Evaluation and mitigation of the limitations of large language models in clinical decision-making.

Clinical decision-making is one of the most impactful parts of a physician's responsibilities and stands to benefit greatly from artificial intelligence solutions and large language models (LLMs) in particular. However, while LLMs have achieved excellent performance on medical licensing exams, these tests fail to assess many skills necessary for deployment in a realistic clinical decision-making environment, including gathering information, adhering to guidelines, and integrating into clinical workflows. Here we have created a curated dataset based on the Medical Information Mart for Intensive Care database spanning 2,400 real patient cases and four common abdominal pathologies as well as a framework to simulate a realistic clinical setting.

Precision measurement of cardiac structure and function in cardiovascular magnetic resonance using machine learning.

Background: Measurement of cardiac structure and function from images (e.g. volumes, mass and derived parameters such as left ventricular (LV) ejection fraction [LVEF]) guides care for millions.

Rich-club organization of the newborn human brain.

Combining diffusion magnetic resonance imaging and network analysis in the adult human brain has identified a set of highly connected cortical hubs that form a "rich club"--a high-cost, high-capacity backbone thought to enable efficient network communication. Rich-club architecture appears to be a persistent feature of the mature mammalian brain, but it is not known when this structure emerges during human development. In this longitudinal study we chart the emergence of structural organization in mid to late gestation.

Segmentation of MR images via discriminative dictionary learning and sparse coding: application to hippocampus labeling.

We propose a novel method for the automatic segmentation of brain MRI images by using discriminative dictionary learning and sparse coding techniques. In the proposed method, dictionaries and classifiers are learned simultaneously from a set of brain atlases, which can then be used for the reconstruction and segmentation of an unseen target image. The proposed segmentation strategy is based on image reconstruction, which is in contrast to most existing atlas-based labeling approaches that rely on comparing image similarities between atlases and target images.

A combined manifold learning analysis of shape and appearance to characterize neonatal brain development.

Large medical image datasets form a rich source of anatomical descriptions for research into pathology and clinical biomarkers. Many features may be extracted from data such as MR images to provide, through manifold learning methods, new representations of the population's anatomy. However, the ability of any individual feature to fully capture all aspects morphology is limited.

Combining morphological information in a manifold learning framework: application to neonatal MRI.

MR image data can provide many features or measures although any single measure is unlikely to comprehensively characterize the underlying morphology. We present a framework in which multiple measures are used in manifold learning steps to generate coordinate embeddings which are then combined to give an improved single representation of the population. An application to neonatal brain MRI data shows that the use of shape and appearance measures in particular leads to biologically plausible and consistent representations correlating well with clinical data.

Multi-atlas based segmentation of brain images: atlas selection and its effect on accuracy.

Quantitative research in neuroimaging often relies on anatomical segmentation of human brain MR images. Recent multi-atlas based approaches provide highly accurate structural segmentations of the brain by propagating manual delineations from multiple atlases in a database to a query subject and combining them. The atlas databases which can be used for these purposes are growing steadily.

Assessment of brain growth in early childhood using deformation-based morphometry.

We present methods for the quantitative analysis of brain growth based on the registration of longitudinal MR image data with the use of Jacobian determinant maps to characterise neuroanatomical changes. The individual anatomies, growth maps and tissue classes are also spatially normalised in an 'average space' and aggregated to provide atlases for the population at each timepoint. The average space representation is obtained using the average intersubject transformation within each timepoint.