1
|
Bernatz S, Reddin IG, Fenton TR, Vogl TJ, Wild PJ, Köllermann J, Mandel P, Wenzel M, Hoeh B, Mahmoudi S, Koch V, Grünewald LD, Hammerstingl R, Döring C, Harter PN, Weber KJ. Epigenetic profiling of prostate cancer reveals potential prognostic signatures. J Cancer Res Clin Oncol 2024; 150:396. [PMID: 39180680 PMCID: PMC11344710 DOI: 10.1007/s00432-024-05921-0] [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: 07/03/2024] [Accepted: 08/11/2024] [Indexed: 08/26/2024]
Abstract
PURPOSE While epigenetic profiling discovered biomarkers in several tumor entities, its application in prostate cancer is still limited. We explored DNA methylation-based deconvolution of benign and malignant prostate tissue for biomarker discovery and the potential of radiomics as a non-invasive surrogate. METHODS We retrospectively included 30 patients (63 [58-79] years) with prostate cancer (PCa) who had a multiparametric MRI of the prostate before radical prostatectomy between 2014 and 2019. The control group comprised four patients with benign prostate tissue adjacent to the PCa lesions and four patients with benign prostatic hyperplasia. Tissue punches of all lesions were obtained. DNA methylation analysis and reference-free in silico deconvolution were conducted to retrieve Latent Methylation Components (LCMs). LCM-based clustering was analyzed for cellular composition and correlated with clinical disease parameters. Additionally, PCa and adjacent benign lesions were analyzed using radiomics to predict the epigenetic signatures non-invasively. RESULTS LCMs identified two clusters with potential prognostic impact. Cluster one was associated with malignant prostate tissue (p < 0.001) and reduced immune-cell-related signatures (p = 0.004) of CD19 and CD4 cells. Cluster one comprised exclusively malignant prostate tissue enriched for significant prostate cancer and advanced tumor stages (p < 0.03 for both). No radiomics model could non-invasively predict the epigenetic clusters. CONCLUSION Epigenetic clusters were associated with prognostically and clinically relevant metrics in prostate cancer. Further, immune cell-related signatures differed significantly between prognostically favorable and unfavorable clusters. Further research is necessary to explore potential diagnostic and therapeutic implications.
Collapse
Affiliation(s)
- Simon Bernatz
- Goethe University Frankfurt, University Hospital, Clinic for Radiology and Nuclear Medicine, Frankfurt am Main, Germany
- Goethe University Frankfurt, University Hospital, Dr. Senckenberg Institute for Pathology, Frankfurt am Main, Germany
- Frankfurt Cancer Institute (FCI), Frankfurt am Main, Germany
| | - Ian G Reddin
- School of Cancer Sciences, University of Southampton, Southampton, UK
| | - Tim R Fenton
- School of Cancer Sciences, University of Southampton, Southampton, UK
| | - Thomas J Vogl
- Goethe University Frankfurt, University Hospital, Clinic for Radiology and Nuclear Medicine, Frankfurt am Main, Germany
| | - Peter J Wild
- Goethe University Frankfurt, University Hospital, Dr. Senckenberg Institute for Pathology, Frankfurt am Main, Germany
- Frankfurt Institute for Advanced Studies (FIAS), Frankfurt am Main, Germany
| | - Jens Köllermann
- Goethe University Frankfurt, University Hospital, Dr. Senckenberg Institute for Pathology, Frankfurt am Main, Germany
| | - Philipp Mandel
- Goethe University Frankfurt, University Hospital, Department of Urology, Frankfurt am Main, Germany
| | - Mike Wenzel
- Goethe University Frankfurt, University Hospital, Department of Urology, Frankfurt am Main, Germany
| | - Benedikt Hoeh
- Goethe University Frankfurt, University Hospital, Department of Urology, Frankfurt am Main, Germany
| | - Scherwin Mahmoudi
- Goethe University Frankfurt, University Hospital, Clinic for Radiology and Nuclear Medicine, Frankfurt am Main, Germany
| | - Vitali Koch
- Goethe University Frankfurt, University Hospital, Clinic for Radiology and Nuclear Medicine, Frankfurt am Main, Germany
| | - Leon D Grünewald
- Goethe University Frankfurt, University Hospital, Clinic for Radiology and Nuclear Medicine, Frankfurt am Main, Germany
| | - Renate Hammerstingl
- Goethe University Frankfurt, University Hospital, Clinic for Radiology and Nuclear Medicine, Frankfurt am Main, Germany
| | - Claudia Döring
- Goethe University Frankfurt, University Hospital, Dr. Senckenberg Institute for Pathology, Frankfurt am Main, Germany
| | - Patrick N Harter
- Frankfurt Cancer Institute (FCI), Frankfurt am Main, Germany
- Goethe University Frankfurt, University Hospital, Neurological Institute (Edinger Institute), Frankfurt am Main, Germany
- German Cancer Consortium (DKTK) Partner Site Frankfurt/Mainz, Frankfurt am Main, Germany
- German Cancer Research Center (DKFZ), Heidelberg, Germany
- Goethe University Frankfurt, University Hospital, University Cancer Center (UCT), Frankfurt am Main, Germany
- Center for Neuropathology and Prion Research, Faculty of Medicine, LMU Munich, Munich, Germany
- German Cancer Consortium (DKTK), Partner Site Munich, A Partnership Between DKFZ and University/University Hospital, LMU Munich, Munich, Germany
| | - Katharina J Weber
- Frankfurt Cancer Institute (FCI), Frankfurt am Main, Germany.
- Goethe University Frankfurt, University Hospital, Neurological Institute (Edinger Institute), Frankfurt am Main, Germany.
- German Cancer Consortium (DKTK) Partner Site Frankfurt/Mainz, Frankfurt am Main, Germany.
- German Cancer Research Center (DKFZ), Heidelberg, Germany.
- Goethe University Frankfurt, University Hospital, University Cancer Center (UCT), Frankfurt am Main, Germany.
| |
Collapse
|
2
|
Mendes B, Domingues I, Santos J. Radiomic Pipelines for Prostate Cancer in External Beam Radiation Therapy: A Review of Methods and Future Directions. J Clin Med 2024; 13:3907. [PMID: 38999473 PMCID: PMC11242211 DOI: 10.3390/jcm13133907] [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: 05/26/2024] [Revised: 06/27/2024] [Accepted: 07/01/2024] [Indexed: 07/14/2024] Open
Abstract
Background: Prostate Cancer (PCa) is asymptomatic at an early stage and often painless, requiring only active surveillance. External Beam Radiotherapy (EBRT) is currently a curative option for localised and locally advanced diseases and a palliative option for metastatic low-volume disease. Although highly effective, especially in a hypofractionation scheme, 17.4% to 39.4% of all patients suffer from cancer recurrence after EBRT. But, radiographic findings also correlate with significant differences in protein expression patterns. In the PCa EBRT workflow, several imaging modalities are available for grading, staging and contouring. Using image data characterisation algorithms (radiomics), one can provide a quantitative analysis of prognostic and predictive treatment outcomes. Methods: This literature review searched for original studies in radiomics for PCa in the context of EBRT. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, this review includes 73 new studies and analyses datasets, imaging modality, segmentation technique, feature extraction, selection and model building methods. Results: Magnetic Resonance Imaging (MRI) is the preferred imaging modality for radiomic studies in PCa but Computed Tomography (CT), Positron Emission Tomography (PET) and Ultrasound (US) may offer valuable insights on tumour characterisation and treatment response prediction. Conclusions: Most radiomic studies used small, homogeneous and private datasets lacking external validation and variability. Future research should focus on collaborative efforts to create large, multicentric datasets and develop standardised methodologies, ensuring the full potential of radiomics in clinical practice.
Collapse
Affiliation(s)
- Bruno Mendes
- Research Center of the Portuguese Institute of Oncology of Porto (CI-IPOP), Medical Physics, Radiobiology and Radiological Protection Group, R. Dr. António Bernardino de Almeida, 4200-072 Porto, Portugal; (I.D.); (J.S.)
- Faculty of Engineering of the University of Porto (FEUP), R. Dr. Roberto Frias, 4200-465 Porto, Portugal
| | - Inês Domingues
- Research Center of the Portuguese Institute of Oncology of Porto (CI-IPOP), Medical Physics, Radiobiology and Radiological Protection Group, R. Dr. António Bernardino de Almeida, 4200-072 Porto, Portugal; (I.D.); (J.S.)
- Polytechnic Institute of Coimbra, Coimbra Institute of Engineering, Rua Pedro Nunes-Quinta da Nora, 3030-199 Coimbra, Portugal
| | - João Santos
- Research Center of the Portuguese Institute of Oncology of Porto (CI-IPOP), Medical Physics, Radiobiology and Radiological Protection Group, R. Dr. António Bernardino de Almeida, 4200-072 Porto, Portugal; (I.D.); (J.S.)
- School of Medicine and Biomedical Sciences (ICBAS), R. Jorge de Viterbo Ferreira 228, 4050-313 Porto, Portugal
| |
Collapse
|
3
|
Rodrigues NM, Almeida JGD, Verde ASC, Gaivão AM, Bilreiro C, Santiago I, Ip J, Belião S, Moreno R, Matos C, Vanneschi L, Tsiknakis M, Marias K, Regge D, Silva S, Papanikolaou N. Analysis of domain shift in whole prostate gland, zonal and lesions segmentation and detection, using multicentric retrospective data. Comput Biol Med 2024; 171:108216. [PMID: 38442555 DOI: 10.1016/j.compbiomed.2024.108216] [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: 12/12/2023] [Revised: 02/09/2024] [Accepted: 02/25/2024] [Indexed: 03/07/2024]
Abstract
Despite being one of the most prevalent forms of cancer, prostate cancer (PCa) shows a significantly high survival rate, provided there is timely detection and treatment. Computational methods can help make this detection process considerably faster and more robust. However, some modern machine-learning approaches require accurate segmentation of the prostate gland and the index lesion. Since performing manual segmentations is a very time-consuming task, and highly prone to inter-observer variability, there is a need to develop robust semi-automatic segmentation models. In this work, we leverage the large and highly diverse ProstateNet dataset, which includes 638 whole gland and 461 lesion segmentation masks, from 3 different scanner manufacturers provided by 14 institutions, in addition to other 3 independent public datasets, to train accurate and robust segmentation models for the whole prostate gland, zones and lesions. We show that models trained on large amounts of diverse data are better at generalizing to data from other institutions and obtained with other manufacturers, outperforming models trained on single-institution single-manufacturer datasets in all segmentation tasks. Furthermore, we show that lesion segmentation models trained on ProstateNet can be reliably used as lesion detection models.
Collapse
Affiliation(s)
- Nuno Miguel Rodrigues
- Computational Clinical Imaging Group, Champalimaud Foundation, Portugal; LASIGE, Faculty of Sciences, University of Lisbon, Portugal.
| | | | | | - Ana Mascarenhas Gaivão
- Radiology Department, Champalimaud Clinical Center, Champalimaud Foundation, Lisbon, Portugal
| | - Carlos Bilreiro
- Radiology Department, Champalimaud Clinical Center, Champalimaud Foundation, Lisbon, Portugal
| | - Inês Santiago
- Radiology Department, Champalimaud Clinical Center, Champalimaud Foundation, Lisbon, Portugal
| | - Joana Ip
- Radiology Department, Champalimaud Clinical Center, Champalimaud Foundation, Lisbon, Portugal
| | - Sara Belião
- Radiology Department, Champalimaud Clinical Center, Champalimaud Foundation, Lisbon, Portugal
| | - Raquel Moreno
- Computational Clinical Imaging Group, Champalimaud Foundation, Portugal
| | - Celso Matos
- Computational Clinical Imaging Group, Champalimaud Foundation, Portugal
| | - Leonardo Vanneschi
- NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, 1070-312 Lisboa, Portugal
| | - Manolis Tsiknakis
- Institute of Computer Science, Foundation for Research and Technology Hellas (FORTH), GR 700 13, Heraklion, Greece; Department of Electrical and Computer Engineering, Hellenic Mediterranean University, GR 710 04, Heraklion, Greece
| | - Kostas Marias
- Department of Electrical and Computer Engineering, Hellenic Mediterranean University, GR 710 04, Heraklion, Greece; Computational BioMedicine Laboratory (CBML), Institute of Computer Science, Foundation for Research and Technology - Hellas (FORTH), Heraklion, Greece
| | - Daniele Regge
- Department of Radiology, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale 142 Km 3.95, Candiolo, Turin 10060, Italy; Department of Surgical Sciences, University of Turin, Turin 10124, Italy
| | - Sara Silva
- LASIGE, Faculty of Sciences, University of Lisbon, Portugal
| | - Nickolas Papanikolaou
- Computational Clinical Imaging Group, Champalimaud Foundation, Portugal; Department of Radiology, Royal Marsden Hospital, Sutton, UK
| |
Collapse
|
4
|
Nicoletti G, Mazzetti S, Maimone G, Cignini V, Cuocolo R, Faletti R, Gatti M, Imbriaco M, Longo N, Ponsiglione A, Russo F, Serafini A, Stanzione A, Regge D, Giannini V. Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRI. Cancers (Basel) 2024; 16:203. [PMID: 38201630 PMCID: PMC10778513 DOI: 10.3390/cancers16010203] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2023] [Revised: 12/19/2023] [Accepted: 12/29/2023] [Indexed: 01/12/2024] Open
Abstract
In the last years, several studies demonstrated that low-aggressive (Grade Group (GG) ≤ 2) and high-aggressive (GG ≥ 3) prostate cancers (PCas) have different prognoses and mortality. Therefore, the aim of this study was to develop and externally validate a radiomic model to noninvasively classify low-aggressive and high-aggressive PCas based on biparametric magnetic resonance imaging (bpMRI). To this end, 283 patients were retrospectively enrolled from four centers. Features were extracted from apparent diffusion coefficient (ADC) maps and T2-weighted (T2w) sequences. A cross-validation (CV) strategy was adopted to assess the robustness of several classifiers using two out of the four centers. Then, the best classifier was externally validated using the other two centers. An explanation for the final radiomics signature was provided through Shapley additive explanation (SHAP) values and partial dependence plots (PDP). The best combination was a naïve Bayes classifier trained with ten features that reached promising results, i.e., an area under the receiver operating characteristic (ROC) curve (AUC) of 0.75 and 0.73 in the construction and external validation set, respectively. The findings of our work suggest that our radiomics model could help distinguish between low- and high-aggressive PCa. This noninvasive approach, if further validated and integrated into a clinical decision support system able to automatically detect PCa, could help clinicians managing men with suspicion of PCa.
Collapse
Affiliation(s)
- Giulia Nicoletti
- Department of Electronics and Telecommunications, Polytechnic of Turin, Corso Duca degli Abruzzi, 24, 10129 Turin, Italy;
- Department of Surgical Sciences, University of Turin, Corso Dogliotti, 14, 10126 Turin, Italy; (V.C.); (R.F.); (A.S.)
| | - Simone Mazzetti
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale, 142—KM 3.95, 10060 Candiolo, Italy; (S.M.); (G.M.); (F.R.); (D.R.)
| | - Giovanni Maimone
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale, 142—KM 3.95, 10060 Candiolo, Italy; (S.M.); (G.M.); (F.R.); (D.R.)
| | - Valentina Cignini
- Department of Surgical Sciences, University of Turin, Corso Dogliotti, 14, 10126 Turin, Italy; (V.C.); (R.F.); (A.S.)
| | - Renato Cuocolo
- Department of Medicine, Surgery, and Dentistry, University of Salerno, Via Salvador Allende, 43, 84081 Baronissi, Italy;
| | - Riccardo Faletti
- Department of Surgical Sciences, University of Turin, Corso Dogliotti, 14, 10126 Turin, Italy; (V.C.); (R.F.); (A.S.)
| | - Marco Gatti
- Department of Surgical Sciences, University of Turin, Corso Dogliotti, 14, 10126 Turin, Italy; (V.C.); (R.F.); (A.S.)
| | - Massimo Imbriaco
- Department of Advanced Biomedical Sciences, University of Naples “Federico II”, Via Pansini, 5, 80131 Naples, Italy; (M.I.); (A.P.)
| | - Nicola Longo
- Department of Neurosciences, Reproductive Sciences and Odontostomatology, University of Naples “Federico II”, Via Pansini, 5, 80131 Naples, Italy;
| | - Andrea Ponsiglione
- Department of Advanced Biomedical Sciences, University of Naples “Federico II”, Via Pansini, 5, 80131 Naples, Italy; (M.I.); (A.P.)
| | - Filippo Russo
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale, 142—KM 3.95, 10060 Candiolo, Italy; (S.M.); (G.M.); (F.R.); (D.R.)
| | - Alessandro Serafini
- Department of Surgical Sciences, University of Turin, Corso Dogliotti, 14, 10126 Turin, Italy; (V.C.); (R.F.); (A.S.)
| | - Arnaldo Stanzione
- Department of Advanced Biomedical Sciences, University of Naples “Federico II”, Via Pansini, 5, 80131 Naples, Italy; (M.I.); (A.P.)
| | - Daniele Regge
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale, 142—KM 3.95, 10060 Candiolo, Italy; (S.M.); (G.M.); (F.R.); (D.R.)
- Department of Translational Research, Via Risorgimento, 36, University of Pisa, 56126 Pisa, Italy
| | - Valentina Giannini
- Department of Surgical Sciences, University of Turin, Corso Dogliotti, 14, 10126 Turin, Italy; (V.C.); (R.F.); (A.S.)
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale, 142—KM 3.95, 10060 Candiolo, Italy; (S.M.); (G.M.); (F.R.); (D.R.)
| |
Collapse
|
5
|
Khanfari H, Mehranfar S, Cheki M, Mohammadi Sadr M, Moniri S, Heydarheydari S, Rezaeijo SM. Exploring the efficacy of multi-flavored feature extraction with radiomics and deep features for prostate cancer grading on mpMRI. BMC Med Imaging 2023; 23:195. [PMID: 37993801 PMCID: PMC10664625 DOI: 10.1186/s12880-023-01140-0] [Citation(s) in RCA: 19] [Impact Index Per Article: 19.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2023] [Accepted: 10/26/2023] [Indexed: 11/24/2023] Open
Abstract
BACKGROUND The purpose of this study is to investigate the use of radiomics and deep features obtained from multiparametric magnetic resonance imaging (mpMRI) for grading prostate cancer. We propose a novel approach called multi-flavored feature extraction or tensor, which combines four mpMRI images using eight different fusion techniques to create 52 images or datasets for each patient. We evaluate the effectiveness of this approach in grading prostate cancer and compare it to traditional methods. METHODS We used the PROSTATEx-2 dataset consisting of 111 patients' images from T2W-transverse, T2W-sagittal, DWI, and ADC images. We used eight fusion techniques to merge T2W, DWI, and ADC images, namely Laplacian Pyramid, Ratio of the low-pass pyramid, Discrete Wavelet Transform, Dual-Tree Complex Wavelet Transform, Curvelet Transform, Wavelet Fusion, Weighted Fusion, and Principal Component Analysis. Prostate cancer images were manually segmented, and radiomics features were extracted using the Pyradiomics library in Python. We also used an Autoencoder for deep feature extraction. We used five different feature sets to train the classifiers: all radiomics features, all deep features, radiomics features linked with PCA, deep features linked with PCA, and a combination of radiomics and deep features. We processed the data, including balancing, standardization, PCA, correlation, and Least Absolute Shrinkage and Selection Operator (LASSO) regression. Finally, we used nine classifiers to classify different Gleason grades. RESULTS Our results show that the SVM classifier with deep features linked with PCA achieved the most promising results, with an AUC of 0.94 and a balanced accuracy of 0.79. Logistic regression performed best when using only the deep features, with an AUC of 0.93 and balanced accuracy of 0.76. Gaussian Naive Bayes had lower performance compared to other classifiers, while KNN achieved high performance using deep features linked with PCA. Random Forest performed well with the combination of deep features and radiomics features, achieving an AUC of 0.94 and balanced accuracy of 0.76. The Voting classifiers showed higher performance when using only the deep features, with Voting 2 achieving the highest performance, with an AUC of 0.95 and balanced accuracy of 0.78. CONCLUSION Our study concludes that the proposed multi-flavored feature extraction or tensor approach using radiomics and deep features can be an effective method for grading prostate cancer. Our findings suggest that deep features may be more effective than radiomics features alone in accurately classifying prostate cancer.
Collapse
Affiliation(s)
- Hasan Khanfari
- Department of Mechanical Engineering, Petroleum University of Technology, Ahvaz, Iran
| | - Saeed Mehranfar
- Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran
| | - Mohsen Cheki
- Department of Medical Imaging and Radiation Sciences, Faculty of Paramedicine, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran
| | - Mahmoud Mohammadi Sadr
- Department of Medical Physics, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran
| | - Samir Moniri
- Department of Medical Imaging and Radiation Sciences, Faculty of Paramedicine, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran
| | - Sahel Heydarheydari
- Department of Medical Imaging and Radiation Sciences, Faculty of Paramedicine, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran
| | - Seyed Masoud Rezaeijo
- Department of Medical Physics, Faculty of Medicine, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran.
- Cancer Research Center, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran.
| |
Collapse
|
6
|
Duenweg SR, Bobholz SA, Barrett MJ, Lowman AK, Winiarz A, Nath B, Stebbins M, Bukowy J, Iczkowski KA, Jacobsohn KM, Vincent-Sheldon S, LaViolette PS. T2-Weighted MRI Radiomic Features Predict Prostate Cancer Presence and Eventual Biochemical Recurrence. Cancers (Basel) 2023; 15:4437. [PMID: 37760407 PMCID: PMC10526331 DOI: 10.3390/cancers15184437] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Revised: 08/23/2023] [Accepted: 08/31/2023] [Indexed: 09/29/2023] Open
Abstract
Prostate cancer (PCa) is the most diagnosed non-cutaneous cancer in men. Despite therapies such as radical prostatectomy, which is considered curative, distant metastases may form, resulting in biochemical recurrence (BCR). This study used radiomic features calculated from multi-parametric magnetic resonance imaging (MP-MRI) to evaluate their ability to predict BCR and PCa presence. Data from a total of 279 patients, of which 46 experienced BCR, undergoing MP-MRI prior to surgery were assessed for this study. After surgery, the prostate was sectioned using patient-specific 3D-printed slicing jigs modeled using the T2-weighted imaging (T2WI). Sectioned tissue was stained, digitized, and annotated by a GU-fellowship trained pathologist for cancer presence. Digitized slides and annotations were co-registered to the T2WI and radiomic features were calculated across the whole prostate and cancerous lesions. A tree regression model was fitted to assess the ability of radiomic features to predict BCR, and a tree classification model was fitted with the same radiomic features to classify regions of cancer. We found that 10 radiomic features predicted eventual BCR with an AUC of 0.97 and classified cancer at an accuracy of 89.9%. This study showcases the application of a radiomic feature-based tool to screen for the presence of prostate cancer and assess patient prognosis, as determined by biochemical recurrence.
Collapse
Affiliation(s)
- Savannah R. Duenweg
- Department of Biophysics, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA; (S.R.D.); (M.S.)
| | - Samuel A. Bobholz
- Department of Radiology, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA
| | - Michael J. Barrett
- Department of Radiology, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA
| | - Allison K. Lowman
- Department of Radiology, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA
| | - Aleksandra Winiarz
- Department of Biophysics, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA; (S.R.D.); (M.S.)
| | - Biprojit Nath
- Department of Biophysics, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA; (S.R.D.); (M.S.)
| | - Margaret Stebbins
- Department of Biophysics, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA; (S.R.D.); (M.S.)
| | - John Bukowy
- Department of Electrical Engineering and Computer Science, Milwaukee School of Engineering, 1025 N Broadway, Milwaukee, WI 53202, USA
| | - Kenneth A. Iczkowski
- Department of Pathology, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA;
| | - Kenneth M. Jacobsohn
- Department of Urology, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA
| | - Stephanie Vincent-Sheldon
- Department of Radiology, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA
| | - Peter S. LaViolette
- Department of Biophysics, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA; (S.R.D.); (M.S.)
- Department of Radiology, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA
- Department of Biomedical Engineering, Medical College of Wisconsin, 8701 Watertown Plank Rd., Milwaukee, WI 53226, USA
| |
Collapse
|
7
|
Li L, Shiradkar R, Tirumani SH, Bittencourt LK, Fu P, Mahran A, Buzzy C, Stricker PD, Rastinehad AR, Magi-Galluzzi C, Ponsky L, Klein E, Purysko AS, Madabhushi A. Novel radiomic analysis on bi-parametric MRI for characterizing differences between MR non-visible and visible clinically significant prostate cancer. Eur J Radiol Open 2023; 10:100496. [PMID: 37396490 PMCID: PMC10311200 DOI: 10.1016/j.ejro.2023.100496] [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: 03/22/2023] [Revised: 06/01/2023] [Accepted: 06/04/2023] [Indexed: 07/04/2023] Open
Abstract
Background around one third of clinically significant prostate cancer (CsPCa) foci are reported to be MRI non-visible (MRI─). Objective To quantify the differences between MR visible (MRI+) and MRI─ CsPCa using intra- and peri-lesional radiomic features on bi-parametric MRI (bpMRI). Methods This retrospective and multi-institutional study comprised 164 patients with pre-biopsy 3T prostate multi-parametric MRI from 2014 to 2017. The MRI─ CsPCa referred to lesions with PI-RADS v2 score < 3 but ISUP grade group > 1. Three experienced radiologists were involved in annotating lesions and PI-RADS assignment. The validation set (Dv) comprised 52 patients from a single institution, the remaining 112 patients were used for training (Dt). 200 radiomic features were extracted from intra-lesional and peri-lesional regions on bpMRI.Logistic regression with least absolute shrinkage and selection operator (LASSO) and 10-fold cross-validation was applied on Dt to identify radiomic features associated with MRI─ and MRI+ CsPCa to generate corresponding risk scores RMRI─ and RMRI+. RbpMRI was further generated by integrating RMRI─ and RMRI+. Statistical significance was determined using the Wilcoxon signed-rank test. Results Both intra-lesional and peri-lesional bpMRI Haralick and CoLlAGe radiomic features were significantly associated with MRI─ CsPCa (p < 0.05). Intra-lesional ADC Haralick and CoLlAGe radiomic features were significantly different among MRI─ and MRI+ CsPCa (p < 0.05). RbpMRI yielded the highest AUC of 0.82 (95 % CI 0.72-0.91) compared to AUCs of RMRI+ 0.76 (95 % CI 0.63-0.89), and PI-RADS 0.58 (95 % CI 0.50-0.72) on Dv. RbpMRI correctly reclassified 10 out of 14 MRI─ CsPCa on Dv. Conclusion Our preliminary results demonstrated that both intra-lesional and peri-lesional bpMRI radiomic features were significantly associated with MRI─ CsPCa. These features could assist in CsPCa identification on bpMRI.
Collapse
Affiliation(s)
- Lin Li
- Center for Computational Imaging and Personalized Diagnostics, Case Western Reserve University, Cleveland, OH, USA
| | - Rakesh Shiradkar
- Center for Computational Imaging and Personalized Diagnostics, Case Western Reserve University, Cleveland, OH, USA
- Department of Biomedical Engineering, Emory University and Georgia Institute of Technology
| | | | | | - Pingfu Fu
- Department of Population and Quantitative Health Sciences, Case Western Reserve University, Cleveland, OH, USA
| | - Amr Mahran
- Urology Institute, University Hospitals Cleveland Medical Center, Cleveland, OH, USA
| | - Christina Buzzy
- Center for Computational Imaging and Personalized Diagnostics, Case Western Reserve University, Cleveland, OH, USA
| | | | | | | | - Lee Ponsky
- Urology Institute, University Hospitals Cleveland Medical Center, Cleveland, OH, USA
- Case Western Reserve University School of Medicine, Cleveland, OH, USA
| | - Eric Klein
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Andrei S. Purysko
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
- Imaging Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Anant Madabhushi
- Department of Biomedical Engineering, Emory University and Georgia Institute of Technology
- Atlanta Veterans Affairs Medical Center, Atlanta, GA, United States
| |
Collapse
|
8
|
Rodrigues A, Rodrigues N, Santinha J, Lisitskaya MV, Uysal A, Matos C, Domingues I, Papanikolaou N. Value of handcrafted and deep radiomic features towards training robust machine learning classifiers for prediction of prostate cancer disease aggressiveness. Sci Rep 2023; 13:6206. [PMID: 37069257 PMCID: PMC10110526 DOI: 10.1038/s41598-023-33339-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2023] [Accepted: 04/11/2023] [Indexed: 04/19/2023] Open
Abstract
There is a growing piece of evidence that artificial intelligence may be helpful in the entire prostate cancer disease continuum. However, building machine learning algorithms robust to inter- and intra-radiologist segmentation variability is still a challenge. With this goal in mind, several model training approaches were compared: removing unstable features according to the intraclass correlation coefficient (ICC); training independently with features extracted from each radiologist's mask; training with the feature average between both radiologists; extracting radiomic features from the intersection or union of masks; and creating a heterogeneous dataset by randomly selecting one of the radiologists' masks for each patient. The classifier trained with this last resampled dataset presented with the lowest generalization error, suggesting that training with heterogeneous data leads to the development of the most robust classifiers. On the contrary, removing features with low ICC resulted in the highest generalization error. The selected radiomics dataset, with the randomly chosen radiologists, was concatenated with deep features extracted from neural networks trained to segment the whole prostate. This new hybrid dataset was then used to train a classifier. The results revealed that, even though the hybrid classifier was less overfitted than the one trained with deep features, it still was unable to outperform the radiomics model.
Collapse
Affiliation(s)
- Ana Rodrigues
- Champalimaud Research, Champalimaud Foundation, Lisbon, Portugal.
- Faculty of Medicine, University of Porto, Porto, Portugal.
| | - Nuno Rodrigues
- Champalimaud Research, Champalimaud Foundation, Lisbon, Portugal
- LASIGE, Faculty of Sciences, University of Lisbon, Lisbon, Portugal
| | - João Santinha
- Champalimaud Research, Champalimaud Foundation, Lisbon, Portugal
- Instituto Superior Técnico, University of Lisbon, Lisbon, Portugal
| | - Maria V Lisitskaya
- Cand. of Sci. (Med.), Radiologist at Radiology Department with CT and MRI, Medical Research and Educational Center, Lomonosov Moscow State University, Moscow, Russia
| | - Aycan Uysal
- Gulhane Medical School, University of Health Sciences, Ankara, Turkey
| | - Celso Matos
- Champalimaud Research, Champalimaud Foundation, Lisbon, Portugal
| | - Inês Domingues
- Instituto Politécnico de Coimbra, Instituto Superior de Engenharia, Rua Pedro Nunes-Quinta da Nora, 3030-199, Coimbra, Portugal
- Centro de Investigação do Instituto Português de Oncologia do Porto (CI-IPOP): Grupo de Física Médica, Radiobiologia e Protecção Radiológica, Porto, Portugal
| | | |
Collapse
|
9
|
Volumetric visceral fat machine learning phenotype on CT for differential diagnosis of inflammatory bowel disease. Eur Radiol 2023; 33:1862-1872. [PMID: 36255487 DOI: 10.1007/s00330-022-09171-x] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2022] [Revised: 08/17/2022] [Accepted: 09/15/2022] [Indexed: 11/04/2022]
Abstract
OBJECTIVES To investigate whether volumetric visceral adipose tissue (VAT) features extracted using radiomics and three-dimensional convolutional neural network (3D-CNN) approach are effective in differentiating Crohn's disease (CD) and ulcerative colitis (UC). METHODS This retrospective study enrolled 316 patients (mean age, 36.25 ± 13.58 [standard deviation]; 219 men) with confirmed diagnosis of CD and UC who underwent CT enterography between 2012 and 2021. Volumetric VAT was semi-automatically segmented on the arterial phase images. Radiomics analysis was performed using principal component analysis (PCA) and the least absolute shrinkage and selection operator (LASSO) logistic regression algorithm. We developed a 3D-CNN model using VAT imaging data from the training cohort. Clinical covariates including age, sex, modified body mass index, and disease duration that impact VAT were added to the machine learning model for adjustment. The model's performance was evaluated on the testing cohort separating from the model's development process by its discrimination and clinical utility. RESULTS Volumetric VAT radiomics analysis with LASSO had the highest AUC value of 0.717 (95% CI, 0.614-0.820), though difference of diagnostic performance among the 3D-CNN model (AUC = 0.693; 95% CI, 0.587-0.798) and radiomics analysis with PCA (AUC = 0.662; 95% CI, 0.548-0.776) and LASSO have not reached statistical significance (all p > 0.05). The radiomics score was higher in UC than in CD on the testing cohort (mean ± SD, UC 0.29 ± 1.05 versus CD -0.60 ± 1.25; p < 0.001). The LASSO model with adjustment of clinical covariates reached an AUC of 0.775 (95%CI, 0.683-0.868). CONCLUSION The developed volumetric VAT-based radiomics and 3D-CNN models provided comparable and effective performance for the characterization of CD from UC. KEY POINTS • High-output feature data extracted from volumetric visceral adipose tissue on CT enterography had an effective diagnostic performance for differentiating Crohn's disease from ulcerative colitis. • With adjustment of clinical covariates that cause difference in volumetric visceral adipose tissue, adjusted clinical machine learning model reached stronger performance when distinguishing Crohn's disease patients from ulcerative colitis patients.
Collapse
|
10
|
Zhang Y, Li W, Zhang Z, Xue Y, Liu YL, Nie K, Su MY, Ye Q. Differential diagnosis of prostate cancer and benign prostatic hyperplasia based on DCE-MRI using bi-directional CLSTM deep learning and radiomics. Med Biol Eng Comput 2023; 61:757-771. [PMID: 36598674 PMCID: PMC10548872 DOI: 10.1007/s11517-022-02759-x] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2022] [Accepted: 12/22/2022] [Indexed: 01/05/2023]
Abstract
Dynamic contrast-enhanced MRI (DCE-MRI) is routinely included in the prostate MRI protocol for a long time; its role has been questioned. It provides rich spatial and temporal information. However, the contained information cannot be fully extracted in radiologists' visual evaluation. More sophisticated computer algorithms are needed to extract the higher-order information. The purpose of this study was to apply a new deep learning algorithm, the bi-directional convolutional long short-term memory (CLSTM) network, and the radiomics analysis for differential diagnosis of PCa and benign prostatic hyperplasia (BPH). To systematically investigate the optimal amount of peritumoral tissue for improving diagnosis, a total of 9 ROIs were delineated by using 3 different methods. The results showed that bi-directional CLSTM with ± 20% region growing peritumoral ROI achieved the mean AUC of 0.89, better than the mean AUC of 0.84 by using the tumor alone without any peritumoral tissue (p = 0.25, not significant). For all 9 ROIs, deep learning had higher AUC than radiomics, but only reaching the significant difference for ± 20% region growing peritumoral ROI (0.89 vs. 0.79, p = 0.04). In conclusion, the kinetic information extracted from DCE-MRI using bi-directional CLSTM may provide helpful supplementary information for diagnosis of PCa.
Collapse
Affiliation(s)
- Yang Zhang
- Department of Radiation Oncology, Rutgers-Cancer Institute of New Jersey, Robert Wood Johnson Medical School, New Brunswick, NJ, USA
- Department of Radiological Sciences, University of California, 164 Irvine Hall, Irvine, CA, 92697, USA
| | - Weikang Li
- Department of Radiology, The Children's Hospital of Zhejiang University School of Medicine, Hangzhou, China
| | - Zhao Zhang
- Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Yingnan Xue
- Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Yan-Lin Liu
- Department of Radiological Sciences, University of California, 164 Irvine Hall, Irvine, CA, 92697, USA
| | - Ke Nie
- Department of Radiation Oncology, Rutgers-Cancer Institute of New Jersey, Robert Wood Johnson Medical School, New Brunswick, NJ, USA
| | - Min-Ying Su
- Department of Radiological Sciences, University of California, 164 Irvine Hall, Irvine, CA, 92697, USA.
| | - Qiong Ye
- High Magnetic Field Laboratory, Hefei Institutes of Physical Science, Chinese Academy of Sciences, 350 Shushanhu Road, Hefei, 230031, Anhui, People's Republic of China.
| |
Collapse
|
11
|
Belue MJ, Harmon SA, Lay NS, Daryanani A, Phelps TE, Choyke PL, Turkbey B. The Low Rate of Adherence to Checklist for Artificial Intelligence in Medical Imaging Criteria Among Published Prostate MRI Artificial Intelligence Algorithms. J Am Coll Radiol 2023; 20:134-145. [PMID: 35922018 PMCID: PMC9887098 DOI: 10.1016/j.jacr.2022.05.022] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/08/2022] [Revised: 05/13/2022] [Accepted: 05/18/2022] [Indexed: 02/02/2023]
Abstract
OBJECTIVE To determine the rigor, generalizability, and reproducibility of published classification and detection artificial intelligence (AI) models for prostate cancer (PCa) on MRI using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) guidelines, a 42-item checklist that is considered a measure of best practice for presenting and reviewing medical imaging AI research. MATERIALS AND METHODS This review searched English literature for studies proposing PCa AI detection and classification models on MRI. Each study was evaluated with the CLAIM checklist. The additional outcomes for which data were sought included measures of AI model performance (eg, area under the curve [AUC], sensitivity, specificity, free-response operating characteristic curves), training and validation and testing group sample size, AI approach, detection versus classification AI, public data set utilization, MRI sequences used, and definition of gold standard for ground truth. The percentage of CLAIM checklist fulfillment was used to stratify studies into quartiles. Wilcoxon's rank-sum test was used for pair-wise comparisons. RESULTS In all, 75 studies were identified, and 53 studies qualified for analysis. The original CLAIM items that most studies did not fulfill includes item 12 (77% no): de-identification methods; item 13 (68% no): handling missing data; item 15 (47% no): rationale for choosing ground truth reference standard; item 18 (55% no): measurements of inter- and intrareader variability; item 31 (60% no): inclusion of validated interpretability maps; item 37 (92% no): inclusion of failure analysis to elucidate AI model weaknesses. An AUC score versus percentage CLAIM fulfillment quartile revealed a significant difference of the mean AUC scores between quartile 1 versus quartile 2 (0.78 versus 0.86, P = .034) and quartile 1 versus quartile 4 (0.78 versus 0.89, P = .003) scores. Based on additional information and outcome metrics gathered in this study, additional measures of best practice are defined. These new items include disclosure of public dataset usage, ground truth definition in comparison to other referenced works in the defined task, and sample size power calculation. CONCLUSION A large proportion of AI studies do not fulfill key items in CLAIM guidelines within their methods and results sections. The percentage of CLAIM checklist fulfillment is weakly associated with improved AI model performance. Additions or supplementations to CLAIM are recommended to improve publishing standards and aid reviewers in determining study rigor.
Collapse
Affiliation(s)
- Mason J Belue
- Medical Research Scholars Program Fellow, Artificial Intelligence Resource, Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| | - Stephanie A Harmon
- Staff Scientist, Artificial Intelligence Resource, Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| | - Nathan S Lay
- Staff Scientist, Artificial Intelligence Resource, Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| | - Asha Daryanani
- Intramural Research Training Program Fellow, Artificial Intelligence Resource, Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| | - Tim E Phelps
- Postdoctoral Fellow, Artificial Intelligence Resource, Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| | - Peter L Choyke
- Artificial Intelligence Resource, Chief of Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| | - Baris Turkbey
- Senior Clinician/Director, Artificial Intelligence Resource, Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland.
| |
Collapse
|
12
|
Martin-Leo H, Frederick K, Wojciech S, Klaus-Robert M, Emmanuel D, Sonja S, Sylvia H, Ina K, Jörg A, Liron P, Hendrik S, Patrick W. Imaging bridges pathology and radiology. J Pathol Inform 2023; 14:100298. [PMID: 36851923 PMCID: PMC9958472 DOI: 10.1016/j.jpi.2023.100298] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/24/2022] [Revised: 01/23/2023] [Accepted: 01/25/2023] [Indexed: 02/01/2023] Open
Abstract
In recent years, medical disciplines have moved closer together and rigid borders have been increasingly dissolved. The synergetic advantage of combining multiple disciplines is particularly important for radiology, nuclear medicine, and pathology to perform integrative diagnostics. In this review, we discuss how medical subdisciplines can be reintegrated in the future using state-of-the-art methods of digitization, data science, and machine learning. Integration of methods is made possible by the digitalization of radiological and nuclear medical images, as well as pathological images. 3D histology can become a valuable tool, not only for integration into radiological images but also for the visualization of cellular interactions, the so-called connectomes. In human pathology, it has recently become possible to image and calculate the movements and contacts of immunostained cells in fresh tissue explants. Recording the movement of a living cell is proving to be informative and makes it possible to study dynamic connectomes in the diagnosis of lymphoid tissue. By applying computational methods including data science and machine learning, new perspectives for analyzing and understanding diseases become possible.
Collapse
Affiliation(s)
- Hansmann Martin-Leo
- Frankfurt Institute for Advanced Studies, Frankfurt/Main, Germany
- Institute for Pharmacology and Toxicology, Goethe University, Frankfurt/Main, Germany
| | - Klauschen Frederick
- Charité University Hospital, Berlin, Germany
- German Cancer Consortium (DKTK), Munich partner site, and German Cancer Research Center (DKFZ) Heidelberg, Heidelberg, Germany
- BIFOLD -- Berlin Institute for the Foundations of Learning and Data, Berlin, Germany
- Ludwig-Maximilians-Universität, Munich, Germany
- Aignostics GmbH, Berlin, Germany
| | - Samek Wojciech
- BIFOLD -- Berlin Institute for the Foundations of Learning and Data, Berlin, Germany
- Fraunhofer Heinrich Hertz Institute, Berlin, Germany
- Technical University Berlin, Berlin, Germany
| | - Müller Klaus-Robert
- BIFOLD -- Berlin Institute for the Foundations of Learning and Data, Berlin, Germany
- Aignostics GmbH, Berlin, Germany
- Technical University Berlin, Berlin, Germany
- Korea University, Seoul, South Korea
- Max-Planck-Institut für Informatik, Saarbrücken, Germany
| | - Donnadieu Emmanuel
- Université Paris Cité, CNRS, INSERM, Equipe Labellisée Ligue Contre le Cancer, Institut Cochin, F-75014 Paris, France
| | - Scharf Sonja
- Frankfurt Institute for Advanced Studies, Frankfurt/Main, Germany
- Institute for Pharmacology and Toxicology, Goethe University, Frankfurt/Main, Germany
- Department of Molecular Bioinformatics, Goethe University Frankfurt, Frankfurt/Main, Germany
| | - Hartmann Sylvia
- Dr. Senckenberg Institute of Pathology, Goethe University Frankfurt, Frankfurt/Main, Germany
| | - Koch Ina
- Department of Molecular Bioinformatics, Goethe University Frankfurt, Frankfurt/Main, Germany
| | - Ackermann Jörg
- Department of Molecular Bioinformatics, Goethe University Frankfurt, Frankfurt/Main, Germany
| | - Pantanowitz Liron
- Department of Pathology, University of Michigan, Ann Arbor, Michigan
| | - Schäfer Hendrik
- Institute for Pharmacology and Toxicology, Goethe University, Frankfurt/Main, Germany
- Charité University Hospital, Berlin, Germany
| | - Wurzel Patrick
- Frankfurt Institute for Advanced Studies, Frankfurt/Main, Germany
- Institute for Pharmacology and Toxicology, Goethe University, Frankfurt/Main, Germany
- Department of Molecular Bioinformatics, Goethe University Frankfurt, Frankfurt/Main, Germany
| |
Collapse
|
13
|
Zhdanovich Y, Ackermann J, Wild PJ, Köllermann J, Bankov K, Döring C, Flinner N, Reis H, Wenzel M, Höh B, Mandel P, Vogl TJ, Harter P, Filipski K, Koch I, Bernatz S. Evaluation of automatic discrimination between benign and malignant prostate tissue in the era of high precision digital pathology. BMC Bioinformatics 2023; 24:1. [PMID: 36597019 PMCID: PMC9809030 DOI: 10.1186/s12859-022-05124-9] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2022] [Accepted: 12/23/2022] [Indexed: 01/04/2023] Open
Abstract
BACKGROUND Prostate cancer is a major health concern in aging men. Paralleling an aging society, prostate cancer prevalence increases emphasizing the need for efficient diagnostic algorithms. METHODS Retrospectively, 106 prostate tissue samples from 48 patients (mean age, [Formula: see text] years) were included in the study. Patients suffered from prostate cancer (n = 38) or benign prostatic hyperplasia (n = 10) and were treated with radical prostatectomy or Holmium laser enucleation of the prostate, respectively. We constructed tissue microarrays (TMAs) comprising representative malignant (n = 38) and benign (n = 68) tissue cores. TMAs were processed to histological slides, stained, digitized and assessed for the applicability of machine learning strategies and open-source tools in diagnosis of prostate cancer. We applied the software QuPath to extract features for shape, stain intensity, and texture of TMA cores for three stainings, H&E, ERG, and PIN-4. Three machine learning algorithms, neural network (NN), support vector machines (SVM), and random forest (RF), were trained and cross-validated with 100 Monte Carlo random splits into 70% training set and 30% test set. We determined AUC values for single color channels, with and without optimization of hyperparameters by exhaustive grid search. We applied recursive feature elimination to feature sets of multiple color transforms. RESULTS Mean AUC was above 0.80. PIN-4 stainings yielded higher AUC than H&E and ERG. For PIN-4 with the color transform saturation, NN, RF, and SVM revealed AUC of [Formula: see text], [Formula: see text], and [Formula: see text], respectively. Optimization of hyperparameters improved the AUC only slightly by 0.01. For H&E, feature selection resulted in no increase of AUC but to an increase of 0.02-0.06 for ERG and PIN-4. CONCLUSIONS Automated pipelines may be able to discriminate with high accuracy between malignant and benign tissue. We found PIN-4 staining best suited for classification. Further bioinformatic analysis of larger data sets would be crucial to evaluate the reliability of automated classification methods for clinical practice and to evaluate potential discrimination of aggressiveness of cancer to pave the way to automatic precision medicine.
Collapse
Affiliation(s)
- Yauheniya Zhdanovich
- grid.5252.00000 0004 1936 973XInstitute of Pathology, Ludwig-Maximilians University Munich, Thalkirchner Str. 36, 80337 Munich, Germany ,grid.7468.d0000 0001 2248 7639Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, 10117 Berlin, Germany
| | - Jörg Ackermann
- Molecular Bioinformatics Group, Institute of Computer Science, Faculty of Computer Science and Mathematics, Robert-Mayer-Straße 11-15, 60325 Frankfurt, Germany
| | - Peter J. Wild
- Dr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital Frankfurt, 60590 Frankfurt, Germany ,grid.411088.40000 0004 0578 8220Wildlab, University Hospital Frankfurt MVZ GmbH, 60590 Frankfurt, Germany ,grid.417999.b0000 0000 9260 4223Frankfurt Institute for Advanced Studies (FIAS), 60438 Frankfurt, Germany
| | - Jens Köllermann
- Dr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital Frankfurt, 60590 Frankfurt, Germany
| | - Katrin Bankov
- Dr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital Frankfurt, 60590 Frankfurt, Germany
| | - Claudia Döring
- Dr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital Frankfurt, 60590 Frankfurt, Germany
| | - Nadine Flinner
- Dr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital Frankfurt, 60590 Frankfurt, Germany
| | - Henning Reis
- Dr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital Frankfurt, 60590 Frankfurt, Germany
| | - Mike Wenzel
- Department of Urology, Goethe University Frankfurt am Main, University Hospital Frankfurt, 60590 Frankfurt, Germany
| | - Benedikt Höh
- Department of Urology, Goethe University Frankfurt am Main, University Hospital Frankfurt, 60590 Frankfurt, Germany
| | - Philipp Mandel
- Department of Urology, Goethe University Frankfurt am Main, University Hospital Frankfurt, 60590 Frankfurt, Germany
| | - Thomas J. Vogl
- Department of Diagnostic and Interventional Radiology, Goethe University Frankfurt am Main, University Hospital Frankfurt, 60590 Frankfurt, Germany
| | - Patrick Harter
- grid.411088.40000 0004 0578 8220Neurological Institute (Edinger Institute), University Hospital Frankfurt, 60590 Frankfurt, Germany
| | - Katharina Filipski
- grid.411088.40000 0004 0578 8220Neurological Institute (Edinger Institute), University Hospital Frankfurt, 60590 Frankfurt, Germany ,grid.7497.d0000 0004 0492 0584German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), 69120 Heidelberg, Germany ,University Cancer Center (UCT) Frankfurt, Frankfurt, Germany ,grid.411088.40000 0004 0578 8220Frankfurt Cancer Institute (FCI), University Hospital Frankfurt, 60590 Frankfurt, Germany
| | - Ina Koch
- Molecular Bioinformatics Group, Institute of Computer Science, Faculty of Computer Science and Mathematics, Robert-Mayer-Straße 11-15, 60325 Frankfurt, Germany
| | - Simon Bernatz
- Dr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital Frankfurt, 60590 Frankfurt, Germany ,Department of Diagnostic and Interventional Radiology, Goethe University Frankfurt am Main, University Hospital Frankfurt, 60590 Frankfurt, Germany ,grid.411088.40000 0004 0578 8220Frankfurt Cancer Institute (FCI), University Hospital Frankfurt, 60590 Frankfurt, Germany
| |
Collapse
|
14
|
Wei X, Zhu L, Zeng Y, Xue K, Dai Y, Xu J, Liu G, Liu F, Xue W, Wu D, Wu G. Detection of prostate cancer using diffusion-relaxation correlation spectrum imaging with support vector machine model - a feasibility study. Cancer Imaging 2022; 22:77. [PMID: 36575555 PMCID: PMC9795630 DOI: 10.1186/s40644-022-00516-9] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2022] [Accepted: 12/19/2022] [Indexed: 12/28/2022] Open
Abstract
BACKGROUND To evaluate the performance of diffusion-relaxation correlation spectrum imaging (DR-CSI) with support vector machine (SVM) in detecting prostate cancer (PCa). METHODS In total, 114 patients (mean age, 66 years, range, 48-87 years) who received a prostate MRI and underwent biopsy were enrolled in three stages. Thirty-nine were assigned for the exploration stage to establish the model, 18 for the validation stage to choose the appropriate scale for mapping and 57 for the test stage to compare the diagnostic performance of the DR-CSI and PI-RADS. RESULTS In the exploration stage, the DR-CSI model was established and performed better than the ADC and T2 values (both P < 0.001). The validation result shows that at least 2 pixels were required for both the long-axis and short-axis in the mapping procedure. In the test stage, DR-CSI had higher accuracy than PI-RADS ≥ 3 as a positive finding based on patient (84.2% vs. 63.2%, P = 0.004) and lesion (78.8% vs. 57.6%, P = 0.001) as well as PI-RADS ≥ 4 on lesion (76.5% vs. 64.7%, P = 0.029), while there was no significant difference between DR-CSI and PI-RADS ≥ 4 based on patient (P = 0.508). For clinically significant PCa, DR-CSI had higher accuracy than PI-RADS ≥ 3 based on patients (84.2% vs. 63.2%, P = 0.004) and lesions (62.4% vs. 48.2%, P = 0.036). There was no significant difference between DR-CSI and PI-RADS ≥ 4 (P = 1.000 and 0.845 for the patient and lesion levels, respectively). CONCLUSIONS DR-CSI combined with the SVM model may improve the diagnostic accuracy of PCa. TRIAL REGISTRATION This study was approved by the Ethics Committee of our institute (Approval No. KY2018-213). Written informed consent was obtained from all participants.
Collapse
Affiliation(s)
- Xiaobin Wei
- grid.16821.3c0000 0004 0368 8293Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Li Zhu
- grid.16821.3c0000 0004 0368 8293Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Yanyan Zeng
- Quanzhou Maternity and Children’s Hospital, Fujian, China
| | - Ke Xue
- grid.497849.fCentral Research Institute, MR Collaboration, United Imaging Healthcare, Shanghai, China
| | - Yongming Dai
- grid.497849.fCentral Research Institute, MR Collaboration, United Imaging Healthcare, Shanghai, China
| | - Jianrong Xu
- grid.16821.3c0000 0004 0368 8293Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Guiqin Liu
- grid.16821.3c0000 0004 0368 8293Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Fang Liu
- grid.16821.3c0000 0004 0368 8293Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Wei Xue
- grid.16821.3c0000 0004 0368 8293Department of Urology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Dongmei Wu
- grid.22069.3f0000 0004 0369 6365Shanghai Key Laboratory of Magnetic Resonance, School of Physics and Electronics Science, East China Normal University, Shanghai, China
| | - Guangyu Wu
- grid.16821.3c0000 0004 0368 8293Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| |
Collapse
|
15
|
Li S, Zheng T, Fan Z, Qu H, Wang J, Bi J, Lv Q, Zhang G, Cui X, Zhao Y. A dynamic-static combination model based on radiomics features for prostate cancer using multiparametric MRI. Phys Med Biol 2022; 68. [PMID: 36541844 DOI: 10.1088/1361-6560/aca954] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2022] [Accepted: 12/06/2022] [Indexed: 12/12/2022]
Abstract
Objective. To propose a new dynamic multiparametric magnetic resonance imaging (mpMRI) radiomics method for the detection of prostate cancer (PCa), and establish a combined model using dynamic and static radiomics features based on this method.Approach. A total of 166 patients (82 PCa patients and 84 non-PCa patients) were enrolled in the study, and 31 872 mpMRI images were performed in a radiomics workflow. The whole prostate segmentation and traditional static radiomics features extraction were performed on intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI,bvalue of 10, 50, 100, 150, 200, 400, 600, 800, 1000, 1500 s mm-2respectively), apparent diffusion coefficient (ADC), and T2-weighted imaging (T2WI) sequences respectively. Through the building of eachb-value DWI model and the analysis of the static key radiomics features, three types of dynamic features called standard discrete (SD), parameter (P) and relative change rate (RCR) were constructed. And the b-value parameters used to construct dynamic features were divided into three groups ('Df_', 'Db_' and 'Da_'): the front part (10-200 s mm-2), the back part (400-1500 s mm-2), and all (10-1500 s mm-2) of theb-values set, respectively. Afterwards, the dynamic mpMRI model and combined model construction were constructed, and the PCa discrimination performance of each model was evaluated.Main results.The models based on dynamic features showed good potential for PCa identification. Where, the results of Db_SD, Da_P and Db_P models were encouraging (test cohort AUCs: 90.78%, 87.60%, 86.3%), which was better than the commonly used ADC model (AUC of ADC was 75.48%). Among the combined models, the models using static features of T2WI and dynamic features performed the best. The AUC of Db_SD + T2WI, Db_P + T2WI and Db_RCR + T2WI model was 92.90%, 91.29% and 81.46%.Significance.The dynamic-static combination model based on dynamic mpMRI radiomics method has a good effect on the identification of PCa. This method has broad application prospects in PCa individual diagnosis management.
Collapse
Affiliation(s)
- Shuqin Li
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, 110169, People's Republic of China
| | - Tingting Zheng
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, 110169, People's Republic of China
| | - Zhou Fan
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, 110169, People's Republic of China
| | - Hui Qu
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, 110169, People's Republic of China
| | - Jianfeng Wang
- Department of Urology Surgery, The First Hospital of China Medical University, No.155 Nanjing North Street, Heping District, Shenyang, People's Republic of China
| | - Jianbin Bi
- Department of Urology Surgery, The First Hospital of China Medical University, No.155 Nanjing North Street, Heping District, Shenyang, People's Republic of China
| | - Qingjie Lv
- Department of Pathology, Shengjing Hospital of China Medical University, Sanhao Street 36, Shenyang, 110001, People's Republic of China
| | - Gejun Zhang
- Department of Urology Surgery, The First Hospital of China Medical University, No.155 Nanjing North Street, Heping District, Shenyang, People's Republic of China
| | - Xiaoyu Cui
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, 110169, People's Republic of China.,Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, 110169, People's Republic of China
| | - Yue Zhao
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, 110169, People's Republic of China.,National and Local Joint Engineering Research Center of Immunodermatological Theranostics, No.155 Nanjing Bei Street, Heping District, Shenyang, 110001, People's Republic of China
| |
Collapse
|
16
|
Parr H, Hall E, Porta N. Joint models for dynamic prediction in localised prostate cancer: a literature review. BMC Med Res Methodol 2022; 22:245. [PMID: 36123621 PMCID: PMC9487103 DOI: 10.1186/s12874-022-01709-3] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2021] [Accepted: 08/10/2022] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Prostate cancer is a very prevalent disease in men. Patients are monitored regularly during and after treatment with repeated assessment of prostate-specific antigen (PSA) levels. Prognosis of localised prostate cancer is generally good after treatment, and the risk of having a recurrence is usually estimated based on factors measured at diagnosis. Incorporating PSA measurements over time in a dynamic prediction joint model enables updates of patients' risk as new information becomes available. We review joint model strategies that have been applied to model time-dependent PSA trajectories to predict time-to-event outcomes in localised prostate cancer. METHODS We identify articles that developed joint models for prediction of localised prostate cancer recurrence over the last two decades. We report, compare, and summarise the methodological approaches and applications that use joint modelling accounting for two processes: the longitudinal model (PSA), and the time-to-event process (clinical failure). The methods explored differ in how they specify the association between these two processes. RESULTS Twelve relevant articles were identified. A range of methodological frameworks were found, and we describe in detail shared-parameter joint models (9 of 12, 75%) and joint latent class models (3 of 12, 25%). Within each framework, these articles presented model development, estimation of dynamic predictions and model validations. CONCLUSIONS Each framework has its unique principles with corresponding advantages and differing interpretations. Regardless of the framework used, dynamic prediction models enable real-time prediction of individual patient prognosis. They utilise all available longitudinal information, in addition to baseline prognostic risk factors, and are superior to traditional baseline-only prediction models.
Collapse
Affiliation(s)
- Harry Parr
- Clinical Trials and Statistics Unit at The Institute of Cancer Research, London, UK
| | - Emma Hall
- Clinical Trials and Statistics Unit at The Institute of Cancer Research, London, UK
| | - Nuria Porta
- Clinical Trials and Statistics Unit at The Institute of Cancer Research, London, UK
| |
Collapse
|
17
|
Radiomics Models Based on Magnetic Resonance Imaging for Prediction of the Response to Bortezomib-Based Therapy in Patients with Multiple Myeloma. BIOMED RESEARCH INTERNATIONAL 2022; 2022:6911246. [PMID: 36105939 PMCID: PMC9467708 DOI: 10.1155/2022/6911246] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/23/2022] [Revised: 08/04/2022] [Accepted: 08/20/2022] [Indexed: 11/17/2022]
Abstract
Purpose. To identify significant radiomics features based on MRI and establish effective models for predicting the response to bortezomib-based regimens. Materials and Methods. In total, 95 MM patients treated with bortezomib-based therapy were enrolled, including 77 with bortezomib, cyclophosphamide, and dexamethasone (BCD) and 18 with bortezomib, lenalidomide, and dexamethasone (VRD). Based on T1-weighted imaging (T1WI) and T2-weighted imaging with fat suppression (T2WI-fs), radiomics features were extracted and then selected. The random forest (RF),
-nearest neighbor, support vector machine, logistic regression, decision tree, and Bayes models were built using the selected features. The predictive power of six models for response to BCD and VRD regimens were evaluated. The correlation between the selected features and progression-free survival (PFS) was also analyzed. Results. Four wavelet features were correlated with BCD treatment response. The six models all showed predictive power for BCD regimen (AUC: 0.84-0.896 in the training set, 0.801-0.885 in the validation set), and RF performed relatively better than others. Nevertheless, all the BCD-based models were incapable of predicting the VRD treatment response. The wavelet-HLH_firstorder_kurtosis was also associated with PFS (log-rank
). Conclusion. The four wavelet features were valuable biomarkers for predicting the response to BCD regimen. The six models based on these features showed predictive power, and RF was the best. One wavelet feature was also a survival-related biomarker. MRI-based radiomics had the potential to guide clinicians in MM management.
Collapse
|
18
|
Current Value of Biparametric Prostate MRI with Machine-Learning or Deep-Learning in the Detection, Grading, and Characterization of Prostate Cancer: A Systematic Review. Diagnostics (Basel) 2022; 12:diagnostics12040799. [PMID: 35453847 PMCID: PMC9027206 DOI: 10.3390/diagnostics12040799] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2022] [Revised: 03/19/2022] [Accepted: 03/23/2022] [Indexed: 02/04/2023] Open
Abstract
Prostate cancer detection with magnetic resonance imaging is based on a standardized MRI-protocol according to the PI-RADS guidelines including morphologic imaging, diffusion weighted imaging, and perfusion. To facilitate data acquisition and analysis the contrast-enhanced perfusion is often omitted resulting in a biparametric prostate MRI protocol. The intention of this review is to analyze the current value of biparametric prostate MRI in combination with methods of machine-learning and deep learning in the detection, grading, and characterization of prostate cancer; if available a direct comparison with human radiologist performance was performed. PubMed was systematically queried and 29 appropriate studies were identified and retrieved. The data show that detection of clinically significant prostate cancer and differentiation of prostate cancer from non-cancerous tissue using machine-learning and deep learning is feasible with promising results. Some techniques of machine-learning and deep-learning currently seem to be equally good as human radiologists in terms of classification of single lesion according to the PIRADS score.
Collapse
|
19
|
Cho HH, Kim CK, Park H. Overview of radiomics in prostate imaging and future directions. Br J Radiol 2022; 95:20210539. [PMID: 34797688 PMCID: PMC8978251 DOI: 10.1259/bjr.20210539] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2022] Open
Abstract
Recent advancements in imaging technology and analysis methods have led to an analytic framework known as radiomics. This framework extracts comprehensive high-dimensional features from imaging data and performs data mining to build analytical models for improved decision-support. Its features include many categories spanning texture and shape; thus, it can provide abundant information for precision medicine. Many studies of prostate radiomics have shown promising results in the assessment of pathological features, prediction of treatment response, and stratification of risk groups. Herein, we aimed to provide a general overview of radiomics procedures, discuss technical issues, explain various clinical applications, and suggest future research directions, especially for prostate imaging.
Collapse
Affiliation(s)
- Hwan-Ho Cho
- Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, Korea.,Center for Neuroscience Imaging Research, Institute for Basic Science, Suwon, Korea
| | - Chan Kyo Kim
- Department of Radiology and Center for Imaging Science, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea
| | - Hyunjin Park
- Center for Neuroscience Imaging Research, Institute for Basic Science, Suwon, Korea.,School of Electronic and Electrical Engineering, Sungkyunkwan University, Suwon, Korea
| |
Collapse
|
20
|
Bertelli E, Mercatelli L, Marzi C, Pachetti E, Baccini M, Barucci A, Colantonio S, Gherardini L, Lattavo L, Pascali MA, Agostini S, Miele V. Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRI. Front Oncol 2022; 11:802964. [PMID: 35096605 PMCID: PMC8792745 DOI: 10.3389/fonc.2021.802964] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/27/2021] [Accepted: 12/07/2021] [Indexed: 12/24/2022] Open
Abstract
Prostate cancer (PCa) is the most frequent male malignancy and the assessment of PCa aggressiveness, for which a biopsy is required, is fundamental for patient management. Currently, multiparametric (mp) MRI is strongly recommended before biopsy. Quantitative assessment of mpMRI might provide the radiologist with an objective and noninvasive tool for supporting the decision-making in clinical practice and decreasing intra- and inter-reader variability. In this view, high dimensional radiomics features and Machine Learning (ML) techniques, along with Deep Learning (DL) methods working on raw images directly, could assist the radiologist in the clinical workflow. The aim of this study was to develop and validate ML/DL frameworks on mpMRI data to characterize PCas according to their aggressiveness. We optimized several ML/DL frameworks on T2w, ADC and T2w+ADC data, using a patient-based nested validation scheme. The dataset was composed of 112 patients (132 peripheral lesions with Prostate Imaging Reporting and Data System (PI-RADS) score ≥ 3) acquired following both PI-RADS 2.0 and 2.1 guidelines. Firstly, ML/DL frameworks trained and validated on PI-RADS 2.0 data were tested on both PI-RADS 2.0 and 2.1 data. Then, we trained, validated and tested ML/DL frameworks on a multi PI-RADS dataset. We reported the performances in terms of Area Under the Receiver Operating curve (AUROC), specificity and sensitivity. The ML/DL frameworks trained on T2w data achieved the overall best performance. Notably, ML and DL frameworks trained and validated on PI-RADS 2.0 data obtained median AUROC values equal to 0.750 and 0.875, respectively, on unseen PI-RADS 2.0 test set. Similarly, ML/DL frameworks trained and validated on multi PI-RADS T2w data showed median AUROC values equal to 0.795 and 0.750, respectively, on unseen multi PI-RADS test set. Conversely, all the ML/DL frameworks trained and validated on PI-RADS 2.0 data, achieved AUROC values no better than the chance level when tested on PI-RADS 2.1 data. Both ML/DL techniques applied on mpMRI seem to be a valid aid in predicting PCa aggressiveness. In particular, ML/DL frameworks fed with T2w images data (objective, fast and non-invasive) show good performances and might support decision-making in patient diagnostic and therapeutic management, reducing intra- and inter-reader variability.
Collapse
Affiliation(s)
- Elena Bertelli
- Department of Radiology, Careggi University Hospital, Florence, Italy
| | - Laura Mercatelli
- Department of Radiology, Careggi University Hospital, Florence, Italy
| | - Chiara Marzi
- “Nello Carrara” Institute of Applied Physics (IFAC), National Research Council of Italy (CNR), Sesto Fiorentino, Italy
| | - Eva Pachetti
- “Alessandro Faedo” Institute of Information Science and Technologies (ISTI), National Research Council of Italy (CNR), Pisa, Italy
- Department of Information Engineering (DII), University of Pisa, Pisa, Italy
| | - Michela Baccini
- “Giuseppe Parenti” Department of Statistics, Computer Science, Applications(DiSIA), University of Florence, Florence, Italy
- Florence Center for Data Science, University of Florence, Florence, Italy
| | - Andrea Barucci
- “Nello Carrara” Institute of Applied Physics (IFAC), National Research Council of Italy (CNR), Sesto Fiorentino, Italy
| | - Sara Colantonio
- “Alessandro Faedo” Institute of Information Science and Technologies (ISTI), National Research Council of Italy (CNR), Pisa, Italy
| | - Luca Gherardini
- “Giuseppe Parenti” Department of Statistics, Computer Science, Applications(DiSIA), University of Florence, Florence, Italy
| | - Lorenzo Lattavo
- Department of Radiology, Careggi University Hospital, Florence, Italy
| | - Maria Antonietta Pascali
- “Alessandro Faedo” Institute of Information Science and Technologies (ISTI), National Research Council of Italy (CNR), Pisa, Italy
| | - Simone Agostini
- Department of Radiology, Careggi University Hospital, Florence, Italy
| | - Vittorio Miele
- Department of Radiology, Careggi University Hospital, Florence, Italy
| |
Collapse
|
21
|
Huang J, Chen Y, Zhang Y, Xie J, Liang Y, Yuan W, Zhou T, Gao R, Wen R, Xia Y, Long L. Comparison of clinical-computed tomography model with 2D and 3D radiomics models to predict occult peritoneal metastases in advanced gastric cancer. Abdom Radiol (NY) 2022; 47:66-75. [PMID: 34636930 DOI: 10.1007/s00261-021-03287-2] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2021] [Revised: 09/10/2021] [Accepted: 09/11/2021] [Indexed: 02/05/2023]
Abstract
PURPOSE To compare the ability of a clinical-computed tomography (CT) model vs. 2D and 3D radiomics models for predicting occult peritoneal metastasis (PM) in patients with advanced gastric cancer (AGC). METHODS In this retrospective study, we included 49 patients with occult PM and 49 control patients (without PM) who underwent preoperative CT and subsequent surgery between January 2016 and December 2018. Clinical information and CT semantic features were collected, and CT radiomics features were extracted. A predictive clinical-CT model was created using multivariate logistic regression. The least absolute shrinkage and selection operator algorithm and logistic regression were used for constructing 2D and 3D radiomics models. These models were validated with an external cohort (n = 30). Receiver operating characteristics curve with area under the curve (AUC), sensitivity, and specificity were used to evaluate predictive performance. RESULTS Tumor size, mild ascites, and serum CA125 were independent factors predictive of occult PM. The clinical-CT model of these independent factors showed better diagnostic performance than 2D and 3D radiomics models. In the external validation cohort, the AUCs of different models were as follows-clinical-CT model: 0.853 (sensitivity, 66.7%; specificity, 93.3%); 2D radiomics model: 0.622 (sensitivity, 80.0%; specificity, 46.7%); and 3D radiomics model: 0.676 (sensitivity, 60.0%; specificity, 86.0%). The clinical-CT model nomogram showed good clinical predictive efficiency to assess occult PM. CONCLUSION The clinical-CT model was better than the radiomics models in predicting occult PM in AGC.
Collapse
Affiliation(s)
- Jiang Huang
- Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, No. 6 Shuangyong Road, Nanning, 530021, Guangxi, China
| | - Yidi Chen
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China
| | - Yuying Zhang
- Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, No. 6 Shuangyong Road, Nanning, 530021, Guangxi, China
| | - Jinhuan Xie
- Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, No. 6 Shuangyong Road, Nanning, 530021, Guangxi, China
| | - Yiqiong Liang
- Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, No. 6 Shuangyong Road, Nanning, 530021, Guangxi, China
| | - Wenzhao Yuan
- Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, No. 6 Shuangyong Road, Nanning, 530021, Guangxi, China
| | - Ting Zhou
- Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, No. 6 Shuangyong Road, Nanning, 530021, Guangxi, China
| | - Ruizhi Gao
- Department of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical University, Nanning, 530021, Guangxi, China
| | - Rong Wen
- Department of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical University, Nanning, 530021, Guangxi, China
| | - Yuwei Xia
- Huiying Medical Technology Co. Ltd, Beijing, 100192, China
| | - Liling Long
- Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, No. 6 Shuangyong Road, Nanning, 530021, Guangxi, China.
| |
Collapse
|
22
|
Ferro M, de Cobelli O, Musi G, del Giudice F, Carrieri G, Busetto GM, Falagario UG, Sciarra A, Maggi M, Crocetto F, Barone B, Caputo VF, Marchioni M, Lucarelli G, Imbimbo C, Mistretta FA, Luzzago S, Vartolomei MD, Cormio L, Autorino R, Tătaru OS. Radiomics in prostate cancer: an up-to-date review. Ther Adv Urol 2022; 14:17562872221109020. [PMID: 35814914 PMCID: PMC9260602 DOI: 10.1177/17562872221109020] [Citation(s) in RCA: 53] [Impact Index Per Article: 26.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2021] [Accepted: 05/30/2022] [Indexed: 12/24/2022] Open
Abstract
Prostate cancer (PCa) is the most common worldwide diagnosed malignancy in male population. The diagnosis, the identification of aggressive disease, and the post-treatment follow-up needs a more comprehensive and holistic approach. Radiomics is the extraction and interpretation of images phenotypes in a quantitative manner. Radiomics may give an advantage through advancements in imaging modalities and through the potential power of artificial intelligence techniques by translating those features into clinical outcome prediction. This article gives an overview on the current evidence of methodology and reviews the available literature on radiomics in PCa patients, highlighting its potential for personalized treatment and future applications.
Collapse
Affiliation(s)
- Matteo Ferro
- Department of Urology, European Institute of Oncology, IRCCS, Milan, Italy, via Ripamonti 435 Milano, Italy
| | - Ottavio de Cobelli
- Department of Urology, European Institute of Oncology, IRCCS, Milan, Italy; Department of Oncology and Hematology-Oncology, Università degli Studi di Milano, Milan, Italy
| | - Gennaro Musi
- Department of Urology, European Institute of Oncology, IRCCS, Milan, Italy; Department of Oncology and Hematology-Oncology, Università degli Studi di Milano, Milan, Italy
| | - Francesco del Giudice
- Department of Urology, Policlinico Umberto I, Sapienza University of Rome, Rome, Italy
| | - Giuseppe Carrieri
- Department of Urology and Organ Transplantation, University of Foggia, Foggia, Italy
| | - Gian Maria Busetto
- Department of Urology and Organ Transplantation, University of Foggia, Foggia, Italy
| | | | - Alessandro Sciarra
- Department of Urology, Policlinico Umberto I, Sapienza University of Rome, Rome, Italy
| | - Martina Maggi
- Department of Urology, Policlinico Umberto I, Sapienza University of Rome, Rome, Italy
| | - Felice Crocetto
- Department of Neurosciences, Reproductive Sciences and Odontostomatology, University of Naples ‘Federico II’, Naples, Italy
| | - Biagio Barone
- Department of Neurosciences, Reproductive Sciences and Odontostomatology, University of Naples ‘Federico II’, Naples, Italy
| | - Vincenzo Francesco Caputo
- Department of Neurosciences, Reproductive Sciences and Odontostomatology, University of Naples ‘Federico II’, Naples, Italy
| | - Michele Marchioni
- Department of Medical, Oral and Biotechnological Sciences, G. d’Annunzio, University of Chieti, Chieti, Italy; Urology Unit, ‘SS. Annunziata’ Hospital, Chieti, Italy
- Department of Urology, ASL Abruzzo 2, Chieti, Italy
| | - Giuseppe Lucarelli
- Department of Emergency and Organ Transplantation, Urology, Andrology and Kidney Transplantation Unit, University of Bari, Bari, Italy
| | - Ciro Imbimbo
- Department of Neurosciences, Reproductive Sciences and Odontostomatology, University of Naples ‘Federico II’, Naples, Italy
| | - Francesco Alessandro Mistretta
- Department of Urology, European Institute of Oncology, IRCCS, Milan, Italy
- Università degli Studi di Milano, Milan, Italy
| | - Stefano Luzzago
- Department of Urology, European Institute of Oncology, IRCCS, Milan, Italy
- Università degli Studi di Milano, Milan, Italy
| | - Mihai Dorin Vartolomei
- Department of Cell and Molecular Biology, George Emil Palade University of Medicine, Pharmacy, Science, and Technology of Târgu Mures, Târgu Mures, Romania
- Department of Urology, Medical University of Vienna, Vienna, Austria
| | - Luigi Cormio
- Urology and Renal Transplantation Unit, Department of Medical and Surgical Sciences, University of Foggia, Foggia, Italy
- Urology Unit, Bonomo Teaching Hospital, Foggia, Italy
| | | | - Octavian Sabin Tătaru
- Institution Organizing University Doctoral Studies, I.O.S.U.D., George Emil Palade University of Medicine, Pharmacy, Science, and Technology of Târgu Mures, Târgu Mures, Romania
| |
Collapse
|
23
|
Ghezzo S, Bezzi C, Presotto L, Mapelli P, Bettinardi V, Savi A, Neri I, Preza E, Samanes Gajate AM, De Cobelli F, Scifo P, Picchio M. State of the art of radiomic analysis in the clinical management of prostate cancer: A systematic review. Crit Rev Oncol Hematol 2021; 169:103544. [PMID: 34801699 DOI: 10.1016/j.critrevonc.2021.103544] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2021] [Revised: 10/18/2021] [Accepted: 10/18/2021] [Indexed: 02/04/2023] Open
Abstract
We present the current clinical applications of radiomics in the context of prostate cancer (PCa) management. Several online databases for original articles using a combination of the following keywords: "(radiomic or radiomics) AND (prostate cancer or prostate tumour or prostate tumor or prostate neoplasia)" have been searched. The selected papers have been pooled as focus on (i) PCa detection, (ii) assessing the clinical significance of PCa, (iii) biochemical recurrence prediction, (iv) radiation-therapy outcome prediction and treatment efficacy monitoring, (v) metastases detection, (vi) metastases prediction, (vii) prediction of extra-prostatic extension. Seventy-six studies were included for qualitative analyses. Classifiers powered with radiomic features were able to discriminate between healthy tissue and PCa and between low- and high-risk PCa. However, before radiomics can be proposed for clinical use its methods have to be standardized, and these first encouraging results need to be robustly replicated in large and independent cohorts.
Collapse
Affiliation(s)
| | | | - Luca Presotto
- Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Milan, Italy
| | - Paola Mapelli
- Vita-Salute San Raffaele University, Milan, Italy; Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Milan, Italy
| | - Valentino Bettinardi
- Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Milan, Italy
| | - Annarita Savi
- Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Milan, Italy
| | - Ilaria Neri
- Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Milan, Italy
| | - Erik Preza
- Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Milan, Italy
| | | | - Francesco De Cobelli
- Vita-Salute San Raffaele University, Milan, Italy; Radiology Department, IRCCS San Raffaele Scientific Institute, Milan, Italy
| | - Paola Scifo
- Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Milan, Italy
| | - Maria Picchio
- Vita-Salute San Raffaele University, Milan, Italy; Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Milan, Italy.
| |
Collapse
|
24
|
Nicoletti G, Barra D, Defeudis A, Mazzetti S, Gatti M, Faletti R, Russo F, Regge D, Giannini V. Virtual biopsy in prostate cancer: can machine learning distinguish low and high aggressive tumors on MRI? ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021; 2021:3374-3377. [PMID: 34891963 DOI: 10.1109/embc46164.2021.9630988] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
In the last decades, MRI was proven a useful tool for the diagnosis and characterization of Prostate Cancer (PCa). In the literature, many studies focused on characterizing PCa aggressiveness, but a few have distinguished between low-aggressive (Gleason Grade Group (GG) <=2) and high-aggressive (GG>=3) PCas based on biparametric MRI (bpMRI). In this study, 108 PCas were collected from two different centers and were divided into training, testing, and validation set. From Apparent Diffusion Coefficient (ADC) map and T2-Weighted Image (T2WI), we extracted texture features, both 3D and 2D, and we implemented three different methods of Feature Selection (FS): Minimum Redundance Maximum Relevance (MRMR), Affinity Propagation (AP), and Genetic Algorithm (GA). From the resulting subsets of predictors, we trained Support Vector Machine (SVM), Decision Tree, and Ensemble Learning classifiers on the training set, and we evaluated their prediction ability on the testing set. Then, for each FS method, we chose the best classifier, based on both training and testing performances, and we further assessed their generalization capability on the validation set. Between the three best models, a Decision Tree was trained using only two features extracted from the ADC map and selected by MRMR, achieving, on the validation set, an Area Under the ROC (AUC) equal to 81%, with sensitivity and specificity of 77% and 93%, respectively.Clinical Relevance- Our best model demonstrated to be able to distinguish low-aggressive from high-aggressive PCas with high accuracy. Potentially, this approach could help clinician to noninvasively distinguish between PCas that might need active treatment and those that could potentially benefit from active surveillance, avoiding biopsy-related complications.
Collapse
|
25
|
Wenzel M, Würnschimmel C, Chierigo F, Tian Z, Shariat SF, Terrone C, Saad F, Tilki D, Graefen M, Roos FC, A Kluth L, Mandel P, Chun FKH, Karakiewicz PI. Assessment of the optimal number of positive biopsy cores to discriminate between cancer-specific mortality in high-risk versus very high-risk prostate cancer patients. Prostate 2021; 81:1055-1063. [PMID: 34312910 DOI: 10.1002/pros.24202] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/28/2021] [Revised: 06/10/2021] [Accepted: 07/12/2021] [Indexed: 12/23/2022]
Abstract
BACKGROUND Number of positive prostate biopsy cores represents a key determinant between high versus very high-risk prostate cancer (PCa). We performed a critical appraisal of the association between the number of positive prostate biopsy cores and CSM in high versus very high-risk PCa. METHODS Within Surveillance, Epidemiology, and End Results database (2010-2016), 13,836 high versus 20,359 very high-risk PCa patients were identified. Discrimination according to 11 different positive prostate biopsy core cut-offs (≥2-≥12) were tested in Kaplan-Meier, cumulative incidence, and multivariable Cox and competing risks regression models. RESULTS Among 11 tested positive prostate biopsy core cut-offs, more than or equal to 8 (high-risk vs. very high-risk: n = 18,986 vs. n = 15,209, median prostate-specific antigen [PSA]: 10.6 vs. 16.8 ng/ml, <.001) yielded optimal discrimination and was closely followed by the established more than or equal to 5 cut-off (high-risk vs. very high-risk: n = 13,836 vs. n = 20,359, median PSA: 16.5 vs. 11.1 ng/ml, p < .001). Stratification according to more than or equal to 8 positive prostate biopsy cores resulted in CSM rates of 4.1 versus 14.2% (delta: 10.1%, multivariable hazard ratio: 2.2, p < .001) and stratification according to more than or equal to 5 positive prostate biopsy cores with CSM rates of 3.7 versus 11.9% (delta: 8.2%, multivariable hazard ratio: 2.0, p < .001) in respectively high versus very high-risk PCa. CONCLUSIONS The more than or equal to 8 positive prostate biopsy cores cutoff yielded optimal results. It was very closely followed by more than or equal to 5 positive prostate biopsy cores. In consequence, virtually the same endorsement may be made for either cutoff. However, more than or equal to 5 positive prostate biopsy cores cutoff, based on its existing wide implementation, might represent the optimal choice.
Collapse
Affiliation(s)
- Mike Wenzel
- Department of Urology, University Hospital Frankfurt, Frankfurt am Main, Germany
- Division of Urology, Cancer Prognostics and Health Outcomes Unit, University of Montréal Health Center, Montréal, Québec, Canada
| | - Christoph Würnschimmel
- Division of Urology, Cancer Prognostics and Health Outcomes Unit, University of Montréal Health Center, Montréal, Québec, Canada
- Martini-Klinik Prostate Cancer Center, University Hospital Hamburg-Eppendorf, Hamburg, Germany
| | - Francesco Chierigo
- Division of Urology, Cancer Prognostics and Health Outcomes Unit, University of Montréal Health Center, Montréal, Québec, Canada
- Department of Urology, Policlinico San Martino Hospital, University of Genova, Genova, Italy
| | - Zhe Tian
- Division of Urology, Cancer Prognostics and Health Outcomes Unit, University of Montréal Health Center, Montréal, Québec, Canada
| | - Shahrokh F Shariat
- Department of Urology, Comprehensive Cancer Center, Medical University of Vienna, Vienna, Austria
- Departments of Urology, Weill Cornell Medical College, New York, New York, USA
- Department of Urology, University of Texas Southwestern, Dallas, Texas, USA
- Department of Urology, Second Faculty of Medicine, Charles University, Prag, Czech Republic
- Department of Urology, Institute for Urology and Reproductive Health, I. M. Sechenov First Moscow State Medical University, Moscow, Russia
- Division of Urology, Department of Special Surgery, Jordan University Hospital, The University of Jordan, Amman, Jordan
| | - Carlo Terrone
- Department of Urology, Policlinico San Martino Hospital, University of Genova, Genova, Italy
| | - Fred Saad
- Division of Urology, Cancer Prognostics and Health Outcomes Unit, University of Montréal Health Center, Montréal, Québec, Canada
| | - Derya Tilki
- Martini-Klinik Prostate Cancer Center, University Hospital Hamburg-Eppendorf, Hamburg, Germany
- Department of Urology, University Hospital Hamburg-Eppendorf, Hamburg, Germany
| | - Markus Graefen
- Martini-Klinik Prostate Cancer Center, University Hospital Hamburg-Eppendorf, Hamburg, Germany
| | - Frederik C Roos
- Department of Urology, University Hospital Frankfurt, Frankfurt am Main, Germany
| | - Luis A Kluth
- Department of Urology, University Hospital Frankfurt, Frankfurt am Main, Germany
| | - Philipp Mandel
- Department of Urology, University Hospital Frankfurt, Frankfurt am Main, Germany
| | - Felix K H Chun
- Department of Urology, University Hospital Frankfurt, Frankfurt am Main, Germany
| | - Pierre I Karakiewicz
- Division of Urology, Cancer Prognostics and Health Outcomes Unit, University of Montréal Health Center, Montréal, Québec, Canada
| |
Collapse
|
26
|
Prostate Cancer Radiogenomics-From Imaging to Molecular Characterization. Int J Mol Sci 2021; 22:ijms22189971. [PMID: 34576134 PMCID: PMC8465891 DOI: 10.3390/ijms22189971] [Citation(s) in RCA: 51] [Impact Index Per Article: 17.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/30/2021] [Revised: 09/06/2021] [Accepted: 09/10/2021] [Indexed: 12/24/2022] Open
Abstract
Radiomics and genomics represent two of the most promising fields of cancer research, designed to improve the risk stratification and disease management of patients with prostate cancer (PCa). Radiomics involves a conversion of imaging derivate quantitative features using manual or automated algorithms, enhancing existing data through mathematical analysis. This could increase the clinical value in PCa management. To extract features from imaging methods such as magnetic resonance imaging (MRI), the empiric nature of the analysis using machine learning and artificial intelligence could help make the best clinical decisions. Genomics information can be explained or decoded by radiomics. The development of methodologies can create more-efficient predictive models and can better characterize the molecular features of PCa. Additionally, the identification of new imaging biomarkers can overcome the known heterogeneity of PCa, by non-invasive radiological assessment of the whole specific organ. In the future, the validation of recent findings, in large, randomized cohorts of PCa patients, can establish the role of radiogenomics. Briefly, we aimed to review the current literature of highly quantitative and qualitative results from well-designed studies for the diagnoses, treatment, and follow-up of prostate cancer, based on radiomics, genomics and radiogenomics research.
Collapse
|
27
|
Challenges in the Use of Artificial Intelligence for Prostate Cancer Diagnosis from Multiparametric Imaging Data. Cancers (Basel) 2021; 13:cancers13163944. [PMID: 34439099 PMCID: PMC8391234 DOI: 10.3390/cancers13163944] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2021] [Revised: 08/02/2021] [Accepted: 08/02/2021] [Indexed: 11/18/2022] Open
Abstract
Simple Summary Prostate Cancer is one of the main threats to men’s health. Its accurate diagnosis is crucial to properly treat patients depending on the cancer’s level of aggressiveness. Tumor risk-stratification is still a challenging task due to the difficulties met during the reading of multi-parametric Magnetic Resonance Images. Artificial Intelligence models may help radiologists in staging the aggressiveness of the equivocal lesions, reducing inter-observer variability and evaluation time. However, these algorithms need many high-quality images to work efficiently, bringing up overfitting and lack of standardization and reproducibility as emerging issues to be addressed. This study attempts to illustrate the state of the art of current research of Artificial Intelligence methods to stratify prostate cancer for its clinical significance suggesting how widespread use of public databases could be a possible solution to these issues. Abstract Many efforts have been carried out for the standardization of multiparametric Magnetic Resonance (mp-MR) images evaluation to detect Prostate Cancer (PCa), and specifically to differentiate levels of aggressiveness, a crucial aspect for clinical decision-making. Prostate Imaging—Reporting and Data System (PI-RADS) has contributed noteworthily to this aim. Nevertheless, as pointed out by the European Association of Urology (EAU 2020), the PI-RADS still has limitations mainly due to the moderate inter-reader reproducibility of mp-MRI. In recent years, many aspects in the diagnosis of cancer have taken advantage of the use of Artificial Intelligence (AI) such as detection, segmentation of organs and/or lesions, and characterization. Here a focus on AI as a potentially important tool for the aim of standardization and reproducibility in the characterization of PCa by mp-MRI is reported. AI includes methods such as Machine Learning and Deep learning techniques that have shown to be successful in classifying mp-MR images, with similar performances obtained by radiologists. Nevertheless, they perform differently depending on the acquisition system and protocol used. Besides, these methods need a large number of samples that cover most of the variability of the lesion aspect and zone to avoid overfitting. The use of publicly available datasets could improve AI performance to achieve a higher level of generalizability, exploiting large numbers of cases and a big range of variability in the images. Here we explore the promise and the advantages, as well as emphasizing the pitfall and the warnings, outlined in some recent studies that attempted to classify clinically significant PCa and indolent lesions using AI methods. Specifically, we focus on the overfitting issue due to the scarcity of data and the lack of standardization and reproducibility in every step of the mp-MR image acquisition and the classifier implementation. In the end, we point out that a solution can be found in the use of publicly available datasets, whose usage has already been promoted by some important initiatives. Our future perspective is that AI models may become reliable tools for clinicians in PCa diagnosis, reducing inter-observer variability and evaluation time.
Collapse
|
28
|
Montoya Perez I, Merisaari H, Jambor I, Ettala O, Taimen P, Knaapila J, Kekki H, Khan FL, Syrjälä E, Steiner A, Syvänen KT, Verho J, Seppänen M, Rannikko A, Riikonen J, Mirtti T, Lamminen T, Saunavaara J, Falagario U, Martini A, Pahikkala T, Pettersson K, Boström PJ, Aronen HJ. Detection of Prostate Cancer Using Biparametric Prostate MRI, Radiomics, and Kallikreins: A Retrospective Multicenter Study of Men With a Clinical Suspicion of Prostate Cancer. J Magn Reson Imaging 2021; 55:465-477. [PMID: 34227169 DOI: 10.1002/jmri.27811] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2021] [Revised: 06/17/2021] [Accepted: 06/18/2021] [Indexed: 01/21/2023] Open
Abstract
BACKGROUND Accurate detection of clinically significant prostate cancer (csPCa), Gleason Grade Group ≥ 2, remains a challenge. Prostate MRI radiomics and blood kallikreins have been proposed as tools to improve the performance of biparametric MRI (bpMRI). PURPOSE To develop and validate radiomics and kallikrein models for the detection of csPCa. STUDY TYPE Retrospective. POPULATION A total of 543 men with a clinical suspicion of csPCa, 411 (76%, 411/543) had kallikreins available and 360 (88%, 360/411) did not take 5-alpha-reductase inhibitors. Two data splits into training, validation (split 1: single center, n = 72; split 2: random 50% of pooled datasets from all four centers), and testing (split 1: 4 centers, n = 288; split 2: remaining 50%) were evaluated. FIELD STRENGTH/SEQUENCE A 3 T/1.5 T, TSE T2-weighted imaging, 3x SE DWI. ASSESSMENT In total, 20,363 radiomic features calculated from manually delineated whole gland (WG) and bpMRI suspicion lesion masks were evaluated in addition to clinical parameters, prostate-specific antigen, four kallikreins, MRI-based qualitative (PI-RADSv2.1/IMPROD bpMRI Likert) scores. STATISTICAL TESTS For the detection of csPCa, area under receiver operating curve (AUC) was calculated using the DeLong's method. A multivariate analysis was conducted to determine the predictive power of combining variables. The values of P-value < 0.05 were considered significant. RESULTS The highest prediction performance was achieved by IMPROD bpMRI Likert and PI-RADSv2.1 score with AUC = 0.85 and 0.85 in split 1, 0.85 and 0.83 in split 2, respectively. bpMRI WG and/or kallikreins demonstrated AUCs ranging from 0.62 to 0.73 in split 1 and from 0.68 to 0.76 in split 2. AUC of bpMRI lesion-derived radiomics model was not statistically different to IMPROD bpMRI Likert score (split 1: AUC = 0.83, P-value = 0.306; split 2: AUC = 0.83, P-value = 0.488). DATA CONCLUSION The use of radiomics and kallikreins failed to outperform PI-RADSv2.1/IMPROD bpMRI Likert and their combination did not lead to further performance gains. LEVEL OF EVIDENCE 1 TECHNICAL EFFICACY: Stage 2.
Collapse
Affiliation(s)
- Ileana Montoya Perez
- Department of Diagnostic Radiology, University of Turku, Turku, Finland.,Department of Computing, University of Turku, Turku, Finland.,Medical Imaging Centre of Southwest Finland, Turku University Hospital, Turku, Finland
| | - Harri Merisaari
- Department of Diagnostic Radiology, University of Turku, Turku, Finland.,Department of Computing, University of Turku, Turku, Finland.,Medical Imaging Centre of Southwest Finland, Turku University Hospital, Turku, Finland
| | - Ivan Jambor
- Department of Diagnostic Radiology, University of Turku, Turku, Finland.,Medical Imaging Centre of Southwest Finland, Turku University Hospital, Turku, Finland.,Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, Connecticut, USA
| | - Otto Ettala
- Department of Urology, University of Turku, Turku University Hospital, Turku, Finland
| | - Pekka Taimen
- Institute of Biomedicine, Department of Pathology, University of Turku, Turku University Hospital, Turku, Finland
| | - Juha Knaapila
- Department of Urology, University of Turku, Turku University Hospital, Turku, Finland
| | - Henna Kekki
- Department of Biotechnology, University of Turku, Turku, Finland
| | - Ferdhos L Khan
- Department of Biotechnology, University of Turku, Turku, Finland
| | - Elise Syrjälä
- Department of Computing, University of Turku, Turku, Finland
| | - Aida Steiner
- Department of Diagnostic Radiology, University of Turku, Turku, Finland.,Medical Imaging Centre of Southwest Finland, Turku University Hospital, Turku, Finland
| | - Kari T Syvänen
- Department of Urology, University of Turku, Turku University Hospital, Turku, Finland
| | - Janne Verho
- Department of Diagnostic Radiology, University of Turku, Turku, Finland.,Medical Imaging Centre of Southwest Finland, Turku University Hospital, Turku, Finland
| | - Marjo Seppänen
- Department of Surgery, Satakunta Central Hospital, Pori, Finland
| | - Antti Rannikko
- Department of Urology, Helsinki University, Helsinki University Hospital, Helsinki, Finland
| | - Jarno Riikonen
- Department of Urology, Tampere University Hospital, University of Tampere, Tampere, Finland
| | - Tuomas Mirtti
- Department of Pathology, University of Helsinki, Helsinki, Finland
| | - Tarja Lamminen
- Department of Urology, University of Turku, Turku University Hospital, Turku, Finland
| | - Jani Saunavaara
- Department of Medical Physics, Turku University Hospital, Turku, Finland
| | - Ugo Falagario
- Department of Urology, University of Foggia, Foggia, Italy
| | - Alberto Martini
- Department of Oncology/Unit of Urology, Urological Research Institute, IRCCS Ospedale San Raffaele, Milan, Italy
| | - Tapio Pahikkala
- Department of Computing, University of Turku, Turku, Finland
| | - Kim Pettersson
- Department of Biotechnology, University of Turku, Turku, Finland
| | - Peter J Boström
- Department of Urology, University of Turku, Turku University Hospital, Turku, Finland
| | - Hannu J Aronen
- Department of Diagnostic Radiology, University of Turku, Turku, Finland.,Medical Imaging Centre of Southwest Finland, Turku University Hospital, Turku, Finland
| |
Collapse
|
29
|
Shi Y, Wahle E, Du Q, Krajewski L, Liang X, Zhou S, Zhang C, Baine M, Zheng D. Associations between Statin/Omega3 Usage and MRI-Based Radiomics Signatures in Prostate Cancer. Diagnostics (Basel) 2021; 11:diagnostics11010085. [PMID: 33430275 PMCID: PMC7825695 DOI: 10.3390/diagnostics11010085] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2020] [Revised: 12/31/2020] [Accepted: 01/05/2021] [Indexed: 12/19/2022] Open
Abstract
Prostate cancer is the most common noncutaneous cancer and the second leading cause of cancer deaths among American men. Statins and omega-3 are two medications recently found to correlate with prostate cancer risk and aggressiveness, but the observed associations are complex and controversial. We therefore explore the novel application of radiomics in studying statin and omega-3 usage in prostate cancer patients. On MRIs of 91 prostate cancer patients, two regions of interest (ROIs), the whole prostate and the peripheral region of the prostate, were manually segmented. From each ROI, 944 radiomic features were extracted after field bias correction and normalization. Heatmaps were generated to study the radiomic feature patterns against statin or omega-3 usage. Radiomics models were trained on selected features and evaluated with 500-round threefold cross-validation for each drug/ROI combination. On the 1500 validation datasets, the radiomics model achieved average AUCs of 0.70, 0.74, 0.78, and 0.72 for omega-3/prostate, omega-3/peripheral, statin/prostate, and statin/peripheral, respectively. As the first study to analyze radiomics in relation to statin and omega-3 uses in prostate cancer patients, our study preliminarily established the existence of imaging-identifiable tissue-level changes in the prostate and illustrated the potential usefulness of radiomics for further exploring these medications’ effects and mechanisms in prostate cancer.
Collapse
Affiliation(s)
- Yu Shi
- Department of Biological Science, University of Nebraska Lincoln, Lincoln, NE 68588, USA; (Y.S.); (Q.D.)
| | - Ethan Wahle
- Department of Radiation Oncology, University of Nebraska Medical Center, Omaha, NE 68189, USA; (E.W.); (L.K.); (S.Z.)
| | - Qian Du
- Department of Biological Science, University of Nebraska Lincoln, Lincoln, NE 68588, USA; (Y.S.); (Q.D.)
| | - Luke Krajewski
- Department of Radiation Oncology, University of Nebraska Medical Center, Omaha, NE 68189, USA; (E.W.); (L.K.); (S.Z.)
| | - Xiaoying Liang
- Department of Radiation Oncology, University of Florida Proton Institute, Jacksonville, FL 32206, USA;
| | - Sumin Zhou
- Department of Radiation Oncology, University of Nebraska Medical Center, Omaha, NE 68189, USA; (E.W.); (L.K.); (S.Z.)
| | - Chi Zhang
- Department of Biological Science, University of Nebraska Lincoln, Lincoln, NE 68588, USA; (Y.S.); (Q.D.)
- Correspondence: (C.Z.); (M.B.); (D.Z.)
| | - Michael Baine
- Department of Radiation Oncology, University of Nebraska Medical Center, Omaha, NE 68189, USA; (E.W.); (L.K.); (S.Z.)
- Correspondence: (C.Z.); (M.B.); (D.Z.)
| | - Dandan Zheng
- Department of Radiation Oncology, University of Nebraska Medical Center, Omaha, NE 68189, USA; (E.W.); (L.K.); (S.Z.)
- Correspondence: (C.Z.); (M.B.); (D.Z.)
| |
Collapse
|