1
|
Wen Y, Wu W, Liufu Y, Pan X, Zhang Y, Qi S, Guan Y. Differentiation of granulomatous nodules with lobulation and spiculation signs from solid lung adenocarcinomas using a CT deep learning model. BMC Cancer 2024; 24:875. [PMID: 39039511 PMCID: PMC11265160 DOI: 10.1186/s12885-024-12611-0] [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: 12/16/2023] [Accepted: 07/08/2024] [Indexed: 07/24/2024] Open
Abstract
BACKGROUND The diagnosis of solitary pulmonary nodules has always been a difficult and important point in clinical research, especially granulomatous nodules (GNs) with lobulation and spiculation signs, which are easily misdiagnosed as malignant tumors. Therefore, in this study, we utilised a CT deep learning (DL) model to distinguish GNs with lobulation and spiculation signs from solid lung adenocarcinomas (LADCs), to improve the diagnostic accuracy of preoperative diagnosis. METHODS 420 patients with pathologically confirmed GNs and LADCs from three medical institutions were retrospectively enrolled. The regions of interest in non-enhanced CT (NECT) and venous contrast-enhanced CT (VECT) were identified and labeled, and self-supervised labels were constructed. Cases from institution 1 were randomly divided into a training set (TS) and an internal validation set (IVS), and cases from institutions 2 and 3 were treated as an external validation set (EVS). Training and validation were performed using self-supervised transfer learning, and the results were compared with the radiologists' diagnoses. RESULTS The DL model achieved good performance in distinguishing GNs and LADCs, with area under curve (AUC) values of 0.917, 0.876, and 0.896 in the IVS and 0.889, 0.879, and 0.881 in the EVS for NECT, VECT, and non-enhanced with venous contrast-enhanced CT (NEVECT) images, respectively. The AUCs of radiologists 1, 2, 3, and 4 were, respectively, 0.739, 0.783, 0.883, and 0.901 in the (IVS) and 0.760, 0.760, 0.841, and 0.844 in the EVS. CONCLUSIONS A CT DL model showed great value for preoperative differentiation of GNs with lobulation and spiculation signs from solid LADCs, and its predictive performance was higher than that of radiologists.
Collapse
Affiliation(s)
- Yanhua Wen
- Department of Medical Imaging, the Fifth Affiliated Hospital of Guangzhou Medical University, 621 Gangwan Road, Guangzhou, 510700, Guangdong, China
| | - Wensheng Wu
- Department of Medical Imaging, the Fifth Affiliated Hospital of Guangzhou Medical University, 621 Gangwan Road, Guangzhou, 510700, Guangdong, China
| | - Yuling Liufu
- Department of Medical Imaging, the Fifth Affiliated Hospital of Guangzhou Medical University, 621 Gangwan Road, Guangzhou, 510700, Guangdong, China
| | - Xiaohuan Pan
- Department of Radiology, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong, China
| | - Yingying Zhang
- Department of Medical Imaging, the Fifth Affiliated Hospital of Guangzhou Medical University, 621 Gangwan Road, Guangzhou, 510700, Guangdong, China
| | - Shouliang Qi
- Key Laboratory of Intelligent Computing in Medical Image, College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, China
| | - Yubao Guan
- Department of Medical Imaging, the Fifth Affiliated Hospital of Guangzhou Medical University, 621 Gangwan Road, Guangzhou, 510700, Guangdong, China.
| |
Collapse
|
2
|
Li X, Huang W, Holmes JH. Dynamic Contrast-Enhanced (DCE) MRI. Magn Reson Imaging Clin N Am 2024; 32:47-61. [PMID: 38007282 DOI: 10.1016/j.mric.2023.09.001] [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] [Indexed: 11/27/2023]
Abstract
The non-invasive dynamic contrast-enhanced MRI (DCE-MRI) method provides valuable insights into tissue perfusion and vascularity. Primarily used in oncology, DCE-MRI is typically utilized to assess morphology and contrast agent (CA) kinetics in the tissue of interest. Interpretation of the temporal signatures of DCE-MRI data includes qualitative, semi-quantitative, and quantitative approaches. Recent advances in MRI technology allow simultaneous high spatial and temporal resolutions in DCE-MRI data acquisition on most vendor platforms, enabling the more desirable approach of quantitative data analysis using pharmacokinetic (PK) modeling. Many technical factors, including signal-to-noise ratio, temporal resolution, quantifications of arterial input function and native tissue T1, and PK model selection, need to be carefully considered when performing quantitative DCE-MRI. Standardization in data acquisition and analysis is especially important in multi-center studies.
Collapse
Affiliation(s)
- Xin Li
- Advanced Imaging Research Center, Oregon Health & Science University, 3181 SW Sam Jackson Park Road, Portland, OR 97239, USA
| | - Wei Huang
- Advanced Imaging Research Center, Oregon Health & Science University, 3181 SW Sam Jackson Park Road, Portland, OR 97239, USA
| | - James H Holmes
- Radiology, Biomedical Engineering, and Holden Cancer Center, University of Iowa, 169 Newton Road, Iowa City, IA 52242, USA.
| |
Collapse
|
3
|
LoCastro E, Paudyal R, Konar AS, LaViolette PS, Akin O, Hatzoglou V, Goh AC, Bochner BH, Rosenberg J, Wong RJ, Lee NY, Schwartz LH, Shukla-Dave A. A Quantitative Multiparametric MRI Analysis Platform for Estimation of Robust Imaging Biomarkers in Clinical Oncology. Tomography 2023; 9:2052-2066. [PMID: 37987347 PMCID: PMC10661267 DOI: 10.3390/tomography9060161] [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: 09/14/2023] [Revised: 10/12/2023] [Accepted: 10/18/2023] [Indexed: 11/22/2023] Open
Abstract
There is a need to develop user-friendly imaging tools estimating robust quantitative biomarkers (QIBs) from multiparametric (mp)MRI for clinical applications in oncology. Quantitative metrics derived from (mp)MRI can monitor and predict early responses to treatment, often prior to anatomical changes. We have developed a vendor-agnostic, flexible, and user-friendly MATLAB-based toolkit, MRI-Quantitative Analysis and Multiparametric Evaluation Routines ("MRI-QAMPER", current release v3.0), for the estimation of quantitative metrics from dynamic contrast-enhanced (DCE) and multi-b value diffusion-weighted (DW) MR and MR relaxometry. MRI-QAMPER's functionality includes generating numerical parametric maps from these methods reflecting tumor permeability, cellularity, and tissue morphology. MRI-QAMPER routines were validated using digital reference objects (DROs) for DCE and DW MRI, serving as initial approval stages in the National Cancer Institute Quantitative Imaging Network (NCI/QIN) software benchmark. MRI-QAMPER has participated in DCE and DW MRI Collaborative Challenge Projects (CCPs), which are key technical stages in the NCI/QIN benchmark. In a DCE CCP, QAMPER presented the best repeatability coefficient (RC = 0.56) across test-retest brain metastasis data, out of ten participating DCE software packages. In a DW CCP, QAMPER ranked among the top five (out of fourteen) tools with the highest area under the curve (AUC) for prostate cancer detection. This platform can seamlessly process mpMRI data from brain, head and neck, thyroid, prostate, pancreas, and bladder cancer. MRI-QAMPER prospectively analyzes dose de-escalation trial data for oropharyngeal cancer, which has earned it advanced NCI/QIN approval for expanded usage and applications in wider clinical trials.
Collapse
Affiliation(s)
- Eve LoCastro
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (E.L.); (R.P.); (A.S.K.)
| | - Ramesh Paudyal
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (E.L.); (R.P.); (A.S.K.)
| | - Amaresha Shridhar Konar
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (E.L.); (R.P.); (A.S.K.)
| | - Peter S. LaViolette
- Department of Radiology, Medical College of Wisconsin, Milwaukee, WI 53226, USA;
| | - Oguz Akin
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (O.A.); (V.H.); (L.H.S.)
| | - Vaios Hatzoglou
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (O.A.); (V.H.); (L.H.S.)
| | - Alvin C. Goh
- Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (A.C.G.); (B.H.B.); (R.J.W.)
| | - Bernard H. Bochner
- Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (A.C.G.); (B.H.B.); (R.J.W.)
| | - Jonathan Rosenberg
- Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA;
| | - Richard J. Wong
- Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (A.C.G.); (B.H.B.); (R.J.W.)
| | - Nancy Y. Lee
- Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA;
| | - Lawrence H. Schwartz
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (O.A.); (V.H.); (L.H.S.)
| | - Amita Shukla-Dave
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (E.L.); (R.P.); (A.S.K.)
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (O.A.); (V.H.); (L.H.S.)
| |
Collapse
|
4
|
Prezja F, Äyrämö S, Pölönen I, Ojala T, Lahtinen S, Ruusuvuori P, Kuopio T. Improved accuracy in colorectal cancer tissue decomposition through refinement of established deep learning solutions. Sci Rep 2023; 13:15879. [PMID: 37741820 PMCID: PMC10517936 DOI: 10.1038/s41598-023-42357-x] [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: 02/24/2023] [Accepted: 09/08/2023] [Indexed: 09/25/2023] Open
Abstract
Hematoxylin and eosin-stained biopsy slides are regularly available for colorectal cancer patients. These slides are often not used to define objective biomarkers for patient stratification and treatment selection. Standard biomarkers often pertain to costly and slow genetic tests. However, recent work has shown that relevant biomarkers can be extracted from these images using convolutional neural networks (CNNs). The CNN-based biomarkers predicted colorectal cancer patient outcomes comparably to gold standards. Extracting CNN-biomarkers is fast, automatic, and of minimal cost. CNN-based biomarkers rely on the ability of CNNs to recognize distinct tissue types from microscope whole slide images. The quality of these biomarkers (coined 'Deep Stroma') depends on the accuracy of CNNs in decomposing all relevant tissue classes. Improving tissue decomposition accuracy is essential for improving the prognostic potential of CNN-biomarkers. In this study, we implemented a novel training strategy to refine an established CNN model, which then surpassed all previous solutions . We obtained a 95.6% average accuracy in the external test set and 99.5% in the internal test set. Our approach reduced errors in biomarker-relevant classes, such as Lymphocytes, and was the first to include interpretability methods. These methods were used to better apprehend our model's limitations and capabilities.
Collapse
Affiliation(s)
- Fabi Prezja
- Faculty of Information Technology, University of Jyväskylä, Jyväskylä, 40014, Finland.
- Digital Health Intelligence Laboratory, University of Jyväskylä, Jyväskylä, 40014, Finland.
| | - Sami Äyrämö
- Faculty of Information Technology, University of Jyväskylä, Jyväskylä, 40014, Finland
- Digital Health Intelligence Laboratory, University of Jyväskylä, Jyväskylä, 40014, Finland
| | - Ilkka Pölönen
- Faculty of Information Technology, University of Jyväskylä, Jyväskylä, 40014, Finland
- Spectral Imaging Laboratory, University of Jyväskylä, Jyväskylä, 40014, Finland
| | - Timo Ojala
- Faculty of Information Technology, University of Jyväskylä, Jyväskylä, 40014, Finland
- Digital Health Intelligence Laboratory, University of Jyväskylä, Jyväskylä, 40014, Finland
| | - Suvi Lahtinen
- Faculty of Information Technology, University of Jyväskylä, Jyväskylä, 40014, Finland
- Department of Biological and Environmental Science, Faculty of Mathematics and Science, University of Jyväskylä, Jyväskylä, 40014, Finland
| | - Pekka Ruusuvuori
- Institute of Biomedicine, Cancer Research Unit, University of Turku, Turku, 20014, Finland
- FICAN West Cancer Centre, Turku University Hospital, Turku, 20521, Finland
| | - Teijo Kuopio
- Department of Education and Research, Hospital Nova of Central Finland, Jyväskylä, 40620, Finland
- Department of Biological and Environmental Science, University of Jyväskylä, Jyväskylä, 40014, Finland
- Department of Pathology, Hospital Nova of Central Finland, Jyväskylä, 40620, Finland
| |
Collapse
|
5
|
Rogers W, Keek SA, Beuque M, Lavrova E, Primakov S, Wu G, Yan C, Sanduleanu S, Gietema HA, Casale R, Occhipinti M, Woodruff HC, Jochems A, Lambin P. Towards texture accurate slice interpolation of medical images using PixelMiner. Comput Biol Med 2023; 161:106701. [PMID: 37244145 DOI: 10.1016/j.compbiomed.2023.106701] [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: 11/29/2021] [Revised: 08/06/2022] [Accepted: 11/23/2022] [Indexed: 05/29/2023]
Abstract
Quantitative image analysis models are used for medical imaging tasks such as registration, classification, object detection, and segmentation. For these models to be capable of making accurate predictions, they need valid and precise information. We propose PixelMiner, a convolution-based deep-learning model for interpolating computed tomography (CT) imaging slices. PixelMiner was designed to produce texture-accurate slice interpolations by trading off pixel accuracy for texture accuracy. PixelMiner was trained on a dataset of 7829 CT scans and validated using an external dataset. We demonstrated the model's effectiveness by using the structural similarity index (SSIM), peak signal to noise ratio (PSNR), and the root mean squared error (RMSE) of extracted texture features. Additionally, we developed and used a new metric, the mean squared mapped feature error (MSMFE). The performance of PixelMiner was compared to four other interpolation methods: (tri-)linear, (tri-)cubic, windowed sinc (WS), and nearest neighbor (NN). PixelMiner produced texture with a significantly lowest average texture error compared to all other methods with a normalized root mean squared error (NRMSE) of 0.11 (p < .01), and the significantly highest reproducibility with a concordance correlation coefficient (CCC) ≥ 0.85 (p < .01). PixelMiner was not only shown to better preserve features but was also validated using an ablation study by removing auto-regression from the model and was shown to improve segmentations on interpolated slices.
Collapse
Affiliation(s)
- W Rogers
- The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, the Netherlands
| | - S A Keek
- The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, the Netherlands
| | - M Beuque
- The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, the Netherlands
| | - E Lavrova
- The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, the Netherlands; GIGA Cyclotron Research Centre in Vivo Imaging, University of Liège, Liège, Belgium
| | - S Primakov
- The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, the Netherlands
| | - G Wu
- The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, the Netherlands
| | - C Yan
- The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, the Netherlands
| | - S Sanduleanu
- The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, the Netherlands
| | - H A Gietema
- Department of Radiology and Nuclear Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, the Netherlands
| | - R Casale
- The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, the Netherlands; Department of Radiology, Institut Jules Bordet, Université Libre de Bruxelles, Brussels, Belgium
| | - M Occhipinti
- Radiomics, Clos Chanmurly 13, 4000, Liege, Belgium
| | - H C Woodruff
- The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, the Netherlands; Department of Radiology and Nuclear Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, the Netherlands
| | - A Jochems
- The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, the Netherlands
| | - P Lambin
- The D-Lab, Department of Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University, Maastricht, the Netherlands; Department of Radiology and Nuclear Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, the Netherlands.
| |
Collapse
|
6
|
Predicting Soft Tissue Sarcoma Response to Neoadjuvant Chemotherapy Using an MRI-Based Delta-Radiomics Approach. Mol Imaging Biol 2023:10.1007/s11307-023-01803-y. [PMID: 36695966 DOI: 10.1007/s11307-023-01803-y] [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: 10/27/2022] [Revised: 01/14/2023] [Accepted: 01/16/2023] [Indexed: 01/26/2023]
Abstract
OBJECTIVES To evaluate the performance of machine learning-augmented MRI-based radiomics models for predicting response to neoadjuvant chemotherapy (NAC) in soft tissue sarcomas. METHODS Forty-four subjects were identified retrospectively from patients who received NAC at our institution for pathologically proven soft tissue sarcomas. Only subjects who had both a baseline MRI prior to initiating chemotherapy and a post-treatment scan at least 2 months after initiating chemotherapy and prior to surgical resection were included. 3D ROIs were used to delineate whole-tumor volumes on pre- and post-treatment scans, from which 1708 radiomics features were extracted. Delta-radiomics features were calculated by subtraction of baseline from post-treatment values and used to distinguish treatment response through univariate analyses as well as machine learning-augmented radiomics analyses. RESULTS Though only 4.74% of variables overall reached significance at p ≤ 0.05 in univariate analyses, Laws Texture Energy (LTE)-derived metrics represented 46.04% of all such features reaching statistical significance. ROC analyses similarly failed to predict NAC response, with AUCs of 0.40 (95% CI 0.22-0.58) and 0.44 (95% CI 0.26-0.62) for RF and AdaBoost, respectively. CONCLUSION Overall, while our result was not able to separate NAC responders from non-responders, our analyses did identify a subset of LTE-derived metrics that show promise for further investigations. Future studies will likely benefit from larger sample size constructions so as to avoid the need for data filtering and feature selection techniques, which have the potential to significantly bias the machine learning procedures.
Collapse
|
7
|
Huo JW, Luo TY, Diao L, Lv FJ, Chen WD, Yu RZ, Li Q. Using combined CT-clinical radiomics models to identify epidermal growth factor receptor mutation subtypes in lung adenocarcinoma. Front Oncol 2022; 12:846589. [PMID: 36059655 PMCID: PMC9434115 DOI: 10.3389/fonc.2022.846589] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/31/2021] [Accepted: 07/19/2022] [Indexed: 11/13/2022] Open
Abstract
Background To investigate the value of computed tomography (CT)-based radiomics signatures in combination with clinical and CT morphological features to identify epidermal growth factor receptor (EGFR)-mutation subtypes in lung adenocarcinoma (LADC). Methods From February 2012 to October 2019, 608 patients were confirmed with LADC and underwent chest CT scans. Among them, 307 (50.5%) patients had a positive EGFR-mutation and 301 (49.5%) had a negative EGFR-mutation. Of the EGFR-mutant patients, 114 (37.1%) had a 19del -mutation, 155 (50.5%) had a L858R-mutation, and 38 (12.4%) had other rare mutations. Three combined models were generated by incorporating radiomics signatures, clinical, and CT morphological features to predict EGFR-mutation status. Patients were randomly split into training and testing cohorts, 80% and 20%, respectively. Model 1 was used to predict positive and negative EGFR-mutation, model 2 was used to predict 19del and non-19del mutations, and model 3 was used to predict L858R and non-L858R mutations. The receiver operating characteristic curve and the area under the curve (AUC) were used to evaluate their performance. Results For the three models, model 1 had AUC values of 0.969 and 0.886 in the training and validation cohorts, respectively. Model 2 had AUC values of 0.999 and 0.847 in the training and validation cohorts, respectively. Model 3 had AUC values of 0.984 and 0.806 in the training and validation cohorts, respectively. Conclusion Combined models that incorporate radiomics signature, clinical, and CT morphological features may serve as an auxiliary tool to predict EGFR-mutation subtypes and contribute to individualized treatment for patients with LADC.
Collapse
Affiliation(s)
- Ji-wen Huo
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Tian-you Luo
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Le Diao
- Ocean International Center, The Infervision Medical Technology Co., Ltd., Beijing, China
| | - Fa-jin Lv
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Wei-dao Chen
- Ocean International Center, The Infervision Medical Technology Co., Ltd., Beijing, China
| | - Rui-ze Yu
- Ocean International Center, The Infervision Medical Technology Co., Ltd., Beijing, China
| | - Qi Li
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
- *Correspondence: Qi Li,
| |
Collapse
|
8
|
Ottens T, Barbieri S, Orton MR, Klaassen R, van Laarhoven HW, Crezee H, Nederveen AJ, Zhen X, Gurney-Champion OJ. Deep learning DCE-MRI parameter estimation: application in pancreatic cancer. Med Image Anal 2022; 80:102512. [DOI: 10.1016/j.media.2022.102512] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2021] [Revised: 05/04/2022] [Accepted: 06/06/2022] [Indexed: 10/18/2022]
|
9
|
Zhang Y, Fang Q. BlenderPhotonics: an integrated open-source software environment for three-dimensional meshing and photon simulations in complex tissues. JOURNAL OF BIOMEDICAL OPTICS 2022; 27:083014. [PMID: 35429155 PMCID: PMC9010662 DOI: 10.1117/1.jbo.27.8.083014] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/12/2022] [Accepted: 03/23/2022] [Indexed: 06/14/2023]
Abstract
SIGNIFICANCE Rapid advances in biophotonics techniques require quantitative, model-based computational approaches to obtain functional and structural information from increasingly complex and multiscaled anatomies. The lack of efficient tools to accurately model tissue structures and subsequently perform quantitative multiphysics modeling greatly impedes the clinical translation of these modalities. AIM Although the mesh-based Monte Carlo (MMC) method expands our capabilities in simulating complex tissues using tetrahedral meshes, the generation of such domains often requires specialized meshing tools, such as Iso2Mesh. Creating a simplified and intuitive interface for tissue anatomical modeling and optical simulations is essential toward making these advanced modeling techniques broadly accessible to the user community. APPROACH We responded to the above challenge by combining the powerful, open-source three-dimensional (3D) modeling software, Blender, with state-of-the-art 3D mesh generation and MC simulation tools, utilizing the interactive graphical user interface in Blender as the front-end to allow users to create complex tissue mesh models and subsequently launch MMC light simulations. RESULTS Here, we present a tutorial to our Python-based Blender add-on-BlenderPhotonics-to interface with Iso2Mesh and MMC, which allows users to create, configure and refine complex simulation domains and run hardware-accelerated 3D light simulations with only a few clicks. We provide a comprehensive introduction to this tool and walk readers through five examples, ranging from simple shapes to sophisticated realistic tissue models. CONCLUSIONS BlenderPhotonics is user friendly and open source, and it leverages the vastly rich ecosystem of Blender. It wraps advanced modeling capabilities within an easy-to-use and interactive interface. The latest software can be downloaded at http://mcx.space/bp.
Collapse
Affiliation(s)
- Yuxuan Zhang
- Northeastern University, Department of Bioengineering, Boston, Massachusetts, United States
| | - Qianqian Fang
- Northeastern University, Department of Bioengineering, Boston, Massachusetts, United States
- Northeastern University, Department of Electrical and Computer Engineering, Boston, Massachusetts, United States
| |
Collapse
|
10
|
Anan N, Zainon R, Tamal M. A review on advances in 18F-FDG PET/CT radiomics standardisation and application in lung disease management. Insights Imaging 2022; 13:22. [PMID: 35124733 PMCID: PMC8817778 DOI: 10.1186/s13244-021-01153-9] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2021] [Accepted: 12/23/2021] [Indexed: 02/06/2023] Open
Abstract
Radiomics analysis quantifies the interpolation of multiple and invisible molecular features present in diagnostic and therapeutic images. Implementation of 18-fluorine-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) radiomics captures various disorders in non-invasive and high-throughput manner. 18F-FDG PET/CT accurately identifies the metabolic and anatomical changes during cancer progression. Therefore, the application of 18F-FDG PET/CT in the field of oncology is well established. Clinical application of 18F-FDG PET/CT radiomics in lung infection and inflammation is also an emerging field. Combination of bioinformatics approaches or textual analysis allows radiomics to extract additional information to predict cell biology at the micro-level. However, radiomics texture analysis is affected by several factors associated with image acquisition and processing. At present, researchers are working on mitigating these interrupters and developing standardised workflow for texture biomarker establishment. This review article focuses on the application of 18F-FDG PET/CT in detecting lung diseases specifically on cancer, infection and inflammation. An overview of different approaches and challenges encountered on standardisation of 18F-FDG PET/CT technique has also been highlighted. The review article provides insights about radiomics standardisation and application of 18F-FDG PET/CT in lung disease management.
Collapse
|
11
|
Xie P, Zuo K, Liu J, Chen M, Zhao S, Kang W, Li F. Interpretable Diagnosis for Whole-Slide Melanoma Histology Images Using Convolutional Neural Network. JOURNAL OF HEALTHCARE ENGINEERING 2021; 2021:8396438. [PMID: 34760142 PMCID: PMC8575613 DOI: 10.1155/2021/8396438] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/06/2021] [Accepted: 10/13/2021] [Indexed: 02/08/2023]
Abstract
At present, deep learning-based medical image diagnosis had achieved high performance in several diseases. However, the black-box nature of the convolutional neural network (CNN) limits their role in diagnosis. In this study, a novel interpretable diagnosis pipeline using the CNN model was proposed. Furthermore, a sizeable melanoma database that contains 841 digital whole-slide images (WSIs) was built to train and evaluate the model. The model achieved strong melanoma classification ability (0.962 areas under the receiver operating characteristic, 0.887 sensitivity, and 0.925 specificity). Moreover, the proposed model outperformed the existing schemes in terms of accuracy that is 20 pathologists (0.933 vs 0.732 accuracy). Finally, the gradient-weighted class activation mapping (Grad-CAM) method was used to show the inner logic of the proposed model and its feasibility to improve diagnosis process in healthcare. The mechanism of feature heat maps which is visualized through a saliency mapping has demonstrated that features learned or extracted by the proposed model are compatible with the accepted pathological features. Conclusively, the proposed model provides a rapid and accurate diagnosis by locating the distinctive features of melanoma to build doctors' trust in the CNNs' diagnosis results.
Collapse
Affiliation(s)
- Peizhen Xie
- National University of Defense Technology, Changsha 410073, China
| | - Ke Zuo
- National University of Defense Technology, Changsha 410073, China
| | - Jie Liu
- National University of Defense Technology, Changsha 410073, China
| | - Mingliang Chen
- Department of Dermatology, Xiangya Hospital, Central South University, Changsha 410008, China
| | - Shuang Zhao
- Department of Dermatology, Xiangya Hospital, Central South University, Changsha 410008, China
- Hunan Key Laboratory of Skin Cancer and Psoriasis, Changsha 410005, China
- Hunan Engineering Research Center of Skin Health and Disease, Changsha 410005, China
| | - Wenjie Kang
- National University of Defense Technology, Changsha 410073, China
- Hunan Provincial Key Laboratory of Network Investigational Technology, Hunan Police Academy, Changsha 410138, China
- Key Laboratory of Police Internet of Things Application,Ministry of Public Security, Changsha 410138, China
| | - Fangfang Li
- Department of Dermatology, Xiangya Hospital, Central South University, Changsha 410008, China
- Hunan Key Laboratory of Skin Cancer and Psoriasis, Changsha 410005, China
- Hunan Engineering Research Center of Skin Health and Disease, Changsha 410005, China
| |
Collapse
|
12
|
Chen W, Hou X, Hu Y, Huang G, Ye X, Nie S. A deep learning- and CT image-based prognostic model for the prediction of survival in non-small cell lung cancer. Med Phys 2021; 48:7946-7958. [PMID: 34661294 DOI: 10.1002/mp.15302] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2021] [Revised: 09/19/2021] [Accepted: 10/10/2021] [Indexed: 12/19/2022] Open
Abstract
OBJECTIVE To assist clinicians in arranging personalized treatment, planning follow-up programs and extending survival times for non-small cell lung cancer (NSCLC) patients, a method of deep learning combined with computed tomography (CT) imaging for survival prediction was designed. METHODS Data were collected from 484 patients from four research centers. The data from 344 patients were utilized to build the A_CNN survival prognosis model to classify 2-year overall survival time ranges (730 days cut-off). Data from 140 patients, including independent internal and external test sets, were utilized for model testing. First, a series of preprocessing techniques were used to process the original CT images and generate training and test data sets from the axial, coronal, and sagittal planes. Second, the structure of the A_CNN model was designed based on asymmetric convolution, bottleneck blocks, the uniform cross-entropy (UC) loss function, and other advanced techniques. After that, the A_CNN model was trained, and numerous comparative experiments were designed to obtain the best prognostic survival model. Last, the model performance was evaluated, and the predicted survival curves were analyzed. RESULTS The A_CNN survival prognosis model yielded a high patient-level accuracy of 88.8%, a patch-level accuracy of 82.9%, and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.932. When tested on an external data set, the maximum patient-level accuracy was 80.0%. CONCLUSIONS The results suggest that using a deep learning method can improve prognosis in patients with NSCLC and has important application value in establishing individualized prognostic models.
Collapse
Affiliation(s)
- Wen Chen
- School of Medical Imaging, Shanghai University of Medicine & Health Science, Shanghai, China
| | - Xuewen Hou
- School of Medical Imaging, Shanghai University of Medicine & Health Science, Shanghai, China
| | - Ying Hu
- School of Medical Imaging, Shanghai University of Medicine & Health Science, Shanghai, China
| | - Gang Huang
- Department of Radiology, Shanghai Chest Hospital, Shanghai, China
| | - Xiaodan Ye
- Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, China
| | - Shengdong Nie
- School of Medical Imaging, Shanghai University of Medicine & Health Science, Shanghai, China
| |
Collapse
|
13
|
Bliesener Y, Lebel RM, Acharya J, Frayne R, Nayak KS. Pseudo Test-Retest Evaluation of Millimeter-Resolution Whole-Brain Dynamic Contrast-enhanced MRI in Patients with High-Grade Glioma. Radiology 2021; 300:410-420. [PMID: 34100683 PMCID: PMC8328086 DOI: 10.1148/radiol.2021203628] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/02/2022]
Abstract
Background Advances in sub-Nyquist–sampled dynamic contrast-enhanced (DCE) MRI enable monitoring of brain tumors with millimeter resolution and whole-brain coverage. Such undersampled quantitative methods need careful characterization regarding achievable test-retest reproducibility. Purpose To demonstrate a fully automated high-resolution whole-brain DCE MRI pipeline with 30-fold sparse undersampling and estimate its reproducibility on the basis of reference regions of stable tissue types during multiple posttreatment time points by using longitudinal clinical images of high-grade glioma. Materials and Methods Two methods for sub-Nyquist–sampled DCE MRI were extended with automatic estimation of vascular input functions. Continuously acquired three-dimensional k-space data with ramped-up flip angles were partitioned to yield high-resolution, whole-brain tracer kinetic parameter maps with matched precontrast-agent T1 and M0 maps. Reproducibility was estimated in a retrospective study in participants with high-grade glioma, who underwent three consecutive standard-of-care examinations between December 2016 and April 2019. Coefficients of variation and reproducibility coefficients were reported for histogram statistics of the tracer kinetic parameters plasma volume fraction and volume transfer constant (Ktrans) on five healthy tissue types. Results The images from 13 participants (mean age ± standard deviation, 61 years ± 10; nine women) with high-grade glioma were evaluated. In healthy tissues, the protocol achieved a coefficient of variation less than 57% for median Ktrans, if Ktrans was estimated consecutively. The maximum reproducibility coefficient for median Ktrans was estimated to be at 0.06 min–1 for large or low-enhancing tissues and to be as high as 0.48 min–1 in smaller or strongly enhancing tissues. Conclusion A fully automated, sparsely sampled DCE MRI reconstruction with patient-specific vascular input function offered high spatial and temporal resolution and whole-brain coverage; in healthy tissues, the protocol estimated median volume transfer constant with maximum reproducibility coefficient of 0.06 min–1 in large, low-enhancing tissue regions and maximum reproducibility coefficient of less than 0.48 min–1 in smaller or more strongly enhancing tissue regions. Published under a CC BY 4.0 license. Online supplemental material is available for this article. See also the editorial by Lenkinski in this issue.
Collapse
Affiliation(s)
- Yannick Bliesener
- From the Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, 3740 McClintock Ave, EEB 400, Los Angeles, CA 90089-2564 (Y.B., K.S.N.); GE Healthcare, Calgary, Canada (R.M.L.); Department of Radiology, University of Calgary, Calgary, Canada (R.M.L.); Seaman Family MR Research Centre, Foothills Hospital, Calgary, Canada (R.M.L., R.F.); Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, Calif (J.A., K.S.N.); and Departments of Radiology and Clinical Neuroscience, Hotchkiss Brain Institute, University of Calgary, Calgary, Canada (R.F.)
| | - R Marc Lebel
- From the Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, 3740 McClintock Ave, EEB 400, Los Angeles, CA 90089-2564 (Y.B., K.S.N.); GE Healthcare, Calgary, Canada (R.M.L.); Department of Radiology, University of Calgary, Calgary, Canada (R.M.L.); Seaman Family MR Research Centre, Foothills Hospital, Calgary, Canada (R.M.L., R.F.); Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, Calif (J.A., K.S.N.); and Departments of Radiology and Clinical Neuroscience, Hotchkiss Brain Institute, University of Calgary, Calgary, Canada (R.F.)
| | - Jay Acharya
- From the Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, 3740 McClintock Ave, EEB 400, Los Angeles, CA 90089-2564 (Y.B., K.S.N.); GE Healthcare, Calgary, Canada (R.M.L.); Department of Radiology, University of Calgary, Calgary, Canada (R.M.L.); Seaman Family MR Research Centre, Foothills Hospital, Calgary, Canada (R.M.L., R.F.); Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, Calif (J.A., K.S.N.); and Departments of Radiology and Clinical Neuroscience, Hotchkiss Brain Institute, University of Calgary, Calgary, Canada (R.F.)
| | - Richard Frayne
- From the Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, 3740 McClintock Ave, EEB 400, Los Angeles, CA 90089-2564 (Y.B., K.S.N.); GE Healthcare, Calgary, Canada (R.M.L.); Department of Radiology, University of Calgary, Calgary, Canada (R.M.L.); Seaman Family MR Research Centre, Foothills Hospital, Calgary, Canada (R.M.L., R.F.); Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, Calif (J.A., K.S.N.); and Departments of Radiology and Clinical Neuroscience, Hotchkiss Brain Institute, University of Calgary, Calgary, Canada (R.F.)
| | - Krishna S Nayak
- From the Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, 3740 McClintock Ave, EEB 400, Los Angeles, CA 90089-2564 (Y.B., K.S.N.); GE Healthcare, Calgary, Canada (R.M.L.); Department of Radiology, University of Calgary, Calgary, Canada (R.M.L.); Seaman Family MR Research Centre, Foothills Hospital, Calgary, Canada (R.M.L., R.F.); Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, Calif (J.A., K.S.N.); and Departments of Radiology and Clinical Neuroscience, Hotchkiss Brain Institute, University of Calgary, Calgary, Canada (R.F.)
| |
Collapse
|
14
|
Guo J, Li Z, Qu X, Xian J. Value of MRI-based radiomics analysis for differentiation of benign and malignant epithelial neoplasms in the lacrimal gland: a retrospective study. Acta Radiol 2021; 62:743-751. [PMID: 32660315 DOI: 10.1177/0284185120940258] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
BACKGROUND It is essential to distinguish malignant from benign epithelial neoplasms in the lacrimal gland for different treatment options and prognosis. PURPOSE To retrospectively assess the performance of magnetic resonance imaging (MRI)-based radiomics features in the differentiation of benign and malignant epithelial neoplasms in the lacrimal gland. MATERIAL AND METHODS Seventy-six consecutive patients with histopathology-proven epithelial neoplasms of the lacrimal gland were enrolled in the study, including 41 benign and 35 malignant neoplasms. Radiomics features were extracted from T2-weighted and post-contrast T1-weighted imaging. The least absolute shrinkage and selection operator method was used to select imaging features and reduce data dimension to discriminate malignant from benign neoplasms in the lacrimal gland. Diagnostic performance of the radiomics model was assessed by receive operation characteristic (ROC) curve and compared with that of radiologists. RESULTS Four quantitative image features including inverse difference moment normalized (IDMN), mean deviation (MD), standard deviation (SD), and long-run emphasis (LRE) were selected to distinguish malignant from benign epithelial neoplasms in the lacrimal gland. Area under the curve (AUC) of these four features were 0.88, 086, 0.88, and 0.86, respectively, with 0.93 for the combination model. The model identified malignant epithelial neoplasms from benign group with 89% sensitivity, 93% specificity, and 89% accuracy. There was a significant difference in the diagnostic performance of radiomics model and the radiologists, with AUC of 0.70 for radiologists. The diagnostic performance of radiomics is superior to that of radiologists. CONCLUSION MRI-based radiomics analysis has potential for differentiation of benign and malignant epithelial neoplasms in the lacrimal gland.
Collapse
Affiliation(s)
- Jian Guo
- Department of Radiology, Beijing Tongren Hospital, Capital Medical University, Beijing, PR China
- Clinical Center for Eye Tumors, Capital Medical University, Beijing, PR China
| | - Zheng Li
- Department of Radiology, Beijing Tongren Hospital, Capital Medical University, Beijing, PR China
- Clinical Center for Eye Tumors, Capital Medical University, Beijing, PR China
| | - Xiaoxia Qu
- Department of Radiology, Beijing Tongren Hospital, Capital Medical University, Beijing, PR China
- Clinical Center for Eye Tumors, Capital Medical University, Beijing, PR China
| | - Junfang Xian
- Department of Radiology, Beijing Tongren Hospital, Capital Medical University, Beijing, PR China
- Clinical Center for Eye Tumors, Capital Medical University, Beijing, PR China
| |
Collapse
|
15
|
Zhou J, Li H, Cheng B, Cao R, Zou F, Yang D, Liu X, Song M, Wu T. Derivation and Validation of a Prognostic Scoring Model Based on Clinical and Pathological Features for Risk Stratification in Oral Squamous Cell Carcinoma Patients: A Retrospective Multicenter Study. Front Oncol 2021; 11:652553. [PMID: 34123806 PMCID: PMC8195273 DOI: 10.3389/fonc.2021.652553] [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: 01/12/2021] [Accepted: 04/12/2021] [Indexed: 12/12/2022] Open
Abstract
Objective To develop and validate a simple-to-use prognostic scoring model based on clinical and pathological features which can predict overall survival (OS) of patients with oral squamous cell carcinoma (OSCC) and facilitate personalized treatment planning. Materials and Methods OSCC patients (n = 404) from a public hospital were divided into a training cohort (n = 282) and an internal validation cohort (n = 122). A total of 12 clinical and pathological features were included in Kaplan-Meier analysis to identify the factors associated with OS. Multivariable Cox proportional hazards regression analysis was performed to further identify important variables and establish prognostic models. Nomogram was generated to predict the individual's 1-, 3- and 5-year OS rates. The performance of the prognostic scoring model was compared with that of the pathological one and the AJCC TNM staging system by the receiver operating characteristic curve (ROC), concordance index (C-index), calibration curve, and decision curve analysis (DCA). Patients were classified into high- and low-risk groups according to the risk scores of the nomogram. The nomogram-illustrated model was independently tested in an external validation cohort of 95 patients. Results Four significant variables (physical examination-tumor size, imaging examination-tumor size, pathological nodal involvement stage, and histologic grade) were included into the nomogram-illustrated model (clinical-pathological model). The area under the ROC curve (AUC) of the clinical-pathological model was 0.687, 0.719, and 0.722 for 1-, 3- and 5-year survival, respectively, which was superior to that of the pathological model (AUC = 0.649, 0.707, 0.717, respectively) and AJCC TNM staging system (AUC = 0.628, 0.668, 0.677, respectively). The clinical-pathological model exhibited improved discriminative power compared with pathological model and AJCC TNM staging system (C-index = 0.755, 0.702, 0.642, respectively) in the external validation cohort. The calibration curves and DCA also displayed excellent predictive performances. Conclusion This clinical and pathological feature based prognostic scoring model showed better predictive ability compared with the pathological one, which would be a useful tool of personalized accurate risk stratification and precision therapy planning for OSCC patients.
Collapse
Affiliation(s)
- Jiaying Zhou
- Hospital of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University, Guangzhou, China
| | - Huan Li
- Department of ICU, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China
| | - Bin Cheng
- Hospital of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University, Guangzhou, China
| | - Ruoyan Cao
- Hospital of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University, Guangzhou, China
| | - Fengyuan Zou
- Department of Data Sciences, AID Cloud Technology Co., Ltd, Guangzhou, China
| | - Dong Yang
- Department of Data Sciences, AID Cloud Technology Co., Ltd, Guangzhou, China
| | - Xiang Liu
- Department of Data Sciences, AID Cloud Technology Co., Ltd, Guangzhou, China
| | - Ming Song
- Department of Head and Neck Surgery, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China
| | - Tong Wu
- Hospital of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Stomatology, Guanghua School of Stomatology, Sun Yat-sen University, Guangzhou, China
| |
Collapse
|
16
|
Cancer Clinical Trials: What Every Radiologist Wants to Know but Is Afraid to Ask. AJR Am J Roentgenol 2021; 216:1099-1111. [PMID: 33594911 DOI: 10.2214/ajr.20.22852] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
OBJECTIVE. The purpose of this article is to provide radiologists with a guide to the fundamental principles of oncology clinical trials. The review summarizes the evolution and structure of modern clinical trials with an emphasis on the relevance of clinical trials in the field of oncologic imaging. CONCLUSION. Understanding the structure and clinical relevance of modern clinical trials is beneficial for radiologists in the field of oncologic imaging.
Collapse
|
17
|
Abstract
Magnetic resonance imaging (MRI) is a noninvasive imaging tool for neuroradiological diagnosis. Numerous concepts of automated MRI analysis and the use of machine learning have been proposed to assist diagnosis and prognosis. While these academic innovations have proven effective in principle within controlled environments, their application to clinical practice has faced unmet requirements, such as the ability to perform reliably across a heterogeneous population, to work robustly in the presence of comorbidities, and to be invariant to scanner hardware and image quality. The lack of realistic confidence bounds and the inability to handle missing data have also reduced the application of most of these methods outside of academic studies. Mastering the complex challenges in the diagnostic process may help researchers discover novel biological constructs in multimodal data and improve stratification for clinical trials, paving the way for precision medicine. This review presents the state of the art of computerized brain MRI analysis for diagnostic purposes. We critically evaluate the current clinical usefulness of the methods and highlight challenges and future perspectives of the field.
Collapse
Affiliation(s)
- Saima Rathore
- Center for Biomedical Image Computing and Analytics, Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania 19104, USA
| | - Ahmed Abdulkadir
- Center for Biomedical Image Computing and Analytics, Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania 19104, USA
- University Hospital of of Old Age Psychiatry and Psychotherapy, University of Bern, 3008 Bern, Switzerland
| | - Christos Davatzikos
- Center for Biomedical Image Computing and Analytics, Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania 19104, USA
| |
Collapse
|
18
|
Abstract
Radiomics has been shown to have considerable potential and value in quantifying the tumor phenotype and predicting the treatment response. In most scenarios, the commercial and open-source software programs are available for quantitative analysis in medical images to streamline radiomics research. However, at this stage, most of these programs are local applications and require users to have experience in programming and software engineering, which clinicians usually do not have. Therefore, in this article, a web-based tool was proposed to flexibly support radiomics research workflow tasks. Radiomics in RayPlus requires zero installation, is easy to maintain, and accessible anywhere via any PC or MAC with an Internet connection. The system provides functions including multimodality image import and viewing, ROI definition, feature extraction, and data sharing. As a web application, it appears an effective way to multi-institution and multi-department collaborative radiomics research and moreover, its transparency, flexibility, and portability can greatly accelerate the pace of clinical data analysis.
Collapse
|
19
|
Naghavi-Behzad M, Bjerg Petersen C, Vogsen M, Braad PE, Grubbe Hildebrandt M, Gerke O. Prognostic Value of Dual-Time-Point 18F-Fluorodeoxyglucose PET/CT in Metastatic Breast Cancer: An Exploratory Study of Quantitative Measures. Diagnostics (Basel) 2020; 10:diagnostics10060398. [PMID: 32545312 PMCID: PMC7344801 DOI: 10.3390/diagnostics10060398] [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: 05/26/2020] [Revised: 06/06/2020] [Accepted: 06/08/2020] [Indexed: 11/28/2022] Open
Abstract
This study aimed to compare the prognostic value of quantitative measures of [18F]-fluorodeoxyglucose positron emission tomography with integrated computed tomography (FDG-PET/CT) for the response monitoring of patients with metastatic breast cancer (MBC). In this prospective study, 22 patients with biopsy-verified MBC diagnosed between 2011 and 2014 at Odense University Hospital (Denmark) were followed up until 2019. A dual-time-point FDG-PET/CT scan protocol (1 and 3 h) was applied at baseline, when MBC was diagnosed. Baseline characteristics and quantitative measures of maximum standardized uptake value (SUVmax), mean standardized uptake value (SUVmean), corrected SUVmean (cSUVmean), metabolic tumor volume (MTV), total lesion glycolysis (TLG), and corrected TLG (cTLG) were collected. Survival time was analyzed using the Kaplan–Meier method and was regressed on MTV, TLG, and cTLG while adjusting for clinicopathological characteristics. Among the 22 patients included (median age: 59.5 years), 21 patients (95%) died within the follow-up period. Median survival time was 29.13 months (95% Confidence interval: 20.4–40 months). Multivariable Cox proportional hazards regression analyses of survival time showed no influence from the SUVmean, cSUVmean, or SUVmax, while increased values of MTV, TLG, and cTLG were significantly associated with slightly higher risk, with hazard ratios ranging between 1.0003 and 1.004 (p = 0.007 to p = 0.026). Changes from 1 to 3 h were insignificant for all PET measures in the regression model. In conclusion, MTV and TLG are potential prognostic markers for overall survival in MBC patients.
Collapse
Affiliation(s)
- Mohammad Naghavi-Behzad
- Department of Clinical Research, University of Southern Denmark, 5000 Odense, Denmark; (C.B.P.); (M.V.); (M.G.H.); (O.G.)
- Department of Nuclear Medicine, Odense University Hospital, 5000 Odense, Denmark;
- Open Patient data Explorative Network (OPEN), Odense University Hospital, 5000 Odense, Denmark
- Correspondence: or ; Tel.: +45-91609622
| | - Charlotte Bjerg Petersen
- Department of Clinical Research, University of Southern Denmark, 5000 Odense, Denmark; (C.B.P.); (M.V.); (M.G.H.); (O.G.)
| | - Marianne Vogsen
- Department of Clinical Research, University of Southern Denmark, 5000 Odense, Denmark; (C.B.P.); (M.V.); (M.G.H.); (O.G.)
- Department of Nuclear Medicine, Odense University Hospital, 5000 Odense, Denmark;
- Open Patient data Explorative Network (OPEN), Odense University Hospital, 5000 Odense, Denmark
- Department of Oncology, Odense University Hospital, 5000 Odense, Denmark
| | - Poul-Erik Braad
- Department of Nuclear Medicine, Odense University Hospital, 5000 Odense, Denmark;
| | - Malene Grubbe Hildebrandt
- Department of Clinical Research, University of Southern Denmark, 5000 Odense, Denmark; (C.B.P.); (M.V.); (M.G.H.); (O.G.)
- Department of Nuclear Medicine, Odense University Hospital, 5000 Odense, Denmark;
- Open Patient data Explorative Network (OPEN), Odense University Hospital, 5000 Odense, Denmark
- Centre for Innovative Medical Technology, Odense University Hospital, 5000 Odense, Denmark
- Centre for Personalized Response Monitoring in Oncology, Odense University Hospital, 5000 Odense, Denmark
| | - Oke Gerke
- Department of Clinical Research, University of Southern Denmark, 5000 Odense, Denmark; (C.B.P.); (M.V.); (M.G.H.); (O.G.)
- Department of Nuclear Medicine, Odense University Hospital, 5000 Odense, Denmark;
| |
Collapse
|
20
|
Jones EF, Buatti JM, Shu HK, Wahl RL, Kurland BF, Linden HM, Mankoff DA, Rubin DL, Tata D, Nordstrom RJ, Hadjiyski L, Holdhoff M, Schwartz LH. Clinical Trial Design and Development Work Group Within the Quantitative Imaging Network. Tomography 2020; 6:60-64. [PMID: 32548281 PMCID: PMC7289239 DOI: 10.18383/j.tom.2019.00022] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022] Open
Abstract
The Clinical Trial Design and Development Working Group within the Quantitative Imaging Network focuses on providing support for the development, validation, and harmonization of quantitative imaging (QI) methods and tools for use in cancer clinical trials. In the past 10 years, the Group has been working in several areas to identify challenges and opportunities in clinical trials involving QI and radiation oncology. The Group has been working with Quantitative Imaging Network members and the Quantitative Imaging Biomarkers Alliance leadership to develop guidelines for standardizing the reporting of quantitative imaging. As a validation platform, the Group led a multireader study to test a semi-automated positron emission tomography quantification software. Clinical translation of QI tools cannot be possible without a continuing dialogue with clinical users. This article also highlights the outreach activities extended to cooperative groups and other organizations that promote the use of QI tools to support clinical decisions.
Collapse
Affiliation(s)
- Ella F. Jones
- School of Medicine, University of California San Francisco, San Francisco, CA
| | - John M. Buatti
- Carver College of Medicine, The University of Iowa, Iowa City, IA
| | - Hui-Kuo Shu
- Winship Cancer Institute, Emory University, Atlanta, GA
| | | | - Brenda F. Kurland
- Department of Biostatistics, University of Pittsburgh, Pittsburgh, PA
- School of Medicine, University of Washington, Seattle, WA
| | | | - David A. Mankoff
- Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
| | | | - Darrell Tata
- Cancer Imaging Program, National Cancer Institute, Bethesda, MD
| | | | | | - Matthias Holdhoff
- Sidney Kimmel Comprehensive Cancer Center, John Hopkins University, Baltimore, MD; and
| | - Lawrence H. Schwartz
- Irving Medical Center, Columbia University, New York Presbyterian Hospital, New York, NY
| |
Collapse
|
21
|
Bliesener Y, Acharya J, Nayak KS. Efficient DCE-MRI Parameter and Uncertainty Estimation Using a Neural Network. IEEE TRANSACTIONS ON MEDICAL IMAGING 2020; 39:1712-1723. [PMID: 31794389 PMCID: PMC8887912 DOI: 10.1109/tmi.2019.2953901] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
Quantitative DCE-MRI provides voxel-wise estimates of tracer-kinetic parameters that are valuable in the assessment of health and disease. These maps suffer from many known sources of variability. This variability is expensive to compute using current methods, and is typically not reported. Here, we demonstrate a novel approach for simultaneous estimation of tracer-kinetic parameters and their uncertainty due to intrinsic characteristics of the tracer-kinetic model, with very low computation time. We train and use a neural network to estimate the approximate joint posterior distribution of tracer-kinetic parameters. Uncertainties are estimated for each voxel and are specific to the patient, exam, and lesion. We demonstrate the methods' ability to produce accurate tracer-kinetic maps. We compare predicted parameter ranges with uncertainties introduced by noise and by differences in post-processing in a digital reference object. The predicted parameter ranges correlate well with tracer-kinetic parameter ranges observed across different noise realizations and regression algorithms. We also demonstrate the value of this approach to differentiate significant from insignificant changes in brain tumor pharmacokinetics over time. This is achieved by enforcing consistency in resolving model singularities in the applied tracer-kinetic model.
Collapse
|
22
|
Aryal MP, Lee C, Hawkins PG, Chapman C, Eisbruch A, Mierzwa M, Cao Y. Real-Time Quantitative Assessment of Accuracy and Precision of Blood Volume Derived from DCE-MRI in Individual Patients During a Clinical Trial. ACTA ACUST UNITED AC 2020; 5:61-67. [PMID: 30854443 PMCID: PMC6403042 DOI: 10.18383/j.tom.2018.00029] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
Abstract
Accuracy and precision of quantitative imaging (QI) metrics should be assessed in real time in each patient during a clinical trial to support QI-based decision-making. We developed a framework for real-time quantitative assessment of QI metrics and evaluated accuracy and precision of dynamic contrast-enhanced (DCE)-magnetic resonance imaging (MRI)–derived blood volume (BV) in a clinical trial for head and neck cancers. Patients underwent DCE-MRI before and after 2 weeks of radiation therapy (2wkRT). A mean as a reference value and a repeatability coefficient (RC) of BV values established from n patients in cerebellum volumes of interest (VOIs), which were normal and affected little by therapy, served as accuracy and precision measurements. The BV maps of a new patient were called accurate and precise if the values in cerebellum VOIs and the difference between the 2 scans agreed with the respective mean and RC with 95% confidence. The new data could be used to update reference values. Otherwise, the data were flagged for further evaluation before use in the trial. BV maps from 62 patients enrolled on the trial were evaluated. Mean BV values were 2.21 (±0.14) mL/100 g pre-RT and 2.22 (±0.17) mL/100 g at 2wkRT; relative RC was 15.9%. The BV maps from 3 patients were identified to be inaccurate and imprecise before use in the clinical trial. Our framework of real-time quantitative assessment of QI metrics during a clinical trial can be translated to different QI metrics and organ-sites for supporting QI-based decision-making that warrants success of a clinical trial.
Collapse
Affiliation(s)
| | | | | | | | | | | | - Yue Cao
- Departments of Radiation Oncology.,Radiology; and.,Biomedical Engineering, University of Michigan, Ann Arbor, MI
| |
Collapse
|
23
|
Bing MMD, Shaobo DMD, Ruiqing LMD, Na LP, Yaqiong LP, Lianzhong ZMD. The Roles of Ultrasound-Based Radiomics In Precision Diagnosis and Treatment of Different Cancers: A Literature Review. ADVANCED ULTRASOUND IN DIAGNOSIS AND THERAPY 2020. [DOI: 10.37015/audt.2020.200051] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/27/2023] Open
|
24
|
Bliesener Y, Lingala SG, Haldar JP, Nayak KS. Impact of (k,t) sampling on DCE MRI tracer kinetic parameter estimation in digital reference objects. Magn Reson Med 2019; 83:1625-1639. [PMID: 31605556 PMCID: PMC6982604 DOI: 10.1002/mrm.28024] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2019] [Revised: 09/06/2019] [Accepted: 09/09/2019] [Indexed: 12/12/2022]
Abstract
Purpose To evaluate the impact of (k,t) data sampling on the variance of tracer‐kinetic parameter (TK) estimation in high‐resolution whole‐brain dynamic contrast enhanced magnetic resonance imaging (DCE‐MRI) using digital reference objects. We study this in the context of TK model constraints, and in the absence of other constraints. Methods Three anatomically and physiologically realistic brain‐tumor digital reference objects were generated. Data sampling strategies included uniform and variable density; zone‐based, lattice, pseudo‐random, and pseudo‐radial; with 50‐time frames and 4‐fold to 25‐fold undersampling. In all cases, we assume a fully sampled first time frame, and prior knowledge of the arterial input function. TK parameters were estimated by indirect estimation (i.e., image‐time‐series reconstruction followed by model fitting), and direct estimation from the under‐sampled data. We evaluated methods based on the Cramér‐Rao bound and Monte‐Carlo simulations, over the range of signal‐to‐noise ratio (SNR) seen in clinical brain DCE‐MRI. Results Lattice‐based sampling provided the lowest SDs, followed by pseudo‐random, pseudo‐radial, and zone‐based. This ranking was consistent for the Patlak and extended Tofts model. Pseudo‐random sampling resulted in 19% higher averaged SD compared to lattice‐based sampling. Zone‐based sampling resulted in substantially higher SD at undersampling factors above 10. CRB analysis showed only a small difference between uniform and variable density for both lattice‐based and pseudo‐random sampling up to undersampling factors of 25. Conclusion Lattice sampling provided the lowest SDs, although the differences between sampling schemes were not substantial at low undersampling factors. The differences between lattice‐based and pseudo‐random sampling strategies with both uniform and variable density were within the range of error induced by other sources, at up to 25‐fold undersampling.
Collapse
Affiliation(s)
- Yannick Bliesener
- Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, California
| | - Sajan G Lingala
- Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, California
| | - Justin P Haldar
- Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, California
| | - Krishna S Nayak
- Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, California
| |
Collapse
|
25
|
Nie K, Al-Hallaq H, Li XA, Benedict SH, Sohn JW, Moran JM, Fan Y, Huang M, Knopp MV, Michalski JM, Monroe J, Obcemea C, Tsien CI, Solberg T, Wu J, Xia P, Xiao Y, El Naqa I. NCTN Assessment on Current Applications of Radiomics in Oncology. Int J Radiat Oncol Biol Phys 2019; 104:302-315. [PMID: 30711529 PMCID: PMC6499656 DOI: 10.1016/j.ijrobp.2019.01.087] [Citation(s) in RCA: 32] [Impact Index Per Article: 6.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2018] [Revised: 01/17/2019] [Accepted: 01/23/2019] [Indexed: 02/06/2023]
Abstract
Radiomics is a fast-growing research area based on converting standard-of-care imaging into quantitative minable data and building subsequent predictive models to personalize treatment. Radiomics has been proposed as a study objective in clinical trial concepts and a potential biomarker for stratifying patients across interventional treatment arms. In recognizing the growing importance of radiomics in oncology, a group of medical physicists and clinicians from NRG Oncology reviewed the current status of the field and identified critical issues, providing a general assessment and early recommendations for incorporation in oncology studies.
Collapse
Affiliation(s)
- Ke Nie
- Department of Radiation Oncology, Rutgers Cancer Institute of New Jersey, Rutgers-Robert Wood Johnson Medical School, New Brunswick, New Jersey.
| | - Hania Al-Hallaq
- Department of Radiation and Cellular Oncology, University of Chicago, Chicago, Illinois
| | - X Allen Li
- Department of Radiation Oncology, Medical College of Wisconsin, Milwaukee, Wisconsin
| | - Stanley H Benedict
- Department of Radiation Oncology, University of California-Davis, Sacramento, California
| | - Jason W Sohn
- Department of Radiation Oncology, Allegheny Health Network, Pittsburgh, Pennsylvania
| | - Jean M Moran
- Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan
| | - Yong Fan
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Mi Huang
- Department of Radiation Oncology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Michael V Knopp
- Division of Imaging Science, Department of Radiology, Ohio State University, Columbus, Ohio
| | - Jeff M Michalski
- Department of Radiation Oncology, Washington University School of Medicine in St. Louis, St. Louis, Missouri
| | - James Monroe
- Department of Radiation Oncology, St. Anthony's Cancer Center, St. Louis, Missouri
| | - Ceferino Obcemea
- Radiation Research Program, National Cancer Institute, Bethesda, Maryland
| | - Christina I Tsien
- Department of Radiation Oncology, Washington University School of Medicine in St. Louis, St. Louis, Missouri
| | - Timothy Solberg
- Department of Radiation Oncology, University of California-San Francisco, San Francisco, California
| | - Jackie Wu
- Department of Radiation Oncology, Duke University, Durham, North Carolina
| | - Ping Xia
- Department of Radiation Oncology, Cleveland Clinic, Cleveland, Ohio
| | - Ying Xiao
- Department of Radiation Oncology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Issam El Naqa
- Department of Radiation and Cellular Oncology, University of Chicago, Chicago, Illinois
| |
Collapse
|
26
|
Erdal BS, Prevedello LM, Qian S, Demirer M, Little K, Ryu J, O'Donnell T, White RD. Radiology and Enterprise Medical Imaging Extensions (REMIX). J Digit Imaging 2019; 31:91-106. [PMID: 28840365 PMCID: PMC5788816 DOI: 10.1007/s10278-017-0010-6] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022] Open
Abstract
Radiology and Enterprise Medical Imaging Extensions (REMIX) is a platform originally designed to both support the medical imaging-driven clinical and clinical research operational needs of Department of Radiology of The Ohio State University Wexner Medical Center. REMIX accommodates the storage and handling of “big imaging data,” as needed for large multi-disciplinary cancer-focused programs. The evolving REMIX platform contains an array of integrated tools/software packages for the following: (1) server and storage management; (2) image reconstruction; (3) digital pathology; (4) de-identification; (5) business intelligence; (6) texture analysis; and (7) artificial intelligence. These capabilities, along with documentation and guidance, explaining how to interact with a commercial system (e.g., PACS, EHR, commercial database) that currently exists in clinical environments, are to be made freely available.
Collapse
Affiliation(s)
- Barbaros S Erdal
- Radiology Department, The Ohio State University Wexner Medical Center, 395 W 12th Ave, Columbus, OH, 43210, USA.
| | - Luciano M Prevedello
- Radiology Department, The Ohio State University Wexner Medical Center, 395 W 12th Ave, Columbus, OH, 43210, USA
| | - Songyue Qian
- Radiology Department, The Ohio State University Wexner Medical Center, 395 W 12th Ave, Columbus, OH, 43210, USA
| | - Mutlu Demirer
- Radiology Department, The Ohio State University Wexner Medical Center, 395 W 12th Ave, Columbus, OH, 43210, USA
| | - Kevin Little
- Radiology Department, The Ohio State University Wexner Medical Center, 395 W 12th Ave, Columbus, OH, 43210, USA
| | - John Ryu
- Radiology Department, The Ohio State University Wexner Medical Center, 395 W 12th Ave, Columbus, OH, 43210, USA
| | - Thomas O'Donnell
- Siemens Medical Solutions USA, Inc, 40 Liberty Boulevard, Malvern, PA, 19355, USA
| | - Richard D White
- Radiology Department, The Ohio State University Wexner Medical Center, 395 W 12th Ave, Columbus, OH, 43210, USA
| |
Collapse
|
27
|
Kather JN, Krisam J, Charoentong P, Luedde T, Herpel E, Weis CA, Gaiser T, Marx A, Valous NA, Ferber D, Jansen L, Reyes-Aldasoro CC, Zörnig I, Jäger D, Brenner H, Chang-Claude J, Hoffmeister M, Halama N. Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study. PLoS Med 2019; 16:e1002730. [PMID: 30677016 PMCID: PMC6345440 DOI: 10.1371/journal.pmed.1002730] [Citation(s) in RCA: 394] [Impact Index Per Article: 78.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/23/2018] [Accepted: 12/17/2018] [Indexed: 11/19/2022] Open
Abstract
BACKGROUND For virtually every patient with colorectal cancer (CRC), hematoxylin-eosin (HE)-stained tissue slides are available. These images contain quantitative information, which is not routinely used to objectively extract prognostic biomarkers. In the present study, we investigated whether deep convolutional neural networks (CNNs) can extract prognosticators directly from these widely available images. METHODS AND FINDINGS We hand-delineated single-tissue regions in 86 CRC tissue slides, yielding more than 100,000 HE image patches, and used these to train a CNN by transfer learning, reaching a nine-class accuracy of >94% in an independent data set of 7,180 images from 25 CRC patients. With this tool, we performed automated tissue decomposition of representative multitissue HE images from 862 HE slides in 500 stage I-IV CRC patients in the The Cancer Genome Atlas (TCGA) cohort, a large international multicenter collection of CRC tissue. Based on the output neuron activations in the CNN, we calculated a "deep stroma score," which was an independent prognostic factor for overall survival (OS) in a multivariable Cox proportional hazard model (hazard ratio [HR] with 95% confidence interval [CI]: 1.99 [1.27-3.12], p = 0.0028), while in the same cohort, manual quantification of stromal areas and a gene expression signature of cancer-associated fibroblasts (CAFs) were only prognostic in specific tumor stages. We validated these findings in an independent cohort of 409 stage I-IV CRC patients from the "Darmkrebs: Chancen der Verhütung durch Screening" (DACHS) study who were recruited between 2003 and 2007 in multiple institutions in Germany. Again, the score was an independent prognostic factor for OS (HR 1.63 [1.14-2.33], p = 0.008), CRC-specific OS (HR 2.29 [1.5-3.48], p = 0.0004), and relapse-free survival (RFS; HR 1.92 [1.34-2.76], p = 0.0004). A prospective validation is required before this biomarker can be implemented in clinical workflows. CONCLUSIONS In our retrospective study, we show that a CNN can assess the human tumor microenvironment and predict prognosis directly from histopathological images.
Collapse
Affiliation(s)
- Jakob Nikolas Kather
- Department of Medical Oncology and Internal Medicine VI, National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany
- German Cancer Consortium (DKTK), Heidelberg, Germany
- Applied Tumor Immunity, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Division of Gastroenterology, Hepatology and Hepatobiliary Oncology, University Hospital RWTH Aachen, Aachen, Germany
| | - Johannes Krisam
- Institute of Medical Biometry and Informatics, University Hospital Heidelberg, Heidelberg, Germany
| | - Pornpimol Charoentong
- Department of Medical Oncology and Internal Medicine VI, National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany
- Applied Tumor Immunity, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Tom Luedde
- Division of Gastroenterology, Hepatology and Hepatobiliary Oncology, University Hospital RWTH Aachen, Aachen, Germany
| | - Esther Herpel
- Institute of Pathology, Heidelberg University, Heidelberg, Germany
- Tissue Bank of the National Center for Tumor Diseases (NCT), Heidelberg, Germany
| | - Cleo-Aron Weis
- Institute of Pathology, University Medical Center Mannheim, Mannheim, Germany
| | - Timo Gaiser
- Institute of Pathology, University Medical Center Mannheim, Mannheim, Germany
| | - Alexander Marx
- Institute of Pathology, University Medical Center Mannheim, Mannheim, Germany
| | - Nektarios A Valous
- Department of Medical Oncology and Internal Medicine VI, National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany
- Applied Tumor Immunity, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Dyke Ferber
- Department of Medical Oncology and Internal Medicine VI, National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany
- Applied Tumor Immunity, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Lina Jansen
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | | | - Inka Zörnig
- Department of Medical Oncology and Internal Medicine VI, National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany
- Applied Tumor Immunity, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Dirk Jäger
- Department of Medical Oncology and Internal Medicine VI, National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany
- German Cancer Consortium (DKTK), Heidelberg, Germany
- Applied Tumor Immunity, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Hermann Brenner
- German Cancer Consortium (DKTK), Heidelberg, Germany
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Division of Preventive Oncology, German Cancer Research Center (DKFZ) and National Center for Tumor Diseases (NCT), Heidelberg, Germany
| | - Jenny Chang-Claude
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Michael Hoffmeister
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Niels Halama
- Department of Medical Oncology and Internal Medicine VI, National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany
- German Cancer Consortium (DKTK), Heidelberg, Germany
- Applied Tumor Immunity, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Translational Immunotherapy, German Cancer Research Center (DKFZ), Heidelberg, Germany
| |
Collapse
|
28
|
Giganti F, Tang L, Baba H. Gastric cancer and imaging biomarkers: Part 1 - a critical review of DW-MRI and CE-MDCT findings. Eur Radiol 2018; 29:1743-1753. [PMID: 30280246 PMCID: PMC6420485 DOI: 10.1007/s00330-018-5732-4] [Citation(s) in RCA: 31] [Impact Index Per Article: 5.2] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2018] [Revised: 08/13/2018] [Accepted: 08/28/2018] [Indexed: 12/17/2022]
Abstract
Abstract The current standard of care for gastric cancer imaging includes heterogeneity in image acquisition techniques and qualitative image interpretation. In addition to qualitative assessment, several imaging techniques, including diffusion-weighted magnetic resonance imaging (DW-MRI), contrast-enhanced multidetector computed tomography (CE-MDCT), dynamic-contrast enhanced MRI and 18F-fluorodeoxyglucose positron emission tomography, can allow quantitative analysis. However, so far there is no consensus regarding the application of functional imaging in the management of gastric cancer. The aim of this article is to specifically review two promising biomarkers for gastric cancer with reasonable spatial resolution: the apparent diffusion coefficient (ADC) from DW-MRI and textural features from CE-MDCT. We searched MEDLINE/ PubMed for manuscripts published from inception to 6 February 2018. Initially, we searched for (gastric cancer OR gastric tumour) AND diffusion weighted magnetic resonance imaging. Then, we searched for (gastric cancer OR gastric tumour) AND texture analysis AND computed tomography. We collated the results from the studies related to this query. There is evidence that: (1) the ADC is a promising biomarker for the evaluation of the aggressiveness (T and N stage), treatment response and prognosis of gastric cancer; (2) textural features are related to the degree of differentiation, Lauren classification, treatment response and prognosis of gastric cancer. We conclude that these imaging biomarkers hold promise as effective additional tools in the diagnostic pathway of gastric cancer and may facilitate the multidisciplinary work between the radiologist and clinician, and across different institutions, to provide a greater biological understanding of gastric cancer. Key Points • Quantitative imaging is the extraction of quantifiable features from medical images for the assessment of normal or pathological conditions and represents a promising area for gastric cancer. • Quantitative analysis from CE-MDCT and DW-MRI allows the extrapolation of multiple imaging biomarkers. • ADC from DW-MRI and CE- MDCT-based texture features are non-invasive, quantitative imaging biomarkers that hold promise in the evaluation of the aggressiveness, treatment response and prognosis of gastric cancer.
Collapse
Affiliation(s)
- Francesco Giganti
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK. .,Division of Surgery and Interventional Science, Faculty of Medical Sciences, University College London, 3rd Floor, Charles Bell House, 43-45 Foley St, London, W1W 7TS, UK.
| | - Lei Tang
- Department of Radiology, Peking University Cancer Hospital, Beijing, China
| | - Hideo Baba
- Department of Gastroenterological Surgery, Graduate School of Medical Sciences, Kumamoto University, Kumamoto, Japan
| |
Collapse
|
29
|
Bane O, Hectors S, Wagner M, Arlinghaus LL, Aryal M, Cao Y, Chenevert T, Fennessy F, Huang W, Hylton N, Kalpathy-Cramer J, Keenan K, Malyarenko D, Mulkern R, Newitt D, Russek SE, Stupic KF, Tudorica A, Wilmes L, Yankeelov TE, Yen YF, Boss M, Taouli B. Accuracy, repeatability, and interplatform reproducibility of T 1 quantification methods used for DCE-MRI: Results from a multicenter phantom study. Magn Reson Med 2018; 79:2564-2575. [PMID: 28913930 PMCID: PMC5821553 DOI: 10.1002/mrm.26903] [Citation(s) in RCA: 60] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/21/2017] [Revised: 08/14/2017] [Accepted: 08/16/2017] [Indexed: 02/05/2023]
Abstract
PURPOSE To determine the in vitro accuracy, test-retest repeatability, and interplatform reproducibility of T1 quantification protocols used for dynamic contrast-enhanced MRI at 1.5 and 3 T. METHODS A T1 phantom with 14 samples was imaged at eight centers with a common inversion-recovery spin-echo (IR-SE) protocol and a variable flip angle (VFA) protocol using seven flip angles, as well as site-specific protocols (VFA with different flip angles, variable repetition time, proton density, and Look-Locker inversion recovery). Factors influencing the accuracy (deviation from reference NMR T1 measurements) and repeatability were assessed using general linear mixed models. Interplatform reproducibility was assessed using coefficients of variation. RESULTS For the common IR-SE protocol, accuracy (median error across platforms = 1.4-5.5%) was influenced predominantly by T1 sample (P < 10-6 ), whereas test-retest repeatability (median error = 0.2-8.3%) was influenced by the scanner (P < 10-6 ). For the common VFA protocol, accuracy (median error = 5.7-32.2%) was influenced by field strength (P = 0.006), whereas repeatability (median error = 0.7-25.8%) was influenced by the scanner (P < 0.0001). Interplatform reproducibility with the common VFA was lower at 3 T than 1.5 T (P = 0.004), and lower than that of the common IR-SE protocol (coefficient of variation 1.5T: VFA/IR-SE = 11.13%/8.21%, P = 0.028; 3 T: VFA/IR-SE = 22.87%/5.46%, P = 0.001). Among the site-specific protocols, Look-Locker inversion recovery and VFA (2-3 flip angles) protocols showed the best accuracy and repeatability (errors < 15%). CONCLUSIONS The VFA protocols with 2 to 3 flip angles optimized for different applications achieved acceptable balance of extensive spatial coverage, accuracy, and repeatability in T1 quantification (errors < 15%). Further optimization in terms of flip-angle choice for each tissue application, and the use of B1 correction, are needed to improve the robustness of VFA protocols for T1 mapping. Magn Reson Med 79:2564-2575, 2018. © 2017 International Society for Magnetic Resonance in Medicine.
Collapse
Affiliation(s)
- Octavia Bane
- Translational and Molecular Imaging Institute, Icahn School of Medicine at Mount Sinai,Radiology, Icahn School of Medicine at Mount Sinai
| | - Stefanie Hectors
- Translational and Molecular Imaging Institute, Icahn School of Medicine at Mount Sinai,Radiology, Icahn School of Medicine at Mount Sinai
| | - Mathilde Wagner
- Translational and Molecular Imaging Institute, Icahn School of Medicine at Mount Sinai,Radiology, Icahn School of Medicine at Mount Sinai
| | | | | | - Yue Cao
- Radiation Oncology, University of Michigan
| | | | | | - Wei Huang
- Advanced Imaging Research Center, Knight Cancer Institute, Oregon Health and Science University
| | - Nola Hylton
- Radiology, University of California San Francisco
| | | | | | | | | | - David Newitt
- Radiology, University of California San Francisco
| | | | | | | | - Lisa Wilmes
- Radiology, University of California San Francisco
| | | | - Yi-Fei Yen
- Radiology, Massachusetts General Hospital
| | | | - Bachir Taouli
- Translational and Molecular Imaging Institute, Icahn School of Medicine at Mount Sinai,Radiology, Icahn School of Medicine at Mount Sinai
| |
Collapse
|
30
|
Kaalep A, Sera T, Rijnsdorp S, Yaqub M, Talsma A, Lodge MA, Boellaard R. Feasibility of state of the art PET/CT systems performance harmonisation. Eur J Nucl Med Mol Imaging 2018; 45:1344-1361. [PMID: 29500480 PMCID: PMC5993859 DOI: 10.1007/s00259-018-3977-4] [Citation(s) in RCA: 89] [Impact Index Per Article: 14.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2017] [Accepted: 02/12/2018] [Indexed: 12/16/2022]
Abstract
PURPOSE The objective of this study was to explore the feasibility of harmonising performance for PET/CT systems equipped with time-of-flight (ToF) and resolution modelling/point spread function (PSF) technologies. A second aim was producing a working prototype of new harmonising criteria with higher contrast recoveries than current EARL standards using various SUV metrics. METHODS Four PET/CT systems with both ToF and PSF capabilities from three major vendors were used to acquire and reconstruct images of the NEMA NU2-2007 body phantom filled conforming EANM EARL guidelines. A total of 15 reconstruction parameter sets of varying pixel size, post filtering and reconstruction type, with three different acquisition durations were used to compare the quantitative performance of the systems. A target range for recovery curves was established such that it would accommodate the highest matching recoveries from all investigated systems. These updated criteria were validated on 18 additional scanners from 16 sites in order to demonstrate the scanners' ability to meet the new target range. RESULTS Each of the four systems was found to be capable of producing harmonising reconstructions with similar recovery curves. The five reconstruction parameter sets producing harmonising results significantly increased SUVmean (25%) and SUVmax (26%) contrast recoveries compared with current EARL specifications. Additional prospective validation performed on 18 scanners from 16 EARL accredited sites demonstrated the feasibility of updated harmonising specifications. SUVpeak was found to significantly reduce the variability in quantitative results while producing lower recoveries in smaller (≤17 mm diameter) sphere sizes. CONCLUSIONS Harmonising PET/CT systems with ToF and PSF technologies from different vendors was found to be feasible. The harmonisation of such systems would require an update to the current multicentre accreditation program EARL in order to accommodate higher recoveries. SUVpeak should be further investigated as a noise resistant alternative quantitative metric to SUVmax.
Collapse
Affiliation(s)
- Andres Kaalep
- Department of Medical Technology, North Estonia Medical Centre Foundation, J. Sutiste Str 19, 13419, Tallinn, Estonia.
| | - Terez Sera
- Department of Nuclear Medicine, University of Szeged, Szeged, Hungary
- On behalf of EANM Research Limited (EARL), Vienna, Austria
| | - Sjoerd Rijnsdorp
- Department of Medical Physics, Catharina Hospital, Eindhoven, The Netherlands
| | - Maqsood Yaqub
- Department of Radiology and Nuclear Medicine, VU University Medical Center, Amsterdam, The Netherlands
| | - Anne Talsma
- Department of Radiology, Martini Hospital, Groningen, Netherlands
| | - Martin A Lodge
- Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University, Baltimore, MD, 21287, USA
| | - Ronald Boellaard
- On behalf of EANM Research Limited (EARL), Vienna, Austria.
- Department of Radiology and Nuclear Medicine, VU University Medical Center, Amsterdam, The Netherlands.
- Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Centre Groningen, Hanzeplein 1, Groningen, the Netherlands.
| |
Collapse
|
31
|
Radiomic features analysis in computed tomography images of lung nodule classification. PLoS One 2018; 13:e0192002. [PMID: 29401463 PMCID: PMC5798832 DOI: 10.1371/journal.pone.0192002] [Citation(s) in RCA: 85] [Impact Index Per Article: 14.2] [Reference Citation Analysis] [Abstract] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2017] [Accepted: 01/14/2018] [Indexed: 02/08/2023] Open
Abstract
Purpose Radiomics, which extract large amount of quantification image features from diagnostic medical images had been widely used for prognostication, treatment response prediction and cancer detection. The treatment options for lung nodules depend on their diagnosis, benign or malignant. Conventionally, lung nodule diagnosis is based on invasive biopsy. Recently, radiomics features, a non-invasive method based on clinical images, have shown high potential in lesion classification, treatment outcome prediction. Methods Lung nodule classification using radiomics based on Computed Tomography (CT) image data was investigated and a 4-feature signature was introduced for lung nodule classification. Retrospectively, 72 patients with 75 pulmonary nodules were collected. Radiomics feature extraction was performed on non-enhanced CT images with contours which were delineated by an experienced radiation oncologist. Result Among the 750 image features in each case, 76 features were found to have significant differences between benign and malignant lesions. A radiomics signature was composed of the best 4 features which included Laws_LSL_min, Laws_SLL_energy, Laws_SSL_skewness and Laws_EEL_uniformity. The accuracy using the signature in benign or malignant classification was 84% with the sensitivity of 92.85% and the specificity of 72.73%. Conclusion The classification signature based on radiomics features demonstrated very good accuracy and high potential in clinical application.
Collapse
|
32
|
Salem A, Asselin MC, Reymen B, Jackson A, Lambin P, West CML, O'Connor JPB, Faivre-Finn C. Targeting Hypoxia to Improve Non-Small Cell Lung Cancer Outcome. J Natl Cancer Inst 2018; 110:4096546. [PMID: 28922791 DOI: 10.1093/jnci/djx160] [Citation(s) in RCA: 161] [Impact Index Per Article: 26.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2017] [Accepted: 07/03/2017] [Indexed: 12/18/2022] Open
Abstract
Oxygen deprivation (hypoxia) in non-small cell lung cancer (NSCLC) is an important factor in treatment resistance and poor survival. Hypoxia is an attractive therapeutic target, particularly in the context of radiotherapy, which is delivered to more than half of NSCLC patients. However, NSCLC hypoxia-targeted therapy trials have not yet translated into patient benefit. Recently, early termination of promising evofosfamide and tarloxotinib bromide studies due to futility highlighted the need for a paradigm shift in our approach to avoid disappointments in future trials. Radiotherapy dose painting strategies based on hypoxia imaging require careful refinement prior to clinical investigation. This review will summarize the role of hypoxia, highlight the potential of hypoxia as a therapeutic target, and outline past and ongoing hypoxia-targeted therapy trials in NSCLC. Evidence supporting radiotherapy dose painting based on hypoxia imaging will be critically appraised. Carefully selected hypoxia biomarkers suitable for integration within future NSCLC hypoxia-targeted therapy trials will be examined. Research gaps will be identified to guide future investigation. Although this review will focus on NSCLC hypoxia, more general discussions (eg, obstacles of hypoxia biomarker research and developing a framework for future hypoxia trials) are applicable to other tumor sites.
Collapse
Affiliation(s)
- Ahmed Salem
- Division of Cancer Sciences and Division of Informatics, Imaging and Data Sciences, University of Manchester, Manchester, UK; Department of Radiation Oncology (MAASTRO Lab), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, the Netherlands
| | - Marie-Claude Asselin
- Division of Cancer Sciences and Division of Informatics, Imaging and Data Sciences, University of Manchester, Manchester, UK; Department of Radiation Oncology (MAASTRO Lab), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, the Netherlands
| | - Bart Reymen
- Division of Cancer Sciences and Division of Informatics, Imaging and Data Sciences, University of Manchester, Manchester, UK; Department of Radiation Oncology (MAASTRO Lab), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, the Netherlands
| | - Alan Jackson
- Division of Cancer Sciences and Division of Informatics, Imaging and Data Sciences, University of Manchester, Manchester, UK; Department of Radiation Oncology (MAASTRO Lab), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, the Netherlands
| | - Philippe Lambin
- Division of Cancer Sciences and Division of Informatics, Imaging and Data Sciences, University of Manchester, Manchester, UK; Department of Radiation Oncology (MAASTRO Lab), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, the Netherlands
| | - Catharine M L West
- Division of Cancer Sciences and Division of Informatics, Imaging and Data Sciences, University of Manchester, Manchester, UK; Department of Radiation Oncology (MAASTRO Lab), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, the Netherlands
| | - James P B O'Connor
- Division of Cancer Sciences and Division of Informatics, Imaging and Data Sciences, University of Manchester, Manchester, UK; Department of Radiation Oncology (MAASTRO Lab), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, the Netherlands
| | - Corinne Faivre-Finn
- Division of Cancer Sciences and Division of Informatics, Imaging and Data Sciences, University of Manchester, Manchester, UK; Department of Radiation Oncology (MAASTRO Lab), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, the Netherlands
| |
Collapse
|
33
|
Nordstrom RJ. Special Section Guest Editorial: Quantitative Imaging and the Pioneering Efforts of Laurence P. Clarke. J Med Imaging (Bellingham) 2017; 5:011001. [PMID: 28924577 DOI: 10.1117/1.jmi.5.1.011001] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/12/2023] Open
Abstract
This guest editorial introduces the Special Section honoring Dr. Laurence P. Clarke.
Collapse
Affiliation(s)
- Robert J Nordstrom
- National Cancer Institute, Chief, Image Guided Interventions, Cancer Imaging Program, Division of Cancer Treatment and Diagnosis
| |
Collapse
|
34
|
Managers of Molecular Imaging Laboratories (MOMIL) Interest Group. Mol Imaging Biol 2017; 19:332-335. [PMID: 28299547 DOI: 10.1007/s11307-017-1075-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Abstract
The Managers of Molecular Imaging Laboratories (MOMIL) interest group in the World Molecular Imaging Society provides a forum for exchanging information between researchers who manage molecular imaging laboratories and institutional core facilities. This information exchange includes operational procedures for acquiring and analyzing imaging results, including considerations for quality assurance and quality control, and animal handling and care for imaging studies. MOMIL also exchanges administrative policies, interactions with collaborators and clients, and industry relations. In addition to this comprehensive review of MOMIL, more information is available at http://www.wmis.org /.
Collapse
|
35
|
Malyarenko DI, Wilmes LJ, Arlinghaus LR, Jacobs MA, Huang W, Helmer KG, Taouli B, Yankeelov TE, Newitt D, Chenevert TL. QIN DAWG Validation of Gradient Nonlinearity Bias Correction Workflow for Quantitative Diffusion-Weighted Imaging in Multicenter Trials. ACTA ACUST UNITED AC 2016; 2:396-405. [PMID: 28105469 PMCID: PMC5241082 DOI: 10.18383/j.tom.2016.00214] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022]
Abstract
Previous research has shown that system-dependent gradient nonlinearity (GNL) introduces a significant spatial bias (nonuniformity) in apparent diffusion coefficient (ADC) maps. Here, the feasibility of centralized retrospective system-specific correction of GNL bias for quantitative diffusion-weighted imaging (DWI) in multisite clinical trials is demonstrated across diverse scanners independent of the scanned object. Using corrector maps generated from system characterization by ice-water phantom measurement completed in the previous project phase, GNL bias correction was performed for test ADC measurements from an independent DWI phantom (room temperature agar) at two offset locations in the bore. The precomputed three-dimensional GNL correctors were retrospectively applied to test DWI scans by the central analysis site. The correction was blinded to reference DWI of the agar phantom at magnet isocenter where the GNL bias is negligible. The performance was evaluated from changes in ADC region of interest histogram statistics before and after correction with respect to the unbiased reference ADC values provided by sites. Both absolute error and nonuniformity of the ADC map induced by GNL (median, 12%; range, -35% to +10%) were substantially reduced by correction (7-fold in median and 3-fold in range). The residual ADC nonuniformity errors were attributed to measurement noise and other non-GNL sources. Correction of systematic GNL bias resulted in a 2-fold decrease in technical variability across scanners (down to site temperature range). The described validation of GNL bias correction marks progress toward implementation of this technology in multicenter trials that utilize quantitative DWI.
Collapse
Affiliation(s)
| | - Lisa J Wilmes
- Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, California
| | - Lori R Arlinghaus
- Vanderbilt University (VU) Institute of Imaging Science, VU Medical Center, Nashville, Tennessee
| | - Michael A Jacobs
- Russel H. Morgan Department of Radiology and Radiological Science, John Hopkins University School of Medicine, Baltimore, Maryland
| | - Wei Huang
- Advanced Imaging Research Center, Oregon Health and Science University, Portland, Oregon
| | - Karl G Helmer
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts
| | - Bachir Taouli
- Translational and Molecular Imaging Institute, Icahn School of Medicine at Mt Sinai, New York, New York
| | - Thomas E Yankeelov
- Department of Biomedical Engineering, University of Texas at Austin, Austin, Texas
| | - David Newitt
- Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, California
| | | |
Collapse
|
36
|
Abramson RG, Arlinghaus LR, Dula AN, Quarles CC, Stokes AM, Weis JA, Whisenant JG, Chekmenev EY, Zhukov I, Williams JM, Yankeelov TE. MR Imaging Biomarkers in Oncology Clinical Trials. Magn Reson Imaging Clin N Am 2016; 24:11-29. [PMID: 26613873 DOI: 10.1016/j.mric.2015.08.002] [Citation(s) in RCA: 28] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
The authors discuss eight areas of quantitative MR imaging that are currently used (RECIST, DCE-MR imaging, DSC-MR imaging, diffusion MR imaging) in clinical trials or emerging (CEST, elastography, hyperpolarized MR imaging, multiparameter MR imaging) as promising techniques in diagnosing cancer and assessing or predicting response of cancer to therapy. Illustrative applications of the techniques in the clinical setting are summarized before describing the current limitations of the methods.
Collapse
Affiliation(s)
- Richard G Abramson
- Department of Radiology and Radiological Sciences, Institute of Imaging Science, Vanderbilt University, VUIIS 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA
| | - Lori R Arlinghaus
- Department of Radiology and Radiological Sciences, Vanderbilt University, 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA
| | - Adrienne N Dula
- Department of Radiology and Radiological Sciences, Institute of Imaging Science, Vanderbilt University, VUIIS 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA
| | - C Chad Quarles
- Department of Radiology and Radiological Sciences, Institute of Imaging Science, Vanderbilt University, VUIIS 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA; Department of Biomedical Engineering, Institute of Imaging Science, Vanderbilt University, VUIIS 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA; Department of Cancer Biology, Institute of Imaging Science, Vanderbilt University, 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA
| | - Ashley M Stokes
- Department of Radiology and Radiological Sciences, Institute of Imaging Science, Vanderbilt University, VUIIS 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA
| | - Jared A Weis
- Department of Biomedical Engineering, Vanderbilt University, VUIIS 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA
| | - Jennifer G Whisenant
- Department of Radiology and Radiological Sciences, Institute of Imaging Science, Vanderbilt University, VUIIS 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA
| | - Eduard Y Chekmenev
- Department of Radiology and Radiological Sciences, Institute of Imaging Science, Vanderbilt University, VUIIS 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA; Department of Biomedical Engineering, Institute of Imaging Science, Vanderbilt University, VUIIS 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA; Department of Biochemistry, Institute of Imaging Science, Vanderbilt University, 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA
| | - Igor Zhukov
- National Research Nuclear University MEPhI, Kashirskoye highway, 31, Moscow 115409, Russia
| | - Jason M Williams
- Department of Radiology and Radiological Sciences, Institute of Imaging Science, Vanderbilt University, 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA
| | - Thomas E Yankeelov
- Department of Radiology and Radiological Sciences, Institute of Imaging Science, Vanderbilt University, VUIIS 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA; Department of Biomedical Engineering, Institute of Imaging Science, Vanderbilt University, VUIIS 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA; Department of Cancer Biology, Institute of Imaging Science, Vanderbilt University, 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA; Department of Physics, Institute of Imaging Science, Vanderbilt University, VUIIS 1161 21st Avenue South, AA 1105 MCN, Nashville, TN 37232-2310, USA.
| |
Collapse
|
37
|
Post AR, Pai AK, Willard R, May BJ, West AC, Agravat S, Granite SJ, Winslow RL, Stephens DS. Metadata-driven Clinical Data Loading into i2b2 for Clinical and Translational Science Institutes. AMIA JOINT SUMMITS ON TRANSLATIONAL SCIENCE PROCEEDINGS. AMIA JOINT SUMMITS ON TRANSLATIONAL SCIENCE 2016; 2016:184-93. [PMID: 27570667 PMCID: PMC5001768] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 11/04/2022]
Abstract
Clinical and Translational Science Award (CTSA) recipients have a need to create research data marts from their clinical data warehouses, through research data networks and the use of i2b2 and SHRINE technologies. These data marts may have different data requirements and representations, thus necessitating separate extract, transform and load (ETL) processes for populating each mart. Maintaining duplicative procedural logic for each ETL process is onerous. We have created an entirely metadata-driven ETL process that can be customized for different data marts through separate configurations, each stored in an extension of i2b2 's ontology database schema. We extended our previously reported and open source Eureka! Clinical Analytics software with this capability. The same software has created i2b2 data marts for several projects, the largest being the nascent Accrual for Clinical Trials (ACT) network, for which it has loaded over 147 million facts about 1.2 million patients.
Collapse
Affiliation(s)
- Andrew R. Post
- Atlanta Clinical and Translational Science Institute, Emory University, Atlanta, GA
| | - Akshatha K. Pai
- Atlanta Clinical and Translational Science Institute, Emory University, Atlanta, GA
| | - Richard Willard
- Atlanta Clinical and Translational Science Institute, Emory University, Atlanta, GA
| | - Bradley J. May
- Atlanta Clinical and Translational Science Institute, Emory University, Atlanta, GA
| | - Andrew C. West
- Atlanta Clinical and Translational Science Institute, Emory University, Atlanta, GA
| | - Sanjay Agravat
- Atlanta Clinical and Translational Science Institute, Emory University, Atlanta, GA
| | - Stephen J. Granite
- Institute for Computational Medicine, Johns Hopkins University, Baltimore, MD
| | - Raimond L. Winslow
- Institute for Computational Medicine, Johns Hopkins University, Baltimore, MD
| | - David S. Stephens
- Atlanta Clinical and Translational Science Institute, Emory University, Atlanta, GA
| |
Collapse
|
38
|
Abstract
Radiomics is an emerging field in quantitative imaging that uses advanced imaging features to objectively and quantitatively describe tumour phenotypes. Radiomic features have recently drawn considerable interest due to its potential predictive power for treatment outcomes and cancer genetics, which may have important applications in personalized medicine. In this technical review, we describe applications and challenges of the radiomic field. We will review radiomic application areas and technical issues, as well as proper practices for the designs of radiomic studies.
Collapse
Affiliation(s)
- Stephen S F Yip
- Department of Radiation Oncology, Brigham and Women's Hospital, Dana-Farber Cancer Institute and Harvard Medical School, Boston, MA, USA
| | | |
Collapse
|
39
|
Peerlings J, Troost EGC, Nelemans PJ, Cobben DCP, de Boer JCJ, Hoffmann AL, Beets-Tan RGH. The Diagnostic Value of MR Imaging in Determining the Lymph Node Status of Patients with Non-Small Cell Lung Cancer: A Meta-Analysis. Radiology 2016; 281:86-98. [PMID: 27110732 DOI: 10.1148/radiol.2016151631] [Citation(s) in RCA: 31] [Impact Index Per Article: 3.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/25/2022]
Abstract
Purpose To summarize existing evidence of thoracic magnetic resonance (MR) imaging in determining the nodal status of non-small cell lung cancer (NSCLC) with the aim of elucidating its diagnostic value on a per-patient basis (eg, in treatment decision making) and a per-node basis (eg, in target volume delineation for radiation therapy), with results of cytologic and/or histologic examination as the reference standard. Materials and Methods A systematic literature search for original diagnostic studies was performed in PubMed, Web of Science, Embase, and MEDLINE. The methodologic quality of each study was evaluated by using the Quality Assessment of Diagnostic Accuracy Studies 2, or QUADAS-2, tool. Hierarchic summary receiver operating characteristic curves were generated to estimate the diagnostic performance of MR imaging. Subgroup analyses, expressed as relative diagnostic odds ratios (DORs) (rDORs), were performed to evaluate whether publication year, methodologic quality, and/or method of evaluation (qualitative [ie, lesion size and/or morphology] vs quantitative [eg, apparent diffusion coefficients in diffusion-weighted images]) affected diagnostic performance. Results Twelve of 2551 initially identified studies were included in this meta-analysis (1122 patients; 4302 lymph nodes). On a per-patient basis, the pooled estimates of MR imaging for sensitivity, specificity, and DOR were 0.87 (95% confidence interval [CI]: 0.78, 0.92), 0.88 (95% CI: 0.77, 0.94), and 48.1 (95% CI: 23.4, 98.9), respectively. On a per-node basis, the respective measures were 0.88 (95% CI: 0.78, 0.94), 0.95 (95% CI: 0.87, 0.98), and 129.5 (95% CI: 49.3, 340.0). Subgroup analyses suggested greater diagnostic performance of quantitative evaluation on both a per-patient and per-node basis (rDOR = 2.76 [95% CI: 0.83, 9.10], P = .09 and rDOR = 7.25 [95% CI: 1.75, 30.09], P = .01, respectively). Conclusion This meta-analysis demonstrated high diagnostic performance of MR imaging in staging hilar and mediastinal lymph nodes in NSCLC on both a per-patient and per-node basis. (©) RSNA, 2016 Online supplemental material is available for this article.
Collapse
Affiliation(s)
- Jurgen Peerlings
- From the Department of Radiation Oncology (MAASTRO Clinic), GROW School for Oncology and Developmental Biology (J.P., E.G.C.T., A.L.H.), Department of Radiology (J.P., R.G.H.B.), and Department of Epidemiology (P.J.N.), Maastricht University Medical Centre, Dr. Tanslaan 12, 6229 ET Maastricht, the Netherlands; Department of Radiation Oncology, University Medical Centre, Utrecht, the Netherlands (D.C.P.C., J.C.J.d.B.); and Department of Radiation Oncology, Dr Bernard Verbeeten Institute, Tilburg, the Netherlands (D.C.P.C.)
| | - Esther G C Troost
- From the Department of Radiation Oncology (MAASTRO Clinic), GROW School for Oncology and Developmental Biology (J.P., E.G.C.T., A.L.H.), Department of Radiology (J.P., R.G.H.B.), and Department of Epidemiology (P.J.N.), Maastricht University Medical Centre, Dr. Tanslaan 12, 6229 ET Maastricht, the Netherlands; Department of Radiation Oncology, University Medical Centre, Utrecht, the Netherlands (D.C.P.C., J.C.J.d.B.); and Department of Radiation Oncology, Dr Bernard Verbeeten Institute, Tilburg, the Netherlands (D.C.P.C.)
| | - Patricia J Nelemans
- From the Department of Radiation Oncology (MAASTRO Clinic), GROW School for Oncology and Developmental Biology (J.P., E.G.C.T., A.L.H.), Department of Radiology (J.P., R.G.H.B.), and Department of Epidemiology (P.J.N.), Maastricht University Medical Centre, Dr. Tanslaan 12, 6229 ET Maastricht, the Netherlands; Department of Radiation Oncology, University Medical Centre, Utrecht, the Netherlands (D.C.P.C., J.C.J.d.B.); and Department of Radiation Oncology, Dr Bernard Verbeeten Institute, Tilburg, the Netherlands (D.C.P.C.)
| | - David C P Cobben
- From the Department of Radiation Oncology (MAASTRO Clinic), GROW School for Oncology and Developmental Biology (J.P., E.G.C.T., A.L.H.), Department of Radiology (J.P., R.G.H.B.), and Department of Epidemiology (P.J.N.), Maastricht University Medical Centre, Dr. Tanslaan 12, 6229 ET Maastricht, the Netherlands; Department of Radiation Oncology, University Medical Centre, Utrecht, the Netherlands (D.C.P.C., J.C.J.d.B.); and Department of Radiation Oncology, Dr Bernard Verbeeten Institute, Tilburg, the Netherlands (D.C.P.C.)
| | - Johannes C J de Boer
- From the Department of Radiation Oncology (MAASTRO Clinic), GROW School for Oncology and Developmental Biology (J.P., E.G.C.T., A.L.H.), Department of Radiology (J.P., R.G.H.B.), and Department of Epidemiology (P.J.N.), Maastricht University Medical Centre, Dr. Tanslaan 12, 6229 ET Maastricht, the Netherlands; Department of Radiation Oncology, University Medical Centre, Utrecht, the Netherlands (D.C.P.C., J.C.J.d.B.); and Department of Radiation Oncology, Dr Bernard Verbeeten Institute, Tilburg, the Netherlands (D.C.P.C.)
| | - Aswin L Hoffmann
- From the Department of Radiation Oncology (MAASTRO Clinic), GROW School for Oncology and Developmental Biology (J.P., E.G.C.T., A.L.H.), Department of Radiology (J.P., R.G.H.B.), and Department of Epidemiology (P.J.N.), Maastricht University Medical Centre, Dr. Tanslaan 12, 6229 ET Maastricht, the Netherlands; Department of Radiation Oncology, University Medical Centre, Utrecht, the Netherlands (D.C.P.C., J.C.J.d.B.); and Department of Radiation Oncology, Dr Bernard Verbeeten Institute, Tilburg, the Netherlands (D.C.P.C.)
| | - Regina G H Beets-Tan
- From the Department of Radiation Oncology (MAASTRO Clinic), GROW School for Oncology and Developmental Biology (J.P., E.G.C.T., A.L.H.), Department of Radiology (J.P., R.G.H.B.), and Department of Epidemiology (P.J.N.), Maastricht University Medical Centre, Dr. Tanslaan 12, 6229 ET Maastricht, the Netherlands; Department of Radiation Oncology, University Medical Centre, Utrecht, the Netherlands (D.C.P.C., J.C.J.d.B.); and Department of Radiation Oncology, Dr Bernard Verbeeten Institute, Tilburg, the Netherlands (D.C.P.C.)
| |
Collapse
|
40
|
Marinelli B, Espinet-Col C, Ulaner GA, McArthur HL, Gonen M, Jochelson M, Weber WA. Prognostic value of FDG PET/CT-based metabolic tumor volumes in metastatic triple negative breast cancer patients. AMERICAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING 2016; 6:120-127. [PMID: 27186439 PMCID: PMC4858608] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Subscribe] [Scholar Register] [Received: 12/21/2015] [Accepted: 03/08/2016] [Indexed: 06/05/2023]
Abstract
FDG PET/CT-based measures of tumor burden show promise to predict survival in patients with metastatic breast cancer, but the patient populations studied so far are heterogeneous. The reports may have been confounded by the markedly different prognosis of the various subtypes of breast cancer. The purpose of this study is to evaluate the correlation between tumor burden on FDG PET/CT and overall survival (OS) in patients within a defined population: metastatic triple negative breast cancer (MTNBC). FDG PET/CT scans of 47 consecutive MTNBC patients (54±12 years-old) with no other known malignancies were analyzed. A total 393 lesions were identified, and maximum standardized uptake value (SUVmax), mean SUV, metabolic tumor volume (MTV), total lesion number (TLN) and total lesion glycolysis (TLG), were measured and correlated with patient survival by Mantel-Cox tests and Cox regression analysis. At a median follow-up time of 12.4 months, 41 patients died with a median OS of 12.1 months. Patients with MTV less than 51.5 ml lived nearly three times longer (22 vs 7.1 months) than those with a higher MTV (χ(2)=21.3, P<0.0001). In a multivariate Cox regression analysis only TLN and MTV were significantly correlated with survival. Those with an MTV burden in the 75(th) percentile versus the 25(th) percentile had a hazard ratio of 6.94 (p=0.001). In patients with MTNBC, MTV appears to be a strong prognostic factor. If validated in prospective studies, MTV may be a valuable tool for risk stratification of MTNBC patients in clinical trials and to guide patient management.
Collapse
Affiliation(s)
- Brett Marinelli
- Molecular Imaging and Therapy Service, Department of Radiology, Memorial Sloan Kettering Cancer Center1275 York Avenue, NY 10065, New York
- Icahn School of Medicine at Mount SinaiOne Gustave Place, NY 10029, New York
| | - Carina Espinet-Col
- Molecular Imaging and Therapy Service, Department of Radiology, Memorial Sloan Kettering Cancer Center1275 York Avenue, NY 10065, New York
| | - Gary A Ulaner
- Molecular Imaging and Therapy Service, Department of Radiology, Memorial Sloan Kettering Cancer Center1275 York Avenue, NY 10065, New York
- Weill Cornell Medical College1300 York Ave, NY 10065, New York
| | - Heather L McArthur
- Breast Medicine Service, Department of Medicine, Memorial Sloan Kettering Cancer Center300 East 66 Street, NY 10065, New York
| | - Mithat Gonen
- Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center1275 York Avenue, NY 10065, New York
| | - Maxine Jochelson
- Molecular Imaging and Therapy Service, Department of Radiology, Memorial Sloan Kettering Cancer Center1275 York Avenue, NY 10065, New York
- Breast Imaging Service, Department of Radiology, Memorial Sloan Kettering Cancer Center300 East 66 Street, NY 10065, New York
| | - Wolfgang A Weber
- Molecular Imaging and Therapy Service, Department of Radiology, Memorial Sloan Kettering Cancer Center1275 York Avenue, NY 10065, New York
| |
Collapse
|
41
|
Bosca RJ, Jackson EF. Creating an anthropomorphic digital MR phantom—an extensible tool for comparing and evaluating quantitative imaging algorithms. Phys Med Biol 2016; 61:974-82. [DOI: 10.1088/0031-9155/61/2/974] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
|
42
|
Malyarenko DI, Pang Y, Senegas J, Ivancevic MK, Ross BD, Chenevert TL. Correction of Gradient Nonlinearity Bias in Quantitative Diffusion Parameters of Renal Tissue with Intra Voxel Incoherent Motion. ACTA ACUST UNITED AC 2015; 1:145-151. [PMID: 26811845 PMCID: PMC4724207 DOI: 10.18383/j.tom.2015.00160] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/16/2022]
Abstract
Spatially nonuniform diffusion weighting bias as a result of gradient nonlinearity (GNL) causes substantial errors in apparent diffusion coefficient (ADC) maps for anatomical regions imaged distant from the magnet isocenter. Our previously described approach effectively removed spatial ADC bias from 3 orthogonal diffusion-weighted imaging (DWI) measurements for monoexponential media of arbitrary anisotropy. This work evaluates correction feasibility and performance for quantitative diffusion parameters of the 2-component intravoxel incoherent motion (IVIM) model for well-perfused and nearly isotropic renal tissue. Sagittal kidney DWI scans of a volunteer were performed on a clinical 3T magnetic resonance imaging scanner near isocenter and offset superiorly. Spatially nonuniform diffusion weighting caused by GNL resulted both in shifting and broadening of perfusion-suppressed ADC histograms for off-center DWI relative to unbiased measurements close to the isocenter. Direction-average diffusion weighting bias correctors were computed based on the known gradient design provided by the vendor. The computed bias maps were empirically confirmed by coronal DWI measurements for an isotropic gel-flood phantom. Both phantom and renal tissue ADC bias for off-center measurements was effectively removed by applying precomputed 3D correction maps. Comparable ADC accuracy was achieved for corrections of both b maps and DWI intensities in the presence of IVIM perfusion. No significant bias impact was observed for the IVIM perfusion fraction.
Collapse
Affiliation(s)
| | - Yuxi Pang
- Department of Radiology, University of Michigan, Ann Arbor, MI
| | | | | | - Brian D Ross
- Department of Radiology, University of Michigan, Ann Arbor, MI
| | | |
Collapse
|
43
|
Shuhendler AJ, Ye D, Brewer KD, Bazalova-Carter M, Lee KH, Kempen P, Dane Wittrup K, Graves EE, Rutt B, Rao J. Molecular Magnetic Resonance Imaging of Tumor Response to Therapy. Sci Rep 2015; 5:14759. [PMID: 26440059 PMCID: PMC4594000 DOI: 10.1038/srep14759] [Citation(s) in RCA: 40] [Impact Index Per Article: 4.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2015] [Accepted: 09/02/2015] [Indexed: 11/09/2022] Open
Abstract
Personalized cancer medicine requires measurement of therapeutic efficacy as early as possible, which is optimally achieved by three-dimensional imaging given the heterogeneity of cancer. Magnetic resonance imaging (MRI) can obtain images of both anatomy and cellular responses, if acquired with a molecular imaging contrast agent. The poor sensitivity of MRI has limited the development of activatable molecular MR contrast agents. To overcome this limitation of molecular MRI, a novel implementation of our caspase-3-sensitive nanoaggregation MRI (C-SNAM) contrast agent is reported. C-SNAM is triggered to self-assemble into nanoparticles in apoptotic tumor cells, and effectively amplifies molecular level changes through nanoaggregation, enhancing tissue retention and spin-lattice relaxivity. At one-tenth the current clinical dose of contrast agent, and following a single imaging session, C-SNAM MRI accurately measured the response of tumors to either metronomic chemotherapy or radiation therapy, where the degree of signal enhancement is prognostic of long-term therapeutic efficacy. Importantly, C-SNAM is inert to immune activation, permitting radiation therapy monitoring.
Collapse
Affiliation(s)
- Adam J Shuhendler
- Molecular Imaging Program at Stanford, Stanford, California 94305, USA.,Departments of Radiology, Stanford, California 94305, USA
| | - Deju Ye
- Molecular Imaging Program at Stanford, Stanford, California 94305, USA.,Departments of Radiology, Stanford, California 94305, USA
| | - Kimberly D Brewer
- Molecular Imaging Program at Stanford, Stanford, California 94305, USA.,Departments of Radiology, Stanford, California 94305, USA
| | - Magdalena Bazalova-Carter
- Molecular Imaging Program at Stanford, Stanford, California 94305, USA.,Radiation Oncology, Stanford, California 94305, USA
| | - Kyung-Hyun Lee
- Molecular Imaging Program at Stanford, Stanford, California 94305, USA.,Departments of Radiology, Stanford, California 94305, USA
| | - Paul Kempen
- Materials Science and Engineering, Stanford University, Stanford, California 94305, USA
| | - K Dane Wittrup
- Department of Chemical Engineering, Department of Biological Engineering, and Koch Institute for Integrative Cancer Research, Massachusetts Institute of Technology, Cambridge, Massachusetts, 02139, USA
| | - Edward E Graves
- Molecular Imaging Program at Stanford, Stanford, California 94305, USA.,Radiation Oncology, Stanford, California 94305, USA
| | - Brian Rutt
- Molecular Imaging Program at Stanford, Stanford, California 94305, USA.,Departments of Radiology, Stanford, California 94305, USA
| | - Jianghong Rao
- Molecular Imaging Program at Stanford, Stanford, California 94305, USA.,Departments of Radiology, Stanford, California 94305, USA
| |
Collapse
|
44
|
Guo W, Li H, Zhu Y, Lan L, Yang S, Drukker K, Morris E, Burnside E, Whitman G, Giger ML, Ji Y. Prediction of clinical phenotypes in invasive breast carcinomas from the integration of radiomics and genomics data. J Med Imaging (Bellingham) 2015; 2:041007. [PMID: 26835491 DOI: 10.1117/1.jmi.2.4.041007] [Citation(s) in RCA: 110] [Impact Index Per Article: 12.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2015] [Accepted: 07/22/2015] [Indexed: 11/14/2022] Open
Abstract
Genomic and radiomic imaging profiles of invasive breast carcinomas from The Cancer Genome Atlas and The Cancer Imaging Archive were integrated and a comprehensive analysis was conducted to predict clinical outcomes using the radiogenomic features. Variable selection via LASSO and logistic regression were used to select the most-predictive radiogenomic features for the clinical phenotypes, including pathological stage, lymph node metastasis, and status of estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2). Cross-validation with receiver operating characteristic (ROC) analysis was performed and the area under the ROC curve (AUC) was employed as the prediction metric. Higher AUCs were obtained in the prediction of pathological stage, ER, and PR status than for lymph node metastasis and HER2 status. Overall, the prediction performances by genomics alone, radiomics alone, and combined radiogenomics features showed statistically significant correlations with clinical outcomes; however, improvement on the prediction performance by combining genomics and radiomics data was not found to be statistically significant, most likely due to the small sample size of 91 cancer cases with 38 radiomic features and 144 genomic features.
Collapse
Affiliation(s)
- Wentian Guo
- University of Chicago, Department of Public Health Sciences, 5841 South Maryland Avenue MC2000, Chicago, Illinois 60637, United States; Fudan University, School of Public Health, 130 Dongan Road, Shanghai 200032, China
| | - Hui Li
- University of Chicago , Department of Radiology, 5841 South Maryland Avenue, Chicago, Illinois 60637, United States
| | - Yitan Zhu
- NorthShore University Health System , Program of Computational Genomics & Medicine, 1001 University Place, Evanston, Illinois 60201, United States
| | - Li Lan
- University of Chicago , Department of Radiology, 5841 South Maryland Avenue, Chicago, Illinois 60637, United States
| | - Shengjie Yang
- NorthShore University Health System , Program of Computational Genomics & Medicine, 1001 University Place, Evanston, Illinois 60201, United States
| | - Karen Drukker
- University of Chicago , Department of Radiology, 5841 South Maryland Avenue, Chicago, Illinois 60637, United States
| | - Elizabeth Morris
- Memorial Sloan Kettering Cancer Center , Department of Radiology, 1275 York Avenue, New York, New York 10065, United States
| | - Elizabeth Burnside
- University of Wisconsin , School of Medicine and Public Health, Department of Radiology, E3/366 Clinical Science Center, 600 Highland Avenue, Madison, Wisconsin 53792-3252, United States
| | - Gary Whitman
- MD Anderson , 1515 Holcombe Boulevard, Houston, Texas 77030, United States
| | - Maryellen L Giger
- University of Chicago , Department of Radiology, 5841 South Maryland Avenue, Chicago, Illinois 60637, United States
| | - Yuan Ji
- University of Chicago, Department of Public Health Sciences, 5841 South Maryland Avenue MC2000, Chicago, Illinois 60637, United States; NorthShore University Health System, Program of Computational Genomics & Medicine, 1001 University Place, Evanston, Illinois 60201, United States
| | -
- https://wiki.cancerimagingarchive.net/display/Public/TCGA+Breast+Phenotype+Research+Group
| |
Collapse
|
45
|
Leijenaar RTH, Carvalho S, Hoebers FJP, Aerts HJWL, van Elmpt WJC, Huang SH, Chan B, Waldron JN, O'sullivan B, Lambin P. External validation of a prognostic CT-based radiomic signature in oropharyngeal squamous cell carcinoma. Acta Oncol 2015; 54:1423-9. [PMID: 26264429 DOI: 10.3109/0284186x.2015.1061214] [Citation(s) in RCA: 166] [Impact Index Per Article: 18.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/05/2023]
Abstract
BACKGROUND Oropharyngeal squamous cell carcinoma (OPSCC) is one of the fastest growing disease sites of head and neck cancers. A recently described radiomic signature, based exclusively on pre-treatment computed tomography (CT) imaging of the primary tumor volume, was found to be prognostic in independent cohorts of lung and head and neck cancer patients treated in the Netherlands. Here, we further validate this signature in a large and independent North American cohort of OPSCC patients, also considering CT artifacts. METHODS A total of 542 OPSCC patients were included for which we determined the prognostic index (PI) of the radiomic signature. We tested the signature model fit in a Cox regression and assessed model discrimination with Harrell's c-index. Kaplan-Meier survival curves between high and low signature predictions were compared with a log-rank test. Validation was performed in the complete cohort (PMH1) and in the subset of patients without (PMH2) and with (PMH3) visible CT artifacts within the delineated tumor region. RESULTS We identified 267 (49%) patients without and 275 (51%) with visible CT artifacts. The calibration slope (β) on the PI in a Cox proportional hazards model was 1.27 (H0: β = 1, p = 0.152) in the PMH1 (n = 542), 0.855 (H0: β = 1, p = 0.524) in the PMH2 (n = 267) and 1.99 (H0: β = 1, p = 0.002) in the PMH3 (n = 275) cohort. Harrell's c-index was 0.628 (p = 2.72e-9), 0.634 (p = 2.7e-6) and 0.647 (p = 5.35e-6) for the PMH1, PMH2 and PMH3 cohort, respectively. Kaplan-Meier survival curves were significantly different (p < 0.05) between high and low radiomic signature model predictions for all cohorts. CONCLUSION Overall, the signature validated well using all CT images as-is, demonstrating a good model fit and preservation of discrimination. Even though CT artifacts were shown to be of influence, the signature had significant prognostic power regardless if patients with CT artifacts were included.
Collapse
Affiliation(s)
- Ralph T H Leijenaar
- a Department of Radiation Oncology (MAASTRO) , GROW-School for Oncology and Developmental Biology, Maastricht University Medical Centre (MUMC+) , Maastricht , The Netherlands
| | - Sara Carvalho
- a Department of Radiation Oncology (MAASTRO) , GROW-School for Oncology and Developmental Biology, Maastricht University Medical Centre (MUMC+) , Maastricht , The Netherlands
| | - Frank J P Hoebers
- a Department of Radiation Oncology (MAASTRO) , GROW-School for Oncology and Developmental Biology, Maastricht University Medical Centre (MUMC+) , Maastricht , The Netherlands
| | - Hugo J W L Aerts
- a Department of Radiation Oncology (MAASTRO) , GROW-School for Oncology and Developmental Biology, Maastricht University Medical Centre (MUMC+) , Maastricht , The Netherlands
- b Departments of Radiation Oncology and Radiology , Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School , Boston , MA , USA
| | - Wouter J C van Elmpt
- a Department of Radiation Oncology (MAASTRO) , GROW-School for Oncology and Developmental Biology, Maastricht University Medical Centre (MUMC+) , Maastricht , The Netherlands
| | - Shao Hui Huang
- c Department of Radiation Oncology , Princess Margaret Cancer Center, University of Toronto , Toronto, Ontario , Canada
| | - Biu Chan
- c Department of Radiation Oncology , Princess Margaret Cancer Center, University of Toronto , Toronto, Ontario , Canada
| | - John N Waldron
- c Department of Radiation Oncology , Princess Margaret Cancer Center, University of Toronto , Toronto, Ontario , Canada
| | - Brian O'sullivan
- c Department of Radiation Oncology , Princess Margaret Cancer Center, University of Toronto , Toronto, Ontario , Canada
| | - Philippe Lambin
- a Department of Radiation Oncology (MAASTRO) , GROW-School for Oncology and Developmental Biology, Maastricht University Medical Centre (MUMC+) , Maastricht , The Netherlands
| |
Collapse
|
46
|
Do 18F-FDG PET/CT parameters in oropharyngeal and oral cavity squamous cell carcinomas indicate HPV status? Clin Nucl Med 2015; 40:e196-200. [PMID: 25608156 DOI: 10.1097/rlu.0000000000000691] [Citation(s) in RCA: 27] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/20/2023]
Abstract
OBJECTIVE The aim of this study was to explore the relationship of PET/CT parameters with human papillomavirus (HPV) status of oropharyngeal (OP) and oral cavity (OC) squamous cell carcinomas (SCCs). PATIENTS AND METHODS We retrospectively reviewed 39 patients with OC and OP-SCC who underwent staging 18F-FDG PET/CT. PET/CT parameters were measured for the primary tumor and the hottest involved node, including SUV max, SUV mean, SUV peak, metabolic tumor volume, total lesion glycolysis, standardized added metabolic activity (SAM), and normalized SAM. Patient characteristics were compared between HPV positive (HPV+) and negative (HPV-) groups. Receiver operating characteristic analysis was used to dichotomize PET/CT parameters into high and low. Logistic regression models predicting HPV status were fit for each PET/CT parameter. RESULTS The HPV+ group was composed of 18 patients all with OP-SCC; the HPV- group consisted of 21 patients, 4 OP cancer patients and 17 OC cancer patients. The HPV+ group had a higher proportion of N2 stage (94% vs 43%; P < 0.001). Nodal PET/CT parameters were higher in the HPV+ group (P < 0.01); this difference was not present for the primary lesion. After adjusting for sex and age, the association of higher nodal SUV max (odds ratio [OR], 9.67), SUV mean (OR, 10.48), SUV peak (OR 9.67), metabolic tumor volume (OR, 14.52), total lesion glycolysis (OR, 11.84), and SAM, normalized SAM (OR, 16.21) with HPV+ status remained statistically significant (P < 0.05). CONCLUSIONS Nodal PET/CT parameters predict HPV status. High nodal FDG uptake should raise suspicion for positive HPV status in the evaluation of the primary lesion.
Collapse
|
47
|
Häggström I, Schmidtlein CR, Karlsson M, Larsson A. Compartment modeling of dynamic brain PET--the impact of scatter corrections on parameter errors. Med Phys 2015; 41:111907. [PMID: 25370640 DOI: 10.1118/1.4897610] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
Abstract
PURPOSE The aim of this study was to investigate the effect of scatter and its correction on kinetic parameters in dynamic brain positron emission tomography (PET) tumor imaging. The 2-tissue compartment model was used, and two different reconstruction methods and two scatter correction (SC) schemes were investigated. METHODS The gate Monte Carlo (MC) software was used to perform 2 × 15 full PET scan simulations of a voxelized head phantom with inserted tumor regions. The two sets of kinetic parameters of all tissues were chosen to represent the 2-tissue compartment model for the tracer 3'-deoxy-3'-((18)F)fluorothymidine (FLT), and were denoted FLT1 and FLT2. PET data were reconstructed with both 3D filtered back-projection with reprojection (3DRP) and 3D ordered-subset expectation maximization (OSEM). Images including true coincidences with attenuation correction (AC) and true+scattered coincidences with AC and with and without one of two applied SC schemes were reconstructed. Kinetic parameters were estimated by weighted nonlinear least squares fitting of image derived time-activity curves. Calculated parameters were compared to the true input to the MC simulations. RESULTS The relative parameter biases for scatter-eliminated data were 15%, 16%, 4%, 30%, 9%, and 7% (FLT1) and 13%, 6%, 1%, 46%, 12%, and 8% (FLT2) for K1, k2, k3, k4, Va, and Ki, respectively. As expected, SC was essential for most parameters since omitting it increased biases by 10 percentage points on average. SC was not found necessary for the estimation of Ki and k3, however. There was no significant difference in parameter biases between the two investigated SC schemes or from parameter biases from scatter-eliminated PET data. Furthermore, neither 3DRP nor OSEM yielded the smallest parameter biases consistently although there was a slight favor for 3DRP which produced less biased k3 and Ki estimates while OSEM resulted in a less biased Va. The uncertainty in OSEM parameters was about 26% (FLT1) and 12% (FLT2) larger than for 3DRP although identical postfilters were applied. CONCLUSIONS SC was important for good parameter estimations. Both investigated SC schemes performed equally well on average and properly corrected for the scattered radiation, without introducing further bias. Furthermore, 3DRP was slightly favorable over OSEM in terms of kinetic parameter biases and SDs.
Collapse
Affiliation(s)
- Ida Häggström
- Department of Radiation Sciences, Umeå University, Umeå 90187, Sweden
| | - C Ross Schmidtlein
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York 10065
| | - Mikael Karlsson
- Department of Radiation Sciences, Umeå University, Umeå 90187, Sweden
| | - Anne Larsson
- Department of Radiation Sciences, Umeå University, Umeå 90187, Sweden
| |
Collapse
|
48
|
Parmar C, Leijenaar RTH, Grossmann P, Rios Velazquez E, Bussink J, Rietveld D, Rietbergen MM, Haibe-Kains B, Lambin P, Aerts HJWL. Radiomic feature clusters and prognostic signatures specific for Lung and Head & Neck cancer. Sci Rep 2015; 5:11044. [PMID: 26251068 PMCID: PMC4937496 DOI: 10.1038/srep11044] [Citation(s) in RCA: 314] [Impact Index Per Article: 34.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2015] [Accepted: 05/14/2015] [Indexed: 12/13/2022] Open
Abstract
Radiomics provides a comprehensive quantification of tumor phenotypes by extracting and mining large number of quantitative image features. To reduce the redundancy and compare the prognostic characteristics of radiomic features across cancer types, we investigated cancer-specific radiomic feature clusters in four independent Lung and Head & Neck (H∓N) cancer cohorts (in total 878 patients). Radiomic features were extracted from the pre-treatment computed tomography (CT) images. Consensus clustering resulted in eleven and thirteen stable radiomic feature clusters for Lung and H & N cancer, respectively. These clusters were validated in independent external validation cohorts using rand statistic (Lung RS = 0.92, p < 0.001, H & N RS = 0.92, p < 0.001). Our analysis indicated both common as well as cancer-specific clustering and clinical associations of radiomic features. Strongest associations with clinical parameters: Prognosis Lung CI = 0.60 ± 0.01, Prognosis H & N CI = 0.68 ± 0.01; Lung histology AUC = 0.56 ± 0.03, Lung stage AUC = 0.61 ± 0.01, H & N HPV AUC = 0.58 ± 0.03, H & N stage AUC = 0.77 ± 0.02. Full utilization of these cancer-specific characteristics of image features may further improve radiomic biomarkers, providing a non-invasive way of quantifying and monitoring tumor phenotypic characteristics in clinical practice.
Collapse
Affiliation(s)
- Chintan Parmar
- 1] Departments of Radiation Oncology [2] Radiation Oncology (MAASTRO), Research Institute GROW, Maastricht University, Maastricht, the Netherlands [3] Machine Intelligence Unit, Indian Statistical Institute, Kolkata, India
| | - Ralph T H Leijenaar
- Radiation Oncology (MAASTRO), Research Institute GROW, Maastricht University, Maastricht, the Netherlands
| | - Patrick Grossmann
- 1] Departments of Radiation Oncology [2] Department of Biostatistics &Computational Biology, Dana-Farber Cancer Institute, Boston, MA, USA
| | | | - Johan Bussink
- Department of Radiation Oncology, Radboud University Medical Center, Nijmegen, the Netherlands
| | - Derek Rietveld
- Department of Radiation Oncology, VU University Medical Center, Amsterdam, The Netherlands
| | - Michelle M Rietbergen
- Department of Otolaryngology/Head and Neck Surgery, VU University Medical Center, Amsterdam, The Netherlands
| | - Benjamin Haibe-Kains
- 1] Ontario Cancer Institute, Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada [2] Medical Biophysics Department, University of Toronto, Toronto, Ontario, Canada
| | - Philippe Lambin
- Radiation Oncology (MAASTRO), Research Institute GROW, Maastricht University, Maastricht, the Netherlands
| | - Hugo J W L Aerts
- 1] Departments of Radiation Oncology [2] Radiology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA [3] Department of Biostatistics &Computational Biology, Dana-Farber Cancer Institute, Boston, MA, USA
| |
Collapse
|
49
|
Mitra S, Uma Shankar B. Medical image analysis for cancer management in natural computing framework. Inf Sci (N Y) 2015. [DOI: 10.1016/j.ins.2015.02.015] [Citation(s) in RCA: 46] [Impact Index Per Article: 5.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
50
|
Malyarenko DI, Newitt D, J Wilmes L, Tudorica A, Helmer KG, Arlinghaus LR, Jacobs MA, Jajamovich G, Taouli B, Yankeelov TE, Huang W, Chenevert TL. Demonstration of nonlinearity bias in the measurement of the apparent diffusion coefficient in multicenter trials. Magn Reson Med 2015; 75:1312-23. [PMID: 25940607 DOI: 10.1002/mrm.25754] [Citation(s) in RCA: 61] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/25/2015] [Revised: 03/31/2015] [Accepted: 04/08/2015] [Indexed: 12/13/2022]
Abstract
PURPOSE Characterize system-specific bias across common magnetic resonance imaging (MRI) platforms for quantitative diffusion measurements in multicenter trials. METHODS Diffusion weighted imaging (DWI) was performed on an ice-water phantom along the superior-inferior (SI) and right-left (RL) orientations spanning ± 150 mm. The same scanning protocol was implemented on 14 MRI systems at seven imaging centers. The bias was estimated as a deviation of measured from known apparent diffusion coefficient (ADC) along individual DWI directions. The relative contributions of gradient nonlinearity, shim errors, imaging gradients, and eddy currents were assessed independently. The observed bias errors were compared with numerical models. RESULTS The measured systematic ADC errors scaled quadratically with offset from isocenter, and ranged between -55% (SI) and 25% (RL). Nonlinearity bias was dependent on system design and diffusion gradient direction. Consistent with numerical models, minor ADC errors (± 5%) due to shim, imaging and eddy currents were mitigated by double echo DWI and image coregistration of individual gradient directions. CONCLUSION The analysis confirms gradient nonlinearity as a major source of spatial DW bias and variability in off-center ADC measurements across MRI platforms, with minor contributions from shim, imaging gradients and eddy currents. The developed protocol enables empiric description of systematic bias in multicenter quantitative DWI studies.
Collapse
Affiliation(s)
| | - David Newitt
- Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, California, USA
| | - Lisa J Wilmes
- Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, California, USA
| | - Alina Tudorica
- Diagnostic Radiology, Oregon Health and Science University, Portland, Oregon, USA
| | - Karl G Helmer
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts, USA
| | - Lori R Arlinghaus
- Institute of Imaging Science, Vanderbilt University, Nashville, Tennessee, USA
| | - Michael A Jacobs
- John Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - Guido Jajamovich
- Translational and Molecular Imaging Institute Icahn School of Medicine at Mount Sinai, New York, USA
| | - Bachir Taouli
- Translational and Molecular Imaging Institute Icahn School of Medicine at Mount Sinai, New York, USA
| | - Thomas E Yankeelov
- Institute of Imaging Science, Vanderbilt University, Nashville, Tennessee, USA.,Departments of Radiology, Physics and Cancer Biology, Vanderbilt University, Nashville, Tennessee, USA
| | - Wei Huang
- Advanced Imaging Research Center, Oregon Health and Science University, Portland, Oregon, USA
| | | |
Collapse
|