Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 30, 2026

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

A multi-expert deep learning framework with LLM-guided arbitration for multimodal histopathology prediction.

Shyam Sundar Debsarkar¹, V B Surya Prasath²

¹Department of Computer Science, University of Cincinnati, OH 45221, USA.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society

|January 10, 2026

Summary

Related Concept Videos

Introduction to Language of Pathophysiology ll

Introduction to Language of Pathophysiology ll

This lesson explores key terms that describe how diseases progress, their outcomes, and their distribution in populations.Diagnostic tests identify diseases and monitor treatment. These include blood and urine tests, biopsies, imaging (X-ray, MRI), and detection of infectious agents.Remission is a reduction or disappearance of symptoms.Exacerbation refers to the worsening of symptoms, such as increased wheezing during an asthma attack.A precipitating factor triggers an acute episode, while a...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

SpaDiffHis: Sparse-point Guided Diffusion for Histopathology Image Synthesis with Contrastive Learning.

IEEE journal of biomedical and health informatics·2026

Same author

Cross-Architecture Knowledge Distillation for Histopathological Image Analysis.

IEEE access : practical innovations, open solutions·2026

Same author

End-to-End Multimodal Multiple Instance Learning for Cancer Histopathology Classification with Dual-Attention Fusion.

Journal of medical systems·2026

Same author

Pathology Public Datasets for Artificial Intelligence: A Systematic Review.

Journal of imaging informatics in medicine·2026

Same author

Web based AI-driven framework combining multi-modal data with CNN and LLM for Parkinson's disease diagnosis.

Scientific reports·2025

Same author

Benchmarking HEp-2 cell segmentation methods in indirect immunofluorescence images - standard models to deep learning.

Computers in biology and medicine·2025

A new AI framework uses a large language model (LLM) to combine insights from pathology images and clinical data, improving cancer diagnosis accuracy and interpretability. This multi-expert, LLM-arbitrated approach offers more robust and explainable decisions than traditional methods.

Area of Science:

Digital pathology
Artificial intelligence in medicine
Computational pathology

Background:

Deep learning enhances computational pathology accuracy, but conventional methods lack adaptability and interpretability.
Current artificial intelligence (AI) expert models offer complementary views, yet simple output aggregation struggles with disagreement and transparency.
Clinical integration of AI in pathology is hindered by challenges in model adaptability and decision interpretability.

Purpose of the Study:

To develop a novel multi-expert framework using a large language model (LLM) as an arbitrator for improved diagnostic decisions in computational pathology.
To enhance the adaptability and interpretability of AI models in clinical pathology settings by integrating diverse data sources.
To address inter-model disagreement and provide transparent, rational decisions by leveraging LLM's reasoning capabilities.

Keywords:

Agentic AI Deep learning Histopathology Large language models Multimodal

Related Experiment Videos

Last Updated: Jun 30, 2026

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

Main Methods:

Proposed a multi-expert framework integrating vision-based AI predictors and a clinical feature model, with an LLM acting as an arbitrator.
Validated the framework on gastric (HMU-GC-HE-30K) and breast cancer (BCNB) histopathology datasets, including multimodal data.
Tested various LLMs (LLaMA, GPT variants, Mistral) and incorporated learned per-agent trust for improved arbitration.

Main Results:

The multi-expert, LLM-arbitrated framework (MELLMA) outperformed standard convolutional neural networks (CNNs) and transformers in classification tasks.
The proposed framework demonstrated superior performance compared to single-agent CNN/ViT baselines and conventional ensembling methods (majority vote, average, meta-learners).
Learned per-agent trust significantly improved arbitrator decisions without altering prompts or data, enhancing robustness and explainability.

Conclusions:

LLM-guided arbitration provides more robust and explainable performance in computational pathology than individual models or conventional ensembling.
The developed framework shows significant promise for creating transparent and extensible AI systems in digital pathology.
Integrating LLMs as arbitrators represents a key advancement for clinical decision support in AI-driven pathology.