steps. A hybrid color and texture feature, Fourier reduced histogram of uniform improved opponent color local binary patterns (f-IOCLBP), yielded the best feature-based segmentation, but still performed 3.6% worse on average than the modified U-Net. The texture-based method was sensitive to changes in illumination and stain intensity, and segmentation errors were often in large regions of single tissues or at tissue boundaries. The U-Net was able to segment small, few-pixel tissue boundaries, and errors were often trivial to clean up with post-processing. A U-Net approach outperforms hand-crafted features for segmentation of plantar soft tissue stained with modified Hart's stain for elastin.
Collapse
Affiliation(s)
- Lynda Brady
- Center for Limb Loss and MoBility (CLiMB), VA Puget Sound, Seattle, WA, 98108, USA; Department of Mechanical Engineering, University of Washington, Seattle, WA, 98195, USA
| | - Yak-Nam Wang
- Center for Limb Loss and MoBility (CLiMB), VA Puget Sound, Seattle, WA, 98108, USA; Center for Industrial and Medical Ultrasound, Applied Physics Laboratory, University of Washington, Seattle, WA, 98195, USA
| | - Eric Rombokas
- Center for Limb Loss and MoBility (CLiMB), VA Puget Sound, Seattle, WA, 98108, USA; Department of Mechanical Engineering, University of Washington, Seattle, WA, 98195, USA; Department of Electrical Engineering, University of Washington, Seattle, WA, 98195, USA
| | - William R Ledoux
- Center for Limb Loss and MoBility (CLiMB), VA Puget Sound, Seattle, WA, 98108, USA; Department of Mechanical Engineering, University of Washington, Seattle, WA, 98195, USA; Department of Orthopaedics and Sports Medicine, University of Washington, Seattle, WA, 98195, USA.
| |
Collapse
|
30
|
Liu Z, Mhlanga JC, Laforest R, Derenoncourt PR, Siegel BA, Jha AK. A Bayesian approach to tissue-fraction estimation for oncological PET segmentation. Phys Med Biol 2021; 66. [PMID: 34125078 PMCID: PMC8765116 DOI: 10.1088/1361-6560/ac01f4] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/31/2020] [Accepted: 05/17/2021] [Indexed: 01/06/2023]
Abstract
Tumor segmentation in oncological PET is challenging, a major reason being the partial-volume effects (PVEs) that arise due to low system resolution and finite voxel size. The latter results in tissue-fraction effects (TFEs), i.e. voxels contain a mixture of tissue classes. Conventional segmentation methods are typically designed to assign each image voxel as belonging to a certain tissue class. Thus, these methods are inherently limited in modeling TFEs. To address the challenge of accounting for PVEs, and in particular, TFEs, we propose a Bayesian approach to tissue-fraction estimation for oncological PET segmentation. Specifically, this Bayesian approach estimates the posterior mean of the fractional volume that the tumor occupies within each image voxel. The proposed method, implemented using a deep-learning-based technique, was first evaluated using clinically realistic 2D simulation studies with known ground truth, in the context of segmenting the primary tumor in PET images of patients with lung cancer. The evaluation studies demonstrated that the method accurately estimated the tumor-fraction areas and significantly outperformed widely used conventional PET segmentation methods, including a U-net-based method, on the task of segmenting the tumor. In addition, the proposed method was relatively insensitive to PVEs and yielded reliable tumor segmentation for different clinical-scanner configurations. The method was then evaluated using clinical images of patients with stage IIB/III non-small cell lung cancer from ACRIN 6668/RTOG 0235 multi-center clinical trial. Here, the results showed that the proposed method significantly outperformed all other considered methods and yielded accurate tumor segmentation on patient images with Dice similarity coefficient (DSC) of 0.82 (95% CI: 0.78, 0.86). In particular, the method accurately segmented relatively small tumors, yielding a high DSC of 0.77 for the smallest segmented cross-section of 1.30 cm2. Overall, this study demonstrates the efficacy of the proposed method to accurately segment tumors in PET images.
Collapse
Affiliation(s)
- Ziping Liu
- Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, MO 63130, United States of America
| | - Joyce C Mhlanga
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO 63110, United States of America
| | - Richard Laforest
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO 63110, United States of America
| | - Paul-Robert Derenoncourt
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO 63110, United States of America
| | - Barry A Siegel
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO 63110, United States of America
| | - Abhinav K Jha
- Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, MO 63130, United States of America.,Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO 63110, United States of America
| |
Collapse
|
31
|
Cui R, Chen Z, Wu J, Tan Y, Yu G. A Multiprocessing Scheme for PET Image Pre-Screening, Noise Reduction, Segmentation and Lesion Partitioning. IEEE J Biomed Health Inform 2021; 25:1699-1711. [PMID: 32946400 DOI: 10.1109/jbhi.2020.3024563] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
OBJECTIVE Accurate segmentation and partitioning of lesions in PET images provide computer-aided procedures and doctors with parameters for tumour diagnosis, staging and prognosis. Currently, PET segmentation and lesion partitioning are manually measured by radiologists, which is time consuming and laborious, and tedious manual procedures might lead to inaccurate measurement results. Therefore, we designed a new automatic multiprocessing scheme for PET image pre-screening, noise reduction, segmentation and lesion partitioning in this study. PET image pre-screening can reduce the time cost of noise reduction, segmentation and lesion partitioning methods, and denoising can enhance both quantitative metrics and visual quality for better segmentation accuracy. For pre-screening, we propose a new differential activation filter (DAF) to screen the lesion images from whole-body scanning. For noise reduction, neural network inverse (NN inverse) as the inverse transformation of generalized Anscombe transformation (GAT), which does not depend on the distribution of residual noise, was presented to improve the SNR of images. For segmentation and lesion partitioning, definition density peak clustering (DDPC) was proposed to realize instance segmentation of lesion and normal tissue with unsupervised images, which helped reduce the cost of density calculation and completely deleted the cluster halo. The experimental results of clinical data demonstrate that our proposed methods have good results and better performance in noise reduction, segmentation and lesion partitioning compared with state-of-the-art methods.
Collapse
|
32
|
Rosar F, Schön N, Bohnenberger H, Bartholomä M, Stemler T, Maus S, Khreish F, Ezziddin S, Schaefer-Schuler A. Comparison of different methods for post-therapeutic dosimetry in [ 177Lu]Lu-PSMA-617 radioligand therapy. EJNMMI Phys 2021; 8:40. [PMID: 33950333 PMCID: PMC8099965 DOI: 10.1186/s40658-021-00385-4] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2021] [Accepted: 04/23/2021] [Indexed: 12/24/2022] Open
Abstract
Background Dosimetry is of high importance for optimization of patient-individual PSMA-targeted radioligand therapy (PSMA-RLT). The aim of our study was to evaluate and compare the feasibility of different approaches of image-based absorbed dose estimation in terms of accuracy and effort in clinical routine. Methods Whole-body planar images and SPECT/CT images were acquired from 24 patients and 65 cycles at 24h, 48h, and ≥96h after administration of a mean activity of 6.4 GBq [177Lu]Lu-PSMA-617 (range 3–10.9 GBq). Dosimetry was performed by use of the following approaches: 2D planar-based dosimetry, 3D SPECT/CT-based dosimetry, and hybrid dosimetry combining 2D and 3D data. Absorbed doses were calculated according to IDAC 2.1 for the kidneys, the liver, the salivary glands, and bone metastases. Results Mean absorbed doses estimated by 3D dosimetry (the reference method) were 0.54 ± 0.28 Gy/GBq for the kidneys, 0.10 ± 0.05 Gy/GBq for the liver, 0.81 ± 0.34 Gy/GBq for the parotid gland, 0.72 ± 0.39 Gy/GBq for the submandibular gland, and 1.68 ± 1.32 Gy/GBq for bone metastases. Absorbed doses of normal organs estimated by hybrid dosimetry showed small, non-significant differences (median up to 4.0%) to the results of 3D dosimetry. Using 2D dosimetry, in contrast, significant differences (median up to 10.9%) were observed. Regarding bone metastases, small, but significant differences (median up to 7.0%) of absorbed dose were found for both, 2D dosimetry and hybrid dosimetry. Bland-Altman analysis revealed high agreement between hybrid dosimetry and 3D dosimetry for normal organs and bone metastases, but substantial differences between 2D dosimetry and 3D dosimetry. Conclusion Hybrid dosimetry provides high accuracy in estimation of absorbed dose in comparison to 3D dosimetry for all important organs and is therefore feasible for use in individualized PSMA-RLT.
Collapse
Affiliation(s)
- Florian Rosar
- Department of Nuclear Medicine, Saarland University-Medical Center, Kirrberger Str. Geb. 50, D-66421, Homburg, Germany
| | - Niklas Schön
- Department of Nuclear Medicine, Saarland University-Medical Center, Kirrberger Str. Geb. 50, D-66421, Homburg, Germany
| | - Hendrik Bohnenberger
- Department of Nuclear Medicine, Saarland University-Medical Center, Kirrberger Str. Geb. 50, D-66421, Homburg, Germany
| | - Mark Bartholomä
- Department of Nuclear Medicine, Saarland University-Medical Center, Kirrberger Str. Geb. 50, D-66421, Homburg, Germany
| | - Tobias Stemler
- Department of Nuclear Medicine, Saarland University-Medical Center, Kirrberger Str. Geb. 50, D-66421, Homburg, Germany
| | - Stephan Maus
- Department of Nuclear Medicine, Saarland University-Medical Center, Kirrberger Str. Geb. 50, D-66421, Homburg, Germany
| | - Fadi Khreish
- Department of Nuclear Medicine, Saarland University-Medical Center, Kirrberger Str. Geb. 50, D-66421, Homburg, Germany
| | - Samer Ezziddin
- Department of Nuclear Medicine, Saarland University-Medical Center, Kirrberger Str. Geb. 50, D-66421, Homburg, Germany
| | - Andrea Schaefer-Schuler
- Department of Nuclear Medicine, Saarland University-Medical Center, Kirrberger Str. Geb. 50, D-66421, Homburg, Germany.
| |
Collapse
|
33
|
Iantsen A, Ferreira M, Lucia F, Jaouen V, Reinhold C, Bonaffini P, Alfieri J, Rovira R, Masson I, Robin P, Mervoyer A, Rousseau C, Kridelka F, Decuypere M, Lovinfosse P, Pradier O, Hustinx R, Schick U, Visvikis D, Hatt M. Convolutional neural networks for PET functional volume fully automatic segmentation: development and validation in a multi-center setting. Eur J Nucl Med Mol Imaging 2021; 48:3444-3456. [PMID: 33772335 PMCID: PMC8440243 DOI: 10.1007/s00259-021-05244-z] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2020] [Accepted: 02/07/2021] [Indexed: 11/12/2022]
Abstract
Purpose In this work, we addressed fully automatic determination of tumor functional uptake from positron emission tomography (PET) images without relying on other image modalities or additional prior constraints, in the context of multicenter images with heterogeneous characteristics. Methods In cervical cancer, an additional challenge is the location of the tumor uptake near or even stuck to the bladder. PET datasets of 232 patients from five institutions were exploited. To avoid unreliable manual delineations, the ground truth was generated with a semi-automated approach: a volume containing the tumor and excluding the bladder was first manually determined, then a well-validated, semi-automated approach relying on the Fuzzy locally Adaptive Bayesian (FLAB) algorithm was applied to generate the ground truth. Our model built on the U-Net architecture incorporates residual blocks with concurrent spatial squeeze and excitation modules, as well as learnable non-linear downsampling and upsampling blocks. Experiments relied on cross-validation (four institutions for training and validation, and the fifth for testing). Results The model achieved good Dice similarity coefficient (DSC) with little variability across institutions (0.80 ± 0.03), with higher recall (0.90 ± 0.05) than precision (0.75 ± 0.05) and improved results over the standard U-Net (DSC 0.77 ± 0.05, recall 0.87 ± 0.02, precision 0.74 ± 0.08). Both vastly outperformed a fixed threshold at 40% of SUVmax (DSC 0.33 ± 0.15, recall 0.52 ± 0.17, precision 0.30 ± 0.16). In all cases, the model could determine the tumor uptake without including the bladder. Neither shape priors nor anatomical information was required to achieve efficient training. Conclusion The proposed method could facilitate the deployment of a fully automated radiomics pipeline in such a challenging multicenter context. Supplementary Information The online version contains supplementary material available at 10.1007/s00259-021-05244-z.
Collapse
Affiliation(s)
- Andrei Iantsen
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France.
| | - Marta Ferreira
- GIGA-CRC in vivo Imaging, University of Liège, Liège, Belgium
| | - Francois Lucia
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France
| | - Vincent Jaouen
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France
| | - Caroline Reinhold
- Department of Radiology, McGill University Health Centre (MUHC), Montreal, Canada
| | - Pietro Bonaffini
- Department of Radiology, McGill University Health Centre (MUHC), Montreal, Canada
| | - Joanne Alfieri
- Department of Radiation Oncology, McGill University Health Centre (MUHC), Montreal, Canada
| | - Ramon Rovira
- Gynecology Oncology and Laparoscopy Department, Hospital de la Santa Creu i Sant Pau, Barcelona, Spain
| | - Ingrid Masson
- Department of Radiation Oncology, Institut de Cancérologie de l'Ouest (ICO), Nantes, France
| | - Philippe Robin
- Nuclear Medicine Department, University Hospital, Brest, France
| | - Augustin Mervoyer
- Department of Radiation Oncology, Institut de Cancérologie de l'Ouest (ICO), Nantes, France
| | - Caroline Rousseau
- Nuclear Medicine Department, Institut de Cancérologie de l'Ouest (ICO), Nantes, France
| | - Frédéric Kridelka
- Division of Oncological Gynecology, University Hospital of Liège, Liège, Belgium
| | - Marjolein Decuypere
- Division of Oncological Gynecology, University Hospital of Liège, Liège, Belgium
| | - Pierre Lovinfosse
- Division of Nuclear Medicine and Oncological Imaging, University Hospital of Liège, Liège, Belgium
| | | | - Roland Hustinx
- GIGA-CRC in vivo Imaging, University of Liège, Liège, Belgium
| | - Ulrike Schick
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France
| | | | - Mathieu Hatt
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France
| |
Collapse
|
34
|
Liberini V, De Santi B, Rampado O, Gallio E, Dionisi B, Ceci F, Polverari G, Thuillier P, Molinari F, Deandreis D. Impact of segmentation and discretization on radiomic features in 68Ga-DOTA-TOC PET/CT images of neuroendocrine tumor. EJNMMI Phys 2021; 8:21. [PMID: 33638729 PMCID: PMC7914329 DOI: 10.1186/s40658-021-00367-6] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/08/2020] [Accepted: 02/09/2021] [Indexed: 02/08/2023] Open
Abstract
OBJECTIVE To identify the impact of segmentation methods and intensity discretization on radiomic features (RFs) extraction from 68Ga-DOTA-TOC PET images in patients with neuroendocrine tumors. METHODS Forty-nine patients were retrospectively analyzed. Tumor contouring was performed manually by four different operators and with a semi-automatic edge-based segmentation (SAEB) algorithm. Three SUVmax fixed thresholds (20, 30, 40%) were applied. Fifty-one RFs were extracted applying two different intensity rescale factors for gray-level discretization: one absolute (AR60 = SUV from 0 to 60) and one relative (RR = min-max of the VOI SUV). Dice similarity coefficient (DSC) was calculated to quantify segmentation agreement between different segmentation methods. The impact of segmentation and discretization on RFs was assessed by intra-class correlation coefficients (ICC) and the coefficient of variance (COVL). The RFs' correlation with volume and SUVmax was analyzed by calculating Pearson's correlation coefficients. RESULTS DSC mean value was 0.75 ± 0.11 (0.45-0.92) between SAEB and operators and 0.78 ± 0.09 (0.36-0.97), among the four manual segmentations. The study showed high robustness (ICC > 0.9): (a) in 64.7% of RFs for segmentation methods using AR60, improved by applying SUVmax threshold of 40% (86.5%); (b) in 50.9% of RFs for different SUVmax thresholds using AR60; and (c) in 37% of RFs for discretization settings using different segmentation methods. Several RFs were not correlated with volume and SUVmax. CONCLUSIONS RFs robustness to manual segmentation resulted higher in NET 68Ga-DOTA-TOC images compared to 18F-FDG PET/CT images. Forty percent SUVmax thresholds yield superior RFs stability among operators, however leading to a possible loss of biological information. SAEB segmentation appears to be an optimal alternative to manual segmentation, but further validations are needed. Finally, discretization settings highly impacted on RFs robustness and should always be stated.
Collapse
Affiliation(s)
- Virginia Liberini
- Nuclear Medicine Unit, Department of Medical Sciences, University of Turin, Corso Dogliotti 14, 10126, Turin, Italy.
| | - Bruno De Santi
- Biolab, Department of Electronics and Telecomunications, Politecnico di Torino, Turin, Italy
| | - Osvaldo Rampado
- Medical Physics Unit, AOU Città della Salute e della Scienza, Turin, Italy
| | - Elena Gallio
- Medical Physics Unit, AOU Città della Salute e della Scienza, Turin, Italy
| | - Beatrice Dionisi
- Nuclear Medicine Unit, Department of Medical Sciences, University of Turin, Corso Dogliotti 14, 10126, Turin, Italy
| | - Francesco Ceci
- Nuclear Medicine Unit, Department of Medical Sciences, University of Turin, Corso Dogliotti 14, 10126, Turin, Italy
| | - Giulia Polverari
- Nuclear Medicine Unit, Department of Medical Sciences, University of Turin, Corso Dogliotti 14, 10126, Turin, Italy
| | - Philippe Thuillier
- Nuclear Medicine Unit, Department of Medical Sciences, University of Turin, Corso Dogliotti 14, 10126, Turin, Italy
- Department of Endocrinology, University Hospital of Brest, Politecnico di Torino Brest, Turin, France
| | - Filippo Molinari
- Biolab, Department of Electronics and Telecomunications, Politecnico di Torino, Turin, Italy
| | - Désirée Deandreis
- Nuclear Medicine Unit, Department of Medical Sciences, University of Turin, Corso Dogliotti 14, 10126, Turin, Italy
| |
Collapse
|
35
|
Pfaehler E, Mesotten L, Kramer G, Thomeer M, Vanhove K, de Jong J, Adriaensens P, Hoekstra OS, Boellaard R. Repeatability of two semi-automatic artificial intelligence approaches for tumor segmentation in PET. EJNMMI Res 2021; 11:4. [PMID: 33409747 PMCID: PMC7788118 DOI: 10.1186/s13550-020-00744-9] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2020] [Accepted: 12/10/2020] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Positron emission tomography (PET) is routinely used for cancer staging and treatment follow-up. Metabolic active tumor volume (MATV) as well as total MATV (TMATV-including primary tumor, lymph nodes and metastasis) and/or total lesion glycolysis derived from PET images have been identified as prognostic factor or for the evaluation of treatment efficacy in cancer patients. To this end, a segmentation approach with high precision and repeatability is important. However, the implementation of a repeatable and accurate segmentation algorithm remains an ongoing challenge. METHODS In this study, we compare two semi-automatic artificial intelligence (AI)-based segmentation methods with conventional semi-automatic segmentation approaches in terms of repeatability. One segmentation approach is based on a textural feature (TF) segmentation approach designed for accurate and repeatable segmentation of primary tumors and metastasis. Moreover, a convolutional neural network (CNN) is trained. The algorithms are trained, validated and tested using a lung cancer PET dataset. The segmentation accuracy of both segmentation approaches is compared using the Jaccard coefficient (JC). Additionally, the approaches are externally tested on a fully independent test-retest dataset. The repeatability of the methods is compared with those of two majority vote (MV2, MV3) approaches, 41%SUVMAX, and a SUV > 4 segmentation (SUV4). Repeatability is assessed with test-retest coefficients (TRT%) and intraclass correlation coefficient (ICC). An ICC > 0.9 was regarded as representing excellent repeatability. RESULTS The accuracy of the segmentations with the reference segmentation was good (JC median TF: 0.7, CNN: 0.73). Both segmentation approaches outperformed most other conventional segmentation methods in terms of test-retest coefficient (TRT% mean: TF: 13.0%, CNN: 13.9%, MV2: 14.1%, MV3: 28.1%, 41%SUVMAX: 28.1%, SUV4: 18.1%) and ICC (TF: 0.98, MV2: 0.97, CNN: 0.99, MV3: 0.73, SUV4: 0.81, and 41%SUVMAX: 0.68). CONCLUSION The semi-automatic AI-based segmentation approaches used in this study provided better repeatability than conventional segmentation approaches. Moreover, both algorithms lead to accurate segmentations for both primary tumors as well as metastasis and are therefore good candidates for PET tumor segmentation.
Collapse
Affiliation(s)
- Elisabeth Pfaehler
- Department of Nuclear Medicine and Molecular Imaging, Medical Imaging Center, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands.
| | - Liesbet Mesotten
- Faculty of Medicine and Life Sciences, Hasselt University, Agoralaan Building D, 3590, Diepenbeek, Belgium
- Department of Nuclear Medicine, Ziekenhuis Oost Limburg, Schiepse Bos 6, 3600, Genk, Belgium
| | - Gem Kramer
- Department of Radiology and Nuclear Medicine, VU University Medical Center, Amsterdam, The Netherlands
| | - Michiel Thomeer
- Faculty of Medicine and Life Sciences, Hasselt University, Agoralaan Building D, 3590, Diepenbeek, Belgium
- Department of Respiratory Medicine, Ziekenhuis Oost Limburg, Schiepse Bos 6, 3600, Genk, Belgium
| | - Karolien Vanhove
- Faculty of Medicine and Life Sciences, Hasselt University, Agoralaan Building D, 3590, Diepenbeek, Belgium
- Department of Respiratory Medicine, AZ Vesalius Hospital, Hazelereik 51, 3700, Tongeren, Belgium
| | - Johan de Jong
- Department of Nuclear Medicine and Molecular Imaging, Medical Imaging Center, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Peter Adriaensens
- Institute for Materials Research (IMO) - Division Chemistry, Hasselt University, Agoralaan Building D, 3590, Diepenbeek, Belgium
| | - Otto S Hoekstra
- Department of Radiology and Nuclear Medicine, VU University Medical Center, Amsterdam, The Netherlands
| | - Ronald Boellaard
- Department of Nuclear Medicine and Molecular Imaging, Medical Imaging Center, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
- Department of Radiology and Nuclear Medicine, VU University Medical Center, Amsterdam, The Netherlands
| |
Collapse
|
36
|
Leung KH, Marashdeh W, Wray R, Ashrafinia S, Pomper MG, Rahmim A, Jha AK. A physics-guided modular deep-learning based automated framework for tumor segmentation in PET. Phys Med Biol 2020; 65:245032. [PMID: 32235059 DOI: 10.1088/1361-6560/ab8535] [Citation(s) in RCA: 35] [Impact Index Per Article: 8.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Abstract
An important need exists for reliable positron emission tomography (PET) tumor-segmentation methods for tasks such as PET-based radiation-therapy planning and reliable quantification of volumetric and radiomic features. To address this need, we propose an automated physics-guided deep-learning-based three-module framework to segment PET images on a per-slice basis. The framework is designed to help address the challenges of limited spatial resolution and lack of clinical training data with known ground-truth tumor boundaries in PET. The first module generates PET images containing highly realistic tumors with known ground-truth using a new stochastic and physics-based approach, addressing lack of training data. The second module trains a modified U-net using these images, helping it learn the tumor-segmentation task. The third module fine-tunes this network using a small-sized clinical dataset with radiologist-defined delineations as surrogate ground-truth, helping the framework learn features potentially missed in simulated tumors. The framework was evaluated in the context of segmenting primary tumors in 18F-fluorodeoxyglucose (FDG)-PET images of patients with lung cancer. The framework's accuracy, generalizability to different scanners, sensitivity to partial volume effects (PVEs) and efficacy in reducing the number of training images were quantitatively evaluated using Dice similarity coefficient (DSC) and several other metrics. The framework yielded reliable performance in both simulated (DSC: 0.87 (95% confidence interval (CI): 0.86, 0.88)) and patient images (DSC: 0.73 (95% CI: 0.71, 0.76)), outperformed several widely used semi-automated approaches, accurately segmented relatively small tumors (smallest segmented cross-section was 1.83 cm2), generalized across five PET scanners (DSC: 0.74 (95% CI: 0.71, 0.76)), was relatively unaffected by PVEs, and required low training data (training with data from even 30 patients yielded DSC of 0.70 (95% CI: 0.68, 0.71)). In conclusion, the proposed automated physics-guided deep-learning-based PET-segmentation framework yielded reliable performance in delineating tumors in FDG-PET images of patients with lung cancer.
Collapse
Affiliation(s)
- Kevin H Leung
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, United States of America
- The Russell H. Morgan Department of Radiology, Johns Hopkins University, Baltimore, MD, United States of America
| | - Wael Marashdeh
- Department of Radiology and Nuclear Medicine, Jordan University of Science and Technology, Ar Ramtha, Jordan
| | - Rick Wray
- Memorial Sloan Kettering Cancer Center, Greater New York City Area, NY, United States of America
| | - Saeed Ashrafinia
- The Russell H. Morgan Department of Radiology, Johns Hopkins University, Baltimore, MD, United States of America
- Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, United States of America
| | - Martin G Pomper
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, United States of America
- The Russell H. Morgan Department of Radiology, Johns Hopkins University, Baltimore, MD, United States of America
| | - Arman Rahmim
- The Russell H. Morgan Department of Radiology, Johns Hopkins University, Baltimore, MD, United States of America
- Departments of Radiology and Physics, University of British Columbia, Vancouver, BC, Canada
| | - Abhinav K Jha
- Department of Biomedical Engineering and Mallinckrodt Institute of Radiology, Washington University in St. Louis, St. Louis, MO, United States of America
| |
Collapse
|
37
|
Tankyevych O, Tixier F, Antonorsi N, Filali Razzouki A, Mondon R, Pinto-Leite T, Visvikis D, Hatt M, Cheze Le Rest C. Can alternative PET reconstruction schemes improve the prognostic value of radiomic features in non-small cell lung cancer? Methods 2020; 188:73-83. [PMID: 33197567 DOI: 10.1016/j.ymeth.2020.11.002] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2020] [Revised: 11/09/2020] [Accepted: 11/11/2020] [Indexed: 01/06/2023] Open
Abstract
PURPOSE To evaluate the potential benefit of using alternative reconstruction schemes of PET images for the prognostic value of radiomic features. METHODS Patients (n=91) with non-small cell lung cancer were prospectively included. All had a PET/CT examination before treatment. Three different PET images were reconstructed for each patient: the standard clinical protocol (i.e., 4×4×4 mm3 voxels, 5mm Gaussian filter, denoted '200G5'), as well as using smaller voxels (i.e., 2×2×2 mm3 with a larger reconstruction matrix, denoted 400G1) and/or 1mm post-reconstruction Gaussian filter, denoted 200G1). Metabolic volumes of the primary tumors were semi-automatically delineated on the PET images and IBSI compliant radiomic features (intensity, shape, textural) were extracted. First, the distributions of 200G1 and 400G1 features were compared to the reference clinical protocol (200G5) through Bland-Altman tests and the use of linear mixed models. Then, the prognostic value of the features from each of the 3 reconstructions was evaluated in a univariate analysis, through their stratification power in Kaplan-Meier curves through a threshold set at the median. RESULTS The 3 reconstructions led to different distributions for most of the features. The larger shifts and standard deviations of differences was observed between 200G5 and 400G1, which was also confirmed through linear mixed models. However, these relatively important differences in distributions did not translate into a significant impact on the stratification power of the features in terms of prognosis, although a trend in decreasing prognostic value could be observed (smaller number of features with HR above 2, overall lower HR values). Most prognostic features displayed high correlation with either volume or SUVmax, although there was great variability of prognostic value for similar levels of correlation with these basic metrics. CONCLUSIONS Using smaller voxels or less strong filtering options in the reconstruction settings of PET images compared to the standard clinical protocols led to different distributions of the resulting radiomic features. However, the hierarchy between patients according to these distributions remained overall the same and therefore the resulting stratification power of the radiomic features was not significantly altered. These results should be compared to those obtained in the context of other pathologies where radiomic features displaying lower correlation with volume or SUVmax may have predictive value, such as in cervical cancer.
Collapse
Affiliation(s)
- Olena Tankyevych
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France; Nuclear medicine department, CHU Milétrie, Poitiers, France
| | | | - Nils Antonorsi
- Nuclear medicine department, CHU Milétrie, Poitiers, France
| | | | - Raphael Mondon
- Nuclear medicine department, CHU Milétrie, Poitiers, France
| | | | | | - Mathieu Hatt
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France.
| | - Catherine Cheze Le Rest
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France; Nuclear medicine department, CHU Milétrie, Poitiers, France
| |
Collapse
|
38
|
Tamal M. Intensity threshold based solid tumour segmentation method for Positron Emission Tomography (PET) images: A review. Heliyon 2020; 6:e05267. [PMID: 33163642 PMCID: PMC7610228 DOI: 10.1016/j.heliyon.2020.e05267] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2019] [Revised: 05/14/2020] [Accepted: 10/12/2020] [Indexed: 12/02/2022] Open
Abstract
Accurate, robust and reproducible delineation of tumour in Positron Emission Tomography (PET) is essential for diagnosis, treatment planning and response assessment. Since standardized uptake value (SUV) – a normalized semiquantitative parameter used in PET is represented by the intensity of the PET images and related to the radiotracer uptake, a SUV based threshold method is a natural choice to delineate the tumour. However, determination of an optimum threshold value is a challenging task due to low spatial resolution, and signal-to-noise ratio (SNR) along with finite image sampling constraint. The aim of the review is to summarize different fixed and adaptive threshold-based PET image segmentation approaches under a common mathematical framework Advantages and disadvantages of different threshold based methods are also highlighted from the perspectives of diagnosis, treatment planning and response assessment. Several fixed threshold values (30%–70% of the maximum SUV of the tumour (SUVmaxT)) have been investigated. It has been reported that the fixed threshold-based method is very much dependent on the SNR, tumour to background ratio (TBR) and the size of the tumour. Adaptive threshold-based method, an alternative to fixed threshold, can minimize these dependencies by accounting for tumour to background ratio (TBR) and tumour size. However, the parameters for the adaptive methods need to be calibrated for each PET camera system (e.g., scanner geometry, image acquisition protocol, reconstruction algorithm etc.) and it is not straight forward to implement the same procedure to other PET systems to obtain similar results. It has been reported that the performance of the adaptive methods is also not optimum for smaller volumes with lower TBR and SNR. Statistical analysis carried out on the NEMA thorax phantom images also indicates that regions segmented by the fixed threshold method are significantly different for all cases. On the other hand, the adaptive method provides significantly different segmented regions only for low TBR with different SNR. From this viewpoint, a robust threshold based segmentation method that will be less sensitive to SUVmaxT, SNR, TBR and volume needs to be developed. It was really challenging to compare the performance of different threshold-based methods because the performance of each method was tested on dissimilar data set with different data acquisition and reconstruction protocols along with different TBR, SNR and volumes. To avoid such difficulties, it will be desirable to have a common database of clinical PET images acquired with different image acquisition protocols and different PET cameras to compare the performance of automatic segmentation methods. It is also suggested to report the changes in SNR and TBR while reporting the response using threshold based methods.
Collapse
Affiliation(s)
- Mahbubunnabi Tamal
- Department of Biomedical Engineering, Imam Abdulrahman Bin Faisal University, PO Box 1982, Dammam, 31441, Saudi Arabia
| |
Collapse
|
39
|
Bourbonne V, Da-Ano R, Jaouen V, Lucia F, Dissaux G, Bert J, Pradier O, Visvikis D, Hatt M, Schick U. Radiomics analysis of 3D dose distributions to predict toxicity of radiotherapy for lung cancer. Radiother Oncol 2020; 155:144-150. [PMID: 33161012 DOI: 10.1016/j.radonc.2020.10.040] [Citation(s) in RCA: 33] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2020] [Revised: 10/28/2020] [Accepted: 10/29/2020] [Indexed: 12/25/2022]
Abstract
PURPOSE (Chemo)-radiotherapy (RT) is the gold standard treatment for patients with locally advanced lung cancer non accessible for surgery. However, current toxicity prediction models rely on clinical and dose volume histograms (DVHs) and remain unsufficient. The goal of this work is to investigate the added predictive value of the radiomics approach applied to dose maps regarding acute and late toxicities in both the lungs and esophagus. METHODS Acute and late toxicities scored using the CTCAE v4.0 were retrospectively collected on patients treated with RT in our institution. Radiomic features were extracted from 3D dose maps considering Gy values as grey-levels in images. DVH and usual clinical factors were also considered. Three toxicity prediction models (clinical only, clinical + DVH and combined, i.e., including clinical + DVH + radiomics) were incrementally trained using a neural network on 70% of the patients for prediction of grade ≥2 acute and late pulmonary toxicities (APT/LPT) and grade ≥2 acute esophageal toxicities (AET). After bootstrapping (n = 1000), optimal cut-off values were determined based on the Youden Index. The trained models were then evaluated in the remaining 30% of patients using balanced accuracy (BAcc). RESULTS 167 patients were treated from 2015 to 2018: 78% non small-cell lung cancers, 14% small-cell lung cancers and 8% other histology with a median age at treatment of 66 years. Respectively, 22.2%, 16.8% and 30.0% experienced APT, LPT and AET. In the training set (n = 117), the corresponding BAcc for clinical only/clinical + DVH/combined were 0.68/0.79/0.92, 0.66/0.77/0.87 and 0.68/0.73/0.84. In the testing evaluation (n = 50), these trained models obtained a corresponding BAcc of 0.69/0.69/0.92, 0.76/0.80/0.89 and 0.58/0.73/0.72. CONCLUSION In patients with a lung cancer treated with RT, radiomic features extracted from 3D dose maps seem to surpass usual models based on clinical factors and DVHs for the prediction of APT and LPT.
Collapse
Affiliation(s)
- V Bourbonne
- Radiation Oncology Department, University Hospital, Brest, France; LaTIM, UMR 1101, INSERM, Univ Brest, Brest, France.
| | - R Da-Ano
- LaTIM, UMR 1101, INSERM, Univ Brest, Brest, France
| | - V Jaouen
- LaTIM, UMR 1101, INSERM, Univ Brest, Brest, France
| | - F Lucia
- Radiation Oncology Department, University Hospital, Brest, France; LaTIM, UMR 1101, INSERM, Univ Brest, Brest, France
| | - G Dissaux
- Radiation Oncology Department, University Hospital, Brest, France; LaTIM, UMR 1101, INSERM, Univ Brest, Brest, France
| | - J Bert
- LaTIM, UMR 1101, INSERM, Univ Brest, Brest, France
| | - O Pradier
- Radiation Oncology Department, University Hospital, Brest, France; LaTIM, UMR 1101, INSERM, Univ Brest, Brest, France
| | - D Visvikis
- LaTIM, UMR 1101, INSERM, Univ Brest, Brest, France
| | - M Hatt
- LaTIM, UMR 1101, INSERM, Univ Brest, Brest, France
| | - U Schick
- Radiation Oncology Department, University Hospital, Brest, France; LaTIM, UMR 1101, INSERM, Univ Brest, Brest, France
| |
Collapse
|
40
|
Noortman WA, Vriens D, Slump CH, Bussink J, Meijer TWH, de Geus-Oei LF, van Velden FHP. Adding the temporal domain to PET radiomic features. PLoS One 2020; 15:e0239438. [PMID: 32966313 PMCID: PMC7510999 DOI: 10.1371/journal.pone.0239438] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2020] [Accepted: 09/05/2020] [Indexed: 01/18/2023] Open
Abstract
Background Radiomic features, extracted from positron emission tomography, aim to characterize tumour biology based on tracer intensity, tumour geometry and/or tracer uptake heterogeneity. Currently, radiomic features are derived from static images. However, temporal changes in tracer uptake might reveal new aspects of tumour biology. This study aims to explore additional information of these novel dynamic radiomic features compared to those derived from static or metabolic rate images. Methods Thirty-five patients with non-small cell lung carcinoma underwent dynamic [18F]FDG PET/CT scans. Spatial intensity, shape and texture radiomic features were derived from volumes of interest delineated on static PET and parametric metabolic rate PET. Dynamic grey level cooccurrence matrix (GLCM) and grey level run length matrix (GLRLM) features, assessing the temporal domain unidirectionally, were calculated on eight and sixteen time frames of equal length. Spearman’s rank correlations of parametric and dynamic features with static features were calculated to identify features with potential additional information. Survival analysis was performed for the non-redundant temporal features and a selection of static features using Kaplan-Meier analysis. Results Three out of 90 parametric features showed moderate correlations with corresponding static features (ρ≥0.61), all other features showed high correlations (ρ>0.7). Dynamic features are robust independent of frame duration. Five out of 22 dynamic GLCM features showed a negligible to moderate correlation with any static feature, suggesting additional information. All sixteen dynamic GLRLM features showed high correlations with static features, implying redundancy. Log-rank analyses of Kaplan-Meier survival curves for all features dichotomised at the median were insignificant. Conclusion This study suggests that, compared to static features, some dynamic GLCM radiomic features show different information, whereas parametric features provide minimal additional information. Future studies should be conducted in larger populations to assess whether there is a clinical benefit of radiomics using the temporal domain over traditional radiomics.
Collapse
Affiliation(s)
- Wyanne A. Noortman
- Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
- Biomedical Photonic Imaging Group, University of Twente, Enschede, The Netherlands
- * E-mail:
| | - Dennis Vriens
- Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
| | - Cornelis H. Slump
- Robotics and Mechatronics, Technical Medical Centre, University of Twente, Enschede, The Netherlands
| | - Johan Bussink
- Department of Radiation Oncology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Tineke W. H. Meijer
- Department of Radiation Oncology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Lioe-Fee de Geus-Oei
- Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
- Biomedical Photonic Imaging Group, University of Twente, Enschede, The Netherlands
| | | |
Collapse
|
41
|
Li L, Lu W, Tan S. Variational PET/CT Tumor Co-segmentation Integrated with PET Restoration. IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2020; 4:37-49. [PMID: 32939423 DOI: 10.1109/trpms.2019.2911597] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
PET and CT are widely used imaging modalities in radiation oncology. PET imaging has a high contrast but blurry tumor edges due to its limited spatial resolution, while CT imaging has a high resolution but a low contrast between tumor and soft normal tissues. Tumor segmentation from either a single PET or CT image is difficult. It is known that co-segmentation methods utilizing the complementary information between PET and CT can improve segmentation accuracy. These information can be either consistent or inconsistent in the image-level. How to correctly localize tumor edges with these inconsistent information is a major challenge for co-segmentation methods. In this study, we proposed a novel variational method for tumor co-segmentation in PET/CT, with a fusion strategy specifically designed to handle the information inconsistency between PET and CT in an adaptive way - the method can automatically decide which modality should be more trustful when PET and CT disagree to each other for localizing the tumor boundary. The proposed method was constructed based on the Γ-convergence approximation of the Mumford-Shah (MS) segmentation model. A PET restoration process was integrated into the co-segmentation process, which further eliminate the uncertainty for tumor segmentation introduced by the blurring of tumor edges in PET. The performance of the proposed method was validated on a test dataset with fifty non-small cell lung cancer patients. Experimental results demonstrated that the proposed method had a high accuracy for PET/CT co-segmentation and PET restoration, and can accurately estimate the blur kernel of the PET scanner as well. For those complex images in which the tumors exhibit Fluorodeoxyglucose (FDG) uptake inhomogeneity or even invade adjacent soft normal tissues, the proposed method can still accurately segment the tumors. It achieved an average dice similarity indexes (DSI) of 0.85 ± 0.06, volume error (VE) of 0.09 ± 0.08, and classification error (CE) of 0.31 ± 0.13.
Collapse
Affiliation(s)
- Laquan Li
- Key Laboratory of Image Processing and Intelligent Control of Ministry of Education of China, School of Automation, Huazhong University of Science and Technology, Wuhan 430074, China
| | - Wei Lu
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York 10065, USA
| | - Shan Tan
- Key Laboratory of Image Processing and Intelligent Control of Ministry of Education of China, School of Automation, Huazhong University of Science and Technology, Wuhan 430074, China
| |
Collapse
|
42
|
Abgral R, Bourhis D, Calais J, Lucia F, Leclère JC, Salaün PY, Vera P, Schick U. Correlation between fluorodeoxyglucose hotspots on preradiotherapy PET/CT and areas of cancer local relapse: Systematic review of literature. Cancer Radiother 2020; 24:444-452. [DOI: 10.1016/j.canrad.2020.04.010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2020] [Accepted: 04/26/2020] [Indexed: 10/24/2022]
|
43
|
Lucia F, Bourbonne V, Gujral D, Dissaux G, Miranda O, Mauguen M, Pradier O, Abgral R, Schick U. Impact of suboptimal dosimetric coverage of pretherapeutic 18F-FDG PET/CT hotspots on outcome in patients with locally advanced cervical cancer treated with chemoradiotherapy followed by brachytherapy. Clin Transl Radiat Oncol 2020; 23:50-59. [PMID: 32435702 PMCID: PMC7229342 DOI: 10.1016/j.ctro.2020.05.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2020] [Revised: 05/04/2020] [Accepted: 05/06/2020] [Indexed: 11/23/2022] Open
Abstract
INTRODUCTION Areas of high uptake on pre-treatment 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT), denoted as "hotspots", have been identified as preferential sites of local relapse in locally advanced cervical cancer (LACC). The purpose of this study was to analyze the dosimetric coverage of these hotspots with high dose-rate brachytherapy (BT). METHODS For each patient, a rigid registration of the CT from the pre-treatment PET/CT with the radiotherapy planning CT was performed using 3D SlicerTM, followed by a manual volume correction by translation and deformation if necessary. The fuzzy locally adaptive Bayesian (FLAB) algorithm was applied to PET images to simultaneously define an overall tumour volume and the high-uptake sub-volume V1. The inclusion of V1 in the high-risk clinical target volume (CTV HR) and its dosimetric coverage were evaluated using 3D SlicerTM. The average of the 3-4 BT sessions was reported. RESULTS Forty-two patients with recurrence after chemoradiotherapy (CRT) for LACC were matched to 42 patients without recurrence. Mean ± standard deviation follow-up was 26 ± 11 months. In the recurrence group, V1 was not included in the CTV HR and not covered by the 85 Gy isodose in 17/42 patients (41%) (1/20 with pelvic recurrence and 16/22 with distant recurrence) and not by the 80 Gy isodose in 7/42 patients (17%) (all with distant recurrence). In the non-recurrence group, V1 was not included in CTV HR and not covered by the 85 Gy isodose in 3 patients only (7%). The hotspots coverage by the 85 Gy isodose was significantly better in patients who did not recur, but only when compared to patients with distant relapse (p < 0.0001). CONCLUSION Suboptimal dosimetric coverage of high FDG uptakes on pretherapeutic PET could be associated with an increased risk of recurrence.
Collapse
Affiliation(s)
- François Lucia
- Radiation Oncology Department, University Hospital, Brest, France
| | | | - Dorothy Gujral
- Clinical Oncology Department, Imperial College Healthcare NHS Trust, Charing Cross Hospital, Hammersmith, London, UK
- Department of Cancer and Surgery, Imperial College London, London, UK
| | - Gurvan Dissaux
- Radiation Oncology Department, University Hospital, Brest, France
| | - Omar Miranda
- Radiation Oncology Department, University Hospital, Brest, France
| | - Maelle Mauguen
- Radiation Oncology Department, University Hospital, Brest, France
| | - Olivier Pradier
- Radiation Oncology Department, University Hospital, Brest, France
| | - Ronan Abgral
- Nuclear Medicine Department, University Hospital, Brest, France
| | - Ulrike Schick
- Radiation Oncology Department, University Hospital, Brest, France
| |
Collapse
|
44
|
Da-Ano R, Masson I, Lucia F, Doré M, Robin P, Alfieri J, Rousseau C, Mervoyer A, Reinhold C, Castelli J, De Crevoisier R, Rameé JF, Pradier O, Schick U, Visvikis D, Hatt M. Performance comparison of modified ComBat for harmonization of radiomic features for multicenter studies. Sci Rep 2020; 10:10248. [PMID: 32581221 PMCID: PMC7314795 DOI: 10.1038/s41598-020-66110-w] [Citation(s) in RCA: 107] [Impact Index Per Article: 26.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2020] [Accepted: 05/04/2020] [Indexed: 11/08/2022] Open
Abstract
Multicenter studies are needed to demonstrate the clinical potential value of radiomics as a prognostic tool. However, variability in scanner models, acquisition protocols and reconstruction settings are unavoidable and radiomic features are notoriously sensitive to these factors, which hinders pooling them in a statistical analysis. A statistical harmonization method called ComBat was developed to deal with the "batch effect" in gene expression microarray data and was used in radiomics studies to deal with the "center-effect". Our goal was to evaluate modifications in ComBat allowing for more flexibility in choosing a reference and improving robustness of the estimation. Two modified ComBat versions were evaluated: M-ComBat allows to transform all features distributions to a chosen reference, instead of the overall mean, providing more flexibility. B-ComBat adds bootstrap and Monte Carlo for improved robustness in the estimation. BM-ComBat combines both modifications. The four versions were compared regarding their ability to harmonize features in a multicenter context in two different clinical datasets. The first contains 119 locally advanced cervical cancer patients from 3 centers, with magnetic resonance imaging and positron emission tomography imaging. In that case ComBat was applied with 3 labels corresponding to each center. The second one contains 98 locally advanced laryngeal cancer patients from 5 centers with contrast-enhanced computed tomography. In that specific case, because imaging settings were highly heterogeneous even within each of the five centers, unsupervised clustering was used to determine two labels for applying ComBat. The impact of each harmonization was evaluated through three different machine learning pipelines for the modelling step in predicting the clinical outcomes, across two performance metrics (balanced accuracy and Matthews correlation coefficient). Before harmonization, almost all radiomic features had significantly different distributions between labels. These differences were successfully removed with all ComBat versions. The predictive ability of the radiomic models was always improved with harmonization and the improved ComBat provided the best results. This was observed consistently in both datasets, through all machine learning pipelines and performance metrics. The proposed modifications allow for more flexibility and robustness in the estimation. They also slightly but consistently improve the predictive power of resulting radiomic models.
Collapse
Affiliation(s)
- R Da-Ano
- INSERM, UMR 1101, LaTIM, University of Brest, Brest, France.
| | - I Masson
- INSERM, UMR 1101, LaTIM, University of Brest, Brest, France
- Department of Radiation Oncology, Institut de cancérologie de l'Ouest René-Gauducheau, Saint-Herblain, France
| | - F Lucia
- INSERM, UMR 1101, LaTIM, University of Brest, Brest, France
- Radiation Oncology Department, University Hospital, Brest, France
| | - M Doré
- Department of Radiation Oncology, Institut de cancérologie de l'Ouest René-Gauducheau, Saint-Herblain, France
| | - P Robin
- Department of Nuclear Medicine, University of Brest, Brest, France
| | - J Alfieri
- Department of Radiation Oncology, McGill University Health Centre, Montreal, Quebec, Canada
| | - C Rousseau
- Department of Nuclear Medicine, Institut de cancerologie de l'Ouest René-Gauducheau, Saint-Herblain, France
- CRCINA, University of Nantes, INSERM UMR1232, CNRS-ERL6001, Nantes, France
| | - A Mervoyer
- Department of Radiation Oncology, Institut de cancérologie de l'Ouest René-Gauducheau, Saint-Herblain, France
| | - C Reinhold
- Department of Radiology, McGill University Health Centre, Montreal, Canada
| | - J Castelli
- Radiotherapy Department Cancer, Institute Eugene Marquis, Rennes, France
- University of Rennes 1, LTSI, Rennes, France
| | - R De Crevoisier
- Radiotherapy Department Cancer, Institute Eugene Marquis, Rennes, France
- University of Rennes 1, LTSI, Rennes, France
| | - J F Rameé
- Department of Medical Oncology, Centre Hospitalier de Vendee, La Roche sur Yon, France
| | - O Pradier
- INSERM, UMR 1101, LaTIM, University of Brest, Brest, France
- Radiation Oncology Department, University Hospital, Brest, France
| | - U Schick
- INSERM, UMR 1101, LaTIM, University of Brest, Brest, France
- Radiation Oncology Department, University Hospital, Brest, France
| | - D Visvikis
- INSERM, UMR 1101, LaTIM, University of Brest, Brest, France
| | - M Hatt
- INSERM, UMR 1101, LaTIM, University of Brest, Brest, France
| |
Collapse
|
45
|
Truffault B, Bourhis D, Chaput A, Calais J, Robin P, Le Pennec R, Lucia F, Leclère JC, Gujral DM, Vera P, Salaün PY, Schick U, Abgral R. Correlation Between FDG Hotspots on Pre-radiotherapy PET/CT and Areas of HNSCC Local Relapse: Impact of Treatment Position and Images Registration Method. Front Med (Lausanne) 2020; 7:218. [PMID: 32582727 PMCID: PMC7287148 DOI: 10.3389/fmed.2020.00218] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2020] [Accepted: 04/30/2020] [Indexed: 01/04/2023] Open
Abstract
Aim: Several series have already demonstrated that intratumoral subvolumes with high tracer avidity (hotspots) in 18F-flurodesoxyglucose positron-emission tomography (FDG-PET/CT) are preferential sites of local recurrence (LR) in various solid cancers after radiotherapy (RT), becoming potential targets for dose escalation. However, studies conducted on head and neck squamous cell carcinoma (HNSCC) found only a moderate overlap between pre- and post-treatment subvolumes. A limitation of these studies was that scans were not performed in RT treatment position (TP) and were coregistred using a rigid registration (RR) method. We sought to study (i) the influence of FDG-PET/CT acquisition in TP and (ii) the impact of using an elastic registration (ER) method to improve the localization of hotpots in HNSCC. Methods: Consecutive patients with HNSCC treated by RT between March 2015 and September 2017 who underwent FDG-PET/CT in TP at initial staging (PETA) and during follow-up (PETR) were prospectively included. We utilized a control group scanned in non treatment position (NTP) from our previous retrospective study. Scans were registered with both RR and ER methods. Various sub-volumes (AX; x = 30, 40, 50, 60, 70, 80, and 90%SUVmax) within the initial tumor and in the subsequent LR (RX; x = 40 and 70%SUVmax) were overlaid on the initial PET/CT for comparison [Dice, Jaccard, overlap fraction = OF, common volume/baseline volume = AXnRX/AX, common volume/recurrent volume = AXnRX/RX]. Results: Of 199 patients included, 43 (21.6%) had LR (TP = 15; NTP = 28). The overlap between A30, A40, and A50 sub-volumes on PETA and the whole metabolic volume of recurrence R40 and R70 on PETR showed moderate to good agreements (0.41–0.64) with OF and AXnRX/RX index, regardless of registration method or patient position. Comparison of registration method demonstrated OF and AXnRX/RX indices (x = 30% to 50%SUVmax) were significantly higher with ER vs. RR in NTP (p < 0.03), but not in TP. For patient position, the OF and AXnRX/RX indices were higher in TP than in NTP when RR was used with a trend toward significance, particularly for x=40%SUVmax (0.50±0.22 vs. 0.31 ± 0.13, p = 0.094). Conclusion: Our study suggested that PET/CT acquired in TP improves results in the localization of FDG hotspots in HNSCC. If TP is not possible, using an ER method is significantly more accurate than RR for overlap estimation.
Collapse
Affiliation(s)
- Blandine Truffault
- Department of Nuclear Medicine, Brest University Hospital, Brest, France
| | - David Bourhis
- Department of Nuclear Medicine, Brest University Hospital, Brest, France.,European University of Brittany, Brest, France
| | - Anne Chaput
- Department of Nuclear Medicine, Brest University Hospital, Brest, France
| | - Jeremie Calais
- Department of Medical and Molecular Pharmacology, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States.,Department of Nuclear Medicine and Radiology, Henri Becquerel Center, QuantIF (LITIS EA 4108 - FR CNRS 3638), Rouen University Hospital, Rouen, France
| | - Philippe Robin
- Department of Nuclear Medicine, Brest University Hospital, Brest, France.,European University of Brittany, Brest, France
| | - Romain Le Pennec
- Department of Nuclear Medicine, Brest University Hospital, Brest, France
| | - François Lucia
- Department of Radiotherapy, Brest University Hospital, Brest, France
| | | | - Dorothy M Gujral
- Clinical Oncology Department, Imperial College Healthcare NHS Trust, Charing Cross Hospital, Hammersmith, London, United Kingdom.,Department of Cancer and Surgery, Imperial College London, London, United Kingdom
| | - Pierre Vera
- Department of Nuclear Medicine and Radiology, Henri Becquerel Center, QuantIF (LITIS EA 4108 - FR CNRS 3638), Rouen University Hospital, Rouen, France
| | - Pierre-Yves Salaün
- Department of Nuclear Medicine, Brest University Hospital, Brest, France.,European University of Brittany, Brest, France
| | - Ulrike Schick
- Department of Radiotherapy, Brest University Hospital, Brest, France
| | - Ronan Abgral
- Department of Nuclear Medicine, Brest University Hospital, Brest, France.,European University of Brittany, Brest, France
| |
Collapse
|
46
|
Lucia F, Miranda O, Abgral R, Bourbonne V, Dissaux G, Pradier O, Hatt M, Schick U. Use of Baseline 18 F-FDG PET/CT to Identify Initial Sub-Volumes Associated With Local Failure After Concomitant Chemoradiotherapy in Locally Advanced Cervical Cancer. Front Oncol 2020; 10:678. [PMID: 32457839 PMCID: PMC7221149 DOI: 10.3389/fonc.2020.00678] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2020] [Accepted: 04/09/2020] [Indexed: 12/27/2022] Open
Abstract
Introduction: Locally advanced cervical cancer (CC) patients treated by chemoradiotherapy (CRT) have a significant local recurrence rate. The objective of this work was to assess the overlap between the initial high-uptake sub-volume (V1) on baseline 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) scans and the metabolic relapse (V2) sites after CRT in locally advanced CC. Methods: PET/CT performed before treatment and at relapse in 21 patients diagnosed with LACC and treated with CRT were retrospectively analyzed. CT images at the time of recurrence were registered to baseline CT using the 3D Slicer TM Expert Automated Registration module. The corresponding PET images were then registered using the corresponding transform. The fuzzy locally adaptive Bayesian (FLAB) algorithm was implemented using 3 classes (one for the background and the other two for tumor) in PET1 to simultaneously define an overall tumor volume and the sub-volume V1. In PET2, FLAB was implemented using 2 classes (one for background, one for tumor), in order to define V2. Four indices were used to determine the overlap between V1 and V2 (Dice coefficients, overlap fraction, X = (V1nV2)/V1 and Y = (V1nV2)/V2). Results: The mean (±standard deviation) follow-up was 26 ± 11 months. The measured overlaps between V1 and V2 were moderate to good according to the four metrics, with 0.62-0.81 (0.72 ± 0.05), 0.72-1.00 (0.85 ± 0.10), 0.55-1.00 (0.73 ± 0.16) and 0.50-1.00 (0.76 ± 0.12) for Dice, overlap fraction, X and Y, respectively. Conclusion: In our study, the overlaps between the initial high-uptake sub-volume and the recurrent metabolic volume showed moderate to good concordance. These results now need to be confirmed in a larger cohort using a more standardized patient repositioning procedure for sequential PET/CT imaging, as there is potential for RT dose escalation exploiting the pre-treatment PET high-uptake sub-volume.
Collapse
Affiliation(s)
- François Lucia
- Radiation Oncology Department, University Hospital, Brest, France
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | - Omar Miranda
- Radiation Oncology Department, University Hospital, Brest, France
| | - Ronan Abgral
- Nuclear Medicine Department, University Hospital, Brest, France
| | - Vincent Bourbonne
- Radiation Oncology Department, University Hospital, Brest, France
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | - Gurvan Dissaux
- Radiation Oncology Department, University Hospital, Brest, France
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | - Olivier Pradier
- Radiation Oncology Department, University Hospital, Brest, France
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | - Mathieu Hatt
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | - Ulrike Schick
- Radiation Oncology Department, University Hospital, Brest, France
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| |
Collapse
|
47
|
Tixier F, Cheze-le-Rest C, Schick U, Simon B, Dufour X, Key S, Pradier O, Aubry M, Hatt M, Corcos L, Visvikis D. Transcriptomics in cancer revealed by Positron Emission Tomography radiomics. Sci Rep 2020; 10:5660. [PMID: 32221360 PMCID: PMC7101432 DOI: 10.1038/s41598-020-62414-z] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/09/2019] [Accepted: 03/13/2020] [Indexed: 11/09/2022] Open
Abstract
Metabolic images from Positron Emission Tomography (PET) are used routinely for diagnosis, follow-up or treatment planning purposes of cancer patients. In this study we aimed at determining if radiomic features extracted from 18F-Fluoro Deoxy Glucose (FDG) PET images could mirror tumor transcriptomics. In this study we analyzed 45 patients with locally advanced head and neck cancer (H&N) that underwent FDG-PET scans at the time of diagnosis and transcriptome analysis using RNAs from both cancer and healthy tissues on microarrays. Association between PET radiomics and transcriptomics was carried out with the Genomica software and a functional annotation was used to associate PET radiomics, gene expression and altered biological pathways. We identified relationships between PET radiomics and genes involved in cell-cycle, disease, DNA repair, extracellular matrix organization, immune system, metabolism or signal transduction pathways, according to the Reactome classification. Our results suggest that these FDG PET radiomic features could be used to infer tissue gene expression and cellular pathway activity in H&N cancers. These observations strengthen the value of radiomics as a promising approach to personalize treatments through targeting tumor-specific molecular processes.
Collapse
Affiliation(s)
- Florent Tixier
- Department of Nuclear Medicine, Poitiers University Hospital, Poitiers, France.
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France.
| | - Catherine Cheze-le-Rest
- Department of Nuclear Medicine, Poitiers University Hospital, Poitiers, France
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | - Ulrike Schick
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
- Radiation Oncology Department, University Hospital, Brest, France
| | - Brigitte Simon
- INSERM, UMR 1078, Université de Brest, Génétique Génomique Fonctionnelle et Biotechnologies, Etablissement Français du Sang, Brest, France
| | - Xavier Dufour
- Head and Neck Department, Poitiers University Hospital, Poitiers, France
| | - Stéphane Key
- Radiation Oncology Department, University Hospital, Brest, France
| | - Olivier Pradier
- Radiation Oncology Department, University Hospital, Brest, France
| | - Marc Aubry
- CNRS, UMR 6290, IGDR, Université de Rennes 1, Rennes, France
| | - Mathieu Hatt
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | - Laurent Corcos
- INSERM, UMR 1078, Université de Brest, Génétique Génomique Fonctionnelle et Biotechnologies, Etablissement Français du Sang, Brest, France
| | | |
Collapse
|
48
|
Parghane RV, Basu S. PET/Computed Tomography in Treatment Response Assessment in Cancer. PET Clin 2020; 15:101-123. [DOI: 10.1016/j.cpet.2019.08.005] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
|
49
|
Koç A, Güveniş A. Design and evaluation of an accurate CNR-guided small region iterative restoration-based tumor segmentation scheme for PET using both simulated and real heterogeneous tumors. Med Biol Eng Comput 2019; 58:335-355. [PMID: 31848977 DOI: 10.1007/s11517-019-02094-8] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/08/2019] [Accepted: 12/06/2019] [Indexed: 11/30/2022]
Abstract
Tumor delineation accuracy directly affects the effectiveness of radiotherapy. This study presents a methodology that minimizes potential errors during the automated segmentation of tumors in PET images. Iterative blind deconvolution was implemented in a region of interest encompassing the tumor with the number of iterations determined from contrast-to-noise ratios. The active contour and random forest classification-based segmentation method was evaluated using three distinct image databases that included both synthetic and real heterogeneous tumors. Ground truths about tumor volumes were known precisely. The volumes of the tumors were in the range of 0.49-26.34 cm3, 0.64-1.52 cm3, and 40.38-203.84 cm3 respectively. Widely available software tools, namely, MATLAB, MIPAV, and ITK-SNAP were utilized. When using the active contour method, image restoration reduced mean errors in volumes estimation from 95.85 to 3.37%, from 815.63 to 17.45%, and from 32.61 to 6.80% for the three datasets. The accuracy gains were higher using datasets that include smaller tumors for which PVE is known to be more predominant. Computation time was reduced by a factor of about 10 in the smaller deconvolution region. Contrast-to-noise ratios were improved for all tumors in all data. The presented methodology has the potential to improve delineation accuracy in particular for smaller tumors at practically feasible computational times. Graphical abstract Evaluation of accurate lesion volumes using CNR-guided and ROI-based restoration method for PET images.
Collapse
Affiliation(s)
- Alpaslan Koç
- Institute of Biomedical Engineering, Boğaziçi University, Kandilli Kampüs, Çengelköy, 34684, Istanbul, Turkey.
| | - Albert Güveniş
- Institute of Biomedical Engineering, Boğaziçi University, Kandilli Kampüs, Çengelköy, 34684, Istanbul, Turkey
| |
Collapse
|
50
|
Hatt M, Tixier F, Desseroit MC, Badic B, Laurent B, Visvikis D, Rest CCL. Revisiting the identification of tumor sub-volumes predictive of residual uptake after (chemo)radiotherapy: influence of segmentation methods on 18F-FDG PET/CT images. Sci Rep 2019; 9:14925. [PMID: 31624321 PMCID: PMC6797734 DOI: 10.1038/s41598-019-51096-x] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2018] [Accepted: 09/19/2019] [Indexed: 12/19/2022] Open
Abstract
Our aim was to evaluate the impact of the accuracy of image segmentation techniques on establishing an overlap between pre-treatment and post-treatment functional tumour volumes in 18FDG-PET/CT imaging. Simulated images and a clinical cohort were considered. Three different configurations (large, small or non-existent overlap) of a single simulated example was used to elucidate the behaviour of each approach. Fifty-four oesophageal and head and neck (H&N) cancer patients treated with radiochemotherapy with both pre- and post-treatment PET/CT scans were retrospectively analysed. Images were registered and volumes were determined using combinations of thresholds and the fuzzy locally adaptive Bayesian (FLAB) algorithm. Four overlap metrics were calculated. The simulations showed that thresholds lead to biased overlap estimation and that accurate metrics are obtained despite spatially inaccurate volumes. In the clinical dataset, only 17 patients exhibited residual uptake smaller than the pre-treatment volume. Overlaps obtained with FLAB were consistently moderate for esophageal and low for H&N cases across all metrics. Overlaps obtained using threshold combinations varied greatly depending on thresholds and metrics. In both cases overlaps were variable across patients. Our findings do not support optimisation of radiotherapy planning based on pre-treatment 18FDG-PET/CT image definition of high-uptake sub-volumes. Combinations of thresholds may have led to overestimation of overlaps in previous studies.
Collapse
Affiliation(s)
- Mathieu Hatt
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France.
| | - Florent Tixier
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
- Nuclear Medicine department, CHU Milétrie, Poitiers, France
| | - Marie-Charlotte Desseroit
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
- Nuclear Medicine department, CHU Milétrie, Poitiers, France
| | - Bogdan Badic
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | | | | | - Catherine Cheze Le Rest
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
- Nuclear Medicine department, CHU Milétrie, Poitiers, France
| |
Collapse
|