使用U-Net 3+模型在 Fundus图像中的出血细分:在视网膜区域的性能比较
Yeong Hun Kang1, Young Jae Kim2, Kwang Gi Kim3,4,5
1Department of Biomedical Engineering, College of IT Convergence, Gachon University, Seongnam, Korea.
Journal of imaging informatics in medicine
|January 21, 2026
概括
这项研究表明,U-Net3+模型在 fundus 图像中准确地细分了视网膜出血,有助于早期检测糖尿病视网膜病变 (DR). 它的性能可靠跨不同的视网膜区域和疾病严重程度.
科学领域:
- 眼科医生 眼科 眼科
- 医疗成像医学成像
- 人工智能的人工智能
背景情况:
- 糖尿病视网膜病变 (DR) 是糖尿病患者视力丧失的主要原因.
- 早期发现视网膜出血对于及时干预和预防失明至关重要.
研究的目的:
- 评估U-Net3+模型在 fundus图像中的像素级出血细分.
- 分析模型在各种临床相关的视网膜区域和出血负担中的性能.
主要方法:
- 利用U-Net3+深度学习模型进行自动化出血细分.
- 使用准确度,灵敏度,特异性和 Dice 评分来评估性能.
- 分析了周血管/外血管区域,体/外体区域,象限和出血严重程度的细分结果.
主要成果:
- U-Net3+实现了高整体性能:准确率为99.93%,灵敏度为87.03%,特异性为99.97%,子得分为85.02%.
- 细分精度在外血管区域和叶区域更高.
- 模型表明,在较高的出血负担下,可靠性增加.
结论:
- U-Net3+显示了自动化糖尿病视网膜病变查的显著潜力.
- 区域意识评估对于理解模型性能很重要.
- 临床部署需要进一步的多中心验证.
相关概念视频
Pharmacokinetic Models: Comparison and Selection Criterion
351
Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
351
The Sense of Self: Reflected Self-Appraisal and Social Comparison
55.5K
According to Charles Cooley, we base our image on what we think other people see (Cooley 1902). We imagine how we must appear to others, then react to this speculation. We don certain clothes, prepare our hair in a particular manner, wear makeup, use cologne, and the like—all with the notion that our presentation of ourselves is going to affect how others perceive us. We expect a certain reaction, and, if lucky, we get the one we desire and feel good about it. But more than that, Cooley...
55.5K
IR Frequency Region: Fingerprint Region
1.9K
IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...
1.9K
Multiple Comparison Tests
4.4K
Multiple comparison test, abbreviated as MCT, is a post hoc analysis generally performed after comparing multiple samples with one or more tests. An MCT will help identify a significantly different sample among multiple samples or a factor among multiple factors.
It would be easy to compare two samples using a significance alpha level of 0.05. In other words, there is only one sample pair to be compared. However, it would be difficult to identify a significantly different sample if the number...
It would be easy to compare two samples using a significance alpha level of 0.05. In other words, there is only one sample pair to be compared. However, it would be difficult to identify a significantly different sample if the number...
4.4K
The Eukaryotic Promoter Region
18.7K
The eukaryotic promoter region is a segment of DNA located upstream of a gene. It contains an RNA polymerase binding site, a transcription start site, and several cis-regulatory sequences. The proximal promoter region is located in the vicinity of the gene and has cis-regulatory sequences and the core promoter. The core promoter is the binding site for RNA polymerase and is usually located between -35 and +35 nucleotides from the transcription start site. The distal promoter regions are...
18.7K
Region of Convergence
903
The z-transform is a powerful mathematical tool used in the analysis of discrete-time signals and systems. It is a crucial tool in the analysis of discrete-time systems, but its convergence is limited to specific values of the complex variable z. This range of values, known as the Region of Convergence (ROC), is fundamental in determining the behavior and stability of a system or signal. The ROC defines the region in the complex plane where the z-transform converges, which can take various...
903


