Impact of Deep Learning Assistance on the Histopathologic Review of Lymph Nodes for Metastatic Breast Cancer. (December 2018)

• Record Type: Journal Article
• Authors: Steiner, David F.; MacDonald, Robert; Liu, Yun; Truszkowski, Peter; Hipp, Jason D.; Gammage, Christopher; Thng, Florence; Peng, Lily; Stumpe, Martin C.
• Is Part Of: American journal of surgical pathology. Volume 42:Number 12(2018)
• Publication Date: 2018-12
• Subjects: artificial intelligence -- machine learning -- digital pathology -- breast cancer -- computer aided detection; Pathology, Surgical -- Periodicals; 617.0705
• DOI: 10.1097/PAS.0000000000001151
• Languages: English
• ISSNs: 0147-5185

Abstract

Abstract : 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. Abstract : Supplemental Digital Content is available in the text.