Impact of Deep Learning Assistance on the Histopathologic Review of Lymph Nodes for Metastatic Breast Cancer

By David F. Steiner, Robert MacDonald, Yun Liu, P. Truszkowski, J. Hipp, Christopher Gammage, Florence Thng, Lily H. Peng, Martin C. Stumpe. 2018

410 citations recorded by the source corpus.

Advances in the quality of whole-slide images have set the stage for the clinical use of digital images in anatomic pathology. Along with advances in computer image analysis, this raises the possibility for computer-assisted diagnostics in pathology to improve histopathologic interpretation and clinical care. To evaluate the potential impact of digital assistance on interpretation of digitized slides, we conducted a multireader multicase study utilizing our deep learning algorithm for the detection of breast cancer metastasis in lymph nodes. Six pathologists reviewed 70 digitized slides from lymph node sections in 2 reader modes, unassisted and assisted, with a wash-out period between sessions. In the assisted mode, the deep learning algorithm was used to identify and outline regions with high likelihood of containing tumor. Algorithm-assisted pathologists demonstrated higher accuracy than either the algorithm or the pathologist alone. In particular, algorithm assistance significantly increased the sensitivity of detection for micrometastases (91% vs. 83%, P=0.02). In addition, average review time per image was significantly shorter with assistance than without assistance for both micrometastases (61 vs. 116 s, P=0.002) and negative images (111 vs. 137 s, P=0.018). Lastly, pathologists were asked to provide a numeric score regarding the difficulty of each image classification. On the basis of this score, pathologists considered the image review of micrometastases to be significantly easier when interpreted with assistance (P=0.0005). Utilizing a proof of concept assistant tool, this study demonstrates the potential of a deep learning algorithm to improve pathologist accuracy and efficiency in a digital pathology workflow.

Subfields: Artificial Intelligence, Epidemiology, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Epidemiology

Eric J. Topol

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Rapid Trust Calibration through Interpretable and Uncertainty-Aware AI (2020, background): “Several studies have shown that the performance of such teams can be greater than the performance of the human or the AI alone, 4,5 suggesting that each member of the team is able to compensate for the other’s weaknesses.”
Artificial Intelligence-Based Breast Cancer Nodal Metastasis Detection: Insights Into the Black Box for Pathologists. (2018, neutral): “This is the subject of future work.(29)”
Key challenges for delivering clinical impact with artificial intelligence (2019, background): “The limited number of prospective studies to date include diabetic retinopathy grading [48 – 50], detection of breast cancer metastases in sentinel lymph node biopsies [51, 52], wrist fracture detection [53], colonic polyp detection [28, 54], and detection of congenital cataracts [55].”
Role of Artificial Intelligence Applications in Real-Life Clinical Practice: Systematic Review (2020, background): “From our review, 16 studies demonstrated that AI applications could enhance clinical decision-making capacity [31-33,45-47,50,55,58,59,63,64,67,69,71,74,75].”
From patterns to patients: Advances in clinical machine learning for cancer diagnosis, prognosis, and treatment. (2023, background): “42,43 DL models sometimes predict more than a binary cancer versus no cancer label in order to provide clinicians with additional diagnostic information.”
Emerging role of deep learning‐based artificial intelligence in tumor pathology (2020, methodology): “…76.00% [44], [45] With/Without lymph node metastasis AUC: 0.994 and 0.996 [46], [47] Metastatic regions in lymph node Sensitivity: 0.807-0.910 [46]-[48] Evaluation of pathological features Mitotic count F-score: 0.611 [57] Ki-67 index F-score: 0.91 [64] Proliferation score Kappa: 0.613 [58] Immune…”
Computational pathology definitions, best practices, and recommendations for regulatory guidance: a white paper from the Digital Pathology Association (2019, methodology): “By providing information to the reviewing pathologist about the histopathologic features used by the algorithm in a particular instance, trust in the algorithm can be fostered and a synergy between pathologist and machine can be achieved that may exceed the performance of either AI or pathologist al”
Deep neural network models for computational histopathology: A survey (2019, background): “There has been a rapid growth in artificial intelligence (AI) research applied to medical imaging, and its potential impact has been demonstrated by applications which include detection of breast cancer metastasis in lymph nodes (Steiner et al., 2018), interpreting chest X-rays (Nam et al.”
High-performance medicine: the convergence of human and artificial intelligence (2019, methodology): “The combination of pathologists and the algorithm led to the best accuracy, and the algorithm markedly sped up the review of slides 35 .”