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

抄録

<jats:p>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%, <jats:italic toggle="yes">P</jats:italic>=0.02). In addition, average review time per image was significantly shorter with assistance than without assistance for both micrometastases (61 vs. 116 s, <jats:italic toggle="yes">P</jats:italic>=0.002) and negative images (111 vs. 137 s, <jats:italic toggle="yes">P</jats:italic>=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 (<jats:italic toggle="yes">P</jats:italic>=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.</jats:p>

収録刊行物

被引用文献 (8)*注記

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ