Hyperspectral imaging (HSI) is an optical technique that processes the electromagnetic spectrum at a multitude of monochromatic, adjacent frequency bands. The wide-bandwidth spectral signature of a target object’s reflectance allows fingerprinting its physical, biochemical, and physiological properties.

Description Image segmentation seeks to classify individual pixels in an image into semantic classes, such as e.g. the organs in a CT scan. State-of-the-art approaches to image segmentation [5], while very accurate, have limitations in terms of topological correctness.

TL;DR: We want to integrate specialized localization components into LLM-based VLMs to improve their localization capabilities and overall performance on localized tasks such as object detection, referring expression generation. Description Vision-Language Models (VLMs) integrate computer vision and natural language processing approaches to handle both images and text in a single model.

Description: Large Language Models (LLMs) have shown exceptional capabilities in understanding and generating human-like text. In the medical field, these models hold the potential to revolutionize patient care, medical research, and healthcare administration.

Description Deep learning aims at learning general representations of data allowing for downstream tasks such as classification, regression or generation of new data. In practice, however, there are no formal guarantees to what a model learns, resulting in unwanted memorisation of input data and leaking of private information.

Description Equivariant convolutions are a novel approach that incorporate additional geometric properties of the input domain during the convolution process (i.e. symmetry properties such as rotations and reflections) [1]. This additional inductive bias allows the model to learn more robust and general features from less data, rendering them highly promising for application in the medical domain.

Description Anonymizing data means removing or replacing any identifying information from a dataset, such as names or addresses. The aim of anonymization is to protect the privacy of individuals whose data is being collected and processed.

This year’s seminar will look at aspects of multi-modal machine learning in medicine and healthcare, focusing on: Vision language models (VLMs) for medical and healthcare applications Generic multi-modal AI models utilising imaging data, clinical reports, lab test results, electronic health records, and genomics Foundation models for multi-modal medicine Objectives: At the end of the module students should have:

In this course students are given the chance to apply their abilities and knowledge in deep learning to real-world medical data. Students will be assigned a medical dataset and in close consultation with medical doctors create a project plan.

Abstract: The detection and segmentation of bone tumors using magnetic resonance imaging (MRI) have crucial implications for clinical diagnosis and treatment planning. With the advent of deep learning techniques, there’s a growing interest in leveraging these methods to analyze MRI bone tumor images.