Demystifying AI in Histopathology: Trust and Transparency in Cancer Diagnosis

This Research Topic provides a platform for exploring the evolving landscape of explainable artificial intelligence (XAI) in the analysis of histopathological images. As AI continues to revolutionize molecular medicine, the demand for transparency and interpretability in AI models has become increasingly crucial, especially in critical applications like cancer diagnosis and prognosis. Contributions may address the integration of XAI techniques such as Grad-CAM, LIME, and occlusion sensitivity in convolutional neural networks (CNNs) used for classifying and predicting outcomes in various lymphomas and inflammatory conditions. The exploration of XAI in the context of digital pathology not only enhances our understanding of complex disease mechanisms but also fosters trust among clinicians and patients. Historical breakthroughs in AI and computer vision, paired with contemporary innovations in deep learning and transfer learning, offer exciting opportunities for novel applications and improved accuracy in diagnostic workflows. This topic invites researchers to discuss the challenges, methodologies, and future directions in making AI models more interpretable and trustworthy for molecular medicine applications. Topic editors: Joaquim Carreras Source: https://www.frontiersin.org/research-topics/86291/demystifying-ai-in-histopathology-trust-and-transparency-in-cancer-diagnosis