Rehman Marwareed, Shafi Imran, Ahmad Jamil, Garcia Carlos Osorio, Barrera Alina Eugenia Pascual, Ashraf Imran
College of Electrical and Mechanical Engineering, National University of Sciences and Technology (NUST), Islamabad, 44000, Pakistan.
Department of Computing, Abasyn University, Islamabad Campus, Islamabad, 44000, Pakistan.
Med Biol Eng Comput. 2025 May;63(5):1249-1270. doi: 10.1007/s11517-024-03265-y. Epub 2024 Dec 21.
The correct analysis of medical images requires the medical knowledge and expertise of radiologists to understand, clarify, and explain complex patterns and diagnose diseases. After analyzing, radiologists write detailed and well-structured reports that contribute to the precise and timely diagnosis of patients. However, manually writing reports is often expensive and time-consuming, and it is difficult for radiologists to analyze medical images, particularly images with multiple views and perceptions. It is challenging to accurately diagnose diseases, and many methods are proposed to help radiologists, both traditional and deep learning-based. Automatic report generation is widely used to tackle this issue as it streamlines the process and lessens the burden of manual labeling of images. This paper introduces a systematic literature review with a focus on analyses and evaluating existing research on medical report generation. This SLR follows a proper protocol for the planning, reviewing, and reporting of the results. This review recognizes that the most commonly used deep learning models are encoder-decoder frameworks (45 articles), which provide an accuracy of around 92-95%. Transformers-based models (20 articles) are the second most established method and achieve an accuracy of around 91%. The remaining articles explored in this SLR are attention mechanisms (10), RNN-LSTM (10), Large language models (LLM-10), and graph-based methods (4) with promising results. However, these methods also face certain limitations such as overfitting, risk of bias, and high data dependency that impact their performance. The review not only highlights the strengths and challenges of these methods but also suggests ways to handle them in the future to increase the accuracy and timely generation of medical reports. The goal of this review is to direct radiologists toward methods that lessen their workload and provide precise medical diagnoses.
医学图像的正确分析需要放射科医生具备医学知识和专业技能，以便理解、阐释和解释复杂的图像模式并诊断疾病。分析之后，放射科医生会撰写详细且结构合理的报告，这有助于对患者进行准确及时的诊断。然而，手动撰写报告往往成本高昂且耗时，放射科医生分析医学图像，尤其是具有多个视图和视角的图像存在困难。准确诊断疾病具有挑战性，为此人们提出了许多方法来帮助放射科医生，既有传统方法，也有基于深度学习的方法。自动报告生成被广泛用于解决这一问题，因为它简化了流程并减轻了图像手动标注的负担。本文介绍了一项系统的文献综述，重点在于分析和评估关于医学报告生成的现有研究。这项系统文献综述遵循了用于结果规划、评审和报告的适当协议。该综述认识到，最常用的深度学习模型是编码器 - 解码器框架（45篇文章），其准确率约为92 - 95%。基于Transformer的模型（20篇文章）是第二常用的方法，准确率约为91%。本系统文献综述中探讨的其余文章涉及注意力机制（10篇）、循环神经网络 - 长短期记忆网络（10篇）、大语言模型（10篇）以及基于图的方法（4篇），都取得了有前景的成果。然而，这些方法也面临某些局限性，如过拟合、偏差风险和高数据依赖性，这些都会影响其性能。该综述不仅突出了这些方法的优势和挑战，还提出了未来应对这些问题的方法，以提高医学报告的准确性和及时生成。本综述的目标是引导放射科医生采用能够减轻其工作量并提供精确医学诊断的方法。
