Adolescent idiopathic scoliosis (AIS) surgery requires precise fusion segment selection and reliable prediction of postoperative alignment, yet current tools lack individualized, validated solutions. We developed ScoliosisPLAN, an AI-based system integrating a YOLOv8-derived segmentation model (ScolioPlanNet) for personalized fusion planning and a latent diffusion model (ScolioPredNet) for simulating postoperative radiographs. In a retrospective development cohort and prospectively collected internal and external validation cohorts of 1425 patients with ≥2-year follow-up, the system achieved performance comparable to experienced surgeons in replicating fusion planning decisions and predicted key radiographic outcomes within clinically acceptable error margins. ScoliosisPLAN provides an interpretable, data-driven framework linking surgical strategy to outcome prediction, supporting standardized, patient-specific decision-making in AIS care.

The lateral pelvis is a critical anatomical region in colorectal, gynecological, and urological surgeries. However, its anatomical complexity and variability pose significant challenges for pelvic lymph node dissection (PLND). This study aimed to develop an artificial intelligence (AI) model to identify key anatomical structures relevant to PLND and evaluate whether AI assistance enhances surgeons' ability to recognize pelvic anatomical features. Thirty-six surgeons representing colorectal, gynecological, and urological specialties, with varying experience levels, reviewed 640 video snippets (0.5 s each) from PLND procedures. The model was trained on 23,259 annotated and 653 unannotated images extracted from 293 PLND procedure videos. Threefold cross-validation yielded Dice similarity coefficients of 0.6483 for the ureter, 0.8654 for the obturator nerve, 0.8619 for the external iliac artery, and 0.8736 for the external iliac vein. Across all structures, AI assistance led to a significant improvement in sensitivity and specificity among participating surgeons (p < .001). Our findings suggest that the proposed AI model may assist surgeons in identifying pelvic anatomical structures across different specialties and experience levels. Further studies using continuous intraoperative workflows will be required to determine its impact on clinical practice.

The brain morphological connectome derived from structural MRI reflects inter-regional morphological relationships, providing a powerful representation for characterizing individual variability and detecting abnormalities across the lifespan. However, these abnormal alterations are subtle and complex, posing significant challenges for accurate and generalizable diagnosis using machine learning. Here, we present FedFound, the first federated foundation model inspired by the structured educational and residency training pathway of radiologists, designed for robust and scalable analysis of lifespan brain morphological connectomes. Integrating heterogeneous neuroimaging datasets across sites and disorders (22,911 subjects aged 0 to 100 years), FedFound combines self-supervised pre-training and supervised federated disease-specific refinement, supporting multidisciplinary knowledge aggregation through distributed optimization. Across nine diagnostic tasks spanning neurodevelopmental, neuropsychiatric, and neurodegenerative disorders, FedFound demonstrates superior performance and interpretability, revealing both shared and disorder-specific morphological patterns across etiologies. FedFound provides a robust foundation for lifespan neuroimage-based diagnosis that complements clinical expertise, while establishing a scalable and generalizable paradigm for integrating heterogeneous neuroimaging data across institutions, populations, and diseases to advance medical foundation models.

In recent years, numerous studies have investigated the use of poly (ADP-ribose) polymerase (PARP) inhibitors, labelled with various radionuclides, as agents for targeted radionuclide therapy. This review discusses current advances in studies with radiolabelled PARP inhibitors for targeted radionuclide therapy, focusing on radionuclide selection and (radio)biological properties. We highlight differences between radionuclides and their efficacy in killing cancer cells, while safeguarding healthy tissue. Furthermore, important biomarkers and dosimetry are explored, providing insights and future directions for advancing radiolabelled PARP inhibitors.

Frozen section (Frozen) analysis is essential for intraoperative margin assessment in skin cancer surgery, but assessment is limited by freezing artifacts that obscure cellular detail. Formalin-fixed paraffin-embedded (FFPE) histopathology, the gold standard, provides higher quality but requires >24 h for processing. Herein, we developed and validated generative AI models to translate Frozen images into AI-generated FFPE images (GenFFPE) using 2594 slides from 283 cases across five major skin cancer types. Four unpaired image-to-image models (CycleGAN, CUT, AIFFPE, and SANTA) were trained and compared using quantitative metrics and expert rankings; CUT demonstrated the best overall fidelity. External validation and a visual Turing test (accuracy 60.2%) confirmed image realism. Among 55 discrepant cases, GenFFPE-based reassessment increased diagnostic concordance by 53.3%. AI-based Frozen-to-FFPE translation is, thus, feasible and clinically meaningful, offering a potential tool to improve intraoperative diagnostic reliability and support decision-making for challenging tumor types such as extramammary Paget's disease.

PURPOSE: To determine the degree of tumor necrosis on pathology and clinical outcomes among intrahepatic cholangiocarcinoma (iCCA) patients who were treated with transarterial radioembolization (TARE) and the bridge or downstaged to surgery. METHODS: A single center retrospective review was performed to include consecutive patients who underwent TARE using glass microspheres and then subsequently underwent surgical resection or transplant. Baseline characteristics, dosimetry, radiologic response, histological tumor necrosis, and overall survival were evaluated. A total of 20 patients (F: M = 14:6; age: 57.3 ± 10.8 years) underwent TARE and then received resection (n = 15) or living-donor liver transplant (n = 5). A total of 23 selective TARE (two segments or less) were delivered, with a mean dose 301.7 ± 177.5, whereas 18 lobar (left or right hepatic artery) doses were delivered, with a mean dose of 150.3 ± 44.1 Gy. Concurrent systemic therapy was administered in 15 patients. RESULTS: The mean time from the initial TARE to surgery was 7.1 ± 9.2 months. On pathology, complete tumor necrosis, > 90% necrosis, and extensive tumor necrosis (> 50%) were achieved in 1 (5.0%), 13 (65.0%), and 18 (90.0%) patients, respectively. The median survival time (MST) calculated from the time of surgery was 40.2 (95%CI: 15.3-not reached) months, with a 1-yr, 3-yr, and 5-yr OS of 88.2% (95CI: 60.6-96.9%), 57.8% (95%CI: 31.1-77.3%), and 19.8% (95%CI: 1.5-53.5%). From the time of initial TARE, the MST was 41.4 (95%CI:22.9-not reached) month, with a 1-yr, 3-yr, and 5-yr OS of 100%, 69.9% (95%CI: 42.0-86.3%), and 30.9% (95%CI: 9.1-56.3%). Whether the patient received concomitant systemic treatment was associated with extensive tumor necrosis on pathology (Odds Ratio: 16.0, 95%CI: 1.27-200.92, p = 0.032). CONCLUSION: Based on tumor explant data, TARE can result in substantial tumor necrosis in the treatment of iCCA, although complete necrosis is uncommon. The addition of systemic therapy appears to be associated with a higher likelihood of achieving extensive tumor necrosis.