This lecture explores the increasingly important role of signal processing, machine learning, and artificial intelligence in biomedical data analysis and medical imaging. The first part focuses on computational methods in microscopy-based biological research, including multi-vision deconvolution for image reconstruction, automated cell segmentation and tracking, as well as approaches to phenotyping based on cell morphology. In addition, matrix factorization combined with active learning will be presented as an effective strategy for drug prediction and target discovery from high-dimensional biological data.
The second part of the lecture deals with challenges in digital pathology, with a focus on deep learning methods for segmentation of histopathological images. Particular attention will be paid to approaches for the detection of glomeruli in images of renal tissue, as well as the use of generative adversarial networks (GANs) for staining normalization and domain adjustment to improve segmentation performance across various staining protocols and datasets.
Finally, the lecture discusses the broader impact of artificial intelligence in medicine, highlighting its growing role as a diagnostic support tool and decision-making assistant. The lecture will conclude with a discussion on the future of AI and the potential development of general artificial intelligence (AGI) systems for medicine, with a look at the possibilities, limitations, and ethical issues of the next generation of health technologies.