Latest AI and machine learning research in transplantation for healthcare professionals.
We compare the efficacy and distributional effects of supervised fine-tuning (SFT) and reinforcement learning (RL) post-training for PlasmidGPT, a foundation model for whole-plasmid generation, using Group Relative Policy Optimization (GRPO) for the RL model. Using a biologically motivated reward function encoding functional annotations, length constraints, and repeat penalties, the RL model achie...
The peripheral auditory system of dolphins comprises specialised bony, fatty, vascular, and neural structures adapted for underwater hearing and diving physiology. These include the external ear canal, acoustic fat bodies, sinuses, and associated neurovascular networks, which together support sound conduction, protection, and possibly sensory functions. Despite advances in gross anatomical descrip...
Large Language Models (LLMs) generate realistic synthetic data but offer no guarantee that their outputs respect the causal mechanisms governing the t...
The immense value of public gene expression repositories is constrained by the lack of compatibility among datasets generated from diverse experimenta...
Industrial visual inspection systems increasingly rely on deep classifiers whose heatmap explanations may appear visually plausible while failing to i...
Visual reasoning, often interleaved with intermediate visual states, has emerged as a promising direction in the field. A straightforward approach is ...
Background: Previous machine learning models to intraoperatively predict the molecular status of gliomas using stimulated Raman histology (SRH), such ...
By resolving cell-type compositions from multi-cellular spatial measurements, deconvolution is central to resolving the cellular landscape of complex ...
Multi-organ biological aging is often represented as parallel organ-specific clocks, but how age gaps should be interpreted within an anatomically cou...
Background: Per- and polyfluoroalkyl substances (PFAS), particularly perfluorooctane sulfonate (PFOS) and perfluorooctanoic acid (PFOA), are persisten...
Three-dimensional (3D) whole-organ imaging and analysis at cellular resolution (termed 3D histology) provide profound insights into the organization a...
Annotating bounding boxes is costly and limits the scalability of object detection. This challenge is compounded by the need to preserve high accuracy...
Effective anti-tumor T cell response depends on both neoantigen quality (non-selfness) and quantity (abundance). However, existing methods for neoanti...
Foundation models (FMs) have shown great promise in medical imaging, but most FMs are trained on unimodal data within isolated domains, such as brain ...
Recent studies have explored generating virtual spatial transcriptomics (ST) profiles from histological images, offering a promising alternative to la...
We introduce a causal aware foundation-model framework for real time optimal decision making in discrete choice environments. We propose a constrained...
Manually curated biomedical repositories -- spanning bioactivity, genomics, and chemistry -- are expensive to maintain, lag behind primary literature,...
We introduce iTRIALSPACE, a programmable evaluation framework for controlled assessment of lung CT models. Standard benchmarks are static retrospectiv...
Continual learning (CL) is essential for deploying medical image segmentation models in clinical environments where imaging domains, anatomical target...
Background: People with Multiple Long-Term Conditions (MLTC) experience higher rates of organ failure and death following cardiac surgery. The aim of ...