Foundation Models in Medical Imaging -- A Review and Outlook

Foundation models (FMs) are changing the way medical images are analyzed by learning from large collections of unlabeled data. Instead of relying on manually annotated examples, FMs are pre-trained to learn general-purpose visual features that can later be adapted to specific clinical tasks with little additional supervision. In this review, we examine how FMs are being developed and applied in pathology, radiology, and ophthalmology, drawing on evidence from over 150 studies. We explain the core components of FM pipelines, including model architectures, self-supervised learning methods, and strategies for downstream adaptation. We also review how FMs are being used in each imaging domain and compare design choices across applications. Finally, we discuss key challenges and open questions to guide future research.

Geometry-Aware Latent Representation Learning for Modeling Disease Progression of Barrett's Esophagus

Barrett's Esophagus (BE) is the only precursor known to Esophageal Adenocarcinoma (EAC), a type of esophageal cancer with poor prognosis upon diagnosis. Therefore, diagnosing BE is crucial in preventing and treating esophageal cancer. While supervised machine learning supports BE diagnosis, high interobserver variability in histopathological training data limits these methods. Unsupervised representation learning via Variational Autoencoders (VAEs) shows promise, as they map input data to a lower-dimensional manifold with only useful features, characterizing BE progression for improved downstream tasks and insights. However, the VAE's Euclidean latent space distorts point relationships, hindering disease progression modeling. Geometric VAEs provide additional geometric structure to the latent space, with RHVAE assuming a Riemannian manifold and $\mathcal{S}$-VAE a hyperspherical manifold. Our study shows that $\mathcal{S}$-VAE outperforms vanilla VAE with better reconstruction losses, representation classification accuracies, and higher-quality generated images and interpolations in lower-dimensional settings. By disentangling rotation information from the latent space, we improve results further using a group-based architecture. Additionally, we take initial steps towards $\mathcal{S}$-AE, a novel autoencoder model generating qualitative images without a variational framework, but retaining benefits of autoencoders such as stability and reconstruction quality.

Autotuning PID control using Actor-Critic Deep Reinforcement Learning

This work is an exploratory research concerned with determining in what way reinforcement learning can be used to predict optimal PID parameters for a robot designed for apple harvest. To study this, an algorithm called Advantage Actor Critic (A2C) is implemented on a simulated robot arm. The simulation primarily relies on the ROS framework. Experiments for tuning one actuator at a time and two actuators a a time are run, which both show that the model is able to predict PID gains that perform better than the set baseline. In addition, it is studied if the model is able to predict PID parameters based on where an apple is located. Initial tests show that the model is indeed able to adapt its predictions to apple locations, making it an adaptive controller.