集成深度学习和放射学在分辨乳头甲状腺微癌从乳头甲状腺癌与超声波图像的深度学习和放射学
Bing Yu1,2, Huijuan He3, Qiao Zheng2
1Purchasing Center Department, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, 310020, People's Republic of China.
Cancer management and research
|July 14, 2025
概括
结合深度学习和放射学模型,在区分乳头甲状腺癌和小瘤方面表现有前途. 这种方法可以帮助减少乳头甲状腺小癌和相关并发症的过度治疗.
科学领域:
- 医疗成像医学成像
- 人工智能在医学中的应用
- 在瘤学瘤学.
背景情况:
- 乳头甲状腺微瘤 (PTMC) 经常被过度治疗,因为与乳头甲状腺癌 (PTC) 的区分存在挑战.
- 精确的手术前分化对于避免不必要的治疗和潜在的并发症至关重要.
研究的目的:
- 评估基于超声波的放射学,深度学习 (DL) 和联合DL-放射学模型的可行性和准确性.
- 区分PTC和PTMC,减少过度处理的风险.
主要方法:
- 放射学特征和五个DL网络 (VGG13,VGG16,VGG19,AlexNet,EfficientNet) 由549名患者的超声图像生成.
- 组合DL-放射学模型被构建以增强差异化.
- 来自两个医院的独立测试套件被用于验证.
主要成果:
- 放射学模型实现了0.826 (测试组1) 和0.822 (测试组2) 的曲线下面积 (AUC).
- VGG19获得了最高的AUC (0.890),而EfficientNet获得了最佳准确度 (0.867).
- 组合模型 (VGG+radiomics和EfficientNet+radiomics) 显示出卓越的性能,其AUC高达0.946.
结论:
- 结合DL-放射学模型提供了一种非侵入性,手术前的方法来区分PTC和PTMC.
- 这些模型具有显著的潜力,可以减少PTMC的过度治疗和最大限度地减少相关并发症.
相关概念视频
Ultrasonography
6.2K
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...
6.2K
Imaging Studies II: Ultrasonography
59
IntroductionUltrasonography, or renal ultrasound, is a noninvasive medical imaging technique that uses high-frequency sound waves to visualize the kidneys, ureters, bladder, and surrounding tissues.Indications for Urinary System UltrasonographyUrinary system ultrasonography is indicated in various clinical scenarios, such as:Kidney Stones (Urolithiasis): To detect and monitor the size and presence of kidney or urinary tract stones.Hydronephrosis: To assess the dilation of the renal pelvis and...
59


