Computed tomography-based body composition parameters can predict short-term prognosis in ulcerative colitis patients

Insights into Imaging, Journal Year: 2024, Volume and Issue: 15(1)

Published: Feb. 27, 2024

Abstract Objectives Emerging evidence suggests a potential relationship between body composition and short-term prognosis of ulcerative colitis (UC). Early accurate assessment rapid remission based on conventional therapy via abdominal computed tomography (CT) images has rarely been investigated. This study aimed to build prediction model using CT-based parameters for UC risk stratification. Methods In total, 138 patients with CT were enrolled. Eleven quantitative related involving skeletal muscle mass, visceral adipose tissue (VAT), subcutaneous (SAT) measured calculated semi-automated segmentation method. A was established significant multivariable logistic regression. The receiver operating characteristic (ROC) curve plotted evaluate performance. Subgroup analyses implemented the diagnostic efficiency different disease locations, centers, scanners. Delong test used statistical comparison ROC curves. Results VAT density, SAT gender, obesity significantly statistically invalidation groups (all p < 0.05). accuracy, sensitivity, specificity, area under (AUC) 82.61%, 95.45%, 69.89%, 0.855 (0.792–0.917), respectively. positive predictive value negative 70.79% 93.88%, No differences in AUC found subgroups > Conclusions predicting constructed is non-invasive approach identification Additionally, density an independent predictor escalating therapeutic regimens cohorts. Critical relevance statement evaluating stratification patients, identify non-responders making timely accurately. Key points • models help divide into UC. subgroup analysis confirmed stability high 0.820). bad Graphical

Language: Английский

---

Enhancing radiologist's detection: an imaging-based grading system for differentiating Crohn's disease from ulcerative colitis

BMC Medicine, Journal Year: 2024, Volume and Issue: 22(1)

Published: Oct. 8, 2024

Delayed diagnosis of inflammatory bowel disease (IBD) is common, there still no effective imaging system to distinguish Crohn's Disease (CD) and Ulcerative Colitis (UC) patients.

Language: Английский

---

Prediction of Hepatic Encephalopathy After Transjugular Intrahepatic Portosystemic Shunt Based on CT Radiomic Features of Visceral Adipose Tissue

Academic Radiology, Journal Year: 2023, Volume and Issue: 31(5), P. 1849 - 1861

Published: Nov. 24, 2023

Language: Английский

---

Multimodal MRI-based radiomic nomogram for predicting telomerase reverse transcriptase promoter mutation in IDH-wildtype histological lower-grade gliomas

Medicine, Journal Year: 2023, Volume and Issue: 102(51), P. e36581 - e36581

Published: Dec. 22, 2023

The presence of TERTp mutation in isocitrate dehydrogenase-wildtype (IDHwt) histologically lower-grade glioma (LGA) has been linked to a poor prognosis. In this study, we aimed develop and validate radiomic nomogram based on multimodal MRI for predicting mutations IDHwt LGA. One hundred nine IDH wildtype patients (TERTp-mutant, 78; TERTp-wildtype, 31) with clinical, radiomic, molecular information were collected randomly divided into training validation set. Clinical model, fusion combined constructed the discrimination. Radiomic features screened 3 algorithms (Wilcoxon rank sum test, elastic net, recursive feature elimination) clinical characteristics by Akaike criterion. Finally, receiver operating characteristic curve, calibration Hosmer-Lemeshow decision curve analysis utilized assess these models. Fusion model 4 achieved an area under value 0.876 0.845 And, 0.897 (training set) 0.882 (validation set). Above that, test showed that had good agreement between observations predictions set revealed 2 models usefulness prediction status radiomics performed great performance high sensitivity LGA, application.

Language: Английский

---

CT Radiomics Features of Abdominal Adipose and Muscle Tissues Can Predict the Postoperative Early Recurrence of Hepatocellular Carcinoma

Academic Radiology, Journal Year: 2023, Volume and Issue: 31(4), P. 1312 - 1325

Published: Oct. 28, 2023

Language: Английский

---

Radiomics prediction of operation indication in ulcerative colitis refractory to medical treatment

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 10, 2024

Background The indications for operation in drug-resistant ulcerative colitis are determined by complex factors. In this study, we test whether radiomics analysis can be used to predict hospitalized patients. Methods This is a single-center retrospective cohort study using CT at admission of UC patients admitted from 2015 2022. target prediction was the patient would undergo surgery time discharge. Radiomics features were extracted rectal wall level tailbone tip as ROI. data randomly classified into training and validation cohort, LASSO regression performed create formula calculating score. Results Five Univariate logistic clinical information detected significant influence severity (p < 0.001), number drugs until Lichtiger score = 0.024) hemoglobin 0.010). Using nomogram combining these items, found that discriminatory power conservative treatment groups AUC 0.822 (95% confidence interval (CI) 0.841–0.951) 0.868 CI 0.729-1.000) indicating good ability discriminate outcomes. Conclusions images admission, combined with data, showed high predictive regarding strategy or treatment.

Language: Английский

---

Radiomic signature: A novel magnetic resonance imaging-based prognostic biomarker in patients with brainstem cavernous malformation

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 8, 2024

OBJECTIVE: Based on anatomical magnetic resonance imaging (MRI) sequences, we developed a radiomic signature for brainstem cavernous malformation patients (BSCMs) using analysis and explore its effectiveness as prognostic biomarker. METHODS:One hundred fourteen BSCMs with clinical, information were collected randomly divided into training (n = 68) validation set 46). Clinical nomogram constructed the prognosis. Radiomic features screened three algorithms (univariate analysis, Pearson elastic net algorithm). Cox regression model was used to build radiomics nomogram. Finally, concordance index (C-index), time-independent receiver operating characteristic (ROC) Decision curve (DCA) utilized evaluate clinical application of RESULTS: The score calculated 11 hemorrhage-free survival (HFS) related from cohort. high-risk group low-risk help has better HFS than group. In addition, characteristics including number hemorrhages, size, mRS, (Rad-score) develop calibration plots showed that good agreement between predicted actual probabilities. And, C-index 0.784 0.787 in cohort predicting HFS; area under (AUC) 72.51 76.41 3-year 67.62 72.57 5-year survival. Lastly, DCA model. CONCLUSIONS: Radiomics integrating great performance high sensitiveness prediction

Language: Английский

---

Artificial Intelligence in Inflammatory Bowel Disease

Gastrointestinal Endoscopy Clinics of North America, Journal Year: 2024, Volume and Issue: 35(2), P. 367 - 387

Published: Nov. 27, 2024

Language: Английский

---