一个可解释的AI系统通过分层高风险乳腺病变来减少假阳性MRI诊断
Yanting Liang1,2, Zhitao Wei1,2, Yi Dai3
1Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
一个名为BI-RADS 4病变分析系统 (BL4AS) 的AI系统可以从MRI扫描中改善乳腺癌诊断. 它通过提高准确性和降低BI-RADS类别4病变的错误阳性来减少不必要的活检.
科学领域:
- 放射学 放射学是一门学科.
- 人工智能的人工智能
- 在瘤学瘤学.
背景情况:
- 通过MRI诊断乳腺癌面临着高错误阳性率和跨读者变异性的挑战,特别是对于BI-RADS类别4病变.
- 这往往导致不必要的活检,影响患者管理和医疗保健成本.
研究的目的:
- 评估BI-RADS 4病变分析系统 (BL4AS) 的有效性,这是一个AI工具,用于提高使用动态对比增强MRI的乳腺癌检测的诊断准确性.
- 评估BL4AS对降低虚假阳性率和在分类BI-RADS 4病变中的读者间变异性的影响.
主要方法:
- 开发和验证BL4AS人工智能系统,利用动态对比增强MRI的基础模型和时空信息.
- 多中心研究涉及2,686名女性患者的2,803个病变.
- 与放射科医生对BL4AS性能进行比较,包括对诊断准确度,特异性,错误阳性率和读者间变异性的评估.
主要成果:
- BL4AS表现出强的表现,曲线下的面积范围从0.892到0.930.
- 人工智能系统在特异性方面明显超过了放射科医生 (0.889比0.491).
- BL4AS辅助解释提高了诊断准确性,减少了24.5%的读者之间的变化,并减少了27.3%的错误阳性率.
结论:
- BL4AS人工智能系统有效地解决了BI-RADS 4病变的乳腺MRI诊断方面的挑战.
- BL4AS为精确的乳腺癌管理提供了一种实用工具,通过将病变分层为子类别 (4A,4B,4C) 来进行精细的风险评估.
更多相关视频
09:49Non-enzymatic, Serum-free Tissue Culture of Pre-invasive Breast Lesions for Spontaneous Generation of Mammospheres
Published on: November 8, 2014
08:36Ultrasound Imaging-guided Intracardiac Injection to Develop a Mouse Model of Breast Cancer Brain Metastases Followed by Longitudinal MRI
Published on: March 6, 2014
相关概念视频
Stratified Sampling Method
To choose a stratified sample, divide the population into groups called strata and then take a...
False Memories
One primary source of false memories is misattribution, where individuals incorrectly associate external information...
Diagnosing Acidosis and Alkalosis
First, the pH level is assessed to determine whether the blood pH is normal (7.35–7.45), low (acidosis), or high (alkalosis).
Next, the PCO2 and...
Relative Risk
Interpreting R Charts
An R chart plots the range of subsets of measurements collected from a process. Each point on the chart represents the range—defined as the difference between the maximum and minimum...
Classification of Epithelial Tissues: Stratified Epithelium
