深度学习对腹腔大动脉动脉瘤的超声波查进行深度学习的未来临床评估
I-Min Chiu1,2,3, Tien-Yu Chen4, You-Cheng Zheng4
1Department of Emergency Medicine, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.
NPJ digital medicine
|October 15, 2024
概括
深度学习 (DL) 指导新手护士在腹腔大动脉瘤 (AAA) 查中使用护理点超声波 (POCUS). 经过DL辅助的护士获得了与医生可比的扫描质量,改善了早期AAA检测.
科学领域:
- 医疗成像医学成像
- 医疗保健中的人工智能
- 心血管诊断心血管诊断服务
背景情况:
- 腹腔大动脉动脉瘤 (AAA) 通常不会被检测到,直到破裂,因为诊断超声波的访问有限.
- 通过查及早检测对于防止AAA破裂至关重要.
研究的目的:
- 评估深度学习 (DL) 算法的有效性,指导新手护士进行AAA查.
- 在AAA查中,将DL指导的新手护士与经验丰富的医生的表现进行比较.
主要方法:
- 10名没有超声波经验的护士在65岁以上的患者身上进行了15次扫描,并使用DL物体检测算法进行了扫描.
- 超声波扫描的质量由三个盲目的专家医生评估.
- 在预测AAA和大动脉宽度方面,DL模型的性能与医生扫描相比较.
主要成果:
- 在87.5%的病例中,DL引导的新手获得了足够的扫描质量,与医生获得的91.3%相比 (p=0.310).
- DL模型在预测AAA方面表现出很高的准确性 (AUC=0.975,100%的灵敏度,97.8%的特异性).
- 与医生相比,预测大动脉宽度的平均绝对误差为2.8毫米.
结论:
- 深度学习引导的护理点超声波 (POCUS) 可以有效地训练新手护士进行AAA查.
- 这种方法显示了民主化AAA查的潜力,使其超出经验丰富的专家的范围.
- 通过DL引导的POCUS提供了与经验丰富的医生可比的性能,提高了腹腔大动脉动脉瘤的早期检测率.
相关概念视频
Aneurysm II: Clinical Manifestations and Diagnostic Studies
3
Thoracic, aortic arch and abdominal aneurysms are significant vascular conditions that can present with various clinical manifestations and lead to serious complications. Understanding these manifestations and the appropriate diagnostic studies is essential for effective management and treatment.Thoracic Aortic AneurysmsThoracic aortic aneurysms often remain asymptomatic until they reach a size that impinges on adjacent structures. They typically cause deep, diffuse chest pain that radiates to...
3
Ultrasonography
4.3K
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...
4.3K


