Medica l Image Ana lysis & Ar t i f icia l Intel l igence Symposium 2022 Nr. 12: Alexander Seper: Deep learning based diagnostic model for prostate and colon carcinoma Curriculum Vitae: Alexander Seper is a fourth year Medical student at the Danube Private University. His interest for research started in his second year, when he got the opportunity to work in a research group focusing on neurodegenerative disorders, especially on Parkinson’s disease. During an internship at Wiener Neustadt Hospital, he got the chance to participate in a research group consisting of pathologists from Austria and Germany. Since completeing the internship, he is involved in the development of a deep learning-based diagnostic of prostate- and colon carcinoma. Abstract: Deep learning based diagnostic model for prostate and colon carcinoma Digital pathology is an emerging transformation of diagnostic pathology. At that, histological slides can be digitized using histological scanner and reviewed on the monitor without a microscope. One of the promises of digital pathology is an automated analysis of pathological specimens using deep learning-based models. Deep Learning (DL) is a powerful technology for image analysis based on convolutional neural networks. Many studies to date addressed the feasibility of DL for diagnostic applications with high accuracy. However, heterogeneity in the quality of histological slides among different laboratories or even in the same laboratory is a prominent challenge to provide top diagnostic accuracy irrespective of pre-clinical issues and artifacts. We investigate the impact of common histological artifacts on the accuracy of automatized pathologic diagnosis, followed by bringing a higher number of slides into the neural network in order to get more precise results.