1
|
Bhalla D, Rangarajan K, Chandra T, Banerjee S, Arora C. Reproducibility and Explainability of Deep Learning in Mammography: A Systematic Review of Literature. Indian J Radiol Imaging 2024; 34:469-487. [PMID: 38912238 PMCID: PMC11188703 DOI: 10.1055/s-0043-1775737] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/25/2024] Open
Abstract
Background Although abundant literature is currently available on the use of deep learning for breast cancer detection in mammography, the quality of such literature is widely variable. Purpose To evaluate published literature on breast cancer detection in mammography for reproducibility and to ascertain best practices for model design. Methods The PubMed and Scopus databases were searched to identify records that described the use of deep learning to detect lesions or classify images into cancer or noncancer. A modification of Quality Assessment of Diagnostic Accuracy Studies (mQUADAS-2) tool was developed for this review and was applied to the included studies. Results of reported studies (area under curve [AUC] of receiver operator curve [ROC] curve, sensitivity, specificity) were recorded. Results A total of 12,123 records were screened, of which 107 fit the inclusion criteria. Training and test datasets, key idea behind model architecture, and results were recorded for these studies. Based on mQUADAS-2 assessment, 103 studies had high risk of bias due to nonrepresentative patient selection. Four studies were of adequate quality, of which three trained their own model, and one used a commercial network. Ensemble models were used in two of these. Common strategies used for model training included patch classifiers, image classification networks (ResNet in 67%), and object detection networks (RetinaNet in 67%). The highest reported AUC was 0.927 ± 0.008 on a screening dataset, while it reached 0.945 (0.919-0.968) on an enriched subset. Higher values of AUC (0.955) and specificity (98.5%) were reached when combined radiologist and Artificial Intelligence readings were used than either of them alone. None of the studies provided explainability beyond localization accuracy. None of the studies have studied interaction between AI and radiologist in a real world setting. Conclusion While deep learning holds much promise in mammography interpretation, evaluation in a reproducible clinical setting and explainable networks are the need of the hour.
Collapse
Affiliation(s)
- Deeksha Bhalla
- Department of Radiodiagnosis, All India Institute of Medical Sciences, New Delhi, India
| | - Krithika Rangarajan
- Department of Radiodiagnosis, All India Institute of Medical Sciences, New Delhi, India
| | - Tany Chandra
- Department of Radiodiagnosis, All India Institute of Medical Sciences, New Delhi, India
| | - Subhashis Banerjee
- Department of Computer Science and Engineering, Indian Institute of Technology, New Delhi, India
| | - Chetan Arora
- Department of Computer Science and Engineering, Indian Institute of Technology, New Delhi, India
| |
Collapse
|
2
|
Shin SY, Shen TC, Summers RM. Improving segmentation and detection of lesions in CT scans using intensity distribution supervision. Comput Med Imaging Graph 2023; 108:102259. [PMID: 37348281 PMCID: PMC10527342 DOI: 10.1016/j.compmedimag.2023.102259] [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: 03/14/2023] [Revised: 05/12/2023] [Accepted: 06/06/2023] [Indexed: 06/24/2023]
Abstract
We propose a method to incorporate the intensity information of a target lesion on CT scans in training segmentation and detection networks. We first build an intensity-based lesion probability (ILP) function from an intensity histogram of the target lesion. It is used to compute the probability of being the lesion for each voxel based on its intensity. Finally, the computed ILP map of each input CT scan is provided as additional supervision for network training, which aims to inform the network about possible lesion locations in terms of intensity values at no additional labeling cost. The method was applied to improve the segmentation of three different lesion types, namely, small bowel carcinoid tumor, kidney tumor, and lung nodule. The effectiveness of the proposed method on a detection task was also investigated. We observed improvements of 41.3% → 47.8%, 74.2% → 76.0%, and 26.4% → 32.7% in segmenting small bowel carcinoid tumor, kidney tumor, and lung nodule, respectively, in terms of per case Dice scores. An improvement of 64.6% → 75.5% was achieved in detecting kidney tumors in terms of average precision. The results of different usages of the ILP map and the effect of varied amount of training data are also presented.
Collapse
Affiliation(s)
- Seung Yeon Shin
- Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, 20892, MD, USA.
| | - Thomas C Shen
- Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, 20892, MD, USA
| | - Ronald M Summers
- Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, 20892, MD, USA
| |
Collapse
|
3
|
Basile TMA, Fanizzi A, Losurdo L, Bellotti R, Bottigli U, Dentamaro R, Didonna V, Fausto A, Massafra R, Moschetta M, Tamborra P, Tangaro S, La Forgia D. Microcalcification detection in full-field digital mammograms: A fully automated computer-aided system. Phys Med 2019; 64:1-9. [PMID: 31515007 DOI: 10.1016/j.ejmp.2019.05.022] [Citation(s) in RCA: 30] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/14/2019] [Revised: 05/08/2019] [Accepted: 05/25/2019] [Indexed: 11/30/2022] Open
Abstract
BACKGROUND Microcalcification clusters in mammograms can be considered as early signs of breast cancer. However, their detection is a very challenging task because of different factors: large variety of breast composition, highly textured breast anatomy, impalpable size of microcalcifications in some cases, as well as inherent low contrast of mammograms. Thus, the need to support the clinicians' work with an automatic tool. METHODS In this work a three-phases approach for clustered microcalcification detection is presented. Specifically, it is made up of a pre-processing step, aimed at highlighting potentially interesting breast structures, followed by a single microcalcification detection step, based on Hough transform, that is able to grasp the innate characteristic shape of the structures of interest. Finally, a cluster identification step to group microcalcifications is carried out by means of a clustering algorithm able to codify expert domain rules. RESULTS The detection performance of the proposed method has been evaluated on 364 mammograms of 182 patients obtaining a true positive ratio of 91.78% with 2.87 false positives per image. CONCLUSIONS Experimental results demonstrated that the proposed method is able to detect microcalcification clusters in digital mammograms showing performance comparable to different methodologies exploited in the state-of-art approaches, with the advantage that it does not require any training phase and a large set of data. The performance of the proposed approach remains high even for more difficult clinical cases of mammograms of young women having high-density breast tissue thus resulting in a reduced contrast between microcalcifications and surrounding dense tissues.
Collapse
Affiliation(s)
- T M A Basile
- Department of Physics, University of Bari "Aldo Moro", Bari, Italy; INFN National Institute for Nuclear Physics, Bari Division, Bari, Italy.
| | - A Fanizzi
- I.R.C.C.S. "Giovanni Paolo II" National Cancer Centre, Bari, Italy
| | - L Losurdo
- I.R.C.C.S. "Giovanni Paolo II" National Cancer Centre, Bari, Italy
| | - R Bellotti
- Department of Physics, University of Bari "Aldo Moro", Bari, Italy; INFN National Institute for Nuclear Physics, Bari Division, Bari, Italy
| | - U Bottigli
- Department of Physical Sciences, Earth and Environment, University of Siena, Siena, Italy
| | - R Dentamaro
- I.R.C.C.S. "Giovanni Paolo II" National Cancer Centre, Bari, Italy
| | - V Didonna
- I.R.C.C.S. "Giovanni Paolo II" National Cancer Centre, Bari, Italy
| | - A Fausto
- Department of Diagnostic Imaging, University Hospital of Siena, Siena, Italy
| | - R Massafra
- I.R.C.C.S. "Giovanni Paolo II" National Cancer Centre, Bari, Italy
| | - M Moschetta
- Interdisciplinary Department of Medicine, University of Bari "Aldo Moro", Bari, Italy
| | - P Tamborra
- I.R.C.C.S. "Giovanni Paolo II" National Cancer Centre, Bari, Italy
| | - S Tangaro
- INFN National Institute for Nuclear Physics, Bari Division, Bari, Italy
| | - D La Forgia
- I.R.C.C.S. "Giovanni Paolo II" National Cancer Centre, Bari, Italy
| |
Collapse
|
4
|
Maisen C, Auephanwiriyakul S, Theera-Umpon N. Learning vector quantization inference classifier in breast abnormality classification. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2018. [DOI: 10.3233/jifs-169850] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Affiliation(s)
- Chakkraphop Maisen
- Computer Engineering Department, Faculty of Engineering, Chiang Mai University, Chiang Mai, Thailand
- Graduate School, Chiang Mai University, Chiang Mai, Thailand
| | - Sansanee Auephanwiriyakul
- Computer Engineering Department, Faculty of Engineering, Chiang Mai University, Chiang Mai, Thailand
- Biomedical Engineering Institute, Chiang Mai University, Chiang Mai, Thailand
| | - Nipon Theera-Umpon
- Electrical Engineering Department, Faculty of Engineering, Chiang Mai University, Chiang Mai, Thailand
- Biomedical Engineering Institute, Chiang Mai University, Chiang Mai, Thailand
| |
Collapse
|
5
|
Brag J, Auffret M, Ramos C, Liu Y, Baudot P. iBiopsy® for Precision Medicine. EUROPEAN MEDICAL JOURNAL 2018. [DOI: 10.33590/emj/10310309] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022] Open
Abstract
A high-throughput artificial intelligence-powered image-based phenotyping platform, iBiopsy® (Median Technologies, Valbonne, France), which aims to improve precision medicine, is discussed in the presented review. The article introduces novel concepts, including high-throughput, fully automated imaging biomarker extraction; unsupervised predictive learning; large-scale content- based image-based similarity search; the use of large-scale clinical data registries; and cloud-based big data analytics to the problems of disease subtyping and treatment planning. Unlike electronic health record-based approaches, which lack the detailed radiological, pathological, genomic, and molecular data necessary for accurate prediction, iBiopsy generates unique signatures as fingerprints of disease and tumour subtypes from target images. These signatures are then merged with any additional omics data and matched against a large-scale reference registry of deeply phenotyped patients. Initial applications targeted include hepatocellular carcinoma and other chronic liver diseases, such as nonalcoholic steatohepatitis. This new disruptive technology is expected to lead to the identification of appropriate therapies targeting specific molecular pathways involved in the detected phenotypes to bring personalised treatment to patients, taking into account individual biological variability, which is the principal aim of precision medicine.
Collapse
Affiliation(s)
- Johan Brag
- iBiopsy® Clinical Development, Median Technologies, Valbonne, France
| | - Michaël Auffret
- iBiopsy® Clinical Development, Median Technologies, Valbonne, France
| | - Corinne Ramos
- iBiopsy® Clinical Development, Median Technologies, Valbonne, France
| | - Yan Liu
- iBiopsy® Clinical Development, Median Technologies, Valbonne, France
| | - Pierre Baudot
- iBiopsy® Science & Image Processing, Median Technologies, Valbonne, France
| |
Collapse
|