Early user perspectives on using computer-aided detection software for interpreting chest X-ray images to enhance access and quality of care for persons with tuberculosis

BMC Global and Public Health, Journal Year: 2023, Volume and Issue: 1(1)

Published: Dec. 21, 2023

Abstract Despite 30 years as a public health emergency, tuberculosis (TB) remains one of the world’s deadliest diseases. Most deaths are among persons with TB who not reached diagnosis and treatment. Thus, timely screening accurate detection TB, particularly using sensitive tools such chest radiography, is crucial for reducing global burden this disease. However, lack qualified human resources represents common limiting factor in many high TB-burden countries. Artificial intelligence (AI) has emerged powerful complement facets life, including interpretation X-ray images. while AI may serve viable alternative to radiographers radiologists, there likelihood that those suffering from will reap benefits technological advance without appropriate, clinically effective use cost-conscious deployment. The World Health Organization recommended 2021, early adopters technology have been ways. In manuscript, we present compilation user experiences nine countries focused on practical considerations best practices related deployment, threshold case selection, scale-up. While offer technical operational guidance interpreting images detection, our aim maximize benefit programs, implementers, ultimately TB-affected individuals can derive innovative technology.

Language: Английский

---

Detection of sarcopenia using deep learning-based artificial intelligence body part measure system (AIBMS)

Frontiers in Physiology, Journal Year: 2023, Volume and Issue: 14

Published: Jan. 26, 2023

Background: Sarcopenia is an aging syndrome that increases the risks of various adverse outcomes, including falls, fractures, physical disability, and death. can be diagnosed through medical images-based body part analysis, which requires laborious time-consuming outlining irregular contours abdominal parts. Therefore, it critical to develop efficient computational method for automatically segmenting parts predicting diseases. Methods: In this study, we designed Artificial Intelligence Body Part Measure System (AIBMS) based on deep learning automate segmentation from CT scans quantification areas volumes. The system was developed using three network models, SEG-NET, U-NET, Attention trained plain scan data. Results: This model evaluated multi-device developmental independent test datasets demonstrated a high level accuracy with over 0.9 DSC score in segment Based characteristics gave recommendations appropriate selection clinical scenarios. We constructed sarcopenia classification cutoff values (Auto SMI model), AUC 0.874. used Youden index optimize Auto found better threshold 40.69. Conclusion: AI images value achieve prediction accuracy.

Language: Английский

---

Selective Deeply Supervised Multi-Scale Attention Network for Brain Tumor Segmentation

Sensors, Journal Year: 2023, Volume and Issue: 23(4), P. 2346 - 2346

Published: Feb. 20, 2023

Brain tumors are among the deadliest forms of cancer, characterized by abnormal proliferation brain cells. While early identification can greatly aid in their therapy, process manual segmentation performed expert doctors, which is often time-consuming, tedious, and prone to human error, act as a bottleneck diagnostic process. This motivates development automated algorithms for tumor segmentation. However, accurately segmenting enhanced core regions complicated due high levels inter- intra-tumor heterogeneity terms texture, morphology, shape. study proposes fully automatic method called selective deeply supervised multi-scale attention network (SDS-MSA-Net) using with novel deep supervision (SDS) mechanisms training. The utilizes 3D input composed five consecutive slices, addition 2D slice, maintain sequential information. proposed architecture includes two encoding units extract meaningful global local features from inputs, respectively. These coarse then passed through filter out redundant information assigning lower weights. refined fed into decoder block, upscales at various while learning patterns relevant all regions. SDS block introduced immediately upscale intermediate layers decoder, aim producing segmentations whole, enhanced, framework was evaluated on BraTS2020 dataset showed improved performance region segmentation, particularly enhancing regions, demonstrating effectiveness approach. Our code publicly available.

Language: Английский

---

A Comparative Analysis of AlexNet and ResNet for Pneumonia Detection

Published: Feb. 16, 2025

Language: Английский

---

Multi-axis transformer based U-Net with class balanced ensemble model for lung disease classification using X-ray images

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

Published: Feb. 26, 2025

Background: Chest X-rays are an essential diagnostic tool for identifying chest disorders because of its high sensitivity in detecting pathological anomalies the lungs. Classification models based on conventional Convolutional Neural Networks (CNNs) adversely affected due to their localization bias. Objective: In this paper, a new Multi-Axis Transformer U-Net with Class Balanced Ensemble (MaxTU-CBE) is proposed improve multi-label classification performance. Methods: This may be first attempt simultaneously integrate benefits hierarchical into encoder and decoder traditional U-shaped structure improving semantic segmentation superiority lung image. Results: A key element MaxTU-CBE Contextual Fusion Engine (CFE), which uses self-attention mechanism efficiently create global interdependence between features various scales. Also, deep CNN incorporate ensemble learning address issue class unbalanced learning. Conclusions: According experimental findings, our suggested outperforms competing BiDLSTM classifier by 1.42% CBIR-CSNN techniques 5.2%

Language: Английский

---