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

Related Concept Videos

Genome Annotation and Assembly

Genome Annotation and Assembly

The genome refers to all of the genetic material in an organism. It can range from a few million base pairs in microbial cells to several billion base pairs in many eukaryotic organisms. Genome assembly refers to the process of taking the DNA sequencing data and putting it all back together in a correct order to create a close representation of the original genome. This is followed by the identification of functional elements on the newly assembled genome, a process called genome annotation.

You might also read

Related Articles

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

Sort by

Same author

AI for Radiology: A Primer Part II. Interacting with AI Results.

Radiology·2026

Same author

Radiology Reimagined: Interoperability and Lessons Learned from the Imaging AI in Practice Demonstration.

Radiology·2026

Same author

Extensive Molluscum Contagiosum With Atypical Verrucous Lesion on Scalp Mimicking Warts in an Immunocompromised Host.

Indian dermatology online journal·2026

Same author

Brain tumor segmentation in Sub-Saharan Africa patient population: The BraTS-Africa challenge.

Neuro-oncology advances·2026

Same author

Multi-Institutional Annotated Multiparametric MRI Dataset of Pediatric High-Grade Gliomas.

Radiology. Artificial intelligence·2026

Same author

Rethinking Pulmonary Embolism Segmentation: A Study of Current Approaches and Challenges with an Open Weight Model.

Journal of imaging informatics in medicine·2026

Search research articles

Related Experiment Video

Updated: Jun 15, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Open-Weight Language Models and Retrieval-Augmented Generation for Automated Structured Data Extraction from

Mohamed Sobhi Jabal¹, Pranav Warman², Jikai Zhang^3,4

¹Department of Radiology, Duke University Hospital, 2301 Erwin Rd, Durham, NC 27710.

Radiology. Artificial Intelligence

|March 12, 2025

Summary

Open-weight language models (LMs) with retrieval-augmented generation (RAG) can accurately extract structured data from radiology and pathology reports. Fine-tuned LMs and prompt engineering are key for optimal performance in health care reports.

Keywords:

Health Care Reports Large Language Models Pathology Radiology Retrieval-Augmented Generation

More Related Videos

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Related Experiment Videos

Last Updated: Jun 15, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Area of Science:

Artificial Intelligence in Medicine
Natural Language Processing in Healthcare

Background:

Unstructured clinical reports pose challenges for data extraction.
Automated systems are needed to efficiently process radiology and pathology reports.

Purpose of the Study:

To develop and evaluate an automated system for structured clinical information extraction from unstructured reports.
To assess the impact of language models (LMs) and retrieval-augmented generation (RAG) configurations on extraction performance.

Main Methods:

Retrospective study using radiology (BT-RADS scores) and pathology (IDH mutation status) report datasets.
Developed an automated pipeline to benchmark various LMs and RAG configurations.
Systematically evaluated effects of model size, quantization, prompting, and inference parameters.

Main Results:

Achieved up to 98% accuracy for BT-RADS scores and >90% for IDH mutation status.
Medical fine-tuned Llama 3 performed best; larger, newer, domain-fine-tuned models outperformed older/smaller ones.
Few-shot prompting significantly improved accuracy; RAG enhanced complex pathology report extraction.

Conclusions:

Open LMs with RAG show potential for privacy-preserving, automated structured data extraction from clinical reports.
Careful model selection, prompt engineering, and data-driven optimization are crucial for performance.