对YOLO模型的超参数优化,用于侵袭性冠状动脉血管学病变检测和评估
Mario Pascual-González1, Ariadna Jiménez-Partinen2, Esteban J Palomo2
1Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina-IBIMA Plataforma BIONAND, Málaga TechPark, Campanillas, 29590, Spain.
Computers in biology and medicine
|July 25, 2025
概括
这项研究优化了对冠状动脉疾病检测中的YOLOv8模型的超参数搜索. 基于模型的优化器,如CMA-ES和TPE显著提高F1-Score的性能比默认方法.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 心血管疾病 心血管疾病
背景情况:
- 冠状动脉疾病 (CAD) 是导致死亡的主要原因,需要改进基于图像的诊断工具.
- 目前用于狭窄检测的YOLOv8探测器对众多超参数敏感,阻碍了可重现性.
- 优化这些超参数对于提高CAD检测系统的准确性和可靠性至关重要.
研究的目的:
- 系统地评估基于YOLOv8的模型在冠状动脉疾病检测中的超参数优化策略.
- 将基于模型的优化引擎 (CMA-ES,TPE,高斯过程) 与随机搜索和默认程序进行比较.
- 在固定计算预算下确定最有效的优化方法来最大限度地提高F1-Score.
主要方法:
- 配对YOLOv8及其双坐标注意 (DCA) 变体,使用CMA-ES,TPE和高斯过程采样器.
- 使用CADICA和ARCADE数据集用于狭窄检测的基准优化性能.
- 员工分层三重交叉验证以最大限度地提高F1分数.
主要成果:
- 基于模型的优化方法始终改善了F1速度的帕雷托边界.
- 在YOLOv8大型模型上,CMA-ES获得了0.355±0.079的F1分.
- 贝叶斯策略 (TPE,高斯过程) 在中型和小型骨干中领先,F1-分数分别为0.346±0.048和0.304±0.054.
- 所有测试的基于模型的方法都超过了默认优化器,并产生了更多以病变为中心的突出性地图.
结论:
- 适应性概率性搜索策略为调整高维的基于YOLO的CAD检测管道提供了显著的优势.
- 基于模型的优化器提高了冠状动脉疾病深度学习模型的性能和可解释性.
- 该研究提供了一个开源代码库,用于人工智能驱动的心血管诊断中的可重复研究.
相关概念视频
Radiological Investigation III: Pulmonary Angiogram and PET Scan
170
Radiological investigations are paramount in the diagnosis and management of various pulmonary diseases. Two essential investigations are the Pulmonary Angiogram and the Positron Emission Tomography (PET) Scan.
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
170
Sensitivity, Specificity, and Predicted Value
669
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
Sensitivity is the...
669


