An Innovative Solution Based on TSCA-ViT for Osteosarcoma Diagnosis in Resource-Limited Settings

Biomedicines, Journal Year: 2023, Volume and Issue: 11(10), P. 2740 - 2740

Published: Oct. 10, 2023

Identifying and managing osteosarcoma pose significant challenges, especially in resource-constrained developing nations. Advanced diagnostic methods involve isolating the nucleus from cancer cells for comprehensive analysis. However, two main challenges persist: mitigating image noise during capture transmission of cellular sections, providing an efficient, accurate, cost-effective solution cell segmentation. To tackle these issues, we introduce Twin-Self Cross-Attention Vision Transformer (TSCA-ViT). This pioneering AI-based system employs a directed filtering algorithm reduction features innovative transformer architecture with twin attention mechanism effective The model also incorporates cross-attention-enabled skip connections to augment spatial information. We evaluated our method on dataset 1000 pathology slide images Second People’s Hospital Huaihua, achieving remarkable average precision 97.7%. performance surpasses traditional methodologies. Furthermore, TSCA-ViT offers enhanced computational efficiency owing its fewer parameters, which results reduced time equipment costs. These findings underscore superior efficacy TSCA-ViT, offering promising approach addressing ongoing diagnosis treatment, particularly settings limited resources.

Language: Английский

---

Asymptotic multilayer pooled transformer based strategy for medical assistance in developing countries

Computers & Electrical Engineering, Journal Year: 2024, Volume and Issue: 119, P. 109493 - 109493

Published: Aug. 3, 2024

Language: Английский

---

A semantic fidelity interpretable-assisted decision model for lung nodule classification

International Journal of Computer Assisted Radiology and Surgery, Journal Year: 2023, Volume and Issue: 19(4), P. 625 - 633

Published: Dec. 23, 2023

Language: Английский

---

Pathological Image Segmentation Method Based on Multiscale and Dual Attention

International Journal of Intelligent Systems, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

Medical images play a significant part in biomedical diagnosis, but they have feature. The medical images, influenced by factors such as imaging equipment limitations, local volume effect, and others, inevitably exhibit issues like noise, blurred edges, inconsistent signal strength. These imperfections pose challenges create obstacles for doctors during their diagnostic processes. To address these issues, we present pathology image segmentation technique based on the multiscale dual attention mechanism (MSDAUnet), which consists of three primary components. Firstly, an denoising enhancement module is constructed using dynamic residual color histogram to remove noise improve clarity. Then, propose (DAM), extracts messages from both channel spatial dimensions, obtains key features, makes edge lesion area clearer. Finally, capturing information process addresses issue uneven strength certain extent. Each combined automatic pathological segmentation. Compared with traditional typical U‐Net model, MSDAUnet has better performance. On dataset provided Research Center Artificial Intelligence Monash University, IOU index high 72.7%, nearly 7% higher than that U‐Net, DSC 84.9%, also about U‐Net.

Language: Английский

---

TransRNetFuse: a highly accurate and precise boundary FCN-transformer feature integration for medical image segmentation

Complex & Intelligent Systems, Journal Year: 2025, Volume and Issue: 11(5)

Published: March 17, 2025

Language: Английский

---

Enhanced boundary-directed lightweight approach for digital pathological image analysis in critical oncological diagnostics

Journal of X-Ray Science and Technology, Journal Year: 2025, Volume and Issue: unknown

Published: April 22, 2025

Background Pathological images play a crucial role in the diagnosis of critically ill cancer patients. Since patients often seek medical assistance when their condition is severe, doctors face urgent challenge completing accurate diagnoses and developing surgical plans within limited timeframe. The complexity diversity pathological require significant investment time from specialized physicians for processing analysis, which can lead to missing optimal treatment window. Purpose Current decision support systems are challenged by high computational deep learning models, demand extensive data training, making it difficult meet real-time needs emergency diagnostics. Method This study addresses issue malignant bone tumors such as osteosarcoma proposing Lightened Boundary-enhanced Digital Image Recognition Strategy (LB-DPRS). strategy optimizes self-attention mechanism Transformer model innovatively implements boundary segmentation enhancement strategy, thereby improving recognition accuracy tissue backgrounds nuclear boundaries. Additionally, this research introduces row-column attention methods sparsify matrix, reducing burden enhancing speed. Furthermore, proposed complementary further assists convolutional layers fully extracting detailed features . Results DSC value LB-DPRS reached 0.862, IOU 0.749, params was only 10.97 M. Conclusion Experimental results demonstrate that significantly improves efficiency while maintaining prediction interpretability, providing powerful efficient osteosarcoma.

Language: Английский

---

Implementation of artificial intelligence in detection, classification, and prognostication of osteosarcoma utilizing different assessment techniques: a systematic review

Intelligence-Based Medicine, Journal Year: 2025, Volume and Issue: unknown, P. 100250 - 100250

Published: May 1, 2025

Language: Английский

---

Deep learning image segmentation approaches for malignant bone lesions: a systematic review and meta-analysis

Frontiers in Radiology, Journal Year: 2023, Volume and Issue: 3

Published: Aug. 8, 2023

Image segmentation is an important process for quantifying characteristics of malignant bone lesions, but this task challenging and laborious radiologists. Deep learning has shown promise in automating image radiology, including lesions. The purpose review to investigate deep learning-based methods lesions on Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Positron-Emission Tomography/CT (PET/CT).

Language: Английский

---

User trust and evaluation mechanism based on community classification calculation in opportunistic social networks

Journal of Intelligent & Fuzzy Systems, Journal Year: 2023, Volume and Issue: unknown, P. 1 - 18

Published: Nov. 29, 2023

With the development of Internet Things technology, 5G communication has gradually entered people’s daily lives. The number network users also increased dramatically, and it become norm for same user to enjoy services provided by multiple service providers complete exchange sharing a large amount information at time. However, existing opportunistic social routing is not sufficiently scalable in face large-scale data. Moreover, only transaction used as evaluation evidence, ignoring other information, which may lead wrong trust assessment nodes. Based on this, this study proposes an algorithm called Trust Evaluation Mechanism Users Opportunistic Social Network Community Classification Computation (TEMCC). Firstly, communities are established based community classification computation solve problem explosive growth Then mechanism Bayesian model identify judge trustworthiness recommended between This approach ensures that more reliable nodes can be selected interaction data exchange. Through simulation experiments, delivery rate scheme reach 0.8, average end-to-end delay 190 ms.

Language: Английский

---

RDAG U-Net: An Advanced AI Model for Efficient and Accurate CT Scan Analysis of SARS-CoV-2 Pneumonia Lesions

Diagnostics, Journal Year: 2024, Volume and Issue: 14(18), P. 2099 - 2099

Published: Sept. 23, 2024

Background/Objective: This study aims to utilize advanced artificial intelligence (AI) image recog-nition technologies establish a robust system for identifying features in lung computed tomog-raphy (CT) scans, thereby detecting respiratory infections such as SARS-CoV-2 pneumonia. Spe-cifically, the research focuses on developing new model called Residual-Dense-Attention Gates U-Net (RDAG U-Net) improve accuracy and efficiency identification. Methods: employed Attention U-Net, Res newly developed RDAG model. extends architecture by incorporating ResBlock DenseBlock modules encoder retain training parameters reduce computation time. The dataset in-cludes 3,520 CT scans from an open database, augmented 10,560 samples through data en-hancement techniques. also focused optimizing convolutional architectures, preprocessing, interpolation methods, management, extensive fine-tuning of neural network modules. Result: achieved outstanding 93.29% pulmonary lesions, with 45% reduction time compared other models. demonstrated that performed stably during exhibited good generalization capability evaluating loss values, model-predicted lesion annotations, validation-epoch curves. Furthermore, using ITK-Snap convert 2D pre-dictions into 3D segmentation models, results delineated contours, en-hancing interpretability. Conclusion: showed significant improvements analysis images pneumonia, achieving recognition reducing These indicate potential clinical applications, it can accelerate detection lesions effectively enhance diagnostic accuracy. Additionally, visualization allow physicians understand lesions' morphology distribution better, strengthening decision support capabilities providing valuable medical diagnosis treatment planning tools.

Language: Английский

---