Radiology

A two-stage deep learning model with segmentation-guided top-K slice selection for patient-level PAS prediction on MRI.

OBJECTIVE: Placenta accreta spectrum (PAS) can cause severe obstetric complications, and accurate preoperative assessment is critical. However, heterogeneous MRI manifestations and the high cost of fine placental annotations limit deep learning applications. This study developed and validated a two-stage segmentation-guided MRI framework for automated placental localization, ROI selection, and pat...

Interpretable machine learning for Parkinson's disease diagnosis, staging, and biological mechanism exploration: a multicenter analysis.

OBJECTIVE: To develop and validate an interpretable machine learning model based on multicenter T1-weighted MRI radiomics data for the three-way classification of Parkinson's disease (PD)-Normal (NM), early-stage, and mid-late-stage-and to clarify the diagnostic value of key cortical nuclear features, with further elucidation of the molecular basis through proteomic association analysis. METHODS: ...

Transvaginal ultrasound-based radiomics and integrated clinical indicators via multimodal deep learning for prediction of endometrial polyp recurrence after hysteroscopic surgery.

OBJECTIVES: To evaluate a multimodal deep learning model integrating preoperative transvaginal ultrasound (TVUS)-based radiomics features and clinical...

[Computational medicine empowers multi-dimensional diagnosis and treatment of pancreatic cancer].

Due to its high genomic heterogeneity and dense desmoplastic microenvironment, traditional diagnosis and treatment for pancreatic ductal adenocarcinom...

[Arterial variations and management strategies in pancreatic surgery].

The pancreas is local in the retroperitoneal space,in close proximity to critical blood vessels such as celiac trunk, superior mesenteric artery, hepa...

Zero-shot detection of apical periodontitis on periapical radiographs using multimodal large language models: diagnostic accuracy and error patterns.

BACKGROUND: The present study evaluated the diagnostic performance of three general-purpose multimodal large language models (MLLMs)-Claude 4.5 Sonnet...

A multimodal ConvNeXt-Tiny deep learning model for simultaneous prediction of IDH mutation and Ki-67 expression in gliomas.

OBJECTIVE: To construct and validate a multi-task deep learning model based on ConvNeXt-Tiny for synchronous prediction of isocitrate dehydrogenase (I...

Corneal nerve regeneration: treatments and monitoring approaches.

BACKGROUND: Diagnostics and therapeutics for corneal nerve pathologies are rapidly evolving, with continual advancements in imaging, laser, machine le...

Design and Applications of Magnetically Actuated Microrobots in Endovascular Embolization.

Endovascular embolization is one of the core techniques in minimally invasive interventional medicine. It allows catheters to be accurately delivered ...

[Deep learning-driven high-frequency ultrasound method for skin aging assessment].

Ultraviolet radiation is a primary external factor contributing to skin photoaging, as it induces cellular deoxyribonucleic acid damage and collagen d...

[Research on electrical impedance tomography for pediatric pneumonia based on an improved radial basis function neural network].

In the diagnosis of pediatric pneumonia, the weak conductivity contrast of lung tissues leads to limited image resolution in electrical impedance tomo...

Reinforcement learning-driven adaptive game therapy for cognitive impairment patients with improved vision transformer based detection model.

BACKGROUND: Cognitive impairment is the growing challenge that requires early diagnosis and personalized management of neurodegenerative conditions li...

Integrating machine learning with histopathological, immunohistochemical, and PET parameters in the study of invasive breast carcinoma, no special type.

BACKGROUND: This study investigates the relationship between histopathological (HP) features, immunohistochemical (IHC) markers, 18F- FDG PET/CT param...

The optimal SVM model from multi-model comparison outperforms conventional criteria in preoperative prediction of ovarian cancer residual disease.

OBJECTIVE: To develop an interpretable artificial intelligence (AI)-based machine learning model integrating 18F-fluorodeoxyglucose positron emission ...

Development and validation of a multimodal artificial intelligence-based model for predicting post-prostatectomy treatment outcomes from baseline biparametric prostate magnetic resonance imaging.

PURPOSE: Prostate cancer (PCa) is the second most common cancer and cause of cancer deaths among American men. Existing risk prediction methods have l...

SegJointGene: joint cell segmentation and spatial gene prioritization by information entropy guided convolutional neural networks.

MOTIVATION: Spatial sequencing technologies enable the single-cell-level study of molecular organization in tissues. Revealing such spatial patterns r...

Evaluating expert decision-pattern alignment in endovascular planning for intracranial aneurysms using a multimodal large language model.

BACKGROUND: Endovascular treatment planning for intracranial aneurysms requires integrating vascular geometry, branch preservation, device feasibility...

CT in adult patients with Polytrauma: current practices, protocol optimization, structured reporting and future directions.

Computed tomography [CT] is the frontline imaging modality for the assessment of polytrauma patients because of its speed, diagnostic accuracy and inf...

Hypoperfusion Intensity Ratio as a Predictive Marker in Pre-Endovascular Treatment Perfusion MRI for Acute Middle Cerebral Artery Occlusion with Intracranial Atherosclerosis.

Introduction Identifying the cause of MCA occlusion before endovascular treatment (EVT) in acute ischemic stroke is useful. Hypoperfusion intensity ra...

DGCD-3D: Difference-guided conditional diffusion model for low-field 3D MRI enhancement to assist stroke assessment.

Low-field (LF) magnetic resonance imaging (MRI) plays a crucial role in assisting clinicians with rapid stroke diagnosis. However, its inherent limita...