Artificial Intelligence-Based Breast Cancer Nodal Metastasis Detection: Insights Into the Black Box for Pathologists.

By Yun Liu, Timo Kohlberger, Mohammad Norouzi, George E. Dahl, Jenny L. Smith, Arash Mohtashamian, Niels Olson, Lily H. Peng, J. Hipp, Martin C. Stumpe. Archives of Pathology & Laboratory Medicine, 2018

318 citations recorded by the source corpus.

CONTEXT.— Nodal metastasis of a primary tumor influences therapy decisions for a variety of cancers. Histologic identification of tumor cells in lymph nodes can be laborious and error-prone, especially for small tumor foci. OBJECTIVE.— To evaluate the application and clinical implementation of a state-of-the-art deep learning-based artificial intelligence algorithm (LYmph Node Assistant or LYNA) for detection of metastatic breast cancer in sentinel lymph node biopsies. DESIGN.— Whole slide images were obtained from hematoxylin-eosin-stained lymph nodes from 399 patients (publicly available Camelyon16 challenge dataset). LYNA was developed by using 270 slides and evaluated on the remaining 129 slides. We compared the findings to those obtained from an independent laboratory (108 slides from 20 patients/86 blocks) using a different scanner to measure reproducibility. RESULTS.— LYNA achieved a slide-level area under the receiver operating characteristic (AUC) of 99% and a tumor-level sensitivity of 91% at 1 false positive per patient on the Camelyon16 evaluation dataset. We also identified 2 "normal" slides that contained micrometastases. When applied to our second dataset, LYNA achieved an AUC of 99.6%. LYNA was not affected by common histology artifacts such as overfixation, poor staining, and air bubbles. CONCLUSIONS.— Artificial intelligence algorithms can exhaustively evaluate every tissue patch on a slide, achieving higher tumor-level sensitivity than, and comparable slide-level performance to, pathologists. These techniques may improve the pathologist's productivity and reduce the number of false negatives associated with morphologic detection of tumor cells. We provide a framework to aid practicing pathologists in assessing such algorithms for adoption into their workflow (akin to how a pathologist assesses immunohistochemistry results).

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/cfa3d45a6fcf704fe7ab6953424481d1698055a4

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 Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Clinical Trials for Artificial Intelligence in Cancer Diagnosis: A Cross-Sectional Study of Registered Trials in ClinicalTrials.gov (2020, background): “Among all the studies of AI in the field of cancer pathological diagnosis, the implementation in breast cancer was earlier and more mature (8), and AI diagnosis had an excellent application in the diagnosis of primary breast cancer and metastatic breast cancer (31).”
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].”
Artificial Intelligence in Cancer Research and Precision Medicine (2021, background): “These model architectures have indeed excelled at classification of images such as determining whether a digitized stained slide contains cancer cells or not (2, 3, 7–13).”
Deep neural network models for computational histopathology: A survey (2019, background): “These issues can be partly addressed by developing “interpretable” AI systems (Liu et al., 2018; Rudin, 2019) which provide a reliable measure of model confidence and also generalization to different multi-cohort datasets.”
Artificial intelligence (AI) and big data in cancer and precision oncology (2020, background): “Some pathologists have used LYNA and reported that this AI tool provided time saving beneﬁts, coupled with its consistency and accuracy [71].”
On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation (2020, methodology): “More concretely, deep models are now applied to diverse ﬁelds such as physics [ABCG + 15, RWR + 18, HRH18], biology [AIP + 15], healthcare [LAA + 17, NPAA18, LKN + 18], or autonomous driving [KG17, MKG18] to name a few.”
Emerging role of deep learning‐based artificial intelligence in tumor pathology (2020, methodology): “…for the region of invasive cancer Dice coefficient: 75.86% and 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…”
Artificial Intelligence and Human Trust in Healthcare: Focus on Clinicians (2019, background): “While in some applications, AI can outperform human decision-making by incorporating data from multiple sources [29,30], the limitations above suggest that unnecessarily high trust in AI may have catastrophic consequences, especially in life-critical applications.”