Mixture of Expert-Based SoftMax-Weighted Box Fusion for Robust Lesion Detection in Ultrasound Imaging
Open Access
- 28 February 2025
- journal article
- research article
- Published by MDPI AG in Diagnostics
- Vol. 15 (5) , 588
Abstract
Background/Objectives: 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. Methods: 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. Results: 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. Conclusions: CSM-FusionNet demonstrates the potential to significantly improve diagnostic reliability in US-based lesion detection, aiding precise clinical decision-making.Keywords
This publication has 37 references indexed in Scilit:
- Optimizing US for HCC surveillanceAbdominal Radiology, 2024
- Implications of ultrasound-based deep learning model for preoperatively differentiating combined hepatocellular-cholangiocarcinoma from hepatocellular carcinoma and intrahepatic cholangiocarcinomaAbdominal Radiology, 2023
- Management of Hepatocellular CarcinomaJAMA Surgery, 2023
- Aggregated micropatch-based deep learning neural network for ultrasonic diagnosis of cirrhosisArtificial Intelligence in Medicine, 2023
- USC-ENet: a high-efficiency model for the diagnosis of liver tumors combining B-mode ultrasound and clinical dataHealth Information Science and Systems, 2023
- Artificial intelligence (AI) models for the ultrasonographic diagnosis of liver tumors and comparison of diagnostic accuracies between AI and human expertsJournal of Gastroenterology, 2022
- Optimal Intervals of Ultrasonography Screening for Early Diagnosis of Hepatocellular Carcinoma in TaiwanJAMA Network Open, 2021
- Joint segmentation and classification of hepatic lesions in ultrasound images using deep learningEuropean Radiology, 2021
- Randomized controlled trial of screening for hepatocellular carcinomaJournal of Cancer Research and Clinical Oncology, 2004
- A new prognostic system for hepatocellular carcinoma: A retrospective study of 435 patientsHepatology, 1998