51
|
Prediction of breast cancer molecular subtypes on DCE-MRI using convolutional neural network with transfer learning between two centers. Eur Radiol 2020; 31:2559-2567. [PMID: 33001309 DOI: 10.1007/s00330-020-07274-x] [Citation(s) in RCA: 56] [Impact Index Per Article: 14.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2020] [Revised: 07/27/2020] [Accepted: 09/09/2020] [Indexed: 12/11/2022]
Abstract
OBJECTIVES To apply deep learning algorithms using a conventional convolutional neural network (CNN) and a recurrent CNN to differentiate three breast cancer molecular subtypes on MRI. METHODS A total of 244 patients were analyzed, 99 in training dataset scanned at 1.5 T and 83 in testing-1 and 62 in testing-2 scanned at 3 T. Patients were classified into 3 subtypes based on hormonal receptor (HR) and HER2 receptor: (HR+/HER2-), HER2+, and triple negative (TN). Only images acquired in the DCE sequence were used in the analysis. The smallest bounding box covering tumor ROI was used as the input for deep learning to develop the model in the training dataset, by using a conventional CNN and the convolutional long short-term memory (CLSTM). Then, transfer learning was applied to re-tune the model using testing-1(2) and evaluated in testing-2(1). RESULTS In the training dataset, the mean accuracy evaluated using tenfold cross-validation was higher by using CLSTM (0.91) than by using CNN (0.79). When the developed model was applied to the independent testing datasets, the accuracy was 0.4-0.5. With transfer learning by re-tuning parameters in testing-1, the mean accuracy reached 0.91 by CNN and 0.83 by CLSTM, and improved accuracy in testing-2 from 0.47 to 0.78 by CNN and from 0.39 to 0.74 by CLSTM. Overall, transfer learning could improve the classification accuracy by greater than 30%. CONCLUSIONS The recurrent network using CLSTM could track changes in signal intensity during DCE acquisition, and achieved a higher accuracy compared with conventional CNN during training. For datasets acquired using different settings, transfer learning can be applied to re-tune the model and improve accuracy. KEY POINTS • Deep learning can be applied to differentiate breast cancer molecular subtypes. • The recurrent neural network using CLSTM could track the change of signal intensity in DCE images, and achieved a higher accuracy compared with conventional CNN during training. • For datasets acquired using different scanners with different imaging protocols, transfer learning provided an efficient method to re-tune the classification model and improve accuracy.
Collapse
|
52
|
Liu MZ, Mutasa S, Chang P, Siddique M, Jambawalikar S, Ha R. A novel CNN algorithm for pathological complete response prediction using an I-SPY TRIAL breast MRI database. Magn Reson Imaging 2020; 73:148-151. [PMID: 32889091 DOI: 10.1016/j.mri.2020.08.021] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/16/2020] [Revised: 08/13/2020] [Accepted: 08/27/2020] [Indexed: 12/12/2022]
Abstract
PURPOSE To apply our convolutional neural network (CNN) algorithm to predict neoadjuvant chemotherapy (NAC) response using the I-SPY TRIAL breast MRI dataset. METHODS From the I-SPY TRIAL breast MRI database, 131 patients from 9 institutions were successfully downloaded for analysis. First post-contrast MRI images were used for 3D segmentation using 3D slicer. Our CNN was implemented entirely of 3 × 3 convolutional kernels and linear layers. The convolutional kernels consisted of 6 residual layers, totaling 12 convolutional layers. Dropout with a 0.5 keep probability and L2 normalization was utilized. Training was implemented by using the Adam optimizer. A 5-fold cross validation was used for performance evaluation. Software code was written in Python using the TensorFlow module on a Linux workstation with one NVidia Titan X GPU. RESULTS Of 131 patients, 40 patients achieved pCR following NAC (group 1) and 91 patients did not achieve pCR following NAC (group 2). Diagnostic accuracy of our CNN two classification model distinguishing patients with pCR vs non-pCR was 72.5 (SD ± 8.4), with sensitivity 65.5% (SD ± 28.1) and specificity of 78.9% (SD ± 15.2). The area under a ROC Curve (AUC) was 0.72 (SD ± 0.08). CONCLUSION It is feasible to use our CNN algorithm to predict NAC response in patients using a multi-institution dataset.
Collapse
Affiliation(s)
- Michael Z Liu
- Department of Medical Physics, Columbia University Medical Center, 177 Ft. Washington Ave., Milstein Bldg Room 3-124B, New York, NY, United States of America.
| | - Simukayi Mutasa
- Department of Radiology, Columbia University Medical Center, 622 West 168th Street, PB-1-301, New York, NY, United States of America.
| | - Peter Chang
- Department of Radiological Sciences, Center for Artificial Intelligence in Diagnostic Medicine (CAIDM), University of California, Irvine, Calit2 Building, Suite 4500, 4100 E. Peltason Drive, Irvine, CA, United States of America.
| | - Maham Siddique
- Department of Radiology, Columbia University Medical Center, 622 West 168th Street, PB-1-301, New York, NY, United States of America.
| | - Sachin Jambawalikar
- Department of Medical Physics, Columbia University Medical Center, 177 Ft. Washington Ave., Milstein Bldg Room 3-124B, New York, NY, United States of America.
| | - Richard Ha
- Breast Imaging Section, New York Presbyterian Hospital, Columbia University Medical Center, 622 West 168th Street, PB-1-301, New York, NY 10032, United States of America.
| |
Collapse
|
53
|
Mutasa S, Sun S, Ha R. Understanding artificial intelligence based radiology studies: What is overfitting? Clin Imaging 2020; 65:96-99. [PMID: 32387803 PMCID: PMC8150901 DOI: 10.1016/j.clinimag.2020.04.025] [Citation(s) in RCA: 36] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2020] [Revised: 04/10/2020] [Accepted: 04/17/2020] [Indexed: 12/14/2022]
Abstract
Artificial intelligence (AI) is a broad umbrella term used to encompass a wide variety of subfields dedicated to creating algorithms to perform tasks that mimic human intelligence. As AI development grows closer to clinical integration, radiologists will need to become familiar with the principles of artificial intelligence to properly evaluate and use this powerful tool. This series aims to explain certain basic concepts of artificial intelligence, and their applications in medical imaging starting with a concept of overfitting.
Collapse
Affiliation(s)
- Simukayi Mutasa
- Columbia University Medical Center, New York Presbyterian Hospital, 622 West 168th Street, PB-1-301, New York, NY 10032, United States of America.
| | - Shawn Sun
- Columbia University Medical Center, New York Presbyterian Hospital, 622 West 168th Street, PB-1-301, New York, NY 10032, United States of America.
| | - Richard Ha
- Columbia University Medical Center, New York Presbyterian Hospital, 622 West 168th Street, PB-1-301, New York, NY 10032, United States of America.
| |
Collapse
|
54
|
Meyer-Bäse A, Morra L, Meyer-Bäse U, Pinker K. Current Status and Future Perspectives of Artificial Intelligence in Magnetic Resonance Breast Imaging. CONTRAST MEDIA & MOLECULAR IMAGING 2020; 2020:6805710. [PMID: 32934610 PMCID: PMC7474774 DOI: 10.1155/2020/6805710] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/09/2020] [Revised: 04/17/2020] [Accepted: 05/28/2020] [Indexed: 12/12/2022]
Abstract
Recent advances in artificial intelligence (AI) and deep learning (DL) have impacted many scientific fields including biomedical maging. Magnetic resonance imaging (MRI) is a well-established method in breast imaging with several indications including screening, staging, and therapy monitoring. The rapid development and subsequent implementation of AI into clinical breast MRI has the potential to affect clinical decision-making, guide treatment selection, and improve patient outcomes. The goal of this review is to provide a comprehensive picture of the current status and future perspectives of AI in breast MRI. We will review DL applications and compare them to standard data-driven techniques. We will emphasize the important aspect of developing quantitative imaging biomarkers for precision medicine and the potential of breast MRI and DL in this context. Finally, we will discuss future challenges of DL applications for breast MRI and an AI-augmented clinical decision strategy.
Collapse
Affiliation(s)
- Anke Meyer-Bäse
- Department of Scientific Computing, Florida State University, Tallahassee, Florida 32310-4120, USA
| | - Lia Morra
- Dipartimento di Automatica e Informatica, Politecnico di Torino, Torino, Italy
| | - Uwe Meyer-Bäse
- Department of Electrical and Computer Engineering, Florida A&M University and Florida State University, Tallahassee, Florida 32310-4120, USA
| | - Katja Pinker
- Department of Biomedical Imaging and Image-Guided Therapy, Division of Molecular and Gender Imaging, Medical University of Vienna, Vienna, Austria
- Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, New York 10065, USA
| |
Collapse
|
55
|
Trivizakis E, Papadakis GZ, Souglakos I, Papanikolaou N, Koumakis L, Spandidos DA, Tsatsakis A, Karantanas AH, Marias K. Artificial intelligence radiogenomics for advancing precision and effectiveness in oncologic care (Review). Int J Oncol 2020; 57:43-53. [PMID: 32467997 PMCID: PMC7252460 DOI: 10.3892/ijo.2020.5063] [Citation(s) in RCA: 40] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2020] [Accepted: 05/05/2020] [Indexed: 12/11/2022] Open
Abstract
The new era of artificial intelligence (AI) has introduced revolutionary data-driven analysis paradigms that have led to significant advancements in information processing techniques in the context of clinical decision-support systems. These advances have created unprecedented momentum in computational medical imaging applications and have given rise to new precision medicine research areas. Radiogenomics is a novel research field focusing on establishing associations between radiological features and genomic or molecular expression in order to shed light on the underlying disease mechanisms and enhance diagnostic procedures towards personalized medicine. The aim of the current review was to elucidate recent advances in radiogenomics research, focusing on deep learning with emphasis on radiology and oncology applications. The main deep learning radiogenomics architectures, together with the clinical questions addressed, and the achieved genetic or molecular correlations are presented, while a performance comparison of the proposed methodologies is conducted. Finally, current limitations, potentially understudied topics and future research directions are discussed.
Collapse
Affiliation(s)
- Eleftherios Trivizakis
- Computational Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece
| | - Georgios Z Papadakis
- Computational Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece
| | - Ioannis Souglakos
- Laboratory of Translational Oncology, Medical School, University of Crete, 71003 Heraklion, Greece
| | - Nikolaos Papanikolaou
- Computational Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece
| | - Lefteris Koumakis
- Computational Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece
| | - Demetrios A Spandidos
- Laboratory of Clinical Virology, Medical School, University of Crete, 71003 Heraklion, Greece
| | - Aristidis Tsatsakis
- Laboratory of Forensic Sciences and Toxicology, Medical School, University of Crete, 71003 Heraklion, Greece
| | - Apostolos H Karantanas
- Computational Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece
| | - Kostas Marias
- Computational Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece
| |
Collapse
|
56
|
Artificial intelligence and machine learning in nephropathology. Kidney Int 2020; 98:65-75. [PMID: 32475607 DOI: 10.1016/j.kint.2020.02.027] [Citation(s) in RCA: 44] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2019] [Revised: 01/03/2020] [Accepted: 02/12/2020] [Indexed: 12/15/2022]
Abstract
Artificial intelligence (AI) for the purpose of this review is an umbrella term for technologies emulating a nephropathologist's ability to extract information on diagnosis, prognosis, and therapy responsiveness from native or transplant kidney biopsies. Although AI can be used to analyze a wide variety of biopsy-related data, this review focuses on whole slide images traditionally used in nephropathology. AI applications in nephropathology have recently become available through several advancing technologies, including (i) widespread introduction of glass slide scanners, (ii) data servers in pathology departments worldwide, and (iii) through greatly improved computer hardware to enable AI training. In this review, we explain how AI can enhance the reproducibility of nephropathology results for certain parameters in the context of precision medicine using advanced architectures, such as convolutional neural networks, that are currently the state of the art in machine learning software for this task. Because AI applications in nephropathology are still in their infancy, we show the power and potential of AI applications mostly in the example of oncopathology. Moreover, we discuss the technological obstacles as well as the current stakeholder and regulatory concerns about developing AI applications in nephropathology from the perspective of nephropathologists and the wider nephrology community. We expect the gradual introduction of these technologies into routine diagnostics and research for selective tasks, suggesting that this technology will enhance the performance of nephropathologists rather than making them redundant.
Collapse
|
57
|
Molecular Subtypes Recognition of Breast Cancer in Dynamic Contrast-Enhanced Breast Magnetic Resonance Imaging Phenotypes from Radiomics Data. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2019; 2019:6978650. [PMID: 31827586 PMCID: PMC6885255 DOI: 10.1155/2019/6978650] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/09/2019] [Accepted: 10/10/2019] [Indexed: 12/28/2022]
Abstract
Background and Objective Breast cancer is a major cause of mortality among women if not treated in early stages. Recognizing molecular markers from DCE-MRI directly to distinguish the four molecular subtypes without invasive biopsy is helpful for guiding treatment plans for breast cancer, which provides a fast way to consequential treatment plan decision in early time and best opportunity for patients. Methods This study presents an approach of molecular subtypes recognition from breast cancer image phenotypes by radiomics. An improved region growth algorithm with dynamic threshold without user interaction is proposed for cancer lesion segmentation, which gives the precise border of lesion other than area with background. The lesions are extracted automatically based on radiologists' annotation which guarantees the lesion is segmented correctly. Various features are extracted on lesions data including texture, morphology, dynamic kinetics, and statistics features carried out on a large patient cohort, which are used to validate the relationship between image phenotypes and the molecular subtypes. A new algorithm of multimodel-based recursive feature elimination is applied on the radiomics data generated by the feature extraction process. This method obtains the feature subset with stable performance for different classification models, and the gradient boosting decision tree model gets the best results of both classification performance and imbalance performance on molecular subtypes. Result From the experimental results, 69 optimal features from 143 original features are found by the multimodel-based recursive feature elimination algorithms and the gradient boosting decision tree classifier obtains a good performance with accuracy 0.87, precise 0.88, recall 0.87, and F1-score 0.87. The dataset with 637 patients in this paper has serious imbalance problem on different molecular subtypes, and the the robust features that are generated by multimodel-based recursive feature eliminiation algorithm make the gradient boosting decision tree classifier have good behaviors. The recognition precision for the four molecular subtypes of luminal A, luminal B, HER-2, and basal-like are 0.91, 0.89, 0.83, and 0.87, respectively. Conclusions The improved lesion segmentation method gives more precise lesion edge, which not only saves the time of automatic extraction of lesion region of interest without threshold setting for each case, but also prevents the segmentation error by manual and prejudice from different radiologists. The feature selection algorithm of multimodel-based recursive feature elimination has the ability to find robust and optimal features that distinguish the four molecular subtypes from image phenotypes. The gradient boosting decision tree classifier rather plays a main role in recognition than other models used in this paper.
Collapse
|
58
|
MLW-gcForest: A Multi-Weighted gcForest Model for Cancer Subtype Classification by Methylation Data. APPLIED SCIENCES-BASEL 2019. [DOI: 10.3390/app9173589] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Effective cancer treatment requires a clear subtype. Due to the small sample size, high dimensionality, and class imbalances of cancer gene data, classifying cancer subtypes by traditional machine learning methods remains challenging. The gcForest algorithm is a combination of machine learning methods and a deep neural network and has been indicated to achieve better classification of small samples of data. However, the gcForest algorithm still faces many challenges when this method is applied to the classification of cancer subtypes. In this paper, we propose an improved gcForest algorithm (MLW-gcForest) to study the applicability of this method to the small sample sizes, high dimensionality, and class imbalances of genetic data. The main contributions of this algorithm are as follows: (1) Different weights are assigned to different random forests according to the classification ability of the forests. (2) We propose a sorting optimization algorithm that assigns different weights to the feature vectors generated under different sliding windows. The MLW-gcForest model is trained on the methylation data of five data sets from the cancer genome atlas (TCGA). The experimental results show that the MLW-gcForest algorithm achieves high accuracy and area under curve (AUC) values for the classification of cancer subtypes compared with those of traditional machine learning methods and state of the art methods. The results also show that methylation data can be effectively used to diagnose cancer.
Collapse
|
59
|
Reig B, Heacock L, Geras KJ, Moy L. Machine learning in breast MRI. J Magn Reson Imaging 2019; 52:998-1018. [PMID: 31276247 DOI: 10.1002/jmri.26852] [Citation(s) in RCA: 84] [Impact Index Per Article: 16.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2019] [Revised: 06/18/2019] [Accepted: 06/19/2019] [Indexed: 12/13/2022] Open
Abstract
Machine-learning techniques have led to remarkable advances in data extraction and analysis of medical imaging. Applications of machine learning to breast MRI continue to expand rapidly as increasingly accurate 3D breast and lesion segmentation allows the combination of radiologist-level interpretation (eg, BI-RADS lexicon), data from advanced multiparametric imaging techniques, and patient-level data such as genetic risk markers. Advances in breast MRI feature extraction have led to rapid dataset analysis, which offers promise in large pooled multiinstitutional data analysis. The object of this review is to provide an overview of machine-learning and deep-learning techniques for breast MRI, including supervised and unsupervised methods, anatomic breast segmentation, and lesion segmentation. Finally, it explores the role of machine learning, current limitations, and future applications to texture analysis, radiomics, and radiogenomics. Level of Evidence: 3 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2019. J. Magn. Reson. Imaging 2020;52:998-1018.
Collapse
Affiliation(s)
- Beatriu Reig
- The Department of Radiology, New York University School of Medicine, New York, New York, USA
| | - Laura Heacock
- Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University School of Medicine, New York, New York, USA
| | - Krzysztof J Geras
- Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University School of Medicine, New York, New York, USA
| | - Linda Moy
- Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University School of Medicine, New York, New York, USA.,Center for Advanced Imaging Innovation and Research (CAI2 R), New York University School of Medicine, New York, New York, USA
| |
Collapse
|
60
|
Herent P, Schmauch B, Jehanno P, Dehaene O, Saillard C, Balleyguier C, Arfi-Rouche J, Jégou S. Detection and characterization of MRI breast lesions using deep learning. Diagn Interv Imaging 2019; 100:219-225. [DOI: 10.1016/j.diii.2019.02.008] [Citation(s) in RCA: 35] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2019] [Accepted: 02/22/2019] [Indexed: 10/27/2022]
|