基于YOLOv10检测黑色细胞瘤:反向排除优化用于黑色素瘤查
ShengJie Wang1, Jian Wang1, Rui Yin1
1International Sakharov Environmental Institute, Belarusian State University, Minsk, Belarus.
Frontiers in artificial intelligence
|September 29, 2025
概括
这项研究引入了一种新的AI模型,用于在中国患者中早期检测黑色素瘤,大大减少了假阴性和不必要的活检. 反向排除策略优先确定良性病变,提高查准确度.
科学领域:
- 皮肤病学 皮肤病学
- 人工智能的人工智能
- 医疗成像医学成像
背景情况:
- 恶性黑色素瘤是一种致命的皮肤癌,在早期阶段经常被误诊为良性瘤.
- 目前的查方法有很高的失败率,导致过度活检,特别是在东亚人群中.
- 需要改进早期检测工具,以减少死亡率和医疗保健成本.
研究的目的:
- 开发和验证一种人工智能模型,用于在中国东亚患者中准确早期检测黑色素瘤.
- 为了提高诊断效率,实施反向排除策略 ("先良性,排除恶性").
- 显著降低黑色素瘤假阴性率 (FNR) 并尽量减少不必要的活检.
主要方法:
- 一个实时物体检测模型 (YOLOv10) 被增强了PP-LCNet骨干,多尺度上下文注意力 (MCA) 部和Shape-IoU损失.
- 该模型在来自中国大陆的2,040个良性 nevi的多中心数据集上进行了训练.
- 独立测试对来自人口统计学上不同群体的365种活检证明的黑色素瘤进行了独立测试.
主要成果:
- 对于良性病变,人工智能模型实现了97.69%的检测平均精度 (mAP@0.5).
- 黑色素瘤假阴性率 (FNR) 非常低,为0.27%,远低于0.5%的临床安全上限.
- 该模型在识别良性病变方面表现出高精度,从而有效排除恶性病变.
结论:
- 拟议的AI模型为中国临床环境中早期黑色素瘤查提供了高精度,低风险的途径.
- 这种方法可以大幅减少不必要的活检,同时保持临床上可接受的错误率.
- 早期检测和准确的诊断得到保留,扩大了救命治疗的窗口.
相关概念视频
01:30Skin Cancer
5.7K
Skin cancer is a type of cancer that occurs when there is an abnormal growth of skin cells, usually triggered by damage to the DNA within the skin cells. It is primarily caused by exposure to ultraviolet (UV) radiation from the sun or artificial sources like tanning beds. Skin cancer is the most common type of cancer worldwide, and its incidence continues to rise.
Basal Cell Carcinoma (BCC): BCC is the most common type of skin cancer, accounting for about 80% of cases. It typically develops in...
Basal Cell Carcinoma (BCC): BCC is the most common type of skin cancer, accounting for about 80% of cases. It typically develops in...
5.7K
01:21Cancer Survival Analysis
648
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
648
01:05Difference from Background: Limit of Detection
8.0K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
8.0K