Rhyou Se-Yeol, Yu Minyung, Yoo Jae-Chern
Department of Electrical and Computer Engineering, College of Information and Communication Engineering, Sungkyunkwan University, Suwon 440-746, Republic of Korea.
Diagnostics (Basel). 2025 Feb 28;15(5):588. doi: 10.3390/diagnostics15050588.
Ultrasound (US) imaging plays a crucial role in the early detection and treatment of hepatocellular carcinoma (HCC). However, challenges such as speckle noise, low contrast, and diverse lesion morphology hinder its diagnostic accuracy. To address these issues, we propose CSM-FusionNet, a novel framework that integrates clustering, SoftMax-weighted Box Fusion (SM-WBF), and padding. Using raw US images from a leading hospital, Samsung Medical Center (SMC), we applied intensity adjustment, adaptive histogram equalization, low-pass, and high-pass filters to reduce noise and enhance resolution. Data augmentation generated ten images per one raw US image, allowing the training of 10 YOLOv8 networks. The mAP@0.5 of each network was used as SoftMax-derived weights in SM-WBF. Threshold-lowered bounding boxes were clustered using Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and outliers were managed within clusters. SM-WBF reduced redundant boxes, and padding enriched features, improving classification accuracy. The accuracy improved from 82.48% to 97.58% with sensitivity reaching 100%. The framework increased lesion detection accuracy from 56.11% to 95.56% after clustering and SM-WBF. CSM-FusionNet demonstrates the potential to significantly improve diagnostic reliability in US-based lesion detection, aiding precise clinical decision-making.
超声（US）成像在肝细胞癌（HCC）的早期检测和治疗中起着至关重要的作用。然而，诸如斑点噪声、低对比度和多样的病变形态等挑战阻碍了其诊断准确性。为了解决这些问题，我们提出了CSM-FusionNet，这是一个集成了聚类、SoftMax加权框融合（SM-WBF）和填充的新颖框架。我们使用来自领先医院三星医疗中心（SMC）的原始超声图像，应用强度调整、自适应直方图均衡化、低通和高通滤波器来减少噪声并提高分辨率。数据增强为每一幅原始超声图像生成十幅图像，从而能够训练10个YOLOv8网络。每个网络的mAP@0.5被用作SM-WBF中基于SoftMax的权重。使用基于密度的带噪声空间聚类（DBSCAN）对降低阈值的边界框进行聚类，并在聚类内处理离群值。SM-WBF减少了冗余框，填充丰富了特征，提高了分类准确率。准确率从82.48%提高到97.58%，灵敏度达到100%。经过聚类和SM-WBF后，该框架将病变检测准确率从56.11%提高到95.56%。CSM-FusionNet展示了在基于超声的病变检测中显著提高诊断可靠性的潜力，有助于精确的临床决策。
