Classifying Breast Histopathology Images with a Ductal Instance-Oriented Pipeline
This work provides a potentially more accurate and efficient diagnostic tool for pathologists classifying breast histopathology images, offering an incremental improvement over existing methods.
This paper introduces the Ductal Instance-Oriented Pipeline (DIOP) for classifying breast histopathology images, which uses duct-level instance segmentation, tissue-level semantic segmentation, and three levels of features. The DIOP outperforms previous methods in all diagnostic tasks and achieves comparable performance to general pathologists for the four-way classification task on a unique dataset.
In this study, we propose the Ductal Instance-Oriented Pipeline (DIOP) that contains a duct-level instance segmentation model, a tissue-level semantic segmentation model, and three-levels of features for diagnostic classification. Based on recent advancements in instance segmentation and the Mask R-CNN model, our duct-level segmenter tries to identify each ductal individual inside a microscopic image; then, it extracts tissue-level information from the identified ductal instances. Leveraging three levels of information obtained from these ductal instances and also the histopathology image, the proposed DIOP outperforms previous approaches (both feature-based and CNN-based) in all diagnostic tasks; for the four-way classification task, the DIOP achieves comparable performance to general pathologists in this unique dataset. The proposed DIOP only takes a few seconds to run in the inference time, which could be used interactively on most modern computers. More clinical explorations are needed to study the robustness and generalizability of this system in the future.