arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.09378cs.CLcs.CV
收藏

一个自指导的放射学报告生成框架

A Self-Guided Framework for Radiology Report Generation

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);Shenzhen University General Hospital(深圳大学总医院)

Jun Li, Shibo Li, Ying Hu, Huiren Tao

摘要:

放射学报告的自动生成是计算机辅助诊断的关键。通过图像描述的成功,医疗报告的生成已经是可以实现的。然而,缺乏注释的疾病标签仍然是该领域的瓶颈。此外,图文数据偏差问题和复杂的句子使得生成准确的报告更加困难。为了解决这些差距,我们提出了一个自我指导框架(SGF),这是一套无监督和有监督的深度学习方法,用于模仿人类学习和写作的过程。具体地说,我们的框架从医疗报告中获取领域知识,而不需要额外的疾病标签,并引导自己提取与文本相关的细粒度视觉特征。此外,SGF成功地提高了医疗报告生成的准确性和长度,通过引入一个相似性比较机制,模仿人类自我完善的过程中,通过比较实践。大量的实验证明了我们的SGF在大多数情况下的实用性,显示出其优越的性能超过国家的最先进的方法。我们的研究结果突出了所提出的框架的能力,区分细粒度的视觉细节之间的话,并验证其优势,在生成医疗报告。

英文摘要:

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 still the bottleneck of this area. In addition, the image-text data bias problem and complex sentences make it more difficult to generate accurate reports. To address these gaps, we pre-sent a self-guided framework (SGF), a suite of unsupervised and supervised deep learning methods to mimic the process of human learning and writing. In detail, our framework obtains the domain knowledge from medical reports with-out extra disease labels and guides itself to extract fined-grain visual features as-sociated with the text. Moreover, SGF successfully improves the accuracy and length of medical report generation by incorporating a similarity comparison mechanism that imitates the process of human self-improvement through compar-ative practice. Extensive experiments demonstrate the utility of our SGF in the majority of cases, showing its superior performance over state-of-the-art meth-ods. Our results highlight the capacity of the proposed framework to distinguish fined-grained visual details between words and verify its advantage in generating medical reports.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑