Frontiers in Microbiology, Journal Year: 2024, Volume and Issue: 15
Published: Dec. 13, 2024
The current study aims to delineate subcutaneous adipose tissue (SAT), visceral (VAT), the sacrospinalis muscle, and all abdominal musculature at L3-L5 vertebral level from non-contrast computed tomography (CT) imagery using deep learning algorithms. Subsequently, radiomic features are collected these segmented images subjected medical interpretation.
Language: Английский
Frontiers in Medicine, Journal Year: 2025, Volume and Issue: 12
Published: Jan. 24, 2025
Purpose Acute Mesenteric Ischemia (AMI) is a critical condition marked by restricted blood flow to the intestine, which can lead tissue necrosis and fatal outcomes. We aimed develop deep learning (DL) model based on CT angiography (CTA) imaging clinical data diagnose AMI. Methods A retrospective study was conducted 228 patients suspected of AMI, divided into training test sets. Clinical (medical history laboratory indicators) included in multivariate logistic regression analysis identify independent factors associated with AMI establish model. The arterial venous CTA images were utilized construct DL Fusion Model constructed integrating performance models assessed using receiver operating characteristic (ROC) curves decision curve (DCA). Results Albumin International Normalized Ratio (INR) univariate ( P < 0.05). In set, area under ROC (AUC) factor 0.60 (sensitivity 0.47, specificity 0.86). AUC reached 0.90, significantly higher than values model, as confirmed DeLong also showed exceptional terms AUC, accuracy, sensitivity, specificity, precision, 0.96, 0.94, 0.95, 0.98, respectively. DCA indicated that provided greater net benefit those solely information across majority reasonable threshold probabilities. Conclusion incorporation markedly enhances diagnostic accuracy efficiency This approach provides reliable tool for early diagnosis subsequent implementation appropriate intervention.
Language: Английский
Citations
0
Medicina, Journal Year: 2025, Volume and Issue: 61(4), P. 629 - 629
Published: March 29, 2025
Acute pancreatitis (AP) presents a significant clinical challenge due to its wide range of severity, from mild cases life-threatening complications such as severe acute (SAP), necrosis, and multi-organ failure. Traditional scoring systems, Ranson BISAP, offer foundational tools for risk stratification but often lack early precision. This review aims explore the transformative role artificial intelligence (AI) machine learning (ML) in AP management, focusing on their applications diagnosis, severity prediction, complication treatment optimization. A comprehensive analysis recent studies was conducted, highlighting ML models XGBoost, neural networks, multimodal approaches. These integrate clinical, laboratory, imaging data, including radiomics features, are useful diagnostic prognostic accuracy AP. Special attention given addressing SAP, like kidney injury respiratory distress syndrome, mortality, recurrence. AI-based achieved higher AUC values than traditional predicting outcomes. XGBoost reached an 0.93 SAP BISAP (AUC 0.74) APACHE II 0.81). PrismSAP, integrating highest 0.916. AI also demonstrated superior mortality prediction 0.975) ARDS detection 0.891) represent advance facilitating personalized treatment, stratification, allowing resource utilization be optimized. By challenges model generalizability, ethical considerations, adoption, has potential significantly improve patient outcomes redefine care standards globally.
Language: Английский
Citations
0
Turkish Journal of Emergency Medicine, Journal Year: 2025, Volume and Issue: 25(2), P. 67 - 91
Published: April 1, 2025
Artificial intelligence (AI) is increasingly improving the processes such as emergency patient care and medicine education. This scoping review aims to map use performance of AI models in regarding concepts. The findings show that AI-based medical imaging systems provide disease detection with 85%-90% accuracy techniques X-ray computed tomography scans. In addition, AI-supported triage were found be successful correctly classifying low- high-urgency patients. education, large language have provided high rates evaluating exams. However, there are still challenges integration into clinical workflows model generalization capacity. These demonstrate potential updated models, but larger-scale studies needed.
Language: Английский
Citations
0
Digestive Endoscopy, Journal Year: 2025, Volume and Issue: unknown
Published: May 1, 2025
Language: Английский
Citations
0
BMC Medical Imaging, Journal Year: 2024, Volume and Issue: 24(1)
Published: July 22, 2024
Abstract Objectives Rheumatoid arthritis (RA) is a severe and common autoimmune disease. Conventional diagnostic methods are often subjective, error-prone, repetitive works. There an urgent need for method to detect RA accurately. Therefore, this study aims develop automatic system based on deep learning recognizing staging from radiographs assist physicians in diagnosing quickly Methods We CNN-based fully automated model, exploring five popular CNN architectures two clinical applications. The model trained radiograph dataset containing 240 hand radiographs, of which 39 normal 201 with stages. For evaluation, we use 104 13 91 Results achieves good performance diagnosis radiographs. the recognition, all models achieve AUC above 90% sensitivity over 98%. In particular, GoogLeNet-based 97.80%, 100.0%. staging, 77% 80%. Specifically, VGG16-based 83.36% 92.67% sensitivity. Conclusion presented have best recognition respectively. experimental results demonstrate feasibility applicability radiograph-based diagnosis. has important significance, especially resource-limited areas inexperienced physicians.
Language: Английский
Citations
2
World Journal of Radiology, Journal Year: 2024, Volume and Issue: 16(11), P. 703 - 707
Published: Nov. 26, 2024
Autoimmune pancreatitis (AIP) is a special type of chronic with clinical symptoms obstructive jaundice and abdominal discomfort; this condition caused by autoimmunity marked pancreatic fibrosis dysfunction. Previous studies have revealed close relationship between early atrophy the incidence rate diabetes in 1 AIP patients receiving steroid treatment. Shimada et al performed long-term follow-up study reported that volume (PV) these initially exponentially decreased but then slowly decreased, which was considered to be an important factor related diabetes; moreover, serum IgG4 levels were positively correlated PV during follow-up. In letter, regarding original presented , we present our insights discuss how multimodal medical imaging artificial intelligence can used better assess morphological changes AIP.
Language: Английский
Citations
1
Frontiers in Microbiology, Journal Year: 2024, Volume and Issue: 15
Published: Dec. 13, 2024
The current study aims to delineate subcutaneous adipose tissue (SAT), visceral (VAT), the sacrospinalis muscle, and all abdominal musculature at L3-L5 vertebral level from non-contrast computed tomography (CT) imagery using deep learning algorithms. Subsequently, radiomic features are collected these segmented images subjected medical interpretation.
Language: Английский
Citations
0