Predicting perineural invasion of intrahepatic cholangiocarcinoma based on CT: a multicenter study.

Objective: This study explored the feasibility of preoperatively predicting perineural invasion (PNI) of intrahepatic cholangiocarcinoma (ICC) through machine learning based on clinical and CT image features, which may help in individualized clinical decision making and modification of further treatment strategies.

Materials And Methods: This study enrolled 199 patients with histologically confirmed ICC from three institutions for final analysis. 111 patients from Institution I were recruited as the training cohort and internal validation cohort.

Nanotechnology-enhanced neuroprotection: a novel idebenone nanoprodrug conjugate strategy for Parkinson's disease.

Parkinson's disease (PD) is characterized by the progressive loss of dopamine-producing neurons in the substantia nigra pars compacta, and increased oxidative stress, inflammation, and α-synuclein (α-syn) aggregates have been observed in PD brains. Currently, no effective drugs are available for clinical use to prevent the development of PD. Herein, we propose a novel idebenone (IDB) nanoprodrug conjugate strategy for PD treatment.

MR Cell Size Imaging Revealing Intestinal Fibrosis to Predict Intestinal Disease Progression in Patients with Crohn's Disease.

Background: Intestinal fibrosis in Crohn's disease (CD) is driven by mesenchymal cell activation, resulting in adverse outcomes. We aimed to evaluate the efficacy of time-dependent diffusion MRI (TD-dMRI) in characterizing fibrosis-associated cellular properties and predicting disease progression in CD.

Methods: This prospective study enrolled 145 CD patients undergoing TD-dMRI to map fibrotic cellular characteristics (e.

Vanishing pancreas: CT and MRI features and imaging diagnostic strategies.

The vanishing pancreas is a frequently overlooked condition which can result from partial or complete dorsal pancreatic agenesis, intra-pancreatic fat deposition (IPFD) and pancreatic atrophy caused by chronic pancreatitis. A variety of diseases, including cystic fibrosis, maturity-onset diabetes of the young type 8, Shwachman-Diamond syndrome, and Johanson-Blizzard syndrome, can manifest as IPFD. Dorsal pancreatic agenesis can, albeit rarely, coexist with abnormalities or tumors.

Thin-slice T-weighted images and deep-learning-based super-resolution reconstruction: improved preoperative assessment of vascular invasion for pancreatic ductal adenocarcinoma.

Purpose: To evaluate the efficacy of thin-slice T-weighted imaging (TWI) and super-resolution reconstruction (SRR) for preoperative assessment of vascular invasion in pancreatic ductal adenocarcinoma (PDAC).

Methods: Ninety-five PDACs with preoperative MRI were retrospectively enrolled as a training set, with non-reconstructed TWI (NRT) in different slice thicknesses (NRT-3, 3 mm; NRT-5, ≥ 5 mm). A prospective test set was collected with NRT-5 (n = 125) only.

Integrating Gut Microbiome and Metabolomics with Magnetic Resonance Enterography to Advance Bowel Damage Prediction in Crohn's Disease.

Purpose: Cumulative bowel damage (BD) critically influences the progression and prognosis of Crohn's disease (CD). Although the Lémann Index (LI) remains the standard for BD assessment, its clinical utility is limited by heavy reliance on extensive clinical data. Multiparametric magnetic resonance enterography (MRE) provides noninvasive macroscopic evaluation of BD severity, however, it fails to characterize microscopic alterations.

Added value of multifrequency magnetic resonance elastography in predicting pathological grading of pancreatic neuroendocrine neoplasms.

Objectives: To prospectively investigate the pancreatic stiffness (c) and fluidity (φ) of pancreatic neuroendocrine neoplasms (pNENs), measured using multifrequency magnetic resonance elastography (MRE), and evaluate their performance in predicting pNENs pathological grade.

Materials And Methods: This study included 96 untreated patients with pathologically confirmed pNENs who underwent multifrequency MRE within 2 weeks before surgery between September 2021 and November 2023. Independent predictors of pathological grade were identified using multivariate regression analysis, and predictive performance was assessed using receiver operating characteristic curves.

Explainable Fusion Model for Predicting Postoperative Early Recurrence in Hepatocellular Carcinoma Using Gadoxetic Acid-Enhanced MRI Habitat Imaging.

Rationale And Objectives: To develop an explainable fusion model that combines clinical, radiomic, and habitat features to predict postoperative early recurrence in hepatocellular carcinoma (HCC).

Methods: The bicentric retrospective study included 370 patients with surgically confirmed early-stage HCC who underwent gadoxetic acid-enhanced MRI. The patients were stratified into a training cohort (n=296) and an external validation cohort (n=74).

An Efficient Domain Knowledge-Guided Semantic Prediction Framework for Pathological Subtypes on the Basis of Radiological Images With Limited Annotations.

Accurate prediction of pathological subtypes on radiological images is one of the most important deep learning (DL) tasks for the appropriate selection of clinical treatment. It is challenging for conventional DL models to obtain sufficient pathological labels for training because of the heavy workload, invasive surgery, and knowledge requirements in pathological analysis. However, existing methods based on limited annotations, such as active learning (AL) and semi-supervised learning (SSL), have difficulty in capturing lesion's effective features because of the complicated semantic information of radiologic images.

Altered gut microbiome-metabolite interactions link intestinal inflammation severity and MR enterography abnormalities in Crohn's disease.

Altered gut microbiota‒metabolite interactions may result in intestinal inflammation severity variation in Crohn's disease (CD). Magnetic resonance enterography (MRE) advances anti-inflammatory strategy development. We aimed to identify inflammation-related multiomics factors and MRE interactions for CD management, analyzing 425 CD patients and 42 healthy controls undergoing MRE, ileocolonoscopy, and fecal/blood sampling (microbiota/metabolite analyses), with intestinal inflammation categorized by MRE and ileocolonoscopy.

A comprehensive dataset of magnetic resonance enterography images with intestinal segment annotations.

Inflammatory bowel disease (IBD) is a recurrent bowel disease that usually requires magnetic resonance enterography (MRE) for diagnosis and monitoring. However, recognition of bowel segments from MRE images by a radiologist is challenging and time-consuming. Deep learning-based medical image segmentation has shown the potential to reduce manual effort and provide automated tools to assist in disease management; however, it requires a large-scale fine-annotated dataset for training.

Weight-Loss Plateau during Lifestyle Intervention Predicts Treatment Response in Patients with Metabolic Dysfunction-Associated Steatotic Liver Disease and Obesity.

Introduction: Whether the weight-loss plateau and its values differ in obesity with or without metabolic dysfunction-associated steatotic liver disease (MASLD) undergoing continuous lifestyle intervention remains unknown. We aimed to investigate this problem.

Methods: This prospective observational cohort study included 305 patients with obesity and MASLD and 103 matched individuals with non-MASLD from January 2015 to April 2023, with a 12-month follow-up to monitor weight changes.

Effect of potent nucleos(t)ide analog on alpha fetoprotein changes and occurrence of hepatocellular carcinoma in patients with chronic hepatitis B.

Background: Successful antiviral therapy significantly decreases the incidence of hepatocellular carcinoma (HCC) in patients with chronic hepatitis B (CHB). Alpha-fetoprotein (AFP) in the serum is a valuable early indicator of HCC. However, it is unclear whether different antiviral medications have varying effects on AFP levels.

A Transfer Learning Radiomics Nomogram to Predict the Postoperative Recurrence of Advanced Gastric Cancer.

Background And Aim: In this study, a transfer learning (TL) algorithm was used to predict postoperative recurrence of advanced gastric cancer (AGC) and to evaluate its value in a small-sample clinical study.

Methods: A total of 431 cases of AGC from three centers were included in this retrospective study. First, TL signatures (TLSs) were constructed based on different source domains, including whole slide images (TLS-WSIs) and natural images (TLS-ImageNet).

Role of high-resolution magnetic resonance imaging in preoperative tumor-node-metastasis staging evaluation of esophageal cancer: a narrative review.

Background And Objective: Esophageal cancer (EC) is an aggressive disease characterized by high mortality rates and a propensity for locoregional or distant recurrence. The treatment strategies and prognostic estimation for EC depend on accurate pre-treatment tumor-node-metastasis (TNM) staging. The objective of this review was to illustrate the role of various imaging modalities in achieving accurate preoperative TNM staging of EC, with a particular focus on the utilization of advanced high-resolution magnetic resonance imaging (MRI) sequences for T classification, which have shown promise in enhancing the delineation of tumor depth and extent.

Development and validation of a dynamic contrast-enhanced magnetic resonance imaging-based habitat and peritumoral radiomic model to predict axillary lymph node metastasis in patients with breast cancer: a retrospective study.

Background: The heterogeneity within breast cancer and its microenvironment are associated with metastasis. Analyzing distinct tumor subregions using habitat analysis and characterizing the tumor microenvironment through radiomics may be valuable for predicting axillary lymph node metastasis (ALNM) in breast cancer. This study aimed to develop and validate a nomogram for predicting ALNM in breast cancer patients by integrating clinicopathological, intra- or peri-tumoral radiomic, and habitat signatures based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and determine the optimal peritumoral region size for accurate prediction.

Genetic syndromes associated with pancreatic neuroendocrine neoplasms and imaging diagnostic strategies.

Pancreatic neuroendocrine neoplasms (pNENs) are the second most common pancreatic malignancy. While most cases are sporadic, a small proportion is associated with genetic syndromes, such as Multiple Endocrine Neoplasia (MEN), Von Hippel-Lindau Syndrome (VHL), Neurofibromatosis Type 1 (NF1), and Tuberous Sclerosis Complex (TSC). This review aims to use pNENs as a clue to reveal the full spectrum of disease, providing a comprehensive understanding of diagnosis.

Tissue-matched analysis of MRI evaluating the tumor infiltrating lymphocytes in hepatocellular carcinoma.

Tumor-infiltrating lymphocytes (TILs) play critical roles in the tumor microenvironment and immunotherapy response. This study aims to explore the feasibility of multi-parametric magnetic resonance imaging (MRI) in evaluating TILs and to develop an evaluation model that considers spatial heterogeneity. Multi-parametric MRI was performed on hepatocellular carcinoma (HCC) mice (N = 28).

AI-based fingerprint index of visceral adipose tissue for the prediction of bowel damage in patients with Crohn's disease.

The fingerprint features of visceral adipose tissue (VAT) are intricately linked to bowel damage (BD) in patients with Crohn's disease (CD). We aimed to develop a VAT fingerprint index (VAT-FI) using radiomics and deep learning features extracted from computed tomography (CT) images of 1,135 CD patients across six hospitals (training cohort,  = 600; testing cohort,  = 535) for predicting BD, and to compare it with a subcutaneous adipose tissue (SAT)-FI. VAT-FI exhibited greater predictive accuracy than SAT-FI in both training (area under the receiver operating characteristic curve [AUC] = 0.

Prediction of the early hepatocellular carcinoma development in patients with chronic hepatitis B virus infection using gadoxetic acid-enhanced magnetic resonance imaging.

Background: Non-hypervascular hypointense nodules (NHHNs) can transform into hypervascular hepatocellular carcinoma (HCC) during the long-term follow-up. However, the risk factors for NHHN hypervascular transformation in chronic hepatitis B virus (HBV)-infected populations are unknown. This study assessed the predictive value of gadoxetic acid-enhanced magnetic resonance imaging (MRI) for HCC development in patients with chronic HBV infection.

Multiomics reveals microbial metabolites as key actors in intestinal fibrosis in Crohn's disease.

Intestinal fibrosis is the primary cause of disability in patients with Crohn's disease (CD), yet effective therapeutic strategies are currently lacking. Here, we report a multiomics analysis of gut microbiota and fecal/blood metabolites of 278 CD patients and 28 healthy controls, identifying characteristic alterations in gut microbiota (e.g.

Specific metabolic impairments indicate loss of sustained liver improvements in metabolic dysfunction-associated steatotic liver disease treatment.

Background: High liver fat content (LFC) induces increased risks of both hepatic and extrahepatic progression in metabolic dysfunction-associated steatotic liver disease (MASLD), while maintaining a significant decline in magnetic resonance imaging-based proton density fat fraction (MRI-PDFF) (≥30% decline relative to baseline) without worsening fibrosis results in improved histological severity and prognosis. However, the factors associated with the loss of sustained responses to treatment remain unclear, and we aim to identify them.

Methods: Consecutive treatment-naïve MASLD patients between January 2015 and February 2022, with follow-up until April 2023, were included in this prospective cohort study.

Development and validation of a CT-based radiomics model to predict survival-graded fibrosis in pancreatic ductal adenocarcinoma.

Background: Tumor fibrosis plays an important role in chemotherapy resistance in pancreatic ductal adenocarcinoma (PDAC); however, there remains a contradiction in the prognostic value of fibrosis. The authors aimed to investigate the relationship between tumor fibrosis and survival in patients with PDAC, classify patients into high- and low-fibrosis groups, and develop and validate a CT-based radiomics model to non-invasively predict fibrosis before treatment.

Materials And Methods: This retrospective, bicentric study included 295 patients with PDAC without any treatments before surgery.