Knowledge Matters: Radiology Report Generation with General and Specific Knowledge
This work addresses the challenge of generating accurate radiology reports to reduce workload and errors for radiologists, representing an incremental improvement by enhancing existing methods with domain-specific knowledge.
The paper tackles the problem of automatic radiology report generation by addressing visual and textual biases and lack of expert knowledge in existing image captioning methods, proposing a knowledge-enhanced approach that integrates general and specific medical knowledge to improve report quality, with experimental results showing it outperforms state-of-the-art methods on IU-XRay and MIMIC-CXR datasets.
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 approaches mainly formulate radiology report generation as an image captioning task and adopt the encoder-decoder framework. However, in the medical domain, such pure data-driven approaches suffer from the following problems: 1) visual and textual bias problem; 2) lack of expert knowledge. In this paper, we propose a knowledge-enhanced radiology report generation approach introduces two types of medical knowledge: 1) General knowledge, which is input independent and provides the broad knowledge for report generation; 2) Specific knowledge, which is input dependent and provides the fine-grained knowledge for report generation. To fully utilize both the general and specific knowledge, we also propose a knowledge-enhanced multi-head attention mechanism. By merging the visual features of the radiology image with general knowledge and specific knowledge, the proposed model can improve the quality of generated reports. Experimental results on two publicly available datasets IU-Xray and MIMIC-CXR show that the proposed knowledge enhanced approach outperforms state-of-the-art image captioning based methods. Ablation studies also demonstrate that both general and specific knowledge can help to improve the performance of radiology report generation.