1
|
Bobowicz M, Rygusik M, Buler J, Buler R, Ferlin M, Kwasigroch A, Szurowska E, Grochowski M. Attention-Based Deep Learning System for Classification of Breast Lesions-Multimodal, Weakly Supervised Approach. Cancers (Basel) 2023; 15:2704. [PMID: 37345041 DOI: 10.3390/cancers15102704] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2023] [Revised: 05/02/2023] [Accepted: 05/05/2023] [Indexed: 06/23/2023] Open
Abstract
Breast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering-constrained Attention Multiple Instance Learning (CLAM) classifier able to train under data scarcity effectively. We used a private dataset with 1174 non-cancer and 794 cancer images labelled at the image level with pathological ground truth confirmation. We used feature extractors (ResNet-18, ResNet-34, ResNet-50 and EfficientNet-B0) pre-trained on ImageNet. The best results were achieved with multimodal-view classification using both CC and MLO images simultaneously, resized by half, with a patch size of 224 px and an overlap of 0.25. It resulted in AUC-ROC = 0.896 ± 0.017, F1-score 81.8 ± 3.2, accuracy 81.6 ± 3.2, precision 82.4 ± 3.3, and recall 81.6 ± 3.2. Evaluation with the Chinese Mammography Database, with 5-fold cross-validation, patient-wise breakdowns, and transfer learning, resulted in AUC-ROC 0.848 ± 0.015, F1-score 78.6 ± 2.0, accuracy 78.4 ± 1.9, precision 78.8 ± 2.0, and recall 78.4 ± 1.9. The CLAM algorithm's attentional maps indicate the features most relevant to the algorithm in the images. Our approach was more effective than in many other studies, allowing for some explainability and identifying erroneous predictions based on the wrong premises.
Collapse
Affiliation(s)
- Maciej Bobowicz
- 2nd Department of Radiology, Medical University of Gdansk, 80-214 Gdansk, Poland
| | - Marlena Rygusik
- 2nd Department of Radiology, Medical University of Gdansk, 80-214 Gdansk, Poland
| | - Jakub Buler
- Department of Intelligent Control Systems and Decision Support, Faculty of Electrical and Control Engineering, Gdansk University of Technology, 80-233 Gdansk, Poland
| | - Rafał Buler
- Department of Intelligent Control Systems and Decision Support, Faculty of Electrical and Control Engineering, Gdansk University of Technology, 80-233 Gdansk, Poland
| | - Maria Ferlin
- Department of Intelligent Control Systems and Decision Support, Faculty of Electrical and Control Engineering, Gdansk University of Technology, 80-233 Gdansk, Poland
| | - Arkadiusz Kwasigroch
- Department of Intelligent Control Systems and Decision Support, Faculty of Electrical and Control Engineering, Gdansk University of Technology, 80-233 Gdansk, Poland
| | - Edyta Szurowska
- 2nd Department of Radiology, Medical University of Gdansk, 80-214 Gdansk, Poland
| | - Michał Grochowski
- Department of Intelligent Control Systems and Decision Support, Faculty of Electrical and Control Engineering, Gdansk University of Technology, 80-233 Gdansk, Poland
| |
Collapse
|
2
|
Burnside ES, Warren LM, Myles J, Wilkinson LS, Wallis MG, Patel M, Smith RA, Young KC, Massat NJ, Duffy SW. Quantitative breast density analysis to predict interval and node-positive cancers in pursuit of improved screening protocols: a case-control study. Br J Cancer 2021; 125:884-892. [PMID: 34168297 PMCID: PMC8438060 DOI: 10.1038/s41416-021-01466-y] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2020] [Revised: 05/18/2021] [Accepted: 06/10/2021] [Indexed: 01/20/2023] Open
Abstract
BACKGROUND This study investigates whether quantitative breast density (BD) serves as an imaging biomarker for more intensive breast cancer screening by predicting interval, and node-positive cancers. METHODS This case-control study of 1204 women aged 47-73 includes 599 cancer cases (302 screen-detected, 297 interval; 239 node-positive, 360 node-negative) and 605 controls. Automated BD software calculated fibroglandular volume (FGV), volumetric breast density (VBD) and density grade (DG). A radiologist assessed BD using a visual analogue scale (VAS) from 0 to 100. Logistic regression and area under the receiver operating characteristic curves (AUC) determined whether BD could predict mode of detection (screen-detected or interval); node-negative cancers; node-positive cancers, and all cancers vs. controls. RESULTS FGV, VBD, VAS, and DG all discriminated interval cancers (all p < 0.01) from controls. Only FGV-quartile discriminated screen-detected cancers (p < 0.01). Based on AUC, FGV discriminated all cancer types better than VBD or VAS. FGV showed a significantly greater discrimination of interval cancers, AUC = 0.65, than of screen-detected cancers, AUC = 0.61 (p < 0.01) as did VBD (0.63 and 0.53, respectively, p < 0.001). CONCLUSION FGV, VBD, VAS and DG discriminate interval cancers from controls, reflecting some masking risk. Only FGV discriminates screen-detected cancers perhaps adding a unique component of breast cancer risk.
Collapse
Affiliation(s)
- Elizabeth S Burnside
- Department of Radiology, University of Wisconsin-Madison School of Medicine and Public Health, E3/311 Clinical Science Center, Madison, WI, USA.
| | - Lucy M Warren
- National Co-ordinating Centre for the Physics of Mammography (NCCPM), Medical Physics Department, Royal Surrey County Hospital, Guildford, UK
| | - Jonathan Myles
- Centre for Cancer Prevention, Queen Mary University of London, Wolfson Institute of Preventive Medicine, London, UK
| | | | - Matthew G Wallis
- Cambridge Breast Unit and NIHR Cambridge Biomedical Research Centre, Cambridge University Hospitals NHS Trust, Cambridge, UK
| | - Mishal Patel
- Scientific Computing, Medical Physics Department, Royal Surrey County Hospital, Guildford, UK
| | | | - Kenneth C Young
- National Co-ordinating Centre for the Physics of Mammography (NCCPM), Medical Physics Department, Royal Surrey County Hospital, Guildford, UK
| | - Nathalie J Massat
- Centre for Cancer Prevention, Queen Mary University of London, Wolfson Institute of Preventive Medicine, London, UK
| | - Stephen W Duffy
- Centre for Cancer Prevention, Queen Mary University of London, Wolfson Institute of Preventive Medicine, London, UK
| |
Collapse
|
4
|
Halling-Brown MD, Warren LM, Ward D, Lewis E, Mackenzie A, Wallis MG, Wilkinson LS, Given-Wilson RM, McAvinchey R, Young KC. OPTIMAM Mammography Image Database: A Large-Scale Resource of Mammography Images and Clinical Data. Radiol Artif Intell 2021; 3:e200103. [PMID: 33937853 PMCID: PMC8082293 DOI: 10.1148/ryai.2020200103] [Citation(s) in RCA: 50] [Impact Index Per Article: 16.7] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2020] [Revised: 09/03/2020] [Accepted: 10/05/2020] [Indexed: 11/11/2022]
Abstract
Supplemental material is available for this article.
Collapse
Affiliation(s)
- Mark D. Halling-Brown
- From the Department of Scientific Computing (M.D.H.B., D.W., E.L.) and National Co-ordinating Centre for the Physics of Mammography (L.M.W., A.M., K.C.Y.), Royal Surrey NHS Foundation Trust, Egerton Road, Guildford GU2 7XX, England; Centre for Vision, Speech and Signal Processing (M.D.H.B., E.L.) and Department of Physics (K.C.Y.), University of Surrey, Guildford, England; Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Cambridge, England (M.G.W.); NIHR Cambridge Biomedical Research Centre, Cambridge, England (M.G.W.); Oxford Breast Imaging Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, England (L.S.W.); Department of Radiology, St George’s Healthcare NHS Trust, London, England (R.M.G.W.); and Jarvis Breast Screening Centre, Guildford, England (R.M.)
| | - Lucy M. Warren
- From the Department of Scientific Computing (M.D.H.B., D.W., E.L.) and National Co-ordinating Centre for the Physics of Mammography (L.M.W., A.M., K.C.Y.), Royal Surrey NHS Foundation Trust, Egerton Road, Guildford GU2 7XX, England; Centre for Vision, Speech and Signal Processing (M.D.H.B., E.L.) and Department of Physics (K.C.Y.), University of Surrey, Guildford, England; Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Cambridge, England (M.G.W.); NIHR Cambridge Biomedical Research Centre, Cambridge, England (M.G.W.); Oxford Breast Imaging Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, England (L.S.W.); Department of Radiology, St George’s Healthcare NHS Trust, London, England (R.M.G.W.); and Jarvis Breast Screening Centre, Guildford, England (R.M.)
| | - Dominic Ward
- From the Department of Scientific Computing (M.D.H.B., D.W., E.L.) and National Co-ordinating Centre for the Physics of Mammography (L.M.W., A.M., K.C.Y.), Royal Surrey NHS Foundation Trust, Egerton Road, Guildford GU2 7XX, England; Centre for Vision, Speech and Signal Processing (M.D.H.B., E.L.) and Department of Physics (K.C.Y.), University of Surrey, Guildford, England; Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Cambridge, England (M.G.W.); NIHR Cambridge Biomedical Research Centre, Cambridge, England (M.G.W.); Oxford Breast Imaging Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, England (L.S.W.); Department of Radiology, St George’s Healthcare NHS Trust, London, England (R.M.G.W.); and Jarvis Breast Screening Centre, Guildford, England (R.M.)
| | - Emma Lewis
- From the Department of Scientific Computing (M.D.H.B., D.W., E.L.) and National Co-ordinating Centre for the Physics of Mammography (L.M.W., A.M., K.C.Y.), Royal Surrey NHS Foundation Trust, Egerton Road, Guildford GU2 7XX, England; Centre for Vision, Speech and Signal Processing (M.D.H.B., E.L.) and Department of Physics (K.C.Y.), University of Surrey, Guildford, England; Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Cambridge, England (M.G.W.); NIHR Cambridge Biomedical Research Centre, Cambridge, England (M.G.W.); Oxford Breast Imaging Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, England (L.S.W.); Department of Radiology, St George’s Healthcare NHS Trust, London, England (R.M.G.W.); and Jarvis Breast Screening Centre, Guildford, England (R.M.)
| | - Alistair Mackenzie
- From the Department of Scientific Computing (M.D.H.B., D.W., E.L.) and National Co-ordinating Centre for the Physics of Mammography (L.M.W., A.M., K.C.Y.), Royal Surrey NHS Foundation Trust, Egerton Road, Guildford GU2 7XX, England; Centre for Vision, Speech and Signal Processing (M.D.H.B., E.L.) and Department of Physics (K.C.Y.), University of Surrey, Guildford, England; Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Cambridge, England (M.G.W.); NIHR Cambridge Biomedical Research Centre, Cambridge, England (M.G.W.); Oxford Breast Imaging Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, England (L.S.W.); Department of Radiology, St George’s Healthcare NHS Trust, London, England (R.M.G.W.); and Jarvis Breast Screening Centre, Guildford, England (R.M.)
| | - Matthew G. Wallis
- From the Department of Scientific Computing (M.D.H.B., D.W., E.L.) and National Co-ordinating Centre for the Physics of Mammography (L.M.W., A.M., K.C.Y.), Royal Surrey NHS Foundation Trust, Egerton Road, Guildford GU2 7XX, England; Centre for Vision, Speech and Signal Processing (M.D.H.B., E.L.) and Department of Physics (K.C.Y.), University of Surrey, Guildford, England; Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Cambridge, England (M.G.W.); NIHR Cambridge Biomedical Research Centre, Cambridge, England (M.G.W.); Oxford Breast Imaging Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, England (L.S.W.); Department of Radiology, St George’s Healthcare NHS Trust, London, England (R.M.G.W.); and Jarvis Breast Screening Centre, Guildford, England (R.M.)
| | - Louise S. Wilkinson
- From the Department of Scientific Computing (M.D.H.B., D.W., E.L.) and National Co-ordinating Centre for the Physics of Mammography (L.M.W., A.M., K.C.Y.), Royal Surrey NHS Foundation Trust, Egerton Road, Guildford GU2 7XX, England; Centre for Vision, Speech and Signal Processing (M.D.H.B., E.L.) and Department of Physics (K.C.Y.), University of Surrey, Guildford, England; Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Cambridge, England (M.G.W.); NIHR Cambridge Biomedical Research Centre, Cambridge, England (M.G.W.); Oxford Breast Imaging Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, England (L.S.W.); Department of Radiology, St George’s Healthcare NHS Trust, London, England (R.M.G.W.); and Jarvis Breast Screening Centre, Guildford, England (R.M.)
| | - Rosalind M. Given-Wilson
- From the Department of Scientific Computing (M.D.H.B., D.W., E.L.) and National Co-ordinating Centre for the Physics of Mammography (L.M.W., A.M., K.C.Y.), Royal Surrey NHS Foundation Trust, Egerton Road, Guildford GU2 7XX, England; Centre for Vision, Speech and Signal Processing (M.D.H.B., E.L.) and Department of Physics (K.C.Y.), University of Surrey, Guildford, England; Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Cambridge, England (M.G.W.); NIHR Cambridge Biomedical Research Centre, Cambridge, England (M.G.W.); Oxford Breast Imaging Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, England (L.S.W.); Department of Radiology, St George’s Healthcare NHS Trust, London, England (R.M.G.W.); and Jarvis Breast Screening Centre, Guildford, England (R.M.)
| | - Rita McAvinchey
- From the Department of Scientific Computing (M.D.H.B., D.W., E.L.) and National Co-ordinating Centre for the Physics of Mammography (L.M.W., A.M., K.C.Y.), Royal Surrey NHS Foundation Trust, Egerton Road, Guildford GU2 7XX, England; Centre for Vision, Speech and Signal Processing (M.D.H.B., E.L.) and Department of Physics (K.C.Y.), University of Surrey, Guildford, England; Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Cambridge, England (M.G.W.); NIHR Cambridge Biomedical Research Centre, Cambridge, England (M.G.W.); Oxford Breast Imaging Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, England (L.S.W.); Department of Radiology, St George’s Healthcare NHS Trust, London, England (R.M.G.W.); and Jarvis Breast Screening Centre, Guildford, England (R.M.)
| | - Kenneth C. Young
- From the Department of Scientific Computing (M.D.H.B., D.W., E.L.) and National Co-ordinating Centre for the Physics of Mammography (L.M.W., A.M., K.C.Y.), Royal Surrey NHS Foundation Trust, Egerton Road, Guildford GU2 7XX, England; Centre for Vision, Speech and Signal Processing (M.D.H.B., E.L.) and Department of Physics (K.C.Y.), University of Surrey, Guildford, England; Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Cambridge, England (M.G.W.); NIHR Cambridge Biomedical Research Centre, Cambridge, England (M.G.W.); Oxford Breast Imaging Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, England (L.S.W.); Department of Radiology, St George’s Healthcare NHS Trust, London, England (R.M.G.W.); and Jarvis Breast Screening Centre, Guildford, England (R.M.)
| |
Collapse
|