DiagSet: a dataset for prostate cancer histopathological image classification
This work addresses prostate cancer detection for medical diagnosis by providing a new dataset and a competitive framework, though it is incremental as it builds on existing deep learning methods.
The authors introduced DiagSet, a large histopathological dataset for prostate cancer detection containing over 2.6 million tissue patches, and developed a machine learning framework that achieves 94.6% accuracy in patch-level recognition and shows high statistical agreement with human histopathologists in scan-level diagnosis.
Cancer diseases constitute one of the most significant societal challenges. In this paper, we introduce a novel histopathological dataset for prostate cancer detection. The proposed dataset, consisting of over 2.6 million tissue patches extracted from 430 fully annotated scans, 4675 scans with assigned binary diagnoses, and 46 scans with diagnoses independently provided by a group of histopathologists can be found at https://github.com/michalkoziarski/DiagSet. Furthermore, we propose a machine learning framework for detection of cancerous tissue regions and prediction of scan-level diagnosis, utilizing thresholding to abstain from the decision in uncertain cases. The proposed approach, composed of ensembles of deep neural networks operating on the histopathological scans at different scales, achieves 94.6% accuracy in patch-level recognition and is compared in a scan-level diagnosis with 9 human histopathologists showing high statistical agreement.