Histological tissue examination has been a longstanding practice for cancer diagnosis where pathologists identify the presence of tumors on glass slides. Slides acquired from laboratory routine may contain unintentional artifacts due to complications in surgical resection. Blood and damaged tissue artifacts are two common problems associated with transurethral resection of the bladder tumor. Differences in histotechnical procedures among laboratories may also result in color variations and minor inconsistencies in outcome. A digitized version of a glass slide known as a whole slide image (WSI) holds enormous potential for automated diagnostics. The presence of irrelevant areas in a WSI undermines diagnostic value for pathologists as well as computational pathology (CPATH) systems. Therefore, automatic detection and exclusion of diagnostically irrelevant areas may lead to more reliable predictions. In this paper, we are detecting blood and damaged tissue against diagnostically relevant tissue. We gauge the effectiveness of transfer learning against training from scratch. Best models give 0.99 and 0.89 F1 scores for blood and damaged tissue detection. Since blood and damaged tissue have subtle color differences, we assess the impact of color processing methods on the binary classification performance of five well-known architectures. Finally, we remove the color to understand its importance against morphology on classification performance.
Histopathology is a gold standard for cancer diagnosis under a microscopic examination. However, histological tissue processing procedures result in artifacts, which are ultimately transferred to the digitized version of glass slides, known as whole slide images (WSIs). Artifacts are diagnostically irrelevant areas and may result in wrong deep learning (DL) algorithms predictions. Therefore, detecting and excluding artifacts in the computational pathology (CPATH) system is essential for reliable automated diagnosis. In this paper, we propose a mixture of experts (MoE) scheme for detecting five notable artifacts, including damaged tissue, blur, folded tissue, air bubbles, and histologically irrelevant blood from WSIs. First, we train independent binary DL models as experts to capture particular artifact morphology. Then, we ensemble their predictions using a fusion mechanism. We apply probabilistic thresholding over the final probability distribution to improve the sensitivity of the MoE. We developed DL pipelines using two MoEs and two multiclass models of state-of-the-art deep convolutional neural networks (DCNNs) and vision transformers (ViTs). DCNNs-based MoE and ViTs-based MoE schemes outperformed simpler multiclass models and were tested on datasets from different hospitals and cancer types, where MoE using DCNNs yielded the best results. The proposed MoE yields 86.15% F1 and 97.93% sensitivity scores on unseen data, retaining less computational cost for inference than MoE using ViTs. This best performance of MoEs comes with relatively higher computational trade-offs than multiclass models. The proposed artifact detection pipeline will not only ensure reliable CPATH predictions but may also provide quality control.