Lightweight Deep Learning Framework for Accurate Detection of Sports-Related Bone Fractures

Diagnostics, Journal Year: 2025, Volume and Issue: 15(3), P. 271 - 271

Published: Jan. 23, 2025

Background/Objectives: Sports-related bone fractures are a common challenge in sports medicine, requiring accurate and timely diagnosis to prevent long-term complications enable effective treatment. Conventional diagnostic methods often rely on manual interpretation, which is prone errors inefficiencies, particularly for subtle localized fractures. This study aims develop lightweight efficient deep learning-based framework improve the accuracy computational efficiency of fracture detection, tailored needs medicine. Methods: We proposed novel detection based DenseNet121 architecture, incorporating modifications initial convolutional block final layers optimized feature extraction. Additionally, Canny edge detector was integrated enhance model ability detect structural discontinuities. A custom-curated dataset radiographic images focused sports-related used, with preprocessing techniques such as contrast enhancement, normalization, data augmentation applied ensure robust performance. The evaluated against state-of-the-art using metrics accuracy, recall, precision, complexity. Results: achieved 90.3%, surpassing benchmarks like ResNet-50, VGG-16, EfficientNet-B0. It demonstrated superior sensitivity (recall: 0.89) specificity (precision: 0.875) while maintaining lowest complexity (FLOPs: 0.54 G, Params: 14.78 M). These results highlight its suitability real-time clinical deployment. Conclusions: offers scalable, accurate, solution addressing critical challenges By enabling rapid reliable diagnostics, it has potential workflows outcomes athletes. Future work will focus expanding applications other imaging modalities types.

Language: Английский

Real-Time Object Detector for Medical Diagnostics (RTMDet): A High-Performance Deep Learning Model for Brain Tumor Diagnosis

Bioengineering, Journal Year: 2025, Volume and Issue: 12(3), P. 274 - 274

Published: March 11, 2025

Background: Brain tumor diagnosis requires precise and timely detection, which directly impacts treatment decisions patient outcomes. The integration of deep learning technologies in medical diagnostics has improved the accuracy efficiency these processes, yet real-time processing remains a challenge due to computational intensity current models. This study introduces Real-Time Object Detector for Medical Diagnostics (RTMDet), aims address limitations by optimizing convolutional neural network (CNN) architectures enhanced speed accuracy. Methods: RTMDet model incorporates novel depthwise blocks designed reduce load while maintaining diagnostic precision. effectiveness was evaluated through extensive testing against traditional modern CNN using comprehensive imaging datasets, with focus on capabilities. Results: demonstrated superior performance detecting brain tumors, achieving higher compared existing model’s validated its ability process large datasets real time without sacrificing required reliable diagnosis. Conclusions: represents significant advancement application diagnostics. By balance between precision, enhances capabilities imaging, potentially improving outcomes faster more accurate detection. offers promising solution clinical settings where rapid are critical.

Language: Английский

V3DQutrit a volumetric medical image segmentation based on 3D qutrit optimized modified tensor ring model

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: May 6, 2025

This paper introduces 3D-QTRNet, a novel quantum-inspired neural network for volumetric medical image segmentation. Unlike conventional CNNs, which suffer from slow convergence and high complexity, QINNs, are limited to grayscale segmentation, our approach leverages qutrit encoding tensor ring decomposition. These techniques improve segmentation accuracy, optimize memory usage, accelerate model convergence. The proposed demonstrates superior performance on the BRATS19 Spleen datasets, outperforming state-of-the-art CNN quantum models in terms of Dice similarity precision. work bridges gap between computing imaging, offering scalable solution real-world applications.

Language: Английский