Dermatology

MsM-DPM: Multiscale Mamba Diffusion Probabilistic Model for Medical Image Segmentation.

Diffusion probabilistic models (DPMs) have recently demonstrated promising performance in medical image segmentation. However, traditional DPM has difficulty handling the irregular structure of images and the inherent similarity between lesions and surrounding tissues. To overcome these challenges, we propose an innovative architecture, the multiscale Mamba DPM (MsM-DPM), designed to enhance medic...

A Deep Learning Algorithm for Liver Metastasis Detection at Contrast-enhanced Abdominal CT in Patients with Colorectal Cancer: A Comparative Study with Radiologists.

Purpose To evaluate the performance of a deep learning algorithm (DLA) for detecting liver metastases (LM) in patients with colorectal cancer (CRC) across diverse clinical contexts and compare its accuracy with that of radiologists. Materials and Methods This retrospective, bicentric study included patients with CRC who underwent contrast-enhanced abdominal CT between January 2019 and December 202...

Brain Age in Adult Patients With Early-Treated Phenylketonuria.

Structural brain alterations have been observed in individuals with phenylketonuria (PKU); however, the potential impact of PKU on brain aging remains...

AI-Powered Detection of Cutaneous Involvement in Familial Mediterranean Fever.

Image quality restoration in 15-s breath-hold PET using a diffusion-based neural network.

BACKGROUND: Breath-hold PET imaging helps reduce respiratory motion artifacts in thoracoabdominal scans. However, its clinical application is limited ...

Regulatory roles of microRNAs in epigenetic and immune gene networks in psoriasis.

Psoriasis is a chronic, immune-mediated skin disorder characterized by keratinocyte hyperproliferation, impaired differentiation, and sustained inflam...

ChatGPT, Gemini, and Claude in clinical and dermoscopic image analysis of basal cell carcinoma and its common mimickers: A comparative performance analysis.

Basal cell carcinoma (BCC) is the most common skin cancer. Off-the-shelf multimodal large language models are widely accessible, yet their performance...

Single-nucleus multi-omics dissection of dysregulated trophoblast development and disrupted immune microenvironment in complete hydatidiform moles.

Hydatidiform mole (HM) is driven by aberrant trophoblast proliferation, disrupting embryonic development and leading to pregnancy loss with increased ...

Annotation-free prediction of immunotherapy response in melanoma using single-cell transcriptomic data.

Immune checkpoint inhibitors (ICIs) have transformed the advanced melanoma treatment landscape; however, a subset of patients achieve durable response...

Neuroimaging-Based Deep Learning Applications for Lesion Detection and Predicting the Outcome Following Epilepsy Surgery.

Neuroimaging studies are essential for evaluating patients with drug-resistant focal epilepsy and determining their candidacy for epilepsy surgery. Th...

Deep learning-assisted tumor radiomic dynamics on MRI predict pathological complete response in HCC undergoing immune-based therapy followed by hepatectomy.

BACKGROUND AIMS: Pathological complete response (pCR) following conversion therapy for initially unresectable hepatocellular carcinoma (uHCC) remains ...

Deep Learning for Classification and Prognosis of Melanoma in Whole-Slide Images: A Review.

The rising incidence of melanoma highlights the limitations of traditional diagnostic methods, including inefficiency, subjectivity, and poor quantifi...

Artificial Intelligence in Multiple Sclerosis: Possibilities in Radiological Diagnostics and Progression Assessment.

Multiple sclerosis (MS) is characterized by clinical and radiological heterogeneity. Recent refinements in the McDonald criteria and the integration o...

What practicing pathologists and oncologists should know about the new computational pathology-based companion diagnostic tools.

The integration of artificial intelligence into pathology is transforming the assessment of histological and immunohistochemical (IHC) slides, offerin...

Leveraging infarct topography for early warning: a robust model for predicting malignant cerebral edema after endovascular treatment in acute ischemic stroke.

BACKGROUND: The early prediction of malignant cerebral edema (MCE) following endovascular therapy for acute ischemic stroke is of paramount importance...

TRKB-based signature identifies high-risk squamous cell carcinoma cases and TRKB blockade reprograms tumor and stromal cells toward suppressive phenotypes.

BACKGROUND: Cutaneous squamous cell carcinoma (cSCC) is a common age-related cancer, with a subset prone to recurrence and metastasis. Currently, no u...

Geometric deep learning-based coronary wall shear stress estimation from real-world patients.

BACKGROUND: Coronary wall shear stress (WSS) derived from computational fluid dynamics (CFD) provides mechanistic insight and prognostic information, ...

Deep Learning-Based Diagnostic Model for Ocular Surface Neoplastic Diseases.

PURPOSE: To develop a deep learning (DL) model for diagnosing ocular surface tumors and evaluating its diagnostic performance. SETTING: Development of...

Integrative transcriptomic and machine learning analysis identifies CDH17 and HOXC13 as robust candidate prognostic biomarkers in uveal melanoma.

BACKGROUND: Uveal melanoma (UM), the most common form of ocular melanoma, represents poor prognosis, with approximately 50% of patients developing met...

Diabetic retinopathy classification network with multi-frequency contextual attention module.

Diabetic retinopathy (DR) remains a major cause of visual impairment globally, and early, accurate diagnosis is critical for effective intervention. T...