在超声波扫描中使用Fast-Unet+完全自动化的图像生物标志物预测
Mostafa Ghelich Oghli1, Seyed Morteza Bagheri2, Ali Shabanzadeh3
1Research and Development Department, Med Fanavaran Plus Co., Karaj, Iran. m.g31_mesu@yahoo.com.
Scientific reports
|February 27, 2024
概括
一个新的Fast-Unet++模型精确地分割了超声波中的图像,从而能够精确地测量的尺寸和体积,以检测疾病.
科学领域:
- 医疗成像医学成像
- 人工智能在医学中的应用
- 腎臟病學 (nephrology) 是一種醫學專業.
背景情况:
- 的尺寸和体积变化是疾病的关键指标.
- 准确的细分对于预测这些大小和体积指标至关重要.
- 超声波是评估的主要诊断成像方式.
研究的目的:
- 提出一个新的卷积神经网络,Fast-Unet++,用于超声波图像中精确的脏细分.
- 用细分面具来估计的尺寸和体积.
- 根据现有模型和临床数据评估Fast-Unet++的性能.
主要方法:
- 开发和培训Fast-Unet++卷积神经网络,用于细分斜和轴图像.
- 从预测的细分口罩中估计脏生物标志物 (体积,长度,宽度,厚度,对酶体厚度).
- 使用子度量,贾卡德系数和平均绝对距离进行评估,以获得细分精度.
- 基于公共数据集和一组接受过超声波和计算机断层扫描的患者的验证.
主要成果:
- 实现了高细分精度,Dice的指标为0.97 (斜面) 和0.95 (轴面).
- 在估计尺寸和体积方面表现出强的表现,使用准确度,AUC,灵敏度,特异性,精度和F1.
- 该模型在与相关网络和临床数据进行测试时显示了可比或优异的结果.
结论:
- 在超声波成像中,Fast-Unet++为脏细分提供了快速而准确的解决方案.
- 该模型精确估计的尺寸和体积的能力有助于诊断疾病.
- 这种人工智能驱动的方法具有改善非侵入性评估的巨大潜力.
相关概念视频
Ultrasonography
4.5K
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...
4.5K
Ultrasound II: Endoscopic Ultrasound and FibroScan
105
Endoscopic Ultrasound (EUS) and FibroScan are valuable diagnostic tools in gastroenterology and hepatology, each with specific applications and techniques.
Endoscopic Ultrasound (EUS):
Endoscopic Ultrasound (EUS):
105


