Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer
- PMID: 29234806
- PMCID: PMC5820737
- DOI: 10.1001/jama.2017.14585
Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer
Abstract
Importance: Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency.
Objective: Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin-stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists' diagnoses in a diagnostic setting.
Design, setting, and participants: Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC).
Exposures: Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation.
Main outcomes and measures: The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor.
Results: The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884]; P < .001). The top 5 algorithms had a mean AUC that was comparable with the pathologist interpreting the slides in the absence of time constraints (mean AUC, 0.960 [range, 0.923-0.994] for the top 5 algorithms vs 0.966 [95% CI, 0.927-0.998] for the pathologist WOTC).
Conclusions and relevance: In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints. Whether this approach has clinical utility will require evaluation in a clinical setting.
Conflict of interest statement
Figures
![Figure 1.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/5820737/bin/jama-318-2199-g001.gif)
![Figure 2.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/5820737/bin/jama-318-2199-g002.gif)
![Figure 3.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/5820737/bin/jama-318-2199-g003.gif)
Comment in
-
Deep Learning Algorithms for Detection of Lymph Node Metastases From Breast Cancer: Helping Artificial Intelligence Be Seen.JAMA. 2017 Dec 12;318(22):2184-2186. doi: 10.1001/jama.2017.14580. JAMA. 2017. PMID: 29234791 No abstract available.
-
Using Free-Response Receiver Operating Characteristic Curves to Assess the Accuracy of Machine Diagnosis of Cancer.JAMA. 2017 Dec 12;318(22):2250-2251. doi: 10.1001/jama.2017.18686. JAMA. 2017. PMID: 29234793 No abstract available.
-
Not Just Digital Pathology, Intelligent Digital Pathology.JAMA Oncol. 2018 Mar 1;4(3):403-404. doi: 10.1001/jamaoncol.2017.5449. JAMA Oncol. 2018. PMID: 29392271 No abstract available.
-
AI diagnostics need attention.Nature. 2018 Mar 15;555(7696):285. doi: 10.1038/d41586-018-03067-x. Nature. 2018. PMID: 29542717 No abstract available.
-
Machine Learning Compared With Pathologist Assessment.JAMA. 2018 Apr 24;319(16):1725-1726. doi: 10.1001/jama.2018.1466. JAMA. 2018. PMID: 29710156 No abstract available.
Similar articles
-
Current status and prospects of artificial intelligence in breast cancer pathology: convolutional neural networks to prospective Vision Transformers.Int J Clin Oncol. 2024 Apr 15. doi: 10.1007/s10147-024-02513-3. Online ahead of print. Int J Clin Oncol. 2024. PMID: 38619651 Review.
-
Training pathologists to assess stromal tumour-infiltrating lymphocytes in breast cancer synergises efforts in clinical care and scientific research.Histopathology. 2024 May;84(6):915-923. doi: 10.1111/his.15140. Epub 2024 Mar 3. Histopathology. 2024. PMID: 38433289 Review.
-
Artificial intelligence-based model for lymph node metastases detection on whole slide images in bladder cancer: a retrospective, multicentre, diagnostic study.Lancet Oncol. 2023 Apr;24(4):360-370. doi: 10.1016/S1470-2045(23)00061-X. Epub 2023 Mar 6. Lancet Oncol. 2023. PMID: 36893772
-
Challenge for Diagnostic Assessment of Deep Learning Algorithm for Metastases Classification in Sentinel Lymph Nodes on Frozen Tissue Section Digital Slides in Women with Breast Cancer.Cancer Res Treat. 2020 Oct;52(4):1103-1111. doi: 10.4143/crt.2020.337. Epub 2020 Jun 30. Cancer Res Treat. 2020. PMID: 32599974 Free PMC article.
-
Artificial Intelligence-Based Breast Cancer Nodal Metastasis Detection: Insights Into the Black Box for Pathologists.Arch Pathol Lab Med. 2019 Jul;143(7):859-868. doi: 10.5858/arpa.2018-0147-OA. Epub 2018 Oct 8. Arch Pathol Lab Med. 2019. PMID: 30295070
Cited by
-
Development and deployment of a histopathology-based deep learning algorithm for patient prescreening in a clinical trial.Nat Commun. 2024 Jun 1;15(1):4690. doi: 10.1038/s41467-024-49153-9. Nat Commun. 2024. PMID: 38824132 Free PMC article.
-
Predicting mortality after transcatheter aortic valve replacement using preprocedural CT.Sci Rep. 2024 May 31;14(1):12526. doi: 10.1038/s41598-024-63022-x. Sci Rep. 2024. PMID: 38822074 Free PMC article.
-
Personalized anesthesia and precision medicine: a comprehensive review of genetic factors, artificial intelligence, and patient-specific factors.Front Med (Lausanne). 2024 May 9;11:1365524. doi: 10.3389/fmed.2024.1365524. eCollection 2024. Front Med (Lausanne). 2024. PMID: 38784235 Free PMC article. Review.
-
Histopathologic image-based deep learning classifier for predicting platinum-based treatment responses in high-grade serous ovarian cancer.Nat Commun. 2024 May 18;15(1):4253. doi: 10.1038/s41467-024-48667-6. Nat Commun. 2024. PMID: 38762636 Free PMC article.
-
A prediction model based on digital breast pathology image information.PLoS One. 2024 May 17;19(5):e0294923. doi: 10.1371/journal.pone.0294923. eCollection 2024. PLoS One. 2024. PMID: 38758814 Free PMC article.
References
-
- Griffin J, Treanor D. Digital pathology in clinical use: where are we now and what is holding us back? Histopathology. 2017;70(1):134-145. - PubMed
-
- Gulshan V, Peng L, Coram M, et al. . Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316(22):2402-2410. - PubMed
-
- Vestjens JHMJ, Pepels MJ, de Boer M, et al. . Relevant impact of central pathology review on nodal classification in individual breast cancer patients. Ann Oncol. 2012;23(10):2561-2566. - PubMed
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical