The fields of digital pathology (DP) and computational pathology (CP) are transforming traditional histopathology by replacing manual microscope-based examinations with digital tools. While DP uses digitised whole slide images (WSIs) for research, education, knowledge sharing, telepathology, and even primary diagnosis, CP incorporates deep learning (DL) models for automated image interpretation. The benefits of these novel tools are often inaccessible to low-resource organisations, particularly in low- and middle-income countries (LMICs), due to prohibitive costs. This study highlights a free, open-source, cloud-based platform (DeepLIIF) that enables cost-effective digitisation, sharing, and semi-automated analysis of WSIs using low-cost equipment. The platform was tested on various tissue biopsies, including skin, liver, prostate, and breast, achieving satisfactory quality. Key benefits include ease of use, accessibility to smartphones and low-tech devices, and the ability to share WSIs via browser links for telepathology, education, and research. However, limitations include its reliance on single-fragment or needle core biopsies, restricted video file sizes, and resolution inconsistencies during video capture. Key Words: Digital pathology, Computational pathology, Low-resource setting.
Zehra et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: