一种新的集体学习方法,用于分组最先进的YOLOV10和YOLOV11模型,用于CT和超声波图像中检测结石
Ali Mahmoud Mayya1, Nizar Faisal Alkayem2
1Computer and Automatic Control Engineering Department, Faculty of Mechanical and Electrical Engineering, Latakia University (Formerly Called Tishreen University), Latakia, 2230, Syria.
Journal of imaging informatics in medicine
|April 15, 2025
概括
这项研究引入了一种新的深度学习组合模型,用于改善医疗图像中的结石检测. 新的框架提高了检测准确性,超过了单个模型和当前方法.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 腎臟病學 (nephrology) 是一種醫學專業.
背景情况:
- 检测石对于保持脏健康至关重要,但在医学成像中仍然是一个具有挑战性的任务.
- 准确和精确地定位结石对于有效的治疗计划至关重要.
- 关于结石检测方法的学术文献有限.
研究的目的:
- 开发一个先进的深度学习框架,以准确检测结石.
- 为了提高医疗图像中结石识别的精度和回忆力.
- 创建一个组合模型,将YOLOV10和YOLOV11结合起来,以提高性能.
主要方法:
- 使用了两个成像模式:计算机断层扫描 (CT) 和超声波.
- 开发了一个新的整体框架,集成YOLOV10和YOLOV11深度学习模型.
- 对集体模型的表现与单个模型和最先进的方法进行了评估.
主要成果:
- 与CT图像上的最佳单独模型相比,整体模型的精度提高了5.4%,回忆率提高了2.4%,F1得分提高了1.3%.
- 基于超声波的数据集显示F1得分有1%的改善,Map50得分有1.34%的增加.
- 拟议的深度学习整体框架在单个模型和现有方法论上表现出卓越的性能.
结论:
- 新型组合框架显著提高了结石检测的准确性,并减少了错误.
- 将YOLOV10和YOLOV11结合在一个整体方法中,为结石检测提供了卓越的性能.
- 这种深度学习方法显示出改善科诊断能力的前景.
相关概念视频
Ultrasonography
4.2K
Ultrasonography is an imaging technique that uses high-frequency sound waves to visualize the body's internal structures. It is a non-invasive and safe procedure that does not involve the use of ionizing radiation, making it widely used in various medical fields. Ultrasonography is used to study heart function, blood flow in the neck or extremities, certain conditions such as gallbladder disease, and fetal growth and development.
During an ultrasonography procedure, a handheld device called...
During an ultrasonography procedure, a handheld device called...
4.2K
Kidney Structure
67.0K
The kidneys are two large bean-shaped organs located in the upper abdomen. They filter the blood several times a day to remove toxins and rebalance water and electrolytes of the circulatory system via the renal veins. The kidneys receive blood directly from the heart via the renal arteries. These arteries enter the kidney at the hilum, the concave surface of the bean, where they branch and divide into smaller vessels and capillaries.
67.0K


