Advances in Medical Imaging Analysis and Clinical Diagnosis

The field of medical imaging analysis and clinical diagnosis is rapidly advancing with the development of new AI-powered tools and techniques. Recent research has focused on improving the accuracy and efficiency of medical image analysis, as well as enhancing clinical diagnosis through the integration of multiple modalities and sources of information. Notably, the use of large language models and multimodal fusion approaches has shown significant promise in improving diagnostic performance and patient outcomes. Furthermore, the development of novel frameworks and models, such as those utilizing retrieval-augmented diagnosis and self-learned knowledge, has the potential to revolutionize clinical practice. Some particularly noteworthy papers in this regard include the introduction of Citrus-V, a multimodal medical foundation model that combines image analysis with textual reasoning, and MACD, a multi-agent clinical diagnosis framework that allows large language models to self-learn clinical knowledge. Overall, these advances have the potential to transform the field of medical imaging analysis and clinical diagnosis, enabling more accurate and efficient diagnosis, and ultimately improving patient outcomes.

Sources

Exploring the Capabilities of LLM Encoders for Image-Text Retrieval in Chest X-rays

Deep learning and abstractive summarisation for radiological reports: an empirical study for adapting the PEGASUS models' family with scarce data

Enhancing WSI-Based Survival Analysis with Report-Auxiliary Self-Distillation

Efficient Extractive Text Summarization for Online News Articles Using Machine Learning

From Data to Diagnosis: A Large, Comprehensive Bone Marrow Dataset and AI Methods for Childhood Leukemia Prediction

Network-Based Detection of Autism Spectrum Disorder Using Sustainable and Non-invasive Salivary Biomarkers

KM-GPT: An Automated Pipeline for Reconstructing Individual Patient Data from Kaplan-Meier Plots

Visionerves: Automatic and Reproducible Hybrid AI for Peripheral Nervous System Recognition Applied to Endometriosis Cases

Learning neuroimaging models from health system-scale data

Content and Quality Analysis of mHealth Apps for Feeding Children with Autism Spectrum Disorder

Frequency-Domain Decomposition and Recomposition for Robust Audio-Visual Segmentation

Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoning

HyKid: An Open MRI Dataset with Expert-Annotated Multi-Structure and Choroid Plexus in Pediatric Hydrocephalus

Revisiting Performance Claims for Chest X-Ray Models Using Clinical Context

Frequency-domain Multi-modal Fusion for Language-guided Medical Image Segmentation

RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis

PS3: A Multimodal Transformer Integrating Pathology Reports with Histology Images and Biological Pathways for Cancer Survival Prediction

MACD: Multi-Agent Clinical Diagnosis with Self-Learned Knowledge for LLM

C$^2$MIL: Synchronizing Semantic and Topological Causalities in Multiple Instance Learning for Robust and Interpretable Survival Analysis

A Versatile Foundation Model for AI-enabled Mammogram Interpretation

A co-evolving agentic AI system for medical imaging analysis

Built with on top of