1
|
Wang G, Guo Q, Shi D, Zhai H, Luo W, Zhang H, Ren Z, Yan G, Ren K. Clinical Breast MRI-based Radiomics for Distinguishing Benign and Malignant Lesions: An Analysis of Sequences and Enhanced Phases. J Magn Reson Imaging 2024; 60:1178-1189. [PMID: 38006286 DOI: 10.1002/jmri.29150] [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: 09/25/2023] [Revised: 11/07/2023] [Accepted: 11/09/2023] [Indexed: 11/27/2023] Open
Abstract
BACKGROUND Previous studies have used different imaging sequences and different enhanced phases for breast lesion calsification in radiomics. The optimal sequence and contrast enhanced phase is unclear. PURPOSE To identify the optimal magnetic resonance imaging (MRI) radiomics model for lesion clarification, and to simulate its incremental value for multiparametric MRI (mpMRI)-guided biopsy. STUDY TYPE Retrospective. POPULATION 329 female patients (138 malignant, 191 benign), divided into a training set (first site, n = 192) and an independent test set (second site, n = 137). FIELD STRENGTH/SEQUENCE 3.0-T, fast spoiled gradient-echo and fast spin-echo T1-weighted imaging (T1WI), fast spin-echo T2-weighted imaging (T2WI), echo-planar diffusion-weighted imaging (DWI), and fast spoiled gradient-echo contrast-enhanced MRI (CE-MRI). ASSESSMENT Two breast radiologists with 3 and 10 years' experience developed radiomics model on CE-MRI, CE-MRI + DWI, CE-MRI + DWI + T2WI, CE-MRI + DWI + T2WI + T1WI at each individual phase (P) and for multiple combinations of phases. The optimal radiomics model (Rad-score) was identified as having the highest area under the receiver operating characteristic curve (AUC) in the test set. Specificity was compared between a traditional mpMRI model and an integrated model (mpMRI + Rad-score) at sensitivity >98%. STATISTICAL TESTS Wilcoxon paired-samples signed rank test, Delong test, McNemar test. Significance level was 0.05 and Bonferroni method was used for multiple comparisons (P = 0.007, 0.05/7). RESULTS For radiomics models, CE-MRI/P3 + DWI + T2WI achieved the highest performance in the test set (AUC = 0.888, 95% confidence interval: 0.833-0.944). The integrated model had significantly higher specificity (55.3%) than the mpMRI model (31.6%) in the test set with a sensitivity of 98.4%. DATA CONCLUSION The CE-MRI/P3 + DWI + T2WI model is the optimized choice for breast lesion classification in radiomics, and has potential to reduce benign biopsies (100%-specificity) from 68.4% to 44.7% while retaining sensitivity >98%. LEVEL OF EVIDENCE 3 TECHNICAL EFFICACY: Stage 2.
Collapse
Affiliation(s)
- Guangsong Wang
- Department of Radiology, Xiang'an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Qiu Guo
- Department of Radiology, Xiang'an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Dafa Shi
- Department of Radiology, Xiang'an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Huige Zhai
- Department of Radiology, The Second Affiliated Hospital of Xiamen Medical College, Xiamen, Fujian, China
| | - Wenbin Luo
- Department of Radiology, The Second Affiliated Hospital of Xiamen Medical College, Xiamen, Fujian, China
| | - Haoran Zhang
- Department of Radiology, Xiang'an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Zhendong Ren
- Department of Radiology, Xiang'an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Gen Yan
- Department of Radiology, The Second Affiliated Hospital of Xiamen Medical College, Xiamen, Fujian, China
| | - Ke Ren
- Department of Radiology, Xiang'an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
- Xiamen Key Laboratory of Endocrine-Related Cancer Precision Medicine, Xiang'an Hospital of Xiamen university, Xiamen, Fujian, China
| |
Collapse
|
2
|
Zhao J, Zhang Q, Liu M, Zhao X. MRI-based radiomics approach for the prediction of recurrence-free survival in triple-negative breast cancer after breast-conserving surgery or mastectomy. Medicine (Baltimore) 2023; 102:e35646. [PMID: 37861556 PMCID: PMC10589522 DOI: 10.1097/md.0000000000035646] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/23/2023] [Accepted: 09/22/2023] [Indexed: 10/21/2023] Open
Abstract
To explore the value of a radiomics signature and develop a nomogram combined with a radiomics signature and clinical factors for predicting recurrence-free survival in triple-negative breast cancer patients. We enrolled 151 patients from the cancer imaging archive who underwent preoperative contrast-enhanced magnetic resonance imaging. They were assigned to training, validation and external validation cohorts. Image features with coefficients not equal to zero in the 10-fold cross-validation were selected to generate a radiomics signature. Based on the optimal cutoff value of the radiomics signature determined by maximally selected log-rank statistics, patients were stratified into high- and low-risk groups in the training and validation cohorts. Kaplan-Meier survival analysis was performed for both groups. Kaplan-Meier survival distributions in these groups were compared using log-rank tests. Univariate and multivariate Cox regression analyses were used to construct clinical and combined models. Concordance index was used to assess the predictive performance of the 3 models. Calibration of the combined model was assessed using calibration curves. Four image features were selected to generate the radiomics signature. The Kaplan-Meier survival distributions of patients in the 2 groups were significantly different in the training (P < .001) and validation cohorts (P = .001). The C-indices of the radiomics model, clinical model, and combined model in the training and validation cohorts were 0.772, 0.700, 0.878, and 0.744, 0.574, 0.777, respectively. The C-indices of the radiomics model, clinical model, and combined model in the external validation cohort were 0.778, 0.733, 0.822, respectively. The calibration curves of the combined model showed good calibration. The radiomics signature can predict recurrence-free survival of patients with triple-negative breast cancer and improve the predictive performance of the clinical model.
Collapse
Affiliation(s)
- Jingwei Zhao
- Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Qi Zhang
- Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Muqing Liu
- Department of Radiology, Chaoyang Central Hospital, Chaoyang, China
| | - Xinming Zhao
- Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| |
Collapse
|
3
|
Kushol R, Parnianpour P, Wilman AH, Kalra S, Yang YH. Effects of MRI scanner manufacturers in classification tasks with deep learning models. Sci Rep 2023; 13:16791. [PMID: 37798392 PMCID: PMC10556074 DOI: 10.1038/s41598-023-43715-5] [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: 11/15/2022] [Accepted: 09/27/2023] [Indexed: 10/07/2023] Open
Abstract
Deep learning has become a leading subset of machine learning and has been successfully employed in diverse areas, ranging from natural language processing to medical image analysis. In medical imaging, researchers have progressively turned towards multi-center neuroimaging studies to address complex questions in neuroscience, leveraging larger sample sizes and aiming to enhance the accuracy of deep learning models. However, variations in image pixel/voxel characteristics can arise between centers due to factors including differences in magnetic resonance imaging scanners. Such variations create challenges, particularly inconsistent performance in machine learning-based approaches, often referred to as domain shift, where the trained models fail to achieve satisfactory or improved results when confronted with dissimilar test data. This study analyzes the performance of multiple disease classification tasks using multi-center MRI data obtained from three widely used scanner manufacturers (GE, Philips, and Siemens) across several deep learning-based networks. Furthermore, we investigate the efficacy of mitigating scanner vendor effects using ComBat-based harmonization techniques when applied to multi-center datasets of 3D structural MR images. Our experimental results reveal a substantial decline in classification performance when models trained on one type of scanner manufacturer are tested with data from different manufacturers. Moreover, despite applying ComBat-based harmonization, the harmonized images do not demonstrate any noticeable performance enhancement for disease classification tasks.
Collapse
Affiliation(s)
- Rafsanjany Kushol
- Department of Computing Science, University of Alberta, Edmonton, Canada.
| | - Pedram Parnianpour
- Neuroscience and Mental Health Institute, University of Alberta, Edmonton, Canada
| | - Alan H Wilman
- Departments of Radiology and Diagnostic Imaging and Biomedical Engineering, University of Alberta, Edmonton, Canada
| | - Sanjay Kalra
- Department of Computing Science, University of Alberta, Edmonton, Canada
- Neuroscience and Mental Health Institute, University of Alberta, Edmonton, Canada
- Division of Neurology, Department of Medicine, University of Alberta, Edmonton, Canada
| | - Yee-Hong Yang
- Department of Computing Science, University of Alberta, Edmonton, Canada
| |
Collapse
|
4
|
Adusumilli P, Ravikumar N, Hall G, Swift S, Orsi N, Scarsbrook A. Radiomics in the evaluation of ovarian masses - a systematic review. Insights Imaging 2023; 14:165. [PMID: 37782375 PMCID: PMC10545652 DOI: 10.1186/s13244-023-01500-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2023] [Accepted: 08/12/2023] [Indexed: 10/03/2023] Open
Abstract
OBJECTIVES The study aim was to conduct a systematic review of the literature reporting the application of radiomics to imaging techniques in patients with ovarian lesions. METHODS MEDLINE/PubMed, Web of Science, Scopus, EMBASE, Ovid and ClinicalTrials.gov were searched for relevant articles. Using PRISMA criteria, data were extracted from short-listed studies. Validity and bias were assessed independently by 2 researchers in consensus using the Quality in Prognosis Studies (QUIPS) tool. Radiomic Quality Score (RQS) was utilised to assess radiomic methodology. RESULTS After duplicate removal, 63 articles were identified, of which 33 were eligible. Fifteen assessed lesion classifications, 10 treatment outcomes, 5 outcome predictions, 2 metastatic disease predictions and 1 classification/outcome prediction. The sample size ranged from 28 to 501 patients. Twelve studies investigated CT, 11 MRI, 4 ultrasound and 1 FDG PET-CT. Twenty-three studies (70%) incorporated 3D segmentation. Various modelling methods were used, most commonly LASSO (least absolute shrinkage and selection operator) (10/33). Five studies (15%) compared radiomic models to radiologist interpretation, all demonstrating superior performance. Only 6 studies (18%) included external validation. Five studies (15%) had a low overall risk of bias, 9 (27%) moderate, and 19 (58%) high risk of bias. The highest RQS achieved was 61.1%, and the lowest was - 16.7%. CONCLUSION Radiomics has the potential as a clinical diagnostic tool in patients with ovarian masses and may allow better lesion stratification, guiding more personalised patient care in the future. Standardisation of the feature extraction methodology, larger and more diverse patient cohorts and real-world evaluation is required before clinical translation. CLINICAL RELEVANCE STATEMENT Radiomics shows promising results in improving lesion stratification, treatment selection and outcome prediction. Modelling with larger cohorts and real-world evaluation is required before clinical translation. KEY POINTS • Radiomics is emerging as a tool for enhancing clinical decisions in patients with ovarian masses. • Radiomics shows promising results in improving lesion stratification, treatment selection and outcome prediction. • Modelling with larger cohorts and real-world evaluation is required before clinical translation.
Collapse
Affiliation(s)
- Pratik Adusumilli
- Department of Radiology, Leeds Teaching Hospitals NHS Trust, Leeds, UK.
- Leeds Institute of Medical Research, University of Leeds, Leeds, UK.
- West Yorkshire Radiology Academy, Level B Clarendon Wing, Leeds General Infirmary, Great George Street, Leeds, LS1 3EX, UK.
| | - Nishant Ravikumar
- Centre for Computational Imaging and Simulation Technologies in Biomedicine, University of Leeds, Leeds, UK
| | - Geoff Hall
- Department of Medical Oncology, Leeds Teaching Hospitals NHS Trust, Leeds, UK
- Leeds Institute for Data Analytics, University of Leeds, Leeds, UK
| | - Sarah Swift
- Department of Radiology, Leeds Teaching Hospitals NHS Trust, Leeds, UK
| | - Nicolas Orsi
- Leeds Institute of Medical Research, University of Leeds, Leeds, UK
| | - Andrew Scarsbrook
- Department of Radiology, Leeds Teaching Hospitals NHS Trust, Leeds, UK
- Leeds Institute of Medical Research, University of Leeds, Leeds, UK
| |
Collapse
|
5
|
Jiang M, Li CL, Luo XM, Chuan ZR, Chen RX, Jin CY. An MRI-based Radiomics Approach to Improve Breast Cancer Histological Grading. Acad Radiol 2023; 30:1794-1804. [PMID: 36609032 DOI: 10.1016/j.acra.2022.12.014] [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: 10/13/2022] [Revised: 12/06/2022] [Accepted: 12/06/2022] [Indexed: 01/06/2023]
Abstract
RATIONALE AND OBJECTIVES Nottingham histological grade (NHG) 2 breast cancer has an intermediate risk of recurrence, which is not informative for therapeutic decision-making. We sought to develop and independently validate an MRI-based radiomics signature (Rad-Grade) to improve prognostic re-stratification of NHG 2 tumors. MATERIALS AND METHODS Nine hundred-eight subjects with invasive breast cancer and preoperative MRI scans were retrospectively obtained. The NHG 1 and 3 tumors were randomly split into training and independent test cohort, with the NHG 2 as the prognostic validation set. From MRI image features, a radiomics-based signature predictive of the histological grade was built by use of the LASSO logistic regression algorithm. The model was developed for identifying NHG 1 and 3 radiological patterns, followed with re-stratification of NHG 2 tumors into Rad-Grade (RG)2-low (NHG 1-like) and RG2-high (NHG 3-like) subtypes using the learned patterns, and the prognostic value was assessed in terms of recurrence-free survival (RFS). RESULTS The Rad-Grade showed independent prognostic value for re-stratification of NHG 2 tumors, where RG2-high had an increased risk for recurrence (HR 2.20, 1.10-4.40, p = 0.026) compared with RG2-low after adjusting for established risk factors. RG2-low shared similar phenotypic characteristics and RFS outcomes with NHG 1, and RG2-high with NHG 3, revealing that the model captures radiomic features in NHG 2 that are associated with different aggressiveness. The prognostic value of Rad-Grade was further validated in the NHG2 ER+ (HR 2.53, 1.13-5.56, p = 0.023) and NHG 2 ER+LN- (HR 5.72, 1.24-26.44, p = 0.025) subgroups, and in specific treatment contexts. CONCLUSION The radiomics-based re-stratification of NHG 2 tumors offers a cost-effective promising alternative to gene expression profiling for tumor grading and thus may improve clinical decisions.
Collapse
Affiliation(s)
- Meng Jiang
- Emergency and Trauma Center, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang Province, China.
| | - Chang-Li Li
- Department of FSTC Clinic of The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang Province, China
| | - Xiao-Mao Luo
- Department of Oncology, Yunnan Cancer Hospital & The Third Affiliated Hospital of Kunming Medical University, Kunming, China
| | - Zhi-Rui Chuan
- Department of Oncology, Yunnan Cancer Hospital & The Third Affiliated Hospital of Kunming Medical University, Kunming, China
| | - Rui-Xue Chen
- Department of Oncology, Wuchang Hospital, Wuhan, China
| | - Chao-Ying Jin
- Department of Oncology, Taizhou Hospital of Zhejiang Province, Taizhou, China
| |
Collapse
|
6
|
Huellebrand M, Jarmatz L, Manini C, Laube A, Ivantsits M, Schulz-Menger J, Nordmeyer S, Harloff A, Hansmann J, Kelle S, Hennemuth A. Radiomics-based aortic flow profile characterization with 4D phase-contrast MRI. Front Cardiovasc Med 2023; 10:1102502. [PMID: 37077748 PMCID: PMC10106758 DOI: 10.3389/fcvm.2023.1102502] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2022] [Accepted: 03/06/2023] [Indexed: 04/05/2023] Open
Abstract
4D PC MRI of the aorta has become a routinely available examination, and a multitude of single parameters have been suggested for the quantitative assessment of relevant flow features for clinical studies and diagnosis. However, clinically applicable assessment of complex flow patterns is still challenging. We present a concept for applying radiomics for the quantitative characterization of flow patterns in the aorta. To this end, we derive cross-sectional scalar parameter maps related to parameters suggested in literature such as throughflow, flow direction, vorticity, and normalized helicity. Derived radiomics features are selected with regard to their inter-scanner and inter-observer reproducibility, as well as their performance in the differentiation of sex-, age- and disease-related flow properties. The reproducible features were tested on user-selected examples with respect to their suitability for characterizing flow profile types. In future work, such signatures could be applied for quantitative flow assessment in clinical studies or disease phenotyping.
Collapse
Affiliation(s)
- Markus Huellebrand
- Deutsches Herzzentrum der Charité, Berlin, Germany
- Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany
- Fraunhofer Institute for Digital Medicine MEVIS, Berlin, Germany
- Correspondence: Markus Huellebrand
| | - Lina Jarmatz
- Deutsches Herzzentrum der Charité, Berlin, Germany
- Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany
| | - Chiara Manini
- Deutsches Herzzentrum der Charité, Berlin, Germany
- Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany
| | - Ann Laube
- Deutsches Herzzentrum der Charité, Berlin, Germany
- Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany
- DZHK (German Centre for Cardiovascular Research), partner site Berlin, Berlin, Germany
| | - Matthias Ivantsits
- Deutsches Herzzentrum der Charité, Berlin, Germany
- Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany
| | - Jeanette Schulz-Menger
- Charité Universitätsmedizin Berlin, Working Group on Cardiovascular Magnetic Resonance, Experimental and Clinical Research Center, a joint cooperation between the Charité Universitätsmedizin Berlin and the Max-Delbrück-Center for Molecular Medicine, Berlin, Germany
- DZHK (German Centre for Cardiovascular Research), partner site Berlin, Berlin, Germany
- Helios Hospital Berlin-Buch, Department of Cardiology and Nephrology, Berlin, Germany
| | - Sarah Nordmeyer
- Deutsches Herzzentrum der Charité, Berlin, Germany
- Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany
- DZHK (German Centre for Cardiovascular Research), partner site Berlin, Berlin, Germany
| | - Andreas Harloff
- Department of Neurology, University Medical Center Freiburg, Freiburg, Germany
- Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - Jochen Hansmann
- Department of Radiology, Theresienkrankenhaus und St. Hedwig-Klinik, Mannheim, Germany
| | - Sebastian Kelle
- Deutsches Herzzentrum der Charité, Berlin, Germany
- Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany
- DZHK (German Centre for Cardiovascular Research), partner site Berlin, Berlin, Germany
| | - Anja Hennemuth
- Deutsches Herzzentrum der Charité, Berlin, Germany
- Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany
- Fraunhofer Institute for Digital Medicine MEVIS, Berlin, Germany
- DZHK (German Centre for Cardiovascular Research), partner site Berlin, Berlin, Germany
- Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| |
Collapse
|
7
|
Hooper GW, Ginat DT. MRI radiomics and potential applications to glioblastoma. Front Oncol 2023; 13:1134109. [PMID: 36874083 PMCID: PMC9982088 DOI: 10.3389/fonc.2023.1134109] [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: 12/29/2022] [Accepted: 02/07/2023] [Indexed: 02/19/2023] Open
Abstract
MRI plays an important role in the evaluation of glioblastoma, both at initial diagnosis and follow up after treatment. Quantitative analysis via radiomics can augment the interpretation of MRI in terms of providing insights regarding the differential diagnosis, genotype, treatment response, and prognosis. The various MRI radiomic features of glioblastoma are reviewed in this article.
Collapse
Affiliation(s)
- Grayson W Hooper
- Landstuhl Regional Medical Center, Department of Radiology, Landstuhl, Germany
| | - Daniel T Ginat
- University of Chicago, Department of Radiology, Chicago, IL, United States
| |
Collapse
|
8
|
Caballo M, Sanderink WBG, Han L, Gao Y, Athanasiou A, Mann RM. Four-Dimensional Machine Learning Radiomics for the Pretreatment Assessment of Breast Cancer Pathologic Complete Response to Neoadjuvant Chemotherapy in Dynamic Contrast-Enhanced MRI. J Magn Reson Imaging 2023; 57:97-110. [PMID: 35633290 PMCID: PMC10083908 DOI: 10.1002/jmri.28273] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2022] [Revised: 05/13/2022] [Accepted: 05/13/2022] [Indexed: 02/06/2023] Open
Abstract
BACKGROUND Breast cancer response to neoadjuvant chemotherapy (NAC) is typically evaluated through the assessment of tumor size reduction after a few cycles of NAC. In case of treatment ineffectiveness, this results in the patient suffering potentially severe secondary effects without achieving any actual benefit. PURPOSE To identify patients achieving pathologic complete response (pCR) after NAC by spatio-temporal radiomic analysis of dynamic contrast-enhanced (DCE) MRI images acquired before treatment. STUDY TYPE Single-center, retrospective. POPULATION A total of 251 DCE-MRI pretreatment images of breast cancer patients. FIELD STRENGTH/SEQUENCE 1.5 T/3 T, T1-weighted DCE-MRI. ASSESSMENT Tumor and peritumoral regions were segmented, and 348 radiomic features that quantify texture temporal variation, enhancement kinetics heterogeneity, and morphology were extracted. Based on subsets of features identified through forward selection, machine learning (ML) logistic regression models were trained separately with all images and stratifying on cancer molecular subtype and validated with leave-one-out cross-validation. STATISTICAL TESTS Feature significance was assessed using the Mann-Whitney U-test. Significance of the area under the receiver operating characteristics (ROC) curve (AUC) of the ML models was assessed using the associated 95% confidence interval (CI). Significance threshold was set to 0.05, adjusted with Bonferroni correction. RESULTS Nine features related to texture temporal variation and enhancement kinetics heterogeneity were significant in the discrimination of cases achieving pCR vs. non-pCR. The ML models achieved significant AUC of 0.707 (all cancers, n = 251, 59 pCR), 0.824 (luminal A, n = 107, 14 pCR), 0.823 (luminal B, n = 47, 15 pCR), 0.844 (HER2 enriched, n = 25, 11 pCR), 0.803 (triple negative, n = 72, 19 pCR). DATA CONCLUSIONS Differences in imaging phenotypes were found between complete and noncomplete responders. Furthermore, ML models trained per cancer subtype achieved high performance in classifying pCR vs. non-pCR cases. They may, therefore, have potential to help stratify patients according to the level of response predicted before treatment, pending further validation with larger prospective cohorts. EVIDENCE LEVEL 4 TECHNICAL EFFICACY: Stage 4.
Collapse
Affiliation(s)
- Marco Caballo
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
| | | | - Luyi Han
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands.,Department of Radiology, The Netherlands Cancer Institute, Amsterdam, The Netherlands
| | - Yuan Gao
- Department of Radiology, The Netherlands Cancer Institute, Amsterdam, The Netherlands.,GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, the Netherlands
| | | | - Ritse M Mann
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands.,Department of Radiology, The Netherlands Cancer Institute, Amsterdam, The Netherlands
| |
Collapse
|
9
|
Soleymani Y, Jahanshahi AR, Pourfarshid A, Khezerloo D. Reproducibility assessment of radiomics features in various ultrasound scan settings and different scanner vendors. J Med Imaging Radiat Sci 2022; 53:664-671. [PMID: 36266173 DOI: 10.1016/j.jmir.2022.09.018] [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: 03/19/2022] [Revised: 09/09/2022] [Accepted: 09/22/2022] [Indexed: 11/05/2022]
Abstract
INTRODUCTION Radiomics in Ultrasound (US) imaging has been investigated for the prediction and prognosis of cancers. However, inter-scanner and intra-scanner variations may affect the reproducibility of radiomics results. This study aims to evaluate the reproducibility of US textural radiomics features across various scan settings and scanner vendors. MATERIALS AND METHODS US images in quality control (QC) phantom were obtained by three scanners (Philips, Samsung, and Siemens) with different scan settings and parameters. Circular regions of interest (ROIs) inside isoechoic, hypoechoic, and hyperechoic objects were manually delineated. Forty textural radiomics features were extracted from each ROI, and then the robust features that could distinguish different echogenic objects were obtained by the Mann-Whitney U test. Reproducibility of the robust radiomics features was assessed by the intraclass correlation coefficient (ICC) and coefficient of variation (CV); ICC>0.90 and %CV<20 were considered reproducible. RESULTS According to the Mann-Whitney U test results, ten robust features could differentiate the hypoechoic, and 15 robust features could differentiate the hyperechoic objects from the isoechoic objects (P<0.001). The total ICC of the robust features for each echogenic object was >0.95 in different scanners and scan settings. Four and seven features were individually reproducible (%CV < 20, ICC>0.90) in hypoechoic and hyperechoic objects, respectively. Also, four features seem reproducible by changing the ROI location across the horizontal and vertical lines for both convex and linear array transducers. CONCLUSIONS Most of the US textural radiomics features in this study were not reproducible. However, several features showed high reproducibility at different scan settings and scanners. These features may also be reproducible when ROI size and location change slightly.
Collapse
Affiliation(s)
- Yunus Soleymani
- Department of Neuroscience and Addiction Studies, School of Advanced Technologies in Medicine, Tehran University of Medical Sciences, Tehran, Iran
| | - Amir Reza Jahanshahi
- Tabriz University of Medical Sciences, Faculty of Medicine, Imam Reza Hospital, Department of Radiology
| | - Amin Pourfarshid
- Department of Medical Physics, Faculty of Medicine, Urmia University of Medical Sciences, Urmia, Iran
| | - Davood Khezerloo
- Department of Radiology, Faculty of Alliance Medical Sciences, Tabriz University of Medical Sciences, Tabriz, Iran & Medical Radiation Sciences Research Group, Tabriz University of Medical Sciences, Tabriz, Iran.
| |
Collapse
|
10
|
Le NQK, Ho DKN, Ta HDK, Nguyen HT. Using ensemble learning and genetic algorithm on magnetic resonance imaging radiomics to classify molecular subtypes of breast cancer. PRECISION MEDICAL SCIENCES 2022. [DOI: 10.1002/prm2.12089] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022] Open
Affiliation(s)
- Nguyen Quoc Khanh Le
- Professional Master Program in Artificial Intelligence in Medicine, College of Medicine Taipei Medical University Taipei Taiwan
- Research Center for Artificial Intelligence in Medicine Taipei Medical University Taipei Taiwan
- Translational Imaging Research Center Taipei Medical University Hospital Taipei Taiwan
| | - Dang Khanh Ngan Ho
- School of Nutrition and Health Sciences, College of Nutrition Taipei Medical University Taipei Taiwan
| | - Hoang Dang Khoa Ta
- Ph.D. Program for Cancer Molecular Biology and Drug Discovery, College of Medical Science and Technology Taipei Medical University and Academia Sinica Taipei Taiwan
- Graduate Institute of Cancer Biology and Drug Discovery, College of Medical Science and Technology Taipei Medical University Taipei Taiwan
| | - Hieu Trung Nguyen
- Department of Orthopedic and Trauma, Faculty of Medicine University of Medicine and Pharmacy at Ho Chi Minh City Ho Chi Minh City Vietnam
| |
Collapse
|
11
|
Cui Y, Yin FF. Impact of image quality on radiomics applications. Phys Med Biol 2022; 67. [DOI: 10.1088/1361-6560/ac7fd7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2022] [Accepted: 07/08/2022] [Indexed: 11/12/2022]
Abstract
Abstract
Radiomics features extracted from medical images have been widely reported to be useful in the patient specific outcome modeling for variety of assessment and prediction purposes. Successful application of radiomics features as imaging biomarkers, however, is dependent on the robustness of the approach to the variation in each step of the modeling workflow. Variation in the input image quality is one of the main sources that impacts the reproducibility of radiomics analysis when a model is applied to broader range of medical imaging data. The quality of medical image is generally affected by both the scanner related factors such as image acquisition/reconstruction settings and the patient related factors such as patient motion. This article aimed to review the published literatures in this field that reported the impact of various imaging factors on the radiomics features through the change in image quality. The literatures were categorized by different imaging modalities and also tabulated based on the imaging parameters and the class of radiomics features included in the study. Strategies for image quality standardization were discussed based on the relevant literatures and recommendations for reducing the impact of image quality variation on the radiomics in multi-institutional clinical trial were summarized at the end of this article.
Collapse
|
12
|
Ren Q, Xiong F, Zhu P, Chang X, Wang G, He N, Jin Q. Assessing the robustness of radiomics/deep learning approach in the identification of efficacy of anti–PD-1 treatment in advanced or metastatic non-small cell lung carcinoma patients. Front Oncol 2022; 12:952749. [PMID: 35992867 PMCID: PMC9390967 DOI: 10.3389/fonc.2022.952749] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2022] [Accepted: 07/04/2022] [Indexed: 12/11/2022] Open
Abstract
Administration of anti–PD-1 is now a standard therapy in advanced non-small cell lung carcinoma (NSCLC) patients. The clinical application of biomarkers reflecting tumor immune microenvironment is hurdled by the invasiveness of obtaining tissues despite its importance in immunotherapy. This study aimed to develop a robust and non-invasive radiomics/deep learning machine biomarker for predicting the response to immunotherapy in NSCLC patients. Radiomics/deep learning features were exacted from computed tomography (CT) images of NSCLC patients treated with Nivolumab or Pembrolizumab. The robustness of radiomics/deep learning features was assessed against various perturbations, then robust features were selected based on the Intraclass Correlation Coefficient (ICC). Radiomics/deep learning machine-learning classifiers were constructed by combining seven feature exactors, 13 feature selection methods, and 12 classifiers. The optimal model was selected using the mean area under the curve (AUC) and relative standard deviation (RSD). The consistency of image features against various perturbations was high (the range of median ICC: 0.78–0.97), but the consistency was poor in test–retest testing (the range of median ICC: 0.42–0.67). The optimal model, InceptionV3_RELF_Nearest Neighbors classifiers, had the highest prediction efficacy (AUC: 0.96 and RSD: 0.50) for anti–PD-1/PD-L1 treatment. Accuracy (ACC), sensitivity, specificity, precision, and F1 score were 95.24%, 95.00%, 95.50%, 91.67%, and 95.30%, respectively. For successful model robustification, tailoring perturbations for robustness testing to the target dataset is key. Robust radiomics/deep learning features, when paired with machine-learning methodologies, will work on the exactness and the repeatability of anticipating immunotherapy adequacy.
Collapse
Affiliation(s)
- Qianqian Ren
- Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Hubei Province Key Laboratory of Molecular Imaging, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Fu Xiong
- Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Hubei Province Key Laboratory of Molecular Imaging, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Peng Zhu
- Department of Hepatobiliary Surgery, Wuhan No.1 Hospital, Wuhan, China
| | - Xiaona Chang
- Department of Pathology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Guobin Wang
- Department of Gastrointestinal Surgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Nan He
- Cancer Center, Department of Gastrointestinal Surgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- *Correspondence: Nan He, ; Qianna Jin,
| | - Qianna Jin
- Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Hubei Province Key Laboratory of Molecular Imaging, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- *Correspondence: Nan He, ; Qianna Jin,
| |
Collapse
|
13
|
Scalco E, Rizzo G, Mastropietro A. The stability of oncologic MRI radiomic features and the potential role of deep learning: a review. Phys Med Biol 2022; 67. [DOI: 10.1088/1361-6560/ac60b9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2021] [Accepted: 03/24/2022] [Indexed: 11/11/2022]
Abstract
Abstract
The use of MRI radiomic models for the diagnosis, prognosis and treatment response prediction of tumors has been increasingly reported in literature. However, its widespread adoption in clinics is hampered by issues related to features stability. In the MRI radiomic workflow, the main factors that affect radiomic features computation can be found in the image acquisition and reconstruction phase, in the image pre-processing steps, and in the segmentation of the region of interest on which radiomic indices are extracted. Deep Neural Networks (DNNs), having shown their potentiality in the medical image processing and analysis field, can be seen as an attractive strategy to partially overcome the issues related to radiomic stability and mitigate their impact. In fact, DNN approaches can be prospectively integrated in the MRI radiomic workflow to improve image quality, obtain accurate and reproducible segmentations and generate standardized images. In this review, DNN methods that can be included in the image processing steps of the radiomic workflow are described and discussed, in the light of a detailed analysis of the literature in the context of MRI radiomic reliability.
Collapse
|
14
|
Grimm LJ, Plichta JK, Hwang ES. More Than Incremental: Harnessing Machine Learning to Predict Breast Cancer Risk. J Clin Oncol 2022; 40:1713-1717. [PMID: 35245093 DOI: 10.1200/jco.21.02733] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
Affiliation(s)
- Lars J Grimm
- Department of Radiology, Duke University, Durham, NC
| | | | | |
Collapse
|
15
|
Yu B, Huang C, Xu J, Liu S, Guan Y, Li T, Zheng X, Ding J. Prediction of the degree of pathological differentiation in tongue squamous cell carcinoma based on radiomics analysis of magnetic resonance images. BMC Oral Health 2021; 21:585. [PMID: 34798867 PMCID: PMC8603498 DOI: 10.1186/s12903-021-01947-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2021] [Accepted: 11/03/2021] [Indexed: 12/24/2022] Open
Abstract
Background Tongue squamous cell carcinoma (TSCC) is one of the most difficult malignancies to control. It displays particular and aggressive behaviour even at an early stage. The purpose of this paper is to explore the value of radiomics based on magnetic resonance fat-suppressed T2-weighted images in predicting the degree of pathological differentiation of TSCC. Methods Retrospective analysis of 127 patients with TSCC who were randomly divided into a primary cohort and a test cohort, including well-differentiated, moderately differentiated and poorly differentiated. The tumour regions were manually labelled in fat-suppressed T2-weighted imaging (FS-T2WI), and PyRadiomics was used to extract radiomics features. The radiomics features were then selected by the least absolute shrinkage and selection operator (LASSO) method. The model was established by the logistic regression classifier using a 5-fold cross-validation method, applied to all data and evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity. Results In total, 1132 features were extracted, and seven features were selected for modelling. The AUC in the logistic regression model for well-differentiated TSCC was 0.90 with specificity and precision values of 0.92 and 0.78, respectively, and the sensitivity for poorly differentiated TSCC was 0.74. Conclusions The MRI-based radiomics signature could discriminate between well-differentiated, moderately differentiated and poorly differentiated TSCC and might be used as a biomarker for preoperative grading.
Collapse
Affiliation(s)
- Baoting Yu
- Department of Radiology, China-Japan Union Hospital of Jilin University, Changchun, 130021, China
| | - Chencui Huang
- Department of Research Collaboration, R&D Center, Beijing Deepwise & League of PHD Technology Co., Ltd, No. 829 of Xinmin Street, Chaoyang District, Beijing, 100080, China
| | - Jingxu Xu
- Department of Research Collaboration, R&D Center, Beijing Deepwise & League of PHD Technology Co., Ltd, No. 829 of Xinmin Street, Chaoyang District, Beijing, 100080, China
| | - Shuo Liu
- Department of Radiology, China-Japan Union Hospital of Jilin University, Changchun, 130021, China
| | - Yuyao Guan
- Department of Radiology, China-Japan Union Hospital of Jilin University, Changchun, 130021, China
| | - Tong Li
- Department of Radiology, China-Japan Union Hospital of Jilin University, Changchun, 130021, China
| | - Xuewei Zheng
- Department of Radiology, China-Japan Union Hospital of Jilin University, Changchun, 130021, China
| | - Jun Ding
- Department of Radiology, China-Japan Union Hospital of Jilin University, Changchun, 130021, China. .,Department of Research Collaboration, R&D Center, Beijing Deepwise & League of PHD Technology Co., Ltd, No. 829 of Xinmin Street, Chaoyang District, Beijing, 100080, China.
| |
Collapse
|
16
|
Gong XQ, Tao YY, Wu YK, Liu N, Yu X, Wang R, Zheng J, Liu N, Huang XH, Li JD, Yang G, Wei XQ, Yang L, Zhang XM. Progress of MRI Radiomics in Hepatocellular Carcinoma. Front Oncol 2021; 11:698373. [PMID: 34616673 PMCID: PMC8488263 DOI: 10.3389/fonc.2021.698373] [Citation(s) in RCA: 21] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2021] [Accepted: 08/31/2021] [Indexed: 02/05/2023] Open
Abstract
Background Hepatocellular carcinoma (HCC) is the sixth most common cancer in the world and the third leading cause of cancer-related death. Although the diagnostic scheme of HCC is currently undergoing refinement, the prognosis of HCC is still not satisfactory. In addition to certain factors, such as tumor size and number and vascular invasion displayed on traditional imaging, some histopathological features and gene expression parameters are also important for the prognosis of HCC patients. However, most parameters are based on postoperative pathological examinations, which cannot help with preoperative decision-making. As a new field, radiomics extracts high-throughput imaging data from different types of images to build models and predict clinical outcomes noninvasively before surgery, rendering it a powerful aid for making personalized treatment decisions preoperatively. Objective This study reviewed the workflow of radiomics and the research progress on magnetic resonance imaging (MRI) radiomics in the diagnosis and treatment of HCC. Methods A literature review was conducted by searching PubMed for search of relevant peer-reviewed articles published from May 2017 to June 2021.The search keywords included HCC, MRI, radiomics, deep learning, artificial intelligence, machine learning, neural network, texture analysis, diagnosis, histopathology, microvascular invasion, surgical resection, radiofrequency, recurrence, relapse, transarterial chemoembolization, targeted therapy, immunotherapy, therapeutic response, and prognosis. Results Radiomics features on MRI can be used as biomarkers to determine the differential diagnosis, histological grade, microvascular invasion status, gene expression status, local and systemic therapeutic responses, and prognosis of HCC patients. Conclusion Radiomics is a promising new imaging method. MRI radiomics has high application value in the diagnosis and treatment of HCC.
Collapse
Affiliation(s)
- Xue-Qin Gong
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Yun-Yun Tao
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Yao-Kun Wu
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Ning Liu
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Xi Yu
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Ran Wang
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Jing Zheng
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Nian Liu
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Xiao-Hua Huang
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Jing-Dong Li
- Department of Hepatocellular Surgery, Institute of Hepato-Biliary-Intestinal Disease, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Gang Yang
- Department of Hepatocellular Surgery, Institute of Hepato-Biliary-Intestinal Disease, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Xiao-Qin Wei
- School of Medical Imaging, North Sichuan Medical College, Nanchong, China
| | - Lin Yang
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Xiao-Ming Zhang
- Medical Imaging Key Laboratory of Sichuan Province, Department of Radiology, Medical Research Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| |
Collapse
|
17
|
Whitney HM, Drukker K, Edwards A, Papaioannou J, Medved M, Karczmar G, Giger ML. Robustness of radiomic features of benign breast lesions and hormone receptor positive/HER2-negative cancers across DCE-MR magnet strengths. Magn Reson Imaging 2021; 82:111-121. [PMID: 34174331 PMCID: PMC8386988 DOI: 10.1016/j.mri.2021.06.021] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2020] [Revised: 06/19/2021] [Accepted: 06/21/2021] [Indexed: 02/07/2023]
Abstract
Radiomic features extracted from breast lesion images have shown potential in diagnosis and prognosis of breast cancer. As medical centers transition from 1.5 T to 3.0 T magnetic resonance (MR) imaging, it is beneficial to identify potentially robust radiomic features across field strengths because images acquired at different field strengths could be used in machine learning models. Dynamic contrast-enhanced MR images of benign breast lesions and hormone receptor positive/HER2-negative (HR+/HER2-) breast cancers were acquired retrospectively, yielding 612 unique cases: 150 and 99 benign lesions imaged at 1.5 T and 3.0 T, and 223 and 140 HR+/HER2- cancerous lesions imaged at 1.5 T and 3.0 T, respectively. In addition, an independent set of seven lesions imaged at both field strengths, three benign lesions and four HR+/HER2- cancers, was analyzed separately. Lesions were automatically segmented using a 4D fuzzy c-means method; thirty-eight radiomic features were extracted. Feature value distributions were compared by cancer status and imaging field strength using the Kolmogorov-Smirnov test. Features that did not demonstrate a statistically significant difference were considered to be potentially robust. The area under the receiver operating characteristic curve (AUC), for the task of classifying lesions as benign or HR+/HER2- cancer, was determined for each feature at each field strength. Three features were found to be both potentially robust across field strength and of high classification performance, i.e., AUCs statistically greater than 0.5 in the classification task: one shape feature (irregularity), one texture feature (sum average) and one enhancement variance kinetics features (enhancement variance increasing rate). In the demonstration set of lesions imaged at both field strengths, two of the three potentially robust features showed qualitative agreement across field strength. These findings may contribute to the development of computer-aided diagnosis models that are robust across field strength for this classification task.
Collapse
Affiliation(s)
- Heather M Whitney
- Department of Radiology, The University of Chicago, Chicago, IL 60637, United States of America; Department of Physics, Wheaton College, Wheaton, IL 60187, United States of America.
| | - Karen Drukker
- Department of Radiology, The University of Chicago, Chicago, IL 60637, United States of America
| | - Alexandra Edwards
- Department of Radiology, The University of Chicago, Chicago, IL 60637, United States of America
| | - John Papaioannou
- Department of Radiology, The University of Chicago, Chicago, IL 60637, United States of America
| | - Milica Medved
- Department of Radiology, The University of Chicago, Chicago, IL 60637, United States of America
| | - Gregory Karczmar
- Department of Radiology, The University of Chicago, Chicago, IL 60637, United States of America
| | - Maryellen L Giger
- Department of Radiology, The University of Chicago, Chicago, IL 60637, United States of America.
| |
Collapse
|
18
|
Meyer‐Base A, Morra L, Tahmassebi A, Lobbes M, Meyer‐Base U, Pinker K. AI-Enhanced Diagnosis of Challenging Lesions in Breast MRI: A Methodology and Application Primer. J Magn Reson Imaging 2021; 54:686-702. [PMID: 32864782 PMCID: PMC8451829 DOI: 10.1002/jmri.27332] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2020] [Revised: 07/30/2020] [Accepted: 07/31/2020] [Indexed: 12/11/2022] Open
Abstract
Computer-aided diagnosis (CAD) systems have become an important tool in the assessment of breast tumors with magnetic resonance imaging (MRI). CAD systems can be used for the detection and diagnosis of breast tumors as a "second opinion" review complementing the radiologist's review. CAD systems have many common parts, such as image preprocessing, tumor feature extraction, and data classification that are mostly based on machine-learning (ML) techniques. In this review article, we describe applications of ML-based CAD systems in MRI covering the detection of diagnostically challenging lesions of the breast such as nonmass enhancing (NME) lesions, and furthermore discuss how multiparametric MRI and radiomics can be applied to the study of NME, including prediction of response to neoadjuvant chemotherapy (NAC). Since ML has been widely used in the medical imaging community, we provide an overview about the state-of-the-art and novel techniques applied as classifiers to CAD systems. The differences in the CAD systems in MRI of the breast for several standard and novel applications for NME are explained in detail to provide important examples, illustrating: 1) CAD for detection and diagnosis, 2) CAD in multiparametric imaging, 3) CAD in NAC, and 4) breast cancer radiomics. We aim to provide a comparison between these CAD applications and to illustrate a global view on intelligent CAD systems based on machine and deep learning in MRI of the breast. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY STAGE: 2.
Collapse
Affiliation(s)
- Anke Meyer‐Base
- Department of Scientific ComputingFlorida State UniversityTallahasseeFloridaUSA
- Department of Radiology, Maastricht Medical CenterUniversity of MaastrichtMaastrichtNetherlands
| | - Lia Morra
- Department of Control and Computer EngineeringPolitecnico di TorinoTorinoItaly
| | | | - Marc Lobbes
- Department of Radiology, Maastricht Medical CenterUniversity of MaastrichtMaastrichtNetherlands
- GROW School for Oncology and Developmental BiologyMaastrichtNetherlands
- Zuyderland Medical Center, dep of Medical ImagingSittard‐GeleenNetherlands
| | - Uwe Meyer‐Base
- Department of Electrical and Computer EngineeringFlorida A&M University and Florida State UniversityTallahasseeFloridaUSA
| | - Katja Pinker
- Department of Radiology, Breast Imaging ServiceMemorial Sloan‐Kettering Cancer CenterNew YorkNew YorkUSA
- Department of Biomedical Imaging and Image‐Guided Therapy, Division of Molecular and Gender ImagingMedical University of ViennaViennaAustria
| |
Collapse
|
19
|
Modanwal G, Vellal A, Mazurowski MA. Normalization of breast MRIs using cycle-consistent generative adversarial networks. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2021; 208:106225. [PMID: 34198016 DOI: 10.1016/j.cmpb.2021.106225] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/25/2021] [Accepted: 05/29/2021] [Indexed: 06/13/2023]
Abstract
OBJECTIVES Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) is widely used to complement ultrasound examinations and x-ray mammography for early detection and diagnosis of breast cancer. However, images generated by various MRI scanners (e.g., GE Healthcare, and Siemens) differ both in intensity and noise distribution, preventing algorithms trained on MRIs from one scanner to generalize to data from other scanners. In this work, we propose a method to solve this problem by normalizing images between various scanners. METHODS MRI normalization is challenging because it requires normalizing intensity values and mapping noise distributions between scanners. We utilize a cycle-consistent generative adversarial network to learn a bidirectional mapping and perform normalization between MRIs produced by GE Healthcare and Siemens scanners in an unpaired setting. Initial experiments demonstrate that the traditional CycleGAN architecture struggles to preserve the anatomical structures of the breast during normalization. Thus, we propose two technical innovations in order to preserve both the shape of the breast as well as the tissue structures within the breast. First, we incorporate mutual information loss during training in order to ensure anatomical consistency. Second, we propose a modified discriminator architecture that utilizes a smaller field-of-view to ensure the preservation of finer details in the breast tissue. RESULTS Quantitative and qualitative evaluations show that the second innovation consistently preserves the breast shape and tissue structures while also performing the proper intensity normalization and noise distribution mapping. CONCLUSION Our results demonstrate that the proposed model can successfully learn a bidirectional mapping and perform normalization between MRIs produced by different vendors, potentially enabling improved diagnosis and detection of breast cancer. All the data used in this study are publicly available at https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=70226903.
Collapse
Affiliation(s)
| | - Adithya Vellal
- Department of Computer Science, Duke University, Durham, NC, USA
| | | |
Collapse
|
20
|
Liu X, Zhang D, Liu Z, Li Z, Xie P, Sun K, Wei W, Dai W, Tang Z, Ding Y, Cai G, Tong T, Meng X, Tian J. Deep learning radiomics-based prediction of distant metastasis in patients with locally advanced rectal cancer after neoadjuvant chemoradiotherapy: A multicentre study. EBioMedicine 2021; 69:103442. [PMID: 34157487 PMCID: PMC8237293 DOI: 10.1016/j.ebiom.2021.103442] [Citation(s) in RCA: 38] [Impact Index Per Article: 12.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2021] [Revised: 04/17/2021] [Accepted: 06/01/2021] [Indexed: 12/22/2022] Open
Abstract
BACKGROUND Accurate predictions of distant metastasis (DM) in locally advanced rectal cancer (LARC) patients receiving neoadjuvant chemoradiotherapy (nCRT) are helpful in developing appropriate treatment plans. This study aimed to perform DM prediction through deep learning radiomics. METHODS We retrospectively sampled 235 patients receiving nCRT with the minimum 36 months' postoperative follow-up from three hospitals. Through transfer learning, a deep learning radiomic signature (DLRS) based on multiparametric magnetic resonance imaging (MRI) was constructed. A nomogram was established integrating deep MRI information and clinicopathologic factors for better prediction. Harrell's concordance index (C-index) and time-dependent receiver operating characteristic (ROC) were used as performance metrics. Furthermore, the risk of DM in patients with different response to nCRT was evaluated with the nomogram. FINDINGS DLRS performed well in DM prediction, with a C-index of 0·747 and an area under curve (AUC) at three years of 0·894 in the validation cohort. The performance of nomogram was better, with a C-index of 0·775. In addition, the nomogram could stratify patients with different responses to nCRT into high- and low-risk groups of DM (P < 0·05). INTERPRETATION MRI-based deep learning radiomics had potential in predicting the DM of LARC patients receiving nCRT and could help evaluate the risk of DM in patients who have different responses to nCRT. FUNDING The funding bodies that contributed to this study are listed in the Acknowledgements section.
Collapse
Affiliation(s)
- Xiangyu Liu
- Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi 710126, China; CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
| | - Dafu Zhang
- Department of Radiology, the Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Yunnan Cancer Center, Kunming 650118, China
| | - Zhenyu Liu
- CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; CAS Center for Excellence in Brain Science and Intelligence Technology, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100080, China
| | - Zhenhui Li
- Department of Radiology, the Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Yunnan Cancer Center, Kunming 650118, China
| | - Peiyi Xie
- Department of Radiology, The Sixth Affiliated Hospital of Sun Yat-sen University, Guangzhou 510655, China
| | - Kai Sun
- Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi 710126, China; CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
| | - Wei Wei
- CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
| | - Weixing Dai
- Department of Colorectal Surgery, Fudan University Shanghai Cancer Center, Shanghai 200032, China
| | - Zhenchao Tang
- Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine and Engineering, Beihang University, Beijing 100191, China
| | - Yingying Ding
- Department of Radiology, the Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Yunnan Cancer Center, Kunming 650118, China
| | - Guoxiang Cai
- Department of Colorectal Surgery, Fudan University Shanghai Cancer Center, Shanghai 200032, China
| | - Tong Tong
- Department of Radiology, Fudan University Shanghai Cancer Center, Department of Oncology, Shanghai Medical College, Fudan University, Shanghai 200032, China.
| | - Xiaochun Meng
- Department of Radiology, The Sixth Affiliated Hospital of Sun Yat-sen University, Guangzhou 510655, China.
| | - Jie Tian
- Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi 710126, China; CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine and Engineering, Beihang University, Beijing 100191, China; Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology, Beijing 100191, China.
| |
Collapse
|
21
|
Bobholz SA, Lowman AK, Barrington A, Brehler M, McGarry S, Cochran EJ, Connelly J, Mueller WM, Agarwal M, O'Neill D, Nencka AS, Banerjee A, LaViolette PS. Radiomic Features of Multiparametric MRI Present Stable Associations With Analogous Histological Features in Patients With Brain Cancer. ACTA ACUST UNITED AC 2021; 6:160-169. [PMID: 32548292 PMCID: PMC7289245 DOI: 10.18383/j.tom.2019.00029] [Citation(s) in RCA: 23] [Impact Index Per Article: 7.7] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022]
Abstract
Magnetic resonance (MR)-derived radiomic features have shown substantial predictive utility in modeling different prognostic factors of glioblastoma and other brain cancers. However, the biological relationship underpinning these predictive models has been largely unstudied, and the generalizability of these models had been called into question. Here, we examine the localized relationship between MR-derived radiomic features and histology-derived “histomic” features using a data set of 16 patients with brain cancer. Tile-based radiomic features were collected on T1, post-contrast T1, FLAIR, and diffusion-weighted imaging (DWI)-derived apparent diffusion coefficient (ADC) images acquired before patient death, with analogous histomic features collected for autopsy samples coregistered to the magnetic resonance imaging. Features were collected for each original image, as well as a 3D wavelet decomposition of each image, resulting in 837 features per MR and histology image. Correlative analyses were used to assess the degree of association between radiomic–histomic pairs for each magnetic resonance imaging. The influence of several confounds was also assessed using linear mixed-effect models for the normalized radiomic–histomic distance, testing for main effects of different acquisition field strengths. Results as a whole were largely heterogeneous, but several features showed substantial associations with their histomic analogs, particularly those derived from the FLAIR and postcontrast T1W images. These features with the strongest association typically presented as stable across field strengths as well. These data suggest that a subset of radiomic features can consistently capture texture information on underlying tissue histology.
Collapse
|
22
|
Grimm LJ. Radiomics: A Primer for Breast Radiologists. JOURNAL OF BREAST IMAGING 2021; 3:276-287. [PMID: 38424774 DOI: 10.1093/jbi/wbab014] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2020] [Indexed: 03/02/2024]
Abstract
Radiomics has a long-standing history in breast imaging with computer-aided detection (CAD) for screening mammography developed in the late 20th century. Although conventional CAD had widespread adoption, the clinical benefits for experienced breast radiologists were debatable due to high false-positive marks and subsequent increased recall rates. The dramatic growth in recent years of artificial intelligence-based analysis, including machine learning and deep learning, has provided numerous opportunities for improved modern radiomics work in breast imaging. There has been extensive radiomics work in mammography, digital breast tomosynthesis, MRI, ultrasound, PET-CT, and combined multimodality imaging. Specific radiomics outcomes of interest have been diverse, including CAD, prediction of response to neoadjuvant therapy, lesion classification, and survival, among other outcomes. Additionally, the radiogenomics subfield that correlates radiomics features with genetics has been very proliferative, in parallel with the clinical validation of breast cancer molecular subtypes and gene expression assays. Despite the promise of radiomics, there are important challenges related to image normalization, limited large unbiased data sets, and lack of external validation. Much of the radiomics work to date has been exploratory using single-institution retrospective series for analysis, but several promising lines of investigation have made the leap to clinical practice with commercially available products. As a result, breast radiologists will increasingly be incorporating radiomics-based tools into their daily practice in the near future. Therefore, breast radiologists must have a broad understanding of the scope, applications, and limitations of radiomics work.
Collapse
Affiliation(s)
- Lars J Grimm
- Duke University, Department of Radiology, Durham, NC, USA
| |
Collapse
|
23
|
Jiang M, Han L, Sun H, Li J, Bao N, Li H, Zhou S, Yu T. Cross-modality image feature fusion diagnosis in breast cancer. Phys Med Biol 2021; 66. [PMID: 33784653 DOI: 10.1088/1361-6560/abf38b] [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] [Received: 01/04/2021] [Accepted: 03/30/2021] [Indexed: 01/22/2023]
Abstract
Considering the complementarity of mammography and breast MRI, the research of feature fusion diagnosis based on cross-modality images was explored to improve the accuracy of breast cancer diagnosis. 201 patients with both mammography and breast MRI were collected retrospectively, including 117 cases of benign lesions and 84 cases of malignant ones. Two feature optimization strategies of sequential floating forward selection (SFFS), SFFS-1 and SFFS-2, were defined based on the sequential floating forward selection method. Each strategy was used to analyze the diagnostic performance of single-modality images and then to study the feature fusion diagnosis of cross-modality images. Three feature fusion approaches were compared: optimizing MRI features and then fusing those of mammography; optimizing mammography features and then fusing those of MRI; selecting the effective features from the whole feature set (mammography and MRI). Support vector machine, Naive Bayes, and K-nearest neighbor were employed as the classifiers and were finally integrated to get better performance. The average accuracy and area under the ROC curve (AUC) of MRI (88.56%, 0.9 for SFFS-1, 88.39%, 0.89 for SFFS-2) were better than mammography (84.25%, 0.84 for SFFS-1, 80.43%, 0.80 for SFFS-2). Furthermore, compared with a single modality, the average accuracy and AUC of cross-modality feature fusion can improve from 85.40% and 0.86 to 89.66% and 0.91. Classifier integration improved the accuracy and AUC from 90.49%, 0.92 to 92.37%, and 0.97. Cross-modality image feature fusion can achieve better diagnosis performance than a single modality. Feature selection strategy SFFS-1 has better efficiency than SFFS-2. Classifier integration can further improve diagnostic accuracy.
Collapse
Affiliation(s)
- Mingkuan Jiang
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, People's Republic of China
| | - Lu Han
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, Shenyang, People's Republic of China
| | - Hang Sun
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, People's Republic of China
| | - Jing Li
- Department of Radiology, Affiliated Hospital of Guizhou Medical University, Guiyang, People's Republic of China
| | - Nan Bao
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, People's Republic of China
| | - Hong Li
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, People's Republic of China
| | - Shi Zhou
- Department of Radiology, Affiliated Hospital of Guizhou Medical University, Guiyang, People's Republic of China
| | - Tao Yu
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, Shenyang, People's Republic of China
| |
Collapse
|
24
|
Chen H, He Y, Zhao C, Zheng L, Pan N, Qiu J, Zhang Z, Niu X, Yuan Z. Reproducibility of radiomics features derived from intravoxel incoherent motion diffusion-weighted MRI of cervical cancer. Acta Radiol 2021; 62:679-686. [PMID: 32640886 DOI: 10.1177/0284185120934471] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/21/2023]
Abstract
BACKGROUND The reproducibility of intravoxel incoherent motion (IVIM)-based radiomics studies in humans has not been reported. PURPOSE To determine the inter- and intra-observer variability on the reproducibility of IVIM-based radiomics features in cervical cancer (CC). MATERIAL AND METHODS The IVIM images of 25 patients with CC were retrospectively collected. Based on the high-resolution T2-weighted images, the regions of interest (ROIs) were independently delineated twice in diffusion-weighted images at a b value of 1000 s/mm2 (interval time was one month) by two radiologists. This was done at the largest transversal cross-sections of the tumors. The ROI was subsequently used in apparent diffusion coefficient (ADC), true diffusion coefficient (D), pseudo-diffusion coefficient (D*), and perfusion fraction (f) maps derived from IVIM images. In total, 105 radiomics features were then finally extracted from the IVIM-derived maps. The inter- and intra-observer reproducibility of IVIM-derived features was then evaluated using the intraclass correlation coefficient. RESULTS Inter- and intra-observer variability affected the reproducibility of radiomics features. D* map had 100% and 95% reproducible features, ADC map had 89% and 93%, D map had 97% and 86%, while f map had 54% and 62% reproducible features with good to excellent reliability in the intra-observer analysis. Similarly, D* map had 90% and 94%, ADC map had 85% and 70%, D map had 81% and 78%, while f map had 41% and 93% reproducible features with good to excellent reliability in the inter-observer analysis. CONCLUSION Inter- and intra-observer variability can affect radiomics analysis. Cognizant to this, multicenter studies should pay more attention to intra- and inter-observer variability.
Collapse
Affiliation(s)
- Hao Chen
- Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, PR China
| | - Yaoyao He
- Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, PR China
| | - Cecheng Zhao
- College of informatics, Huazhong Agricultural University, Wuhan, PR China
| | - Lili Zheng
- Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, PR China
| | - Ning Pan
- College of Biomedical Engineering, South Central University for Nationalities, Wuhan, PR China
- Hubei Key Laboratory of Medical Information Analysis and Tumor Diagnosis & Treatment, Wuhan, PR China
| | - Jianfeng Qiu
- Medical Engineering and Technology Center, Shandong First Medical University & Shandong Academy of Medical Sciences, Taian, PR China
| | - Zhaoxi Zhang
- Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, PR China
| | - Xiaohui Niu
- College of informatics, Huazhong Agricultural University, Wuhan, PR China
| | - Zilong Yuan
- Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, PR China
| |
Collapse
|
25
|
Hu Z, Zhuang Q, Xiao Y, Wu G, Shi Z, Chen L, Wang Y, Yu J. MIL normalization -- prerequisites for accurate MRI radiomics analysis. Comput Biol Med 2021; 133:104403. [PMID: 33932645 DOI: 10.1016/j.compbiomed.2021.104403] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2021] [Revised: 04/11/2021] [Accepted: 04/11/2021] [Indexed: 01/15/2023]
Abstract
The quality of magnetic resonance (MR) images obtained with different instruments and imaging parameters varies greatly. A large number of heterogeneous images are collected, and they suffer from acquisition variation. Such imaging quality differences will have a great impact on the radiomics analysis. The main differences in MR images include modality mismatch (M), intensity distribution variance (I), and layer-spacing differences (L), which are referred to as MIL differences in this paper for convenience. An MIL normalization system is proposed to reconstruct uneven MR images into high-quality data with complete modality, a uniform intensity distribution and consistent layer spacing. Three radiomics tasks, including tumor segmentation, pathological grading and genetic diagnosis of glioma, were used to verify the effect of MIL normalization on radiomics analysis. Three retrospective glioma datasets were analyzed in this study: BraTs (285 cases), TCGA (112 cases) and HuaShan (403 cases). They were used to test the effect of MIL on three different radiomics tasks, including tumor segmentation, pathological grading and genetic diagnosis. MIL normalization included three components: multimodal synthesis based on an encoder-decoder network, intensity normalization based on CycleGAN, and layer-spacing unification based on Statistical Parametric Mapping (SPM). The Dice similarity coefficient, areas under the curve (AUC) and six other indicators were calculated and compared after different normalization steps. The MIL normalization system can improved the Dice coefficient of segmentation by 9% (P < .001), the AUC of pathological grading by 32% (P < .001), and IDH1 status prediction by 25% (P < .001) when compared to non-normalization. The proposed MIL normalization system provides high-quality standardized data, which is a prerequisite for accurate radiomics analysis.
Collapse
Affiliation(s)
- Zhaoyu Hu
- School of Information Science and Technology, Fudan University, Shanghai, China
| | - Qiyuan Zhuang
- Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China
| | - Yang Xiao
- Department of Biomedical Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Guoqing Wu
- School of Information Science and Technology, Fudan University, Shanghai, China
| | - Zhifeng Shi
- Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China
| | - Liang Chen
- Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China
| | - Yuanyuan Wang
- School of Information Science and Technology, Fudan University, Shanghai, China
| | - Jinhua Yu
- School of Information Science and Technology, Fudan University, Shanghai, China.
| |
Collapse
|
26
|
Radiomics feature robustness as measured using an MRI phantom. Sci Rep 2021; 11:3973. [PMID: 33597610 PMCID: PMC7889870 DOI: 10.1038/s41598-021-83593-3] [Citation(s) in RCA: 37] [Impact Index Per Article: 12.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2018] [Accepted: 01/15/2021] [Indexed: 12/19/2022] Open
Abstract
Radiomics involves high-throughput extraction of large numbers of quantitative features from medical images and analysis of these features to predict patients’ outcome and support clinical decision-making. However, radiomics features are sensitive to several factors, including scanning protocols. The purpose of this study was to investigate the robustness of magnetic resonance imaging (MRI) radiomics features with various MRI scanning protocol parameters and scanners using an MRI radiomics phantom. The variability of the radiomics features with different scanning parameters and repeatability measured using a test–retest scheme were evaluated using the coefficient of variation and intraclass correlation coefficient (ICC) for both T1- and T2-weighted images. For variability measures, the features were categorized into three groups: large, intermediate, and small variation. For repeatability measures, the average T1- and T2-weighted image ICCs for the phantom (0.963 and 0.959, respectively) were higher than those for a healthy volunteer (0.856 and 0.849, respectively). Our results demonstrated that various radiomics features are dependent on different scanning parameters and scanners. The radiomics features with a low coefficient of variation and high ICC for both the phantom and volunteer can be considered good candidates for MRI radiomics studies. The results of this study will assist current and future MRI radiomics studies.
Collapse
|
27
|
Saint Martin MJ, Orlhac F, Akl P, Khalid F, Nioche C, Buvat I, Malhaire C, Frouin F. A radiomics pipeline dedicated to Breast MRI: validation on a multi-scanner phantom study. MAGNETIC RESONANCE MATERIALS IN PHYSICS BIOLOGY AND MEDICINE 2020; 34:355-366. [PMID: 33180226 DOI: 10.1007/s10334-020-00892-y] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/16/2020] [Revised: 09/27/2020] [Accepted: 10/23/2020] [Indexed: 12/14/2022]
Abstract
OBJECTIVE Quantitative analysis in MRI is challenging due to variabilities in intensity distributions across patients, acquisitions and scanners and suffers from bias field inhomogeneity. Radiomic studies are impacted by these effects that affect radiomic feature values. This paper describes a dedicated pipeline to increase reproducibility in breast MRI radiomic studies. MATERIALS AND METHODS T1, T2, and T1-DCE MR images of two breast phantoms were acquired using two scanners and three dual breast coils. Images were retrospectively corrected for bias field inhomogeneity and further normalised using Z score or histogram matching. Extracted radiomic features were harmonised between coils by the ComBat method. The whole pipeline was assessed qualitatively and quantitatively using statistical comparisons on two series of radiomic feature values computed in the gel mimicking the normal breast tissue or in dense lesions. RESULTS Intra and inter-acquisition variabilities were strongly reduced by the standardisation pipeline. Harmonisation by ComBat lowered the percentage of radiomic features significantly different between the three coils from 87% after bias field correction and MR normalisation to 3% in the gel, while preserving or improving performance of lesion classification in the phantoms. DISCUSSION A dedicated standardisation pipeline was developed to reduce variabilities in breast MRI, which paves the way for robust multi-scanner radiomic studies but needs to be assessed on patient data.
Collapse
Affiliation(s)
- Marie-Judith Saint Martin
- Inserm, Institut Curie,Université Paris-Saclay, Laboratoire d'Imagerie Translationnelle en Oncologie (LITO), Centre de Recherche de l'Institut Curie, Bât 101B rue Henri Becquerel, 91401, Orsay, France.
| | - Fanny Orlhac
- Inserm, Institut Curie,Université Paris-Saclay, Laboratoire d'Imagerie Translationnelle en Oncologie (LITO), Centre de Recherche de l'Institut Curie, Bât 101B rue Henri Becquerel, 91401, Orsay, France
| | - Pia Akl
- Inserm, Institut Curie,Université Paris-Saclay, Laboratoire d'Imagerie Translationnelle en Oncologie (LITO), Centre de Recherche de l'Institut Curie, Bât 101B rue Henri Becquerel, 91401, Orsay, France
- HCL, Radiologie du Groupement Hospitalier Est, Hôpital Femme Mère Enfant, Unité Fonctionnelle: Imagerie de la Femme, 3 Quai des Célestins, 69002, Lyon, France
- Institut Curie, Service de Radiodiagnostic, 26 rue d'Ulm, 75005, Paris, France
| | - Fahad Khalid
- Inserm, Institut Curie,Université Paris-Saclay, Laboratoire d'Imagerie Translationnelle en Oncologie (LITO), Centre de Recherche de l'Institut Curie, Bât 101B rue Henri Becquerel, 91401, Orsay, France
| | - Christophe Nioche
- Inserm, Institut Curie,Université Paris-Saclay, Laboratoire d'Imagerie Translationnelle en Oncologie (LITO), Centre de Recherche de l'Institut Curie, Bât 101B rue Henri Becquerel, 91401, Orsay, France
| | - Irène Buvat
- Inserm, Institut Curie,Université Paris-Saclay, Laboratoire d'Imagerie Translationnelle en Oncologie (LITO), Centre de Recherche de l'Institut Curie, Bât 101B rue Henri Becquerel, 91401, Orsay, France
| | - Caroline Malhaire
- Inserm, Institut Curie,Université Paris-Saclay, Laboratoire d'Imagerie Translationnelle en Oncologie (LITO), Centre de Recherche de l'Institut Curie, Bât 101B rue Henri Becquerel, 91401, Orsay, France
- Institut Curie, Service de Radiodiagnostic, 26 rue d'Ulm, 75005, Paris, France
| | - Frédérique Frouin
- Inserm, Institut Curie,Université Paris-Saclay, Laboratoire d'Imagerie Translationnelle en Oncologie (LITO), Centre de Recherche de l'Institut Curie, Bât 101B rue Henri Becquerel, 91401, Orsay, France
| |
Collapse
|
28
|
Suter Y, Knecht U, Alão M, Valenzuela W, Hewer E, Schucht P, Wiest R, Reyes M. Radiomics for glioblastoma survival analysis in pre-operative MRI: exploring feature robustness, class boundaries, and machine learning techniques. Cancer Imaging 2020; 20:55. [PMID: 32758279 PMCID: PMC7405445 DOI: 10.1186/s40644-020-00329-8] [Citation(s) in RCA: 30] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2020] [Accepted: 07/13/2020] [Indexed: 12/16/2022] Open
Abstract
Background This study aims to identify robust radiomic features for Magnetic Resonance Imaging (MRI), assess feature selection and machine learning methods for overall survival classification of Glioblastoma multiforme patients, and to robustify models trained on single-center data when applied to multi-center data. Methods Tumor regions were automatically segmented on MRI data, and 8327 radiomic features extracted from these regions. Single-center data was perturbed to assess radiomic feature robustness, with over 16 million tests of typical perturbations. Robust features were selected based on the Intraclass Correlation Coefficient to measure agreement across perturbations. Feature selectors and machine learning methods were compared to classify overall survival. Models trained on single-center data (63 patients) were tested on multi-center data (76 patients). Priors using feature robustness and clinical knowledge were evaluated. Results We observed a very large performance drop when applying models trained on single-center on unseen multi-center data, e.g. a decrease of the area under the receiver operating curve (AUC) of 0.56 for the overall survival classification boundary at 1 year. By using robust features alongside priors for two overall survival classes, the AUC drop could be reduced by 21.2%. In contrast, sensitivity was 12.19% lower when applying a prior. Conclusions Our experiments show that it is possible to attain improved levels of robustness and accuracy when models need to be applied to unseen multi-center data. The performance on multi-center data of models trained on single-center data can be increased by using robust features and introducing prior knowledge. For successful model robustification, tailoring perturbations for robustness testing to the target dataset is key.
Collapse
Affiliation(s)
- Yannick Suter
- ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland. .,Insel Data Science Center, Inselspital, Bern University Hospital, Murtenstrasse 42, CH-3008, Bern, Switzerland.
| | - Urspeter Knecht
- Radiology Department, Spital Emmental, Burgdorf and Langnau, Switzerland
| | - Mariana Alão
- ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland.,Departamento de Eletrónica Industrial, University of Minho, Braga, Portugal
| | - Waldo Valenzuela
- Insel Data Science Center, Inselspital, Bern University Hospital, Murtenstrasse 42, CH-3008, Bern, Switzerland
| | - Ekkehard Hewer
- Institute of Pathology, University of Bern, Bern, Switzerland
| | - Philippe Schucht
- Department of Neurosurgery, Inselspital, Bern University Hospital, Bern, Switzerland
| | - Roland Wiest
- Support Center for Advanced Neuroimaging, Inselspital, Bern University Hospital, Bern, Switzerland
| | - Mauricio Reyes
- Insel Data Science Center, Inselspital, Bern University Hospital, Murtenstrasse 42, CH-3008, Bern, Switzerland
| |
Collapse
|
29
|
Saha A, Tso S, Rabski J, Sadeghian A, Cusimano MD. Machine learning applications in imaging analysis for patients with pituitary tumors: a review of the current literature and future directions. Pituitary 2020; 23:273-293. [PMID: 31907710 DOI: 10.1007/s11102-019-01026-x] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/16/2022]
Abstract
PURPOSE To provide an overview of fundamental concepts in machine learning (ML), review the literature on ML applications in imaging analysis of pituitary tumors for the last 10 years, and highlight the future directions on potential applications of ML for pituitary tumor patients. METHOD We presented an overview of the fundamental concepts in ML, its various stages used in healthcare, and highlighted the key components typically present in an imaging-based tumor analysis pipeline. A search was conducted across four databases (PubMed, Ovid, Embase, and Google Scholar) to gather research articles from the past 10 years (2009-2019) involving imaging related to pituitary tumor and ML. We grouped the studies by imaging modalities and analyzed the ML tasks in terms of the data inputs, reference standards, methodologies, and limitations. RESULTS Of the 16 studies included in our analysis, 10 appeared in 2018-2019. Most of the studies utilized retrospective data and followed a semi-automatic ML pipeline. The studies included use of magnetic resonance imaging (MRI), facial photographs, surgical microscopic video, spectrometry, and spectroscopy imaging. The objectives of the studies covered 14 distinct applications and majority of the studies addressed a binary classification problem. Only five of the 11 MRI-based studies had an external validation or a holdout set to test the performance of a final trained model. CONCLUSION Through our concise evaluation and comparison of the studies using the concepts presented, we highlight future directions so that potential ML applications using different imaging modalities can be developed to benefit the clinical care of pituitary tumor patients.
Collapse
Affiliation(s)
- Ashirbani Saha
- Division of Neurosurgery, St. Michael's Hospital, Toronto, ON, Canada.
| | - Samantha Tso
- Division of Neurosurgery, St. Michael's Hospital, Toronto, ON, Canada
| | - Jessica Rabski
- Division of Neurosurgery, St. Michael's Hospital, Toronto, ON, Canada
| | | | - Michael D Cusimano
- Division of Neurosurgery, St. Michael's Hospital, Toronto, ON, Canada
- Department of Surgery, University of Toronto, Toronto, ON, Canada
| |
Collapse
|
30
|
He Y, Rong Y, Chen H, Zhang Z, Qiu J, Zheng L, Benedict S, Niu X, Pan N, Liu Y, Yuan Z. Impact of different b-value combinations on radiomics features of apparent diffusion coefficient in cervical cancer. Acta Radiol 2020; 61:568-576. [PMID: 31466457 DOI: 10.1177/0284185119870157] [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: 12/26/2022]
Abstract
Background The impact of variable b-value combinations on apparent diffusion coefficient (ADC)-based radiomics features has not been fully addressed in literature. Purpose To investigate the correlation between radiomics features extracted from ADC maps and various b-value combinations in cervical cancer. Material and Methods Diffusion-weighted images (b-values: 0, 600, 800, and 1000 s/mm2) of 20 patients with cervical cancer were included. Tumors were identified with the largest transversal cross-section and manually segmented by radiologist. For each b-value combination, 92 radiomics features were extracted and coefficient of variance (CV) was used to evaluate the robustness of radiomics features with different b-value combinations. Features with CV > 5% were normalized by the mean feature variation across the group. Results Out of a total of 92 radiomics features, 18 were classified as robust features with CV ≤5%. Among the rest (CV > 5%), 11, 23, and 40 features demonstrated 5%< CV ≤10%, 10%< CV ≤20%, and CV > 20%, respectively. A subset of features in each category (CV > 5%) showed strong correlation with the b-value combination variation, including 44% (7/16) features in gray level co-occurrence matrix, 62% (8/13) features in gray level dependence matrix, 64% (9/14) features in first order, 50% (8/16) features in gray level run length matrix, 57% (8/14) features in gray level size matrix, and 20% (1/5) features in neighborhood gray-tone difference matrix. Conclusions Variations in b-value combinations demonstrated impact on radiomics features extracted from ADC maps for cervical cancer. The radiomics features with CV <5% can be considered as robust features and are recommended to be used in multicenter radiomics studies.
Collapse
Affiliation(s)
- Yaoyao He
- Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, PR China
- Medical Engineering and Technology Center, Taishan Medical University, Taian, PR China
| | - Yi Rong
- Department of Radiation Oncology, University of California Davis Medical Center, Sacramento, CA, USA
| | - Hao Chen
- Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, PR China
| | - Zhaoxi Zhang
- Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, PR China
| | - Jianfeng Qiu
- Medical Engineering and Technology Center, Taishan Medical University, Taian, PR China
| | - Lili Zheng
- Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, PR China
| | - Stanley Benedict
- Department of Radiation Oncology, University of California Davis Medical Center, Sacramento, CA, USA
| | - Xiaohui Niu
- College of Informatics, Huazhong Agricultural University, Wuhan, PR China
| | - Ning Pan
- College of Biomedical Engineering, South Central University for Nationalities, Wuhan, PR China
- Hubei Key Laboratory of Medical Information Analysis and Tumor Diagnosis & Treatment, Wuhan, PR China
| | - Yulin Liu
- Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, PR China
| | - Zilong Yuan
- Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, PR China
| |
Collapse
|
31
|
Automated volumetric radiomic analysis of breast cancer vascularization improves survival prediction in primary breast cancer. Sci Rep 2020; 10:3664. [PMID: 32111898 PMCID: PMC7048934 DOI: 10.1038/s41598-020-60393-9] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2019] [Accepted: 02/04/2020] [Indexed: 12/23/2022] Open
Abstract
To investigate whether automated volumetric radiomic analysis of breast cancer vascularization (VAV) can improve survival prediction in primary breast cancer. 314 consecutive patients with primary invasive breast cancer received standard clinical MRI before the initiation of treatment according to international recommendations. Diagnostic work-up, treatment, and follow-up was done at one tertiary care, academic breast-center (outcome: disease specific survival/DSS vs. disease specific death/DSD). The Nottingham Prognostic Index (NPI) was used as the reference method with which to predict survival of breast cancer. Based on the MRI scans, VAV was accomplished by commercially available, FDA-cleared software. DSD served as endpoint. Integration of VAV into the NPI gave NPIVAV. Prediction of DSD by NPIVAV compared to standard NPI alone was investigated (Cox regression, likelihood-test, predictive accuracy: Harrell's C, Kaplan Meier statistics and corresponding hazard ratios/HR, confidence intervals/CI). DSD occurred in 35 and DSS in 279 patients. Prognostication of the survival outcome by NPI (Harrell's C = 75.3%) was enhanced by VAV (NPIVAV: Harrell's C = 81.0%). Most of all, the NPIVAV identified patients with unfavourable outcome more reliably than NPI alone (hazard ratio/HR = 4.5; confidence interval/CI = 2.14-9.58; P = 0.0001). Automated volumetric radiomic analysis of breast cancer vascularization improved survival prediction in primary breast cancer. Most of all, it optimized the identification of patients at higher risk of an unfavorable outcome. Future studies should integrate MRI as a "gate keeper" in the management of breast cancer patients. Such a "gate keeper" could assist in selecting patients benefitting from more advanced diagnostic procedures (genetic profiling etc.) in order to decide whether are a more aggressive therapy (chemotherapy) is warranted.
Collapse
|
32
|
Three-dimensional radiomics of triple-negative breast cancer: Prediction of systemic recurrence. Sci Rep 2020; 10:2976. [PMID: 32076078 PMCID: PMC7031504 DOI: 10.1038/s41598-020-59923-2] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2019] [Accepted: 02/05/2020] [Indexed: 01/09/2023] Open
Abstract
This paper evaluated 3-dimensional radiomics features of breast magnetic resonance imaging (MRI) as prognostic factors for predicting systemic recurrence in triple-negative breast cancer (TNBC) and validated the results with a different MRI scanner. The Rad score was generated from 3-dimensional radiomic features of MRI for 231 TNBCs (training set (GE scanner), n = 182; validation set (Philips scanner), n = 49). The Clinical and Rad models to predict systemic recurrence were built up and the models were externally validated. In the training set, the Rad score was significantly higher in the group with systemic recurrence (median, −8.430) than the group without (median, −9.873, P < 0.001). The C-index of the Rad model to predict systemic recurrence in the training set was 0.97, which was significantly higher than in the Clinical model (0.879; P = 0.009). When the models were externally validated, the C-index of the Rad model was 0.848, lower than the 0.939 of the Clinical model, although the difference was not statistically significant (P = 0.100). The Rad model for predicting systemic recurrence in TNBC showed a significantly higher C-index than the Clinical model. However, external validation with a different MRI scanner did not show the Rad model to be superior over the Clinical model.
Collapse
|
33
|
Application and Analysis of Biomedical Imaging Technology in Early Diagnosis of Breast Cancer. Methods Mol Biol 2020; 2204:63-73. [PMID: 32710315 DOI: 10.1007/978-1-0716-0904-0_6] [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: 12/14/2022]
Abstract
Breast cancer is the primary malignant tumor that endangers women's health. The incidence of breast cancer is increasing rapidly in recent years. Accurate disease evaluation before treatment is the key to the selection of treatment options. Biomedical imaging technology plays an irreplaceable role in the diagnosis and staging of tumors. Various imaging methods can provide excellent temporal and spatial resolution from multiple levels and perspectives and have become one of the most commonly used means of breast cancer early detection. With the development of radiomics, it has been found that early imaging diagnosis of breast cancer plays an important guiding role in clinical decision-making. The purpose of this study is to explore the characteristics of various breast cancer imaging technologies, promote the development of individualized accurate diagnosis and treatment of imaging, and improve the clinical application value of radiomics in the early diagnosis of breast cancer.
Collapse
|
34
|
Grimm LJ, Mazurowski MA. Breast Cancer Radiogenomics: Current Status and Future Directions. Acad Radiol 2020; 27:39-46. [PMID: 31818385 DOI: 10.1016/j.acra.2019.09.012] [Citation(s) in RCA: 36] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2019] [Revised: 07/17/2019] [Accepted: 09/08/2019] [Indexed: 12/13/2022]
Abstract
Radiogenomics is an area of research that aims to identify associations between imaging phenotypes ("radio-") and tumor genome ("-genomics"). Breast cancer radiogenomics research in particular has been an especially prolific area of investigation in recent years as evidenced by the wide number and variety of publications and conferences presentations. To date, research has primarily been focused on dynamic contrast enhanced pre-operative breast MRI and breast cancer molecular subtypes, but investigations have extended to all breast imaging modalities as well as multiple additional genetic markers including those that are commercially available. Furthermore, both human and computer-extracted features as well as deep learning techniques have been explored. This review will summarize the specific imaging modalities used in radiogenomics analysis, describe the methods of extracting imaging features, and present the types of genomics, molecular, and related information used for analysis. Finally, the limitations and future directions of breast cancer radiogenomics research will be discussed.
Collapse
|
35
|
Measurement Variability in Treatment Response Determination for Non-Small Cell Lung Cancer: Improvements Using Radiomics. J Thorac Imaging 2019; 34:103-115. [PMID: 30664063 DOI: 10.1097/rti.0000000000000390] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2022]
Abstract
Multimodality imaging measurements of treatment response are critical for clinical practice, oncology trials, and the evaluation of new treatment modalities. The current standard for determining treatment response in non-small cell lung cancer (NSCLC) is based on tumor size using the RECIST criteria. Molecular targeted agents and immunotherapies often cause morphological change without reduction of tumor size. Therefore, it is difficult to evaluate therapeutic response by conventional methods. Radiomics is the study of cancer imaging features that are extracted using machine learning and other semantic features. This method can provide comprehensive information on tumor phenotypes and can be used to assess therapeutic response in this new age of immunotherapy. Delta radiomics, which evaluates the longitudinal changes in radiomics features, shows potential in gauging treatment response in NSCLC. It is well known that quantitative measurement methods may be subject to substantial variability due to differences in technical factors and require standardization. In this review, we describe measurement variability in the evaluation of NSCLC and the emerging role of radiomics.
Collapse
|
36
|
Nakamoto T, Takahashi W, Haga A, Takahashi S, Kiryu S, Nawa K, Ohta T, Ozaki S, Nozawa Y, Tanaka S, Mukasa A, Nakagawa K. Prediction of malignant glioma grades using contrast-enhanced T1-weighted and T2-weighted magnetic resonance images based on a radiomic analysis. Sci Rep 2019; 9:19411. [PMID: 31857632 PMCID: PMC6923390 DOI: 10.1038/s41598-019-55922-0] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/08/2019] [Accepted: 12/04/2019] [Indexed: 01/07/2023] Open
Abstract
We conducted a feasibility study to predict malignant glioma grades via radiomic analysis using contrast-enhanced T1-weighted magnetic resonance images (CE-T1WIs) and T2-weighted magnetic resonance images (T2WIs). We proposed a framework and applied it to CE-T1WIs and T2WIs (with tumor region data) acquired preoperatively from 157 patients with malignant glioma (grade III: 55, grade IV: 102) as the primary dataset and 67 patients with malignant glioma (grade III: 22, grade IV: 45) as the validation dataset. Radiomic features such as size/shape, intensity, histogram, and texture features were extracted from the tumor regions on the CE-T1WIs and T2WIs. The Wilcoxon-Mann-Whitney (WMW) test and least absolute shrinkage and selection operator logistic regression (LASSO-LR) were employed to select the radiomic features. Various machine learning (ML) algorithms were used to construct prediction models for the malignant glioma grades using the selected radiomic features. Leave-one-out cross-validation (LOOCV) was implemented to evaluate the performance of the prediction models in the primary dataset. The selected radiomic features for all folds in the LOOCV of the primary dataset were used to perform an independent validation. As evaluation indices, accuracies, sensitivities, specificities, and values for the area under receiver operating characteristic curve (or simply the area under the curve (AUC)) for all prediction models were calculated. The mean AUC value for all prediction models constructed by the ML algorithms in the LOOCV of the primary dataset was 0.902 ± 0.024 (95% CI (confidence interval), 0.873-0.932). In the independent validation, the mean AUC value for all prediction models was 0.747 ± 0.034 (95% CI, 0.705-0.790). The results of this study suggest that the malignant glioma grades could be sufficiently and easily predicted by preparing the CE-T1WIs, T2WIs, and tumor delineations for each patient. Our proposed framework may be an effective tool for preoperatively grading malignant gliomas.
Collapse
Affiliation(s)
- Takahiro Nakamoto
- Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
- Research Fellow of Japan Society for the Promotion of Science, 5-3-1 Kojimachi, Chiyoda-ku, Tokyo, 102-0083, Japan
| | - Wataru Takahashi
- Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan.
| | - Akihiro Haga
- Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
- Department of Medical Image Informatics, Tokushima University, 3-18-15 Kuramoto-cho, Tokushima, 770-8503, Japan
| | - Satoshi Takahashi
- Department of Neurosurgery, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
| | - Shigeru Kiryu
- Department of Radiology, International University of Health and Welfare Hospital, 537-3 Iguchi, Nasushiobara, Tochigi, 329-2763, Japan
| | - Kanabu Nawa
- Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
| | - Takeshi Ohta
- Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
| | - Sho Ozaki
- Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
| | - Yuki Nozawa
- Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
| | - Shota Tanaka
- Department of Neurosurgery, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
| | - Akitake Mukasa
- Department of Neurosurgery, Graduate School of Medical Sciences, Kumamoto University, 1-1-1 Honjo, Chuo-ku, Kumamoto, 860-8556, Japan
| | - Keiichi Nakagawa
- Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
| |
Collapse
|
37
|
Abstract
OBJECTIVE. The purpose of this article is to review the nascent field of radiomics in cardiac MRI. CONCLUSION. Cardiac MRI produces a large number of images in a fairly inefficient manner with sometimes limited clinical application. In the era of precision medicine, there is increasing need for imaging to account for a broader array of diseases in an efficient and objective manner. Radiomics, the extraction and analysis of quantitative imaging features from medical imaging, may offer potential solutions to this need.
Collapse
|
38
|
Zhu Z, Albadawy E, Saha A, Zhang J, Harowicz MR, Mazurowski MA. Deep learning for identifying radiogenomic associations in breast cancer. Comput Biol Med 2019; 109:85-90. [PMID: 31048129 DOI: 10.1016/j.compbiomed.2019.04.018] [Citation(s) in RCA: 66] [Impact Index Per Article: 13.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2018] [Revised: 03/05/2019] [Accepted: 04/20/2019] [Indexed: 11/27/2022]
Abstract
RATIONALE AND OBJECTIVES To determine whether deep learning models can distinguish between breast cancer molecular subtypes based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). MATERIALS AND METHODS In this institutional review board-approved single-center study, we analyzed DCE-MR images of 270 patients at our institution. Lesions of interest were identified by radiologists. The task was to automatically determine whether the tumor is of the Luminal A subtype or of another subtype based on the MR image patches representing the tumor. Three different deep learning approaches were used to classify the tumor according to their molecular subtypes: learning from scratch where only tumor patches were used for training, transfer learning where networks pre-trained on natural images were fine-tuned using tumor patches, and off-the-shelf deep features where the features extracted by neural networks trained on natural images were used for classification with a support vector machine. Network architectures utilized in our experiments were GoogleNet, VGG, and CIFAR. We used 10-fold crossvalidation method for validation and area under the receiver operating characteristic (AUC) as the measure of performance. RESULTS The best AUC performance for distinguishing molecular subtypes was 0.65 (95% CI:[0.57,0.71]) and was achieved by the off-the-shelf deep features approach. The highest AUC performance for training from scratch was 0.58 (95% CI:[0.51,0.64]) and the best AUC performance for transfer learning was 0.60 (95% CI:[0.52,0.65]) respectively. For the off-the-shelf approach, the features extracted from the fully connected layer performed the best. CONCLUSION Deep learning may play a role in discovering radiogenomic associations in breast cancer.
Collapse
Affiliation(s)
- Zhe Zhu
- Department of Radiology, Duke University, USA.
| | | | | | - Jun Zhang
- Department of Radiology, Duke University, USA.
| | | | - Maciej A Mazurowski
- Department of Radiology and Department of Electrical and Computer Engineering, Duke University, USA.
| |
Collapse
|
39
|
Saeedi E, Dezhkam A, Beigi J, Rastegar S, Yousefi Z, Mehdipour LA, Abdollahi H, Tanha K. Radiomic Feature Robustness and Reproducibility in Quantitative Bone Radiography: A Study on Radiologic Parameter Changes. J Clin Densitom 2019; 22:203-213. [PMID: 30078528 DOI: 10.1016/j.jocd.2018.06.004] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/18/2018] [Revised: 06/16/2018] [Accepted: 06/20/2018] [Indexed: 10/28/2022]
Abstract
The purpose of this study was to investigate the robustness of different radiography radiomic features over different radiologic parameters including kV, mAs, filtration, tube angles, and source skin distance (SSD). A tibia bone phantom was prepared and all imaging studies was conducted on this phantom. Different radiologic parameters including kV, mAs, filtration, tube angles, and SSD were studied. A region of interest was drawn on the images and many features from different feature sets including histogram, gradient, run-length matrix, co-occurrence matrix, autoregressive model, and wavelet derived parameters were extracted. All radiomic features were categorized based on coefficient of variation (COV). Bland-Altman analysis also was used to evaluate the mean, standard deviation, and upper/lower reproducibility limits for radiomic features in response to variation in each testing parameters. Results on COV in all features showed that 22%, 34%, and 45% of features were most robust (COV ≤ 5%) against kV, mAs, and SSD respectively and there was no robust features against filtration and tube angle. Also, all features (100%) and 76% of which showed large variations (COV > 20%) against filtrations and tube angle respectively. Autoregressive model feature set has no robust features against all radiologic parameters. Features including sum-average, sum-entropy, correlation, mean, and percentile (50, 90, and 99) belong to co-occurrence matrix and histogram feature sets were found as most robust features. Bland-Altman analysis showed the high reproducibity of some feature sets against radiologic parameter changes. The results presented here indicated that radiologic parameters have great impacts on radiomic feature values and caution should be taken into account when work with these features. In quantitative bone studies, robust features with low COV can be selected for clinical or research applications. Reproducible features also can be obtained using Bland-Altman analysis.
Collapse
Affiliation(s)
- Ehsan Saeedi
- Student Research Committee, Paramedical Faculty, Rafsanjan University of Medical Sciences, Rafsanjan, Iran; Department of Radiology Technology, Paramedical Faculty, Rafsanjan University of Medical Sciences, Rafsanjan, Iran
| | - Ali Dezhkam
- Student Research Committee, Paramedical Faculty, Rafsanjan University of Medical Sciences, Rafsanjan, Iran; Department of Radiology Technology, Paramedical Faculty, Rafsanjan University of Medical Sciences, Rafsanjan, Iran
| | - Jalal Beigi
- Student Research Committee, Paramedical Faculty, Rafsanjan University of Medical Sciences, Rafsanjan, Iran; Department of Radiology Technology, Paramedical Faculty, Rafsanjan University of Medical Sciences, Rafsanjan, Iran
| | - Sajjad Rastegar
- Student Research Committee, Paramedical Faculty, Rafsanjan University of Medical Sciences, Rafsanjan, Iran; Department of Radiology Technology, Paramedical Faculty, Rafsanjan University of Medical Sciences, Rafsanjan, Iran
| | - Zahra Yousefi
- Student Research Committee, Allied Medicine Faculty, Iran University of Medical Sciences, Tehran, Iran; Department of Radiation Sciences, Allied Medicine Faculty, Iran University of Medical Sciences, Tehran, Iran
| | - Lotf Ali Mehdipour
- Department of Radiology Technology, Paramedical Faculty, Rafsanjan University of Medical Sciences, Rafsanjan, Iran.
| | - Hamid Abdollahi
- Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran.
| | - Kiarash Tanha
- Department of Biostatistics, School of Public Health, Iran University of Medical Sciences, Tehran, Iran
| |
Collapse
|
40
|
Mazurowski MA, Saha A, Harowicz MR, Cain EH, Marks JR, Marcom PK. Association of distant recurrence-free survival with algorithmically extracted MRI characteristics in breast cancer. J Magn Reson Imaging 2019; 49:e231-e240. [PMID: 30672045 DOI: 10.1002/jmri.26648] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2018] [Revised: 12/23/2018] [Accepted: 12/26/2018] [Indexed: 01/01/2023] Open
Abstract
BACKGROUND While important in diagnosis of breast cancer, the scientific assessment of the role of imaging in prognosis of outcomes and treatment planning is limited. PURPOSE To evaluate the potential of using quantitative imaging variables for stratifying risk of distant recurrence in breast cancer patients. STUDY TYPE Retrospective. POPULATION In all, 892 female invasive breast cancer patients. SEQUENCE Dynamic contrast-enhanced MRI with field strength 1.5 T and 3 T. ASSESSMENT Computer vision algorithms were applied to extract a comprehensive set of 529 imaging features quantifying size, shape, enhancement patterns, and heterogeneity of the tumors and the surrounding tissue. Using a development set with 446 cases, we selected 20 imaging features with high prognostic value. STATISTICAL TESTS We evaluated the imaging features using an independent test set with 446 cases. The principal statistical measure was a concordance index between individual imaging features and patient distant recurrence-free survival (DRFS). RESULTS The strongest association with DRFS that persisted after controlling for known prognostic clinical and pathology variables was found for signal enhancement ratio (SER) partial tumor volume (concordance index [C] = 0.768, 95% confidence interval [CI]: 0.679-0.856), tumor major axis length (C = 0.742, 95% CI: 0.650-0.834), kurtosis of the SER map within tumor (C = 0.640, 95% CI: 0.521-0.760), tumor cluster shade (C = 0.313, 95% CI: 0.216-0.410), and washin rate information measure of correlation (C = 0.702, 95% CI: 0.601-0.803). DATA CONCLUSION Quantitative assessment of breast cancer features seen in a routine breast MRI might be able to be used for assessment of risk of distant recurrence. LEVEL OF EVIDENCE 4 Technical Efficacy: Stage 6 J. Magn. Reson. Imaging 2019.
Collapse
Affiliation(s)
- Maciej A Mazurowski
- Department of Radiology, Duke University School of Medicine, Durham, North Carolina, USA
| | - Ashirbani Saha
- Department of Radiology, Duke University School of Medicine, Durham, North Carolina, USA
| | - Michael R Harowicz
- Department of Radiology, Duke University School of Medicine, Durham, North Carolina, USA.,Department of Radiology, Johns Hopkins University, Baltimore, Maryland, USA
| | - Elizabeth Hope Cain
- Department of Radiology, Duke University School of Medicine, Durham, North Carolina, USA
| | - Jeffrey R Marks
- Department of Radiology, Duke University School of Medicine, Durham, North Carolina, USA.,Department of Surgery, Duke University School of Medicine, Durham, North Carolina, USA
| | - P Kelly Marcom
- Department of Radiology, Duke University School of Medicine, Durham, North Carolina, USA.,Department of Medicine, Duke University School of Medicine, Durham, North Carolina, USA
| |
Collapse
|
41
|
Saha A, Grimm LJ, Ghate SV, Kim CE, Soo MS, Yoon SC, Mazurowski MA. Machine learning-based prediction of future breast cancer using algorithmically measured background parenchymal enhancement on high-risk screening MRI. J Magn Reson Imaging 2019; 50:456-464. [PMID: 30648316 DOI: 10.1002/jmri.26636] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2018] [Revised: 12/16/2018] [Accepted: 12/18/2018] [Indexed: 12/14/2022] Open
Abstract
BACKGROUND Preliminary work has demonstrated that background parenchymal enhancement (BPE) assessed by radiologists is predictive of future breast cancer in women undergoing high-risk screening MRI. Algorithmically assessed measures of BPE offer a more precise and reproducible means of measuring BPE than human readers and thus might improve the predictive performance of future cancer development. PURPOSE To determine if algorithmically extracted imaging features of BPE on screening breast MRI in high-risk women are associated with subsequent development of cancer. STUDY TYPE Case-control study. POPULATION In all, 133 women at high risk for developing breast cancer; 46 of these patients developed breast cancer subsequently over a follow-up period of 2 years. FIELD STRENGTH/SEQUENCE 5 T or 3.0 T T1 -weighted precontrast fat-saturated and nonfat-saturated sequences and postcontrast nonfat-saturated sequences. ASSESSMENT Automatic features of BPE were extracted with a computer algorithm. Subjective BPE scores from five breast radiologists (blinded to clinical outcomes) were also available. STATISTICAL TESTS Leave-one-out crossvalidation for a multivariate logistic regression model developed using the automatic features and receiver operating characteristic (ROC) analysis were performed to calculate the area under the curve (AUC). Comparison of automatic features and subjective features was performed using a generalized regression model and the P-value was obtained. Odds ratios for automatic and subjective features were compared. RESULTS The multivariate model discriminated patients who developed cancer from the patients who did not, with an AUC of 0.70 (95% confidence interval: 0.60-0.79, P < 0.001). The imaging features remained independently predictive of subsequent development of cancer (P < 0.003) when compared with the subjective BPE assessment of the readers. DATA CONCLUSION Automatically extracted BPE measurements may potentially be used to further stratify risk in patients undergoing high-risk screening MRI. LEVEL OF EVIDENCE 3 Technical Efficacy: Stage 5 J. Magn. Reson. Imaging 2019;50:456-464.
Collapse
Affiliation(s)
- Ashirbani Saha
- Department of Radiology, Duke University School of Medicine, Durham, North Carolina, USA
| | - Lars J Grimm
- Department of Radiology, Duke University School of Medicine, Durham, North Carolina, USA
| | - Sujata V Ghate
- Department of Radiology, Duke University School of Medicine, Durham, North Carolina, USA
| | - Connie E Kim
- Department of Radiology, Duke University School of Medicine, Durham, North Carolina, USA
| | - Mary S Soo
- Department of Radiology, Duke University School of Medicine, Durham, North Carolina, USA
| | - Sora C Yoon
- Department of Radiology, Duke University School of Medicine, Durham, North Carolina, USA
| | - Maciej A Mazurowski
- Department of Radiology, Duke University School of Medicine, Durham, North Carolina, USA.,Department of Electrical and Computer Eng., Duke University, Durham, North Carolina, USA.,Duke University Medical Physics Program, Durham, North Carolina, USA
| |
Collapse
|
42
|
Buch K, Kuno H, Qureshi MM, Li B, Sakai O. Quantitative variations in texture analysis features dependent on MRI scanning parameters: A phantom model. J Appl Clin Med Phys 2018; 19:253-264. [PMID: 30369010 PMCID: PMC6236836 DOI: 10.1002/acm2.12482] [Citation(s) in RCA: 50] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2018] [Revised: 09/22/2018] [Accepted: 09/24/2018] [Indexed: 12/22/2022] Open
Abstract
Objectives To evaluate the influence of MRI scanning parameters on texture analysis features. Methods Publicly available data from the Reference Image Database to Evaluate Therapy Response (RIDER) project sponsored by The Cancer Imaging Archive included MRIs on a phantom comprised of 18 25‐mm doped, gel‐filled tubes, and 1 20‐mm tube containing 0.25 mM Gd‐DTPA (EuroSpinII Test Object5, Diagnostic Sonar, Ltd, West Lothian, Scotland). MRIs performed on a 1.5 T GE HD, 1.5 T Siemens Espree (VB13), or 3.0 T GE HD with TwinSpeed gradients with an eight‐channel head coil included T1WIs with multiple flip angles (flip‐angle = 2,5,10,15,20,25,30), TR/TE = 4.09–5.47/0.90–1.35 ms, NEX = 1 and DCE with 30° flip‐angle, TR/TE=4.09–5.47/0.90–1.35, and NEX = 1,4. DICOM data were imported into an in‐house developed texture analysis program which extracted 41‐texture features including histogram, gray‐level co‐occurrence matrix (GLCM), and gray‐level run‐length (GLRL). Two‐tailed t tests, corrected for multiple comparisons (Q values) were calculated to compare changes in texture features with variations in MRI scanning parameters (magnet strength, flip‐angle, number of excitations (NEX), scanner platform). Results Significant differences were seen in histogram features (mean, median, standard deviation, range) with variations in NEX (Q = 0.003–0.045) and scanner platform (Q < 0.0001), GLCM features (entropy, contrast, energy, and homogeneity) with NEX (Q = 0.001–0.018) and scanner platform (Q < 0.0001), GLRL features (long‐run emphasis, high gray‐level run emphasis, high gray‐level emphasis) with magnet strength (Q = 0.0003), NEX (Q = 0.003–0.022) and scanner platform (Q < 0.0001). Conclusion Significant differences were seen in many texture features with variations in MRI acquisition emphasizing the need for standardized MRI technique.
Collapse
Affiliation(s)
- Karen Buch
- Department of Radiology, Boston Medical Center, Boston University School of Medicine, Boston, MA, USA
| | - Hirofumi Kuno
- Department of Radiology, Boston Medical Center, Boston University School of Medicine, Boston, MA, USA.,Department of Diagnostic Radiology, National Cancer Center Hospital East, Kashiwa, Chiba, Japan
| | - Muhammad M Qureshi
- Departments of Radiology and Radiation Oncology, Boston Medical Center, Boston University School of Medicine, Boston, MA, USA
| | - Baojun Li
- Department of Radiology, Boston Medical Center, Boston University School of Medicine, Boston, MA, USA
| | - Osamu Sakai
- Departments of Radiology, Otolaryngology - Head and Neck Surgery, and Radiation Oncology, Boston Medical Center, Boston University School of Medicine, Boston, MA, USA
| |
Collapse
|
43
|
Cain EH, Saha A, Harowicz MR, Marks JR, Marcom PK, Mazurowski MA. Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set. Breast Cancer Res Treat 2018; 173:455-463. [PMID: 30328048 DOI: 10.1007/s10549-018-4990-9] [Citation(s) in RCA: 96] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2018] [Accepted: 10/01/2018] [Indexed: 02/07/2023]
Abstract
PURPOSE To determine whether a multivariate machine learning-based model using computer-extracted features of pre-treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can predict pathologic complete response (pCR) to neoadjuvant therapy (NAT) in breast cancer patients. METHODS Institutional review board approval was obtained for this retrospective study of 288 breast cancer patients at our institution who received NAT and had a pre-treatment breast MRI. A comprehensive set of 529 radiomic features was extracted from each patient's pre-treatment MRI. The patients were divided into equal groups to form a training set and an independent test set. Two multivariate machine learning models (logistic regression and a support vector machine) based on imaging features were trained to predict pCR in (a) all patients with NAT, (b) patients with neoadjuvant chemotherapy (NACT), and (c) triple-negative or human epidermal growth factor receptor 2-positive (TN/HER2+) patients who had NAT. The multivariate models were tested using the independent test set, and the area under the receiver operating characteristics (ROC) curve (AUC) was calculated. RESULTS Out of the 288 patients, 64 achieved pCR. The AUC values for predicting pCR in TN/HER+ patients who received NAT were significant (0.707, 95% CI 0.582-0.833, p < 0.002). CONCLUSIONS The multivariate models based on pre-treatment MRI features were able to predict pCR in TN/HER2+ patients.
Collapse
Affiliation(s)
- Elizabeth Hope Cain
- Department of Radiology, Duke University School of Medicine, 2301 Erwin Road, Durham, NC, 27705, USA.
| | - Ashirbani Saha
- Department of Radiology, Duke University School of Medicine, 2301 Erwin Road, Durham, NC, 27705, USA
| | - Michael R Harowicz
- Department of Radiology, Duke University School of Medicine, 2301 Erwin Road, Durham, NC, 27705, USA.,Department of Radiology, Johns Hopkins University, Baltimore, MD, USA
| | - Jeffrey R Marks
- Department of Surgery, Duke University School of Medicine, 2301 Erwin Road, Durham, NC, 27705, USA
| | - P Kelly Marcom
- Department of Medicine, Duke University School of Medicine, 2301 Erwin Road, Durham, NC, 27705, USA
| | - Maciej A Mazurowski
- Department of Radiology, Duke University School of Medicine, 2301 Erwin Road, Durham, NC, 27705, USA.,Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA
| |
Collapse
|
44
|
A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features. Br J Cancer 2018; 119:508-516. [PMID: 30033447 PMCID: PMC6134102 DOI: 10.1038/s41416-018-0185-8] [Citation(s) in RCA: 102] [Impact Index Per Article: 17.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2018] [Revised: 06/14/2018] [Accepted: 06/25/2018] [Indexed: 02/07/2023] Open
Abstract
BACKGROUND Recent studies showed preliminary data on associations of MRI-based imaging phenotypes of breast tumours with breast cancer molecular, genomic, and related characteristics. In this study, we present a comprehensive analysis of this relationship. METHODS We analysed a set of 922 patients with invasive breast cancer and pre-operative MRI. The MRIs were analysed by a computer algorithm to extract 529 features of the tumour and the surrounding tissue. Machine-learning-based models based on the imaging features were trained using a portion of the data (461 patients) to predict the following molecular, genomic, and proliferation characteristics: tumour surrogate molecular subtype, oestrogen receptor, progesterone receptor and human epidermal growth factor status, as well as a tumour proliferation marker (Ki-67). Trained models were evaluated on the set of the remaining 461 patients. RESULTS Multivariate models were predictive of Luminal A subtype with AUC = 0.697 (95% CI: 0.647-0.746, p < .0001), triple negative breast cancer with AUC = 0.654 (95% CI: 0.589-0.727, p < .0001), ER status with AUC = 0.649 (95% CI: 0.591-0.705, p < .001), and PR status with AUC = 0.622 (95% CI: 0.569-0.674, p < .0001). Associations between individual features and subtypes we also found. CONCLUSIONS There is a moderate association between tumour molecular biomarkers and algorithmically assessed imaging features.
Collapse
|
45
|
Saha A, Harowicz MR, Mazurowski MA. Breast cancer MRI radiomics: An overview of algorithmic features and impact of inter-reader variability in annotating tumors. Med Phys 2018; 45:3076-3085. [PMID: 29663411 DOI: 10.1002/mp.12925] [Citation(s) in RCA: 45] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2017] [Revised: 03/01/2018] [Accepted: 04/04/2018] [Indexed: 12/30/2022] Open
Abstract
PURPOSE To review features used in MRI radiomics of breast cancer and study the inter-reader stability of the features. METHODS We implemented 529 algorithmic features that can be extracted from tumor and fibroglandular tissue (FGT) in breast MRIs. The features were identified based on a review of the existing literature with consideration of their usage, prognostic ability, and uniqueness. The set was then extended so that it comprehensively describes breast cancer imaging characteristics. The features were classified into 10 groups based on the type of data used to extract them and the type of calculation being performed. For the assessment of inter-reader variability, four fellowship-trained readers annotated tumors on preoperative dynamic contrast-enhanced MRIs for 50 breast cancer patients. Based on the annotations, an algorithm automatically segmented the image and extracted all features resulting in one set of features for each reader. For a given feature, the inter-reader stability was defined as the intraclass correlation coefficient (ICC) computed using the feature values obtained through all readers for all cases. RESULTS The average inter-reader stability for all features was 0.8474 (95% CI: 0.8068-0.8858). The mean inter-reader stability was lower for tumor-based features (0.6348, 95% CI: 0.5391-0.7257) than FGT-based features (0.9984, 95% CI: 0.9970-0.9992). The feature group with the highest inter-reader stability quantifies breast and FGT volume. The feature group with the lowest inter-reader stability quantifies variations in tumor enhancement. CONCLUSIONS Breast MRI radiomics features widely vary in terms of their stability in the presence of inter-reader variability. Appropriate measures need to be taken for reducing this variability in tumor-based radiomics.
Collapse
Affiliation(s)
- Ashirbani Saha
- Department of Radiology, Duke University School of Medicine, 2424 Erwin Road, Suite 302, Durham, NC, 27705, USA
| | - Michael R Harowicz
- Department of Radiology, Duke University School of Medicine, 2424 Erwin Road, Suite 302, Durham, NC, 27705, USA
| | - Maciej A Mazurowski
- Department of Radiology, Duke University School of Medicine, 2424 Erwin Road, Suite 302, Durham, NC, 27705, USA.,Department of Electrical and Computer Engineering, Duke University, Box 90291, Durham, NC, 27708, USA.,Duke University Medical Physics Program, DUMC 2729, 2424 Erwin Road, Suite 101, Durham, NC, 27705, USA
| |
Collapse
|
46
|
Saha A, Harowicz MR, Wang W, Mazurowski MA. A study of association of Oncotype DX recurrence score with DCE-MRI characteristics using multivariate machine learning models. J Cancer Res Clin Oncol 2018; 144:799-807. [PMID: 29427210 PMCID: PMC5920720 DOI: 10.1007/s00432-018-2595-7] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2017] [Accepted: 01/23/2018] [Indexed: 01/09/2023]
Abstract
PURPOSE To determine whether multivariate machine learning models of algorithmically assessed magnetic resonance imaging (MRI) features from breast cancer patients are associated with Oncotype DX (ODX) test recurrence scores. METHODS A set of 261 female patients with invasive breast cancer, pre-operative dynamic contrast enhanced magnetic resonance (DCE-MR) images and available ODX score at our institution was identified. A computer algorithm extracted a comprehensive set of 529 features from the DCE-MR images of these patients. The set of patients was divided into a training set and a test set. Using the training set we developed two machine learning-based models to discriminate (1) high ODX scores from intermediate and low ODX scores, and (2) high and intermediate ODX scores from low ODX scores. The performance of these models was evaluated on the independent test set. RESULTS High against low and intermediate ODX scores were predicted by the multivariate model with AUC 0.77 (95% CI 0.56-0.98, p < 0.003). Low against intermediate and high ODX score was predicted with AUC 0.51 (95% CI 0.41-0.61, p = 0.75). CONCLUSION A moderate association between imaging and ODX score was identified. The evaluated models currently do not warrant replacement of ODX with imaging alone.
Collapse
Affiliation(s)
- Ashirbani Saha
- Department of Radiology, Duke University School of Medicine, 2424 Erwin Road, Suite 302, Durham, NC, 27705, USA.
| | - Michael R Harowicz
- Department of Radiology, Duke University School of Medicine, 2424 Erwin Road, Suite 302, Durham, NC, 27705, USA
| | - Weiyao Wang
- Department of Mathematics, Duke University, 120 Science Drive, 117 Physics Building, Durham, NC, 27708, USA
| | - Maciej A Mazurowski
- Department of Radiology, Duke University School of Medicine, 2424 Erwin Road, Suite 302, Durham, NC, 27705, USA
- Department of Electrical and Computer Engineering, Duke University, Box 90291, Durham, NC, 27708, USA
- Duke University Medical Physics Graduate Program, 2424 Erwin Road, Suite 101, Durham, NC, 27705, USA
| |
Collapse
|