Cell Maps Representation For Lung Adenocarcinoma Growth Patterns Classification In Whole Slide Images
This work addresses the problem of improving prognosis prediction for lung adenocarcinoma patients by accurately classifying histologic growth patterns, though it is incremental as it builds on existing methods with specific enhancements.
The paper tackled the classification of lung adenocarcinoma growth patterns in whole slide images by developing a machine learning pipeline that uses cell maps and a convolutional neural network, achieving an AUCROC score of 0.97 and approximately 30% higher accuracy on unseen test-sets compared to state-of-the-art approaches.
Lung adenocarcinoma is a morphologically heterogeneous disease, characterized by five primary histologic growth patterns. The quantity of these patterns can be related to tumor behavior and has a significant impact on patient prognosis. In this work, we propose a novel machine learning pipeline capable of classifying tissue tiles into one of the five patterns or as non-tumor, with an Area Under the Receiver Operating Characteristic Curve (AUCROC) score of 0.97. Our model's strength lies in its comprehensive consideration of cellular spatial patterns, where it first generates cell maps from Hematoxylin and Eosin (H&E) whole slide images (WSIs), which are then fed into a convolutional neural network classification model. Exploiting these cell maps provides the model with robust generalizability to new data, achieving approximately 30% higher accuracy on unseen test-sets compared to current state of the art approaches. The insights derived from our model can be used to predict prognosis, enhancing patient outcomes.