Tag: deep learning

A class-adaptive ensemble of three neural networks classifies brain tumors in MRI scans with 99.39 percent benchmark accuracy, validated by ...

A multimodal deep learning framework combining CT radiomics, clinical variables, and EGFR status predicted growth trends of pulmonary ground-glass nodules ...

A new few-shot learning framework called scCAPReSE detects large-scale genomic rearrangements in single-cell Hi-C data using pre-trained image model representations, ...

A hybrid CNN-Transformer framework called LHCT-Net reached 98.55% accuracy for melanoma-versus-non-melanoma classification on the 25,331-image ISIC 2019 dataset.

An explainable transformer model fusing MRI with texture descriptors reached over 99 percent accuracy in Alzheimer's disease staging benchmarks, with ...

A new review examines how neuroscience-inspired deep learning and genetic algorithms can be combined into hybrid, biologically plausible AI systems.

A study of 2,000 CBCT scans found that an XGBoost model using tooth-specific pulp-dentin index values from all four first ...

A new deep learning framework segments, classifies and counts microscopic mineral grains with 97.57% accuracy without requiring annotated segmentation masks.

A retrospective external validation study reports that a multitask deep learning model can estimate McGoon ratios from chest radiographs in ...

A multicenter Chinese study reports that an AI model combining retinal vascular geometric parameters from fundus images with clinical data ...

A new review maps how numerical simulations and artificial intelligence are reshaping the study of turbidity currents, the powerful underwater ...

A prospective Indian study reports a deep-learning ensemble that classifies thyroid FNAC images into 2023 Bethesda categories with 96 percent ...

A new 3D Mamba-based model segments brain tumors with consistent accuracy gains and a 15x efficiency improvement over existing state-of-the-art ...

A new framework combines 3D computational fluid dynamics, sparse Proper Generalized Decomposition surrogates, and data-driven methods such as SINDy and ...

A systematic review of 26 studies finds AI models diagnosing multiple sclerosis with over 95 percent accuracy in some cases, ...

Researchers developed TriAlign-ATG, an AI framework that generates physically executable adversarial network traffic which evades deep-learning intrusion detectors while preserving ...

A new knowledge distillation method compresses large pre-trained models into lightweight detectors that identify vulnerabilities in Python code with Macro-F1 ...

A new multimodal AI system called HMTF-Net combines text, conversation context, user interaction graphs, images and metadata to detect cyberbullying, ...

Researchers report an improved YOLO model that detects small PCB surface defects with 90.63% sensitivity while reducing model size and ...

A SegFormer-B2-based multi-expert ensemble called MUSE-Net achieved a mean Dice of 0.834 for carotid plaque segmentation across a four-center ultrasound ...