Self-supervised learning of a tailored Convolutional Auto Encoder for histopathological prostate grading
This work addresses the problem of limited labeled data for prostate cancer grading for pathologists, representing an incremental improvement in domain-specific medical imaging.
The paper tackles the challenge of grading prostate cancer histopathological images, particularly distinguishing between Grade 3 and Grade 4, by proposing a self-supervised learning framework using a tailored Convolutional Auto Encoder, achieving an overall accuracy of 83% on validation and 76% on test sets with an F1-score of 77% for G4.
According to GLOBOCAN 2020, prostate cancer is the second most common cancer in men worldwide and the fourth most prevalent cancer overall. For pathologists, grading prostate cancer is challenging, especially when discriminating between Grade 3 (G3) and Grade 4 (G4). This paper proposes a Self-Supervised Learning (SSL) framework to classify prostate histopathological images when labeled images are scarce. In particular, a tailored Convolutional Auto Encoder (CAE) is trained to reconstruct 128x128x3 patches of prostate cancer Whole Slide Images (WSIs) as a pretext task. The downstream task of the proposed SSL paradigm is the automatic grading of histopathological patches of prostate cancer. The presented framework reports promising results on the validation set, obtaining an overall accuracy of 83% and on the test set, achieving an overall accuracy value of 76% with F1-score of 77% in G4.