Salehinejad, Hojjat

Abstract Introduction Quantitative interpretation of pediatric brain [ 18 F]-FDG PET is limited by the lack of age-matched normative reference databases, despite substantial developmental variation in cerebral glucose metabolism. This study aimed to construct a large-scale normative pediatric [ 18 F]-FDG PET database and develop an age-specific z-score mapping framework for quantitative evaluation of pediatric epilepsy. Method Pediatric brain PET data were retrospectively derived from clinically acquired whole-body or dedicated [ 18 F]-FDG PET examinations in participants 0–19 years of age without neurologic disease or visible brain abnormalities. A total of 417 PET scans from 341 participants were stratified into five developmental age groups: infancy, early childhood, middle childhood/school age, adolescence, and late adolescence. SUVR maps were generated using whole-brain atlas and brainstem reference regions. Voxel-wise t-test analyses were performed to characterize age- and sex-related metabolic differences. Age-specific voxel-wise mean and standard deviation maps were generated from the normative cohort and used to calculate age-matched hypometabolic z-score maps in 14 pediatric patients with epilepsy. The resulting abnormalities were qualitatively evaluated for concordance with epileptogenic findings identified on clinical MRI and/or PET by expert image review. Results Voxel-wise analyses demonstrated prominent age-dependent SUVR differences, particularly between infancy and older age groups. With whole-brain atlas normalization, older children showed progressively higher relative SUVR in cortical and cerebellar gray matter regions, whereas infancy showed relatively higher SUVR in the occipital cortex, white matter, thalamus, and brainstem. Brainstem normalization produced distinct developmental patterns, emphasizing higher white matter SUVR in infancy and broader gray matter differences in older groups. Sex-related differences were limited and regionally specific. Whole-brain atlas normalization showed lower variability than brainstem normalization and was selected for z-score mapping. In representative epilepsy cases, age-matched z-score maps identified focal or regional hypometabolism corresponding to malformations of cortical development, focal cortical dysplasia, mesial temporal sclerosis, nonlesional MRI cases, remote insult, tumor-related abnormalities, and Sturge-Weber syndrome. Discussion A large-scale normative pediatric [18F]-FDG PET database can support developmentally appropriate quantitative interpretation of pediatric brain PET. Age-matched z-score mapping may complement visual assessment by highlighting abnormal cerebral glucose metabolism in pediatric epilepsy, although findings should be interpreted with MRI, EEG, seizure semiology, and other presurgical data.

ABSTRACT Background Evaluating fairness in artificial intelligence (AI) is essential before clinical implementation to prevent unintended harm across diverse patient populations. This study assesses performance differences of an image-based surgical site infection (SSI) detection model across age, gender, geography, race, and skin color. Methods Model development/validation study using retrospective, multicenter data across surgical subspecialties from adults who submitted an image of their incision via the electronic health record within 30 days of their procedure between 2019-2024. Area under receiver operating curve (AUROC) was compared by age (<55 vs. ≥55 years old), gender (male vs. female), geography (Rochester, Minnesota vs. Jacksonville, Florida vs. Scottsdale, Arizona vs. regional Minnesota/Wisconsin areas), race (White/Caucasian vs. non-White/Caucasian), and skin color (Fitpatrick I-III vs. IV-VI and Monk A-E vs. F-J). Results Training data contained 13,702 images from 4,274 patients between 2019-2022 (50.1% ≥55 years old; 63.2% female; 91.6% White/Caucasian; 58.5% Rochester, 17.3% Florida, 10.5% Arizona; 96.3% light skin tone), of which 1,348 images (9.8%) had an SSI. No differences in SSI detection existed for age, gender, race, or skin color (AUROC 0.83-0.87, p>0.09), however geographical differences were significant: lowest AUROC 0.83 (95% CI 0.77-0.88) vs. highest AUROC 0.87 (95% CI 0.84-0.89, p=0.01). Temporal validation using 4,242 images from 1,353 patients between 2022-2023 showed intact fairness across subgroups (ΔAUROC ≤0.06) except geography (ΔAUROC ≤0.16). Conclusions The model behaved fairly across age, gender, race, and skin color, however geographical differences persisted. These findings have practical implications underscoring the importance of evaluating bias in clinical AI before deployment.

This systematic review evaluates current computer vision models and their applications in laparoscopic cholecystectomy. Using PRISMA guidelines, we analyzed studies reporting on primary computer vision model applications in laparoscopic cholecystectomy, from inception to March 2026. A total of 85 studies were included: workflow analysis (n = 26), anatomy recognition and segmentation (n = 14), safety assessment (n = 14), instrument detection (n = 12), tissue/image characterization (n = 7), event detection and scene understanding (n = 6), and surgical performance assessment (n = 6). The performance of the computer vision models in the studies was heterogeneous, with accuracy, F1-score, mean average precision, Dice coefficient, mean absolute error, and area under the receiver operating characteristic curve being commonly reported. Despite strong model performances in several studies, implementation in the clinical setting remains a challenge. We highlight the need for standardized model performance reporting, broader external and multi-institutional validation of models, and coordinated frameworks for safe and effective implementation of computer vision models in laparoscopic cholecystectomy.

BACKGROUND: Surgeons and ostomy nurses receive a high volume of stoma photos from patients. OBJECTIVE: This study aimed to develop and validate an automated and scalable artificial intelligence pipeline for identification and triage of patient-submitted intestinal ostomy photos. DESIGN: Retrospective derivation and validation study with stakeholder engagement to guide model design. Clinical teams reviewed photos in duplicate and categorized them into: (a) obstructed view, (b) healthy stoma, (c) suitable for conservative management, or (d) requiring in-person review. Pre-trained neural networks including MobileNetV4, ResNet50, ViT and CLIP-ViT were fine-tuned with 5-fold cross-validation. SETTINGS: Nine Mayo Clinic hospitals (2019–2022). PATIENTS: Adult patients (≥18 years) undergoing surgery who submitted images within 30 days after surgery. MAIN OUTCOME MEASURES: Model performance was evaluated with area under the receiver operator curve, precision, recall, and F1-scores. RESULTS: In this study, 538 photos of abdominal ostomies were sent in by 191 patients (median age 52 years, IQR 40–63; 60.4% female). Expert consensus triaged 236 (43.9%) photos as having an obstructed view, 30 (5.6%) as healthy, 177 (32.9%) for conservative management, and 95 (17.7%) for in-person review. All models achieved area under the receiver operator curve >0.97 for identifying stomas. The CLIP-ViT model performed best at triage (macro- area under the receiver operator curve 0.94 ± 0.06; F1 0.77 ± 0.10). End-to-end detection and triage using CLIP-ViT achieved area under the receiver operator curve of 0.99 ± 0.01, precision of 0.87 ± 0.08, recall of 0.93 ± 0.04, and F1 of 0.89 ± 0.07. Attention maps showed that models focused on stomas to determine classification. LIMITATIONS: Low sample size and lack of prospective validation. CONCLUSIONS: A vision language model pipeline accurately detected and triaged patient-submitted ostomy photos. Prospective evaluation is now needed to support integration into multidisciplinary digital workflows. See Video Abstract .

Objective: To develop a predictive model for pathological complete response (pCR) after total neoadjuvant therapy (TNT) to inform selection for watch-and-wait (W/W). Summary Background Data: Patient selection for W/W after TNT for locally advanced rectal cancer remains challenging. Methods: An ensemble of tabular foundation models was fine-tuned in adults with clinical stage II or III microsatellite stable primary rectal adenocarcinoma undergoing TNT and total mesorectal excision (TNT+TME) from 2018-2023 to predict pCR, using pre-TNT, post-TNT and pre-TME variables. This model was externally validated on patients having TNT and W/W (TNT+W/W) to predict persistent clinical complete response (pcCR; the absence of local regrowth, distant metastases, or persistent near-cCR). Area under the receiver operator curve (AUROC), area under the precision-recall curve (AUPRC), and Brier score were calculated with 95% confidence intervals (CI). Results: Among 308 patients that underwent TNT+TME (median age 56; 40% female), the model predicted pCR with an AUROC 0.71 (95% CI 0.65-0.77), AUPRC 0.44 (95% CI 0.35-0.57), and was well calibrated with a Brier score of 0.17 (95% CI 0.15-0.20). At external validation in a cohort of 83 patients that are being managed with TNT+W/W (median age 57; 37% female), the model predicted pcCR with an AUROC 0.69 (95% CI 0.57-0.82), AUPRC 0.90 (95% CI 0.82-0.96), and Brier score of 0.30 (95% CI 0.26-0.33), improving to 0.17 with recalibration. Conclusions: This novel predictive model demonstrated good discrimination and calibration for pCR after TNT+TME with utility in TNT+W/W for pcCR after appropriate recalibration, supporting its application for W/W patient selection.