paper-with-me

홈 › Papers

Uncovering Knowledge Gaps in Radiology Report Generation Models through Knowledge Graphs

2024-08-26 · Xiaoman Zhang, Julián N. Acosta, Hong-Yu Zhou, Pranav Rajpurkar

Recent advancements in artificial intelligence have significantly improved the automatic generation of radiology reports. However, existing evaluation methods fail to reveal the models' understanding of radiological images and their capacity to achieve human-level granularity in descriptions. To bridge this gap, we introduce a system, named ReXKG, which extracts structured information from processed reports to construct a comprehensive radiology knowledge graph. We then propose three metrics to evaluate the similarity of nodes (ReXKG-NSC), distribution of edges (ReXKG-AMS), and coverage of subgraphs (ReXKG-SCS) across various knowledge graphs. We conduct an in-depth comparative analysis of AI-generated and human-written radiology reports, assessing the performance of both specialist and generalist models. Our study provides a deeper understanding of the capabilities and limitations of current AI models in radiology report generation, offering valuable insights for improving model performance and clinical applicability.

📄 PDF Abstract BibTeX arXiv:2408.14397

Code (1)

rajpurkarlab/rexkg 공식 구현 pytorch

Tasks

Knowledge Graphs

Similar Papers 제목 키워드 기반

ReXamine-Global: A Framework for Uncovering Inconsistencies in Radiology Report Generation Metrics

2024-08-29 · Oishi Banerjee, Agustina Saenz, Kay Wu, Warren Clements 외

Given the rapidly expanding capabilities of generative AI models for radiology, there is a need for robust metrics that can accurately measure the quality of AI-generated radiology reports across diverse hospitals. We de…

Knowledge Matters: Radiology Report Generation with General and Specific Knowledge

2021-12-30 · Shuxin Yang, Xian Wu, Shen Ge, Shaohua Kevin Zhou 외

Automatic radiology report generation is critical in clinics which can relieve experienced radiologists from the heavy workload and remind inexperienced radiologists of misdiagnosis or missed diagnose. Existing approache…

DecoderGeneral KnowledgeImage Captioning

Can Prompt Learning Benefit Radiology Report Generation?

2023-08-30 · Jun Wang, Lixing Zhu, Abhir Bhalerao, Yulan He

Radiology report generation aims to automatically provide clinically meaningful descriptions of radiology images such as MRI and X-ray. Although great success has been achieved in natural scene image captioning tasks, ra…

Image CaptioningPrompt EngineeringPrompt Learning

A Self-Guided Framework for Radiology Report Generation

2022-06-19 · Jun Li, Shibo Li, Ying Hu, Huiren Tao

Automatic radiology report generation is essential to computer-aided diagnosis. Through the success of image captioning, medical report generation has been achievable. However, the lack of annotated disease labels is sti…

Image CaptioningMedical Report Generation

Prior Knowledge Enhances Radiology Report Generation

2022-01-11 · Song Wang, Liyan Tang, Mingquan Lin, George Shih 외

Radiology report generation aims to produce computer-aided diagnoses to alleviate the workload of radiologists and has drawn increasing attention recently. However, previous deep learning methods tend to neglect the mutu…