Diagnosing liver steatosis is an essential precaution for detecting hepatocirrhosis and liver cancer in the early stages. However, automatic diagnosis of liver steatosis from ultrasound (US) images remains challenging due to poor visual quality from various origins, such as speckle noise and blurring. In this paper, we propose a fully automated liver steatosis prediction model using three deep learning neural networks. As a result, liver steatosis can be automatically detected with high accuracy and precision. First, transfer learning is used for semantically segmenting the liver and kidney (L-K) on parasagittal US images, and then cropping the L-K area from the original US images. The second neural network also involves semantic segmentation by checking the presence of a ring that is typically located around the kidney and cropping of the L-K area from the original US images. These cropped L-K areas are inputted to the final neural network, SteatosisNet, in order to grade the severity of fatty liver disease. The experimental results demonstrate that the proposed model can predict fatty liver disease with the sensitivity of 99.78%, specificity of 100%, PPV of 100%, NPV of 99.83%, and diagnostic accuracy of 99.91%, which is comparable to the common results annotated by medical experts.
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.
X-ray is the most widely used imaging modality for the initial diagnosis of bone tumors due to its accessibility and cost-effectiveness. However, the longitudinal comparison of benign bone tumors, particularly for assessing size and shape progression over time, remains largely manual and subjective. In this study, we propose FusionX-BBTNet, a deep learning-based framework that enables automated detection, segmentation, and time-sequential analysis of BBTs from X-ray images. The framework combines YOLO-based object detection with U-Net segmentation, and utilizes a novel wavelet-enhanced dataset to improve contour accuracy. To enable real-world quantification, an OCR-based module is used to extract the X-ray scale bar and compute the pixel-to-length conversion ratio. With this, tumor size and area are calculated in millimeters, and their changes over time are visualized through centroid-based alignment. The proposed method was validated on a dataset of 466 expert-annotated X-ray images, achieving a mean IoU of 0.9376 and a boundary F1 score of 0.9827. In addition to providing reliable tumor localization and measurement, the system supports clinical decision-making by offering intuitive shape and area comparisons. This approach has the potential to complement expert interpretation and improve diagnostic efficiency, especially in environments with limited radiological expertise.
Limb Length Discrepancy (LLD) is a common condition that can result in gait abnormalities, pain, and an increased risk of early degenerative osteoarthritis in the lower extremities. Epidemiological studies indicate that mild LLD, defined as a discrepancy of 10 mm or less, affects approximately 60–90% of the population. While more severe cases are less frequent, they are associated with secondary conditions such as low back pain, scoliosis, and osteoarthritis of the hip or knee. LLD not only impacts daily activities, but may also lead to long-term complications, making early detection and precise measurement essential. Current LLD measurement methods include physical examination and imaging techniques, with physical exams being simple and non-invasive but prone to operator-dependent errors. To address these limitations and reduce measurement errors, we have developed an AI-based automated lower-limb length measurement system. This method employs semantic segmentation to accurately identify the positions of the femur and tibia and extracts key anatomical landmarks, achieving a margin of error within 4 mm. By automating the measurement process, this system reduces the time and effort required for manual measurements, enabling clinicians to focus more on treatment and improving the overall quality of care.