Abstract
Detection of nodal micrometastasis (tumor size: 0.2–2.0 mm) is challenging for pathologists due to the small size of metastatic foci. Since lymph nodes with micrometastasis are counted as positive nodes, detecting micrometastasis is crucial for accurate pathologic staging of colorectal cancer. Previously, deep learning algorithms developed with manually annotated images performed well in identifying micrometastasis of breast cancer in sentinel lymph nodes. However, the process of manual annotation is labor intensive and time consuming. Multiple instance learning was later used to identify metastatic breast cancer without manual annotation, but its performance appears worse in detecting micrometastasis. Here, we developed a deep learning model using whole-slide images of regional lymph nodes of colorectal cancer with only a slide-level label (either a positive or negative slide). The training, validation, and testing sets included 1963, 219, and 1000 slides, respectively. A supercomputer TAIWANIA 2 was used to train a deep learning model to identify metastasis. At slide level, our algorithm performed well in identifying both macrometastasis (tumor size > 2.0 mm) and micrometastasis with an area under the receiver operating characteristics curve (AUC) of 0.9993 and 0.9956, respectively. Since most of our slides had more than one lymph node, we then tested the performance of our algorithm on 538 single-lymph node images randomly cropped from the testing set. At single-lymph node level, our algorithm maintained good performance in identifying macrometastasis and micrometastasis with an AUC of 0.9944 and 0.9476, respectively. Visualization using class activation mapping confirmed that our model identified nodal metastasis based on areas of tumor cells. Our results demonstrate for the first time that micrometastasis could be detected by deep learning on whole-slide images without manual annotation.
Highlights
For cancer patients, pathologic staging is crucial for choosing a proper treatment strategy
Nodal micrometastasis has been defined as a metastatic focus with a size between 0.2 and 2.0 mm by the International Union Against Cancer since 2002 [1], and metastatic foci smaller than 0.2 mm are considered isolated tumor cells
We developed a deep learning algorithm to detect nodal metastasis of colorectal cancer using our new method of end-to-end training with annotation-free whole-slide images (WSIs)
Summary
Pathologic staging is crucial for choosing a proper treatment strategy. Memorial Hospital, Taoyuan, Taiwan 4 Chang Gung Molecular Medicine Research Center, Chang Gung. University, Taoyuan, Taiwan 5 Tissue Bank, Chang Gung Memorial Hospital, Taoyuan, Taiwan 6 Center for Artificial Intelligence in Medicine, Chang Gung. An assisting tool to detect small metastatic foci in lymph nodes, if available, would be helpful for pathologic staging. Nodal micrometastasis has been defined as a metastatic focus with a size between 0.2 and 2.0 mm by the International Union Against Cancer since 2002 [1], and metastatic foci smaller than 0.2 mm are considered isolated tumor cells. Despite a minor adverse prognostic effect in a subset of early colorectal cancer patients [4], a lymph node with isolated tumor cells is regarded as a negative node in the AJCC staging [3]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
