 This paper presents a tutorial on deep learning, DL, for digital pathology, DP, image analysis. The authors investigate seven unique DP tasks as use cases to elucidate techniques needed to produce comparable, and in many cases, superior results from state-of-the-art handcrafted feature-based classification approaches. They show how an open-source framework called CAFE can be used for nuclei segmentation, epithelium segmentation, tubule segmentation, lymphocyte detection, mitosis detection, invasive ductal carcinoma detection, and lymphoma classification. The results demonstrate that DL approaches can achieve high accuracy in DP image analysis tasks, even when dealing with challenges such as variations in staining and scanning across sites, biological variants, and manual annotation errors. The paper provides step-by-step instructions for the usage of the supplied source code, train models, and input data, making it accessible to both DL experts and DP slash image processing experts with minimal DL experience. This article was authored by Andrew Jenochik and Anant Matibushi. We are article.tv, links in the description below.