arXiv:2603. 18846v3 Announce Type: replace-cross Abstract: Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL).
The study proposes a diagnostic-guided approach to choose between stochastic and deterministic longitudinal imaging models based on whether inter-visit changes are driven by disease progression or acquisition variability. Applied to a large, heterogeneous Optos fundus autofluorescence archive, the diagnostic revealed weak time-dependent changes and limited benefit from stochastic models, leading to the development of the deterministic Temporal Retinal U‑Net (TRU). TRU outperformed other classical and deep‑learning comparators on image‑level and eye‑specific progression metrics across held‑out and independent zero‑shot transfer cohorts, though with slightly lower precision in a smaller cross‑vendor cohort.
arXiv:2605. 23995v4 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) is increasingly used in medical image analysis to reduce dependence on costly expert annotations by learning transferable representations from unlabeled data.
arXiv:2607. 16681v1 Announce Type: new Abstract: Early sepsis prediction from electronic health records is challenged by irregular sampling, high missingness, and class imbalance.
The paper explores contrastive self‑supervised learning (SSL) for retinal fundus image classification, comparing SimSiam and SimCLR under limited data and computational resources. It investigates how retinal‑specific augmentation strategies and training parameters affect representation quality, evaluated through linear probing and fine‑tuning on multi‑disease classification and diabetic retinopathy grading tasks. The results demonstrate that tailored augmentations enable lightweight SSL models to learn transferable representations, reducing reliance on large annotated datasets while achieving competitive performance.
arXiv:2607. 20274v1 Announce Type: cross Abstract: Medical image encoders from different groups are increasingly treated as interchangeable, on the assumption that scale and clinical supervision concentrate their representations onto a shared structure.
The paper explores contrastive self‑supervised learning (SSL) for retinal fundus image classification, comparing SimSiam and SimCLR under limited data and computational resources. It investigates how retinal‑specific augmentation strategies and training parameters affect representation quality, evaluated through linear probing and fine‑tuning on multi‑disease classification and diabetic retinopathy grading tasks. Results indicate that tailored augmentations enable lightweight SSL models to learn transferable representations, reducing reliance on large annotated datasets while achieving competitive performance.
Co-Annotator is a clinical AI system that distills expert gaze and dictation into two guidance components: a gaze‑aligned Vision Transformer that highlights fixation‑aligned areas of interest (AOIs) and an ontology‑bounded vision‑language model that pre‑fills editable biomarker summaries for retinal OCT. In controlled studies, each modality independently improved diagnostic accuracy and biomarker generation, and when combined across two academic institutions, the system increased correct diagnoses per minute by 40% and reduced comment editing time by 67% without compromising accuracy.
arXiv:2604. 27277v3 Announce Type: replace-cross Abstract: Brain MRI underpins a wide range of neuroscientific and clinical applications, yet most learning-based methods remain task-specific and require substantial labeled data.
arXiv:2607. 25164v1 Announce Type: cross Abstract: A CT examination captures multiple organs, but many biomedical questions concern abnormalities, prognosis, or longitudinal change in a specific organ.
arXiv:2605. 23995v2 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) has emerged as a promising paradigm for addressing the annotation bottleneck in medical imaging by learning representations from unlabeled data.
The paper introduces a reverse spatio‑temporal disease progression model that reconstructs unobserved healthier anatomy from later diseased scans. It employs a two‑stage architecture: a frozen 3D vector‑quantised autoencoder creates a discrete latent space, and a Neural ODE learns continuous‑time dynamics, with a recurrent encoder initializing the latent state from reverse‑ordered observations. Experiments on a synthetic Morpho‑MNIST benchmark and longitudinal Alzheimer’s MRIs show the model can recover unseen prior states and outperform baseline methods in predicting healthy trajectories.