对可解释的人工智能模型和放射科医生审查性能进行比较,以检测752名患者的乳腺癌
Pelin Seher Oztekin1, Oguzhan Katar2, Tulay Omma3
1Department of Radiology, University of Health Sciences, Ankara Training and Research Hospital, Ankara, Turkey.
概括
一个人工智能 (AI) 模型,X2GAI,准确地分类乳腺癌病变,提高诊断可靠性,减少不必要的活检. 这种人工智能工具在协助放射科医生和提高患者护理方面表现有前途.
科学领域:
- 在瘤学瘤学.
- 放射学 放射学是一门学科.
- 人工智能的人工智能
背景情况:
- 准确的乳腺癌诊断至关重要,以避免不必要的患者焦虑和像活检这样的侵入性手术.
- 目前的诊断方法,包括放射性检查,有时会导致假阳性和错误诊断.
- 需要先进,可靠的方法来提高乳腺癌检测的准确性.
研究的目的:
- 开发和评估一种基于人工智能 (AI) 的方法,用于将乳腺固体质病变自动分类为良性或恶性.
- 创建和利用一个新的乳腺癌数据集 (乳腺XD) 来培训和测试AI分类器.
- 提高AI模型在乳腺癌诊断中的可靠性和可解释性.
主要方法:
- 一个新的数据集,乳腺XD,包括来自752名患者的791个固体质病变.
- 六个机器学习分类器,包括SVM,K-NN,RF,DT,LR和XGBoost,在数据集上接受了培训.
- 开发了一个可解释的XGBoost模型 (X2GAI) 用于分类和可靠性评估.
主要成果:
- 在未见的测试数据上,X2GAI模型实现了最高的分类准确率94.34%.
- 该模型表现出强的性能,特别是在放射科医生之前提供了假阳性诊断的情况下.
- 将一个可解释的结构集成到模型中,以增强诊断信任和透明度.
结论:
- 开发的X2GAI模型在分类乳腺病变方面显示了与经验丰富的放射科医生相比或更高的性能.
- 人工智能模型正确识别恶性病变的能力可以帮助减少假阳性和不必要的活检的需要.
- 这种人工智能驱动的方法为提高乳腺癌诊断的准确性和效率提供了一个有希望的工具.
更多相关视频
相关概念视频
01:15Receiver Operating Characteristic Plot
115
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
115
01:30Radiological Investigation I: X-ray and CT
220
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
220