ARA: accurate, reliable and active histopathological image classification framework with Bayesian deep learning

Abstract

Machine learning algorithms hold the promise to effectively automate the analysis of histopathological images that are routinely generated in clinical practice. Any machine learning method used in the clinical diagnostic process has to be extremely accurate and, ideally, provide a measure of uncertainty for its predictions. Such accurate and reliable classifiers need enough labelled data for training, which requires time-consuming and costly manual annotation by pathologists. Thus, it is critical to minimise the amount of data needed to reach the desired accuracy by maximising the efficiency of training. We propose an accurate, reliable and active (ARA) image classification framework and introduce a new Bayesian Convolutional Neural Network (ARA-CNN) for classifying histopathological images of colorectal cancer. The model achieves exceptional classification accuracy, outperforming other models trained on the same dataset. The network outputs an uncertainty measurement for each tested image. We show that uncertainty measures can be used to detect mislabelled training samples and can be employed in an efficient active learning workflow. Using a variational dropout-based entropy measure of uncertainty in the workflow speeds up the learning process by roughly 45%. Finally, we utilise our model to segment whole-slide images of colorectal tissue and compute segmentation-based spatial statistics.

Two Ensemble-CNN Approaches for Colorectal Cancer Tissue Type Classification

“…In [12], J. Kather et al tested different texture descriptors with an SVM classifier. In [41], Ł. Rączkowski et al proposed the Bayesian Convolutional Neural Network approach. In [19], L. Nanni et al proposed an ensemble (FUS_ND+DeepOutput) approach based on combining deep and texture features.…”

Eleven grand challenges in single-cell data science

“…Development of reliable classifiers for immunohistochemical images, however, is challenging due to scarcity of training data. Solutions such as active learning can speed up the training process and reduce the workload of annotating pathologists [298].…”

Potential applications of artificial intelligence in colorectal polyps and cancer: Recent advances and prospects

“…Histopathological diagnosis can be made by pathologists based on images of tissues obtained from a colonoscopic biopsy. Recently, many scholars have begun to explore the application of AI in identifying histopathological images of CRC[ 59 , 60 ]. Yoon et al[ 60 ] evaluated the performance of the CNN model in histologic diagnosis.…”