基于深度学习的自动化对比液囊分析,以改善对赫施普隆病的评估
Paulina Vargova1,2, Matej Varga3, Beatriz Izquierdo Hernandez4
1Department of Pediatric Surgery, Miguel Servet University Hospital, Zaragoza, Spain. pamivarg@gmail.com.
深度神经网络 (DNN) 在分析希尔施普隆病 (HD) 的对比溶液中表现有前途,为专家放射科医生提供了可比的诊断性能. 这种人工智能工具可以帮助标准化诊断,特别是在复杂的病例或资源有限的环境中.
科学领域:
- 放射学 放射学是一门学科.
- 人工智能的人工智能
- 儿科手术 儿科手术
背景情况:
- 赫施普朗格病 (HD) 诊断依赖于对比性阴囊,但准确性因放射科医生的专业知识而异.
- 使用深度神经网络 (DNN) 进行自动图像分析,有可能提高诊断一致性.
研究的目的:
- 通过DNN进行自动化分析,比较使用对比水溶液对希尔施普朗格病 (HD) 的放射性评估.
- 为了评估DNN分类器 (DenseNet121) 在检测HD的性能,用对比的阴囊图像来检测HD.
主要方法:
- 在221名儿科患者 (2011-2023) 中对278个对比液囊进行了回顾性分析.
- 开发一个DenseNet121 DNN分类器用于HD检测.
- 使用平衡的精度,灵敏度,特异性,AUC-ROC,AUC-PR进行性能评估,与专家放射科医生和直肠活检进行比较.
主要成果:
- 在对比液囊水平上,DNN实现了82.8%的平衡精度,72.7%的灵敏度和93.0%的特异性.
- DNN模型实现了0.830的AUC-ROC,与专家放射科医生 (0.804) 相比.
- 放射科医生之间观察者间的适度一致性 (科恩的卡帕=0.475) 被观察到.
结论:
- 该DNN模型在解释怀疑HD的对比溶液时,比放射科医生具有更高的特异性.
- DNN显示出作为诊断支持工具的潜力,有助于标准化,并协助边界或复杂的病例.
- 人工智能驱动的分析可以增强放射性评估,特别是在专家专业知识可能有限的地方.
更多相关视频
09:47Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
06:25Paw-Print Analysis of Contrast-Enhanced Recordings PrAnCER: A Low-Cost, Open-Access Automated Gait Analysis System for Assessing Motor Deficits
Published on: August 12, 2019
相关概念视频
Lower GI Series: Barium Enema
Procedure Details
The examination begins by inserting a lubricated rectal tube into the patient's rectum to administer a radiopaque barium solution. The barium flow is carefully...
Phase Contrast and Differential Interference Contrast Microscopy
In-phase-contrast microscopes, interference between light directly passing through a cell and light refracted by cellular components is used to create high-contrast, high-resolution images without staining. It is the oldest and simplest type of microscope that creates an image by altering the wavelengths of light rays passing through the specimen. Altered wavelength paths are created using an annular stop in the condenser. The annular stop produces a hollow cone of...
Avoidance Learning and Learned Helplessness
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Effect of Hepatic Disease on Pharmacokinetics: Pathophysiologic Assessment and Liver Function Test
Improving Translational Accuracy
Learning Disabilities
Dyslexia
Dyslexia is a...
