“VLM-based solutions in the radiologist practice – Professor Hinton’s prophecy finally arrived?”
In 2016, Geoffrey Hinton famously predicted the end of radiology. A decade later, the narrative has shifted from “replacement” to “unprecedented collaboration.” This presentation provides a strategic evaluation of that prophecy, tracking the evolution from rigid, classical pipelines to the transformative era of Vision-Language Models (VLMs). While there are specialized architectures like YOLO or DETR for object recognition (and can be aligned to medical image analysis) and MedSAM or solutions based on U-Net for automated segmentation, the current ROI is driven by multimodal reasoning. We focus on how frontier models, specifically Gemini, GPT, and the open-weights Gemma family, are bridging the gap between raw pixel data and complex diagnostic interpretation. By synthesizing high-performance vision with language-based logic, we offer a data-driven assessment of the modern clinical landscape – is the business case for replacing radiologists still viable, or has AI matured into the ultimate diagnostic co-pilot?
Bio
Maciej Szymkowski is a Ph.D. in the field of Computer Science. From April 2025, he is working with Future Processing as a Senior Machine Learning Engineer. He is also with Bialystok University of Technology, Faculty of Computer Science (from 2018). He was previously with Warsaw University of Technology (Faculty of Electronics and Information Technology, 2021-2022) and AGH in Cracow (Faculty of Physics and Applied Computer Science, 2021-2022). He gained his experiences also as a researcher and software engineer in diversified projects and companies (e.g., SoftServe, Symmetra, Transition Technologies, Hemolens Diagnostics). He was also with Łukasiewicz Research Network – Poznan Institute of Technology (2022-2024) where he was a Head of AI Development section. Maciej is an author or co-author of more than 45 research papers published in JCR journals, as chapters in the books or in international conference proceedings. His main research area is Computer Vision – especially in the field of medicine and transport. He is interested in explainable AI, Vision-Language Models (VLMs), Large Language Models (LLMs) and machine learning algorithms. In his free time, he loves to extend his knowledge, take a long walk, read a book or watch soccer, basketball or hockey. He is a fan of Legia Warsaw, Real Madrid, Bayern Munchen (soccer), New York Knicks (basketball) and Pittsburgh Penguins (hockey).