arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.16611cs.CVcs.AI
收藏

一种用于医学诊断中实时图像处理的深度学习框架:提升临床应用中的准确性和速度

A Deep Learning Framework for Real-Time Image Processing in Medical Diagnostics: Enhancing Accuracy and Speed in Clinical Applications

University of Rochester(罗切斯特大学);Islamic Azad University(伊斯兰阿扎德大学)

Melika Filvantorkaman, Maral Filvan Torkaman

AI总结:

本文提出融合 U-Net、EfficientNet 与 Transformer 并结合剪枝、量化和 GPU 加速的实时医学影像分析框架,在多模态临床任务中实现高准确率、低延迟与可解释部署。

摘要:

医学成像在现代诊断中发挥着至关重要的作用;然而,解读高分辨率放射学数据仍然耗时,并且容易受到临床医生之间差异的影响。传统图像处理技术往往缺乏实时临床使用所需的精确性、鲁棒性和速度。为克服这些局限,本文提出一种用于实时医学图像分析的深度学习框架,旨在提升多种成像模态(包括 X-ray、CT 和 MRI)中的诊断准确性与计算效率。所提出的系统将 U-Net、EfficientNet 和基于 Transformer 的模型等先进神经网络架构,与模型剪枝、量化和 GPU 加速等实时优化策略相结合。该框架支持在边缘设备、本地服务器和云基础设施上灵活部署,确保与 PACS 和 EHR 等临床系统实现无缝互操作。在公共基准数据集上的实验评估展示了最先进性能,分类准确率超过 92%,分割 Dice 分数超过 91%,推理时间低于 80 毫秒。此外,Grad-CAM 和分割叠加等可视化解释工具增强了透明度和临床可解释性。这些结果表明,所提出的框架能够显著加快诊断工作流程、减轻临床医生负担,并支持在时间紧迫的医疗环境中进行可信的 AI 集成。

英文摘要:

Medical imaging plays a vital role in modern diagnostics; however, interpreting high-resolution radiological data remains time-consuming and susceptible to variability among clinicians. Traditional image processing techniques often lack the precision, robustness, and speed required for real-time clinical use. To overcome these limitations, this paper introduces a deep learning framework for real-time medical image analysis designed to enhance diagnostic accuracy and computational efficiency across multiple imaging modalities, including X-ray, CT, and MRI. The proposed system integrates advanced neural network architectures such as U-Net, EfficientNet, and Transformer-based models with real-time optimization strategies including model pruning, quantization, and GPU acceleration. The framework enables flexible deployment on edge devices, local servers, and cloud infrastructures, ensuring seamless interoperability with clinical systems such as PACS and EHR. Experimental evaluations on public benchmark datasets demonstrate state-of-the-art performance, achieving classification accuracies above 92%, segmentation Dice scores exceeding 91%, and inference times below 80 milliseconds. Furthermore, visual explanation tools such as Grad-CAM and segmentation overlays enhance transparency and clinical interpretability. These results indicate that the proposed framework can substantially accelerate diagnostic workflows, reduce clinician workload, and support trustworthy AI integration in time-critical healthcare environments.

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。

↑