Development of a Deep Learning Algorithm for the Histopathologic Diagnosis and Gleason Grading of Prostate Cancer Biopsies: A Pilot Study
| Autor: | Drew Linsley, Andreas Karagounis, Thomas Serre, Ohad Kott, Boris Gershman, Dragan Golijanin, Carleen Jeffers, Ali Amin |
|---|---|
| Přispěvatelé: | Brown University, Department of Neuroscience and Institute for Brain Science, Brown University, Artificial and Natural Intelligence Toulouse Institute (ANITI) |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Male
Prostate biopsy Biopsy Urology 030232 urology & nephrology Gleason grading Magnification Pilot Projects Malignancy Article [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] 03 medical and health sciences Prostate cancer Deep Learning 0302 clinical medicine Prostate Image Interpretation Computer-Assisted medicine Humans Grading (tumors) ComputingMilieux_MISCELLANEOUS medicine.diagnostic_test business.industry Deep learning Prostatic Neoplasms medicine.disease 3. Good health medicine.anatomical_structure 030220 oncology & carcinogenesis Artificial intelligence Neoplasm Grading business Algorithm Algorithms [SDV.MHEP]Life Sciences [q-bio]/Human health and pathology |
| Zdroj: | European Urology Focus European Urology Focus, Elsevier, 2021, 7 (2), pp.347-351. ⟨10.1016/j.euf.2019.11.003⟩ Eur Urol Focus |
| ISSN: | 2405-4569 |
| DOI: | 10.1016/j.euf.2019.11.003⟩ |
| Popis: | BACKGROUND: The pathologic diagnosis and Gleason grading of prostate cancer are time-consuming, error-prone, and subject to interobserver variability. Machine learning offers opportunities to improve the diagnosis, risk stratification, and prognostication of prostate cancer. OBJECTIVE: To develop a state-of-the-art deep learning algorithm for the histopathologic diagnosis and Gleason grading of prostate biopsy specimens. DESIGN, SETTING, AND PARTICIPANTS: A total of 85 prostate core biopsy specimens from 25 patients were digitized at 20× magnification and annotated for Gleason 3, 4, and 5 prostate adenocarcinoma by a urologic pathologist. From these virtual slides, we sampled 14 803 image patches of 256 × 256 pixels, approximately balanced for malignancy. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: We trained and tested a deep residual convolutional neural network to classify each patch at two levels: (1) coarse (benign vs malignant) and (2) fine (benign vs Gleason 3 vs 4 vs 5). Model performance was evaluated using fivefold cross-validation. Randomization tests were used for hypothesis testing of the model performance versus chance. RESULTS AND LIMITATIONS: The model demonstrated 91.5% accuracy (p < 0.001) at coarse-level classification of image patches as benign versus malignant (0.93 sensitivity, 0.90 specificity, and 0.95 average precision). The model demonstrated 85.4% accuracy (p < 0.001) at fine-level classification of image patches as benign versus Gleason 3 versus Gleason 4 versus Gleason 5 (0.83 sensitivity, 0.94 specificity, and 0.83 average precision), with the greatest number of confusions in distinguishing between Gleason 3 and 4, and between Gleason 4 and 5. Limitations include the small sample size and the need for external validation. CONCLUSIONS: In this study, a deep learning-based computer vision algorithm demonstrated excellent performance for the histopathologic diagnosis and Gleason grading of prostate cancer. PATIENT SUMMARY: We developed a deep learning algorithm that demonstrated excellent performance for the diagnosis and grading of prostate cancer. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect