Pathology

Large Language Models for the Differentiation of Benign and Malignant Liver Nodules based on Multimodal Prompts in Liver US Cases.

OBJECTIVE: Large language models (LLMs) that can process both images and text are increasingly being used in radiology. This study aimed to evaluate the performance of LLMs including GPT-4 Omni (GPT-4o), Claude-3.5-Sonnet (Claude), and Gemini 1.5 Pro (Gemini) in differentiating benign and malignant nodules in liver US cases and compare it with that of human readers. METHODS: Four hundred liver US ...

Machine learning and deep learning models for predicting colorectal cancer metastases: A comprehensive review.

Colorectal cancer (CRC) is a leading cause of cancer-related mortality worldwide, largely due to the development of distant metastases, which is associated with poor survival outcomes. Early detection and accurate prediction of colorectal cancer metastasis can significantly improve patient outcomes. Conventional diagnostic approaches, including imaging and biomarkers, are often limited by suboptim...

Changes in computed tomography derived muscle and pulmonary tissue in patients hospitalized for COVID-19: a 12-month follow-up study.

BACKGROUND: Prolonged muscle loss and persistent pulmonary radiological manifestations have been observed among previously hospitalized COVID-19 patie...

Non-invasive diagnosis strategy integrating PSMA PET/CT and mpMRI for patients with suspected prostate cancer: a multi-center study.

BACKGROUND: Multiparametric MRI (mpMRI) and ^68 Ga-PSMA PET/CT are widely used for prostate cancer (PCa) diagnosis but remain limited by false positiv...

Identification and selection of the best artificial intelligence methods developed for detection and diagnosis of breast cancer.

BACKGROUND: Comprehensive identification and prioritization of developed artificial intelligence methods for the detection and diagnosis of breast can...

What is diagnosis in the age of artificial intelligence.

The integration of artificial intelligence into clinical practice demands fundamental reconsideration of how we conceptualize diagnosis. Clinical and ...

Deep learning and cryogenic electron microscopy modeling for gene editing dynamics.

Advances in cryogenic electron microscopy (cryo-EM) data modeling and deep learning are reshaping our ability to interrogate and engineer genome-editi...

Noninvasive Prediction of Bone Metastasis-Free Survival in Lung Adenocarcinoma Using Interpretable CT-based Deep Learning Model.

RATIONALE AND OBJECTIVES: Preoperatively identifying patients at high risk of bone metastasis (BM) remains challenging in resectable lung adenocarcino...

Reduction of Acquisition Time in FTIR Spectroscopy via Spectral Super-Resolution by Deep Learning.

This study aims to enhance spectral resolution in Fourier transform infrared spectroscopy (FTIR), a crucial element for in-depth molecular analysis in...

Unraveling defect-mediated ion transport behavior in anti-perovskite solid-state electrolytes via machine learning molecular dynamics simulations.

Anti-perovskite (AP) solid-state electrolytes (SSEs) have emerged as promising candidates for high-safety solid-state batteries due to their wide elec...

The long and winding road: the resilience of cervical cytology as a long-standing laboratory tool to aid the diagnosis of HPV-induced lesions.

BACKGROUND: Despite molecular advancements, cervical cytology remains a resilient and fundamental laboratory tool in the prevention of cervical cancer...

Precessional Dynamics of Octahedra in CsPbBr3.

The crystal structure of ABX3 halide perovskites consists of corner-sharing BX6 octahedra, whose collective distortions define the different crystallo...

Circulating extracellular vesicle long RNA profiling combined with machine learning unveils novel diagnostic signature and molecular features in chronic pancreatitis.

BACKGROUND: No clinically useful non-invasive biomarkers have been developed for diagnosis of chronic pancreatitis (CP), and molecular features of CP ...

A vision-language foundation model improves preoperative diagnosis of follicular thyroid neoplasms using ultrasound images.

Preoperative discrimination between follicular thyroid carcinoma (FTC) and follicular thyroid adenoma (FTA) remains challenging, as imaging and cytolo...

Deep learning inference of cell type-specific gene expression from breast tumor histopathology.

Cell type-specific gene expression from single-cell RNA sequencing (RNA-seq) is valuable for breast cancer precision oncology but available cohorts ar...

Region-guided decoupled fusion network for ultrasound-based classification of thyroid nodules with and without Hashimoto's thyroiditis.

RATIONALE AND OBJECTIVES: Differentiating benign from malignant thyroid nodules is particularly challenging in patients with Hashimoto's thyroiditis (...

Morphology-informed deep learning for risk assessment of filamentous bulking in a full-scale industrial wastewater treatment plant.

Filamentous bulking (FB) is a recurring cause of solids-separation failure in activated sludge systems. Standard diagnostics such as sludge volume ind...

MUSIOMICS: A multi-region radiomics framework that outperforms single-region analysis in classifying malignant pulmonary nodules.

BACKGROUND AND OBJECTIVE: Radiomic studies in lung cancer have primarily analyzed single-domain features extracted separately from intranodular (Zone-...

Assessment of high- and low-risk histopathologic subtypes of basal cell carcinoma using artificial intelligence and dermatologist evaluation.

BACKGROUND: Basal cell carcinoma (BCC) is the most common skin cancer, and accurate histopathologic risk stratification is essential for treatment sel...

Enhancing biomedical optical volumetric imaging via self-supervised orthogonal learning.

Optical volumetric imaging grapples with inherent noise problems arising from photon budget constraints, light scattering, and space-bandwidth product...