Bias reduction in representation of histopathology images using deep feature selection

Abstract

Appearing traces of bias in deep networks is a serious reliability issue which can play a significant role in ethics and generalization related concerns. Recent studies report that the deep features extracted from the histopathology images of The Cancer Genome Atlas (TCGA), the largest publicly available archive, are surprisingly able to accurately classify the whole slide images (WSIs) based on their acquisition site while these features are extracted to primarily discriminate cancer types. This is clear evidence that the utilized Deep Neural Networks (DNNs) unexpectedly detect the specific patterns of the source site, i.e, the hospital of origin, rather than histomorphologic patterns, a biased behavior resulting in degraded trust and generalization. This observation motivated us to propose a method to alleviate the destructive impact of hospital bias through a novel feature selection process. To this effect, we have proposed an evolutionary strategy to select a small set of optimal features to not only accurately represent the histological patterns of tissue samples but also to eliminate the features contributing to internal bias toward the institution. The defined objective function for an optimal subset selection of features is to minimize the accuracy of the model to classify the source institutions which is basically defined as a bias indicator. By the conducted experiments, the selected features extracted by the state-of-the-art network trained on TCGA images (i.e., the KimiaNet), considerably decreased the institutional bias, while improving the quality of features to discriminate the cancer types. In addition, the selected features could significantly improve the results of external validation compared to the entire set of features which has been negatively affected by bias. The proposed scheme is a model-independent approach which can be employed when it is possible to define a bias indicator as a participating objective in a feature selection process; even with unknown bias sources.

Learning to predict RNA sequence expressions from whole slide images with applications for search and classification

“…These results still show a reasonable performance, especially when considering the performance of its counterpart, which showed about a 20% decrease in accuracy. Lack of generalization due to overfitting, bias, and shortcuts is a general problem in deep learning 27,28 . However, applying more sophisticated preprocessing may improve the model performance and lead to better sensitivity when using an external dataset.…”

Machine learning in computational histopathology: Challenges and opportunities

“…One notion of bias and fairness that has recently been explored in computational histopathology is the implicit dependence that predictive models may have on the hospital from which the digitized slides are obtained. Reference 247 devises a method to reduce the dependence on the features extracted in histopathology images by explicitly encouraging the model to not capture patterns that are indicative of hospital identity via an evolutionary strategy. Reference 248 develops a learning strategy for predictive models to decrease variation in predictive performance among hospitals.…”

Bias in Histopathology Datasets: A Comprehensive Investigation on Possible Factors

“…Thus, it raises doubts about being biased toward these unrelated signatures for cancer-type detection, which could potentially result in low external validation when dealing with the data collected from unseen data centers. Notably, several studies 25,26 have endeavored slide-based investigations to eliminate these signatures, with the goal of reducing the prediction accuracy of acquisition sites; by doing so, they aim to achieve higher external validation accuracy. However, before proceeding with any further steps, identifying the origin of these signatures as biases not only prevents the occurrence of suddenly biased results in similar histopathology research but also enhances generalization and trustworthiness toward applying AI models for aiding in diagnosis procedures.…”