YOLOv11 Outperforms Detectors for Nipple Injury in Single-Center Study
YOLOv11 performed best in a single-center comparison using augmented clinical photographs to detect and grade nipple injuries, but the study ...
Tag: deep learning
4D virtual cells model drug responses in human cancer cells
Two virtual-cell approaches tested in human cancer-cell cultures used 4D microscopy to model mitochondrial responses to drugs, without demonstrating clinical ...
Machine Learning Shows Promise but Limited Clinical Validation in Keratoconus
A systematic review of 41 studies found that machine learning can classify keratoconus severity and estimate progression and surgical outcomes, ...
Android Prototype Recommends Eyeglasses by Detected Face Type
An Android research prototype combines image processing, deep learning and internet-connected analysis to identify a person’s face type and display ...
Four sensors predict lower-limb joint moments with subject-specific calibration
A four-sensor deep-learning system estimated five lower-limb joint moments during walking and stair tasks, with 10 seconds of unlabeled walking ...
EML-CNN reports 96%+ speaker-identification accuracy across three speech benchmarks
An EML-CNN combining dense convolutional blocks, gated recurrent units and attention achieved speaker-identification accuracies above 96% across three benchmark datasets.
Deep learning assesses right ventricle and links findings to cardiovascular outcomes
DROID-RV estimated right-ventricular size and function from echocardiogram videos, while predictions in a primary-care cohort were associated with heart failure, ...
Benchmark study finds 98.9% accuracy for concurrency-aware SDN intrusion detection
A benchmark study found that concurrency-aware AI achieved up to 98.9% intrusion-detection accuracy, 2.1-times throughput and 57.5% lower average latency ...
Quantum-simulated mesh network classifies five dental occlusion attributes
A geometry-aware mesh network achieved 80.46% accuracy across five dental occlusion classifications in a 200-scan proof-of-concept study using simulated quantum ...
Narrative review finds synthetic CT clinical validation remains limited
A narrative review finds that deep-learning synthetic CT can improve cone-beam CT images and dose calculations, but clinical validation remains ...
Deep learning predicts DNA repair deficiency in HGSOC pathology slides
A retrospective study in high-grade serous tubo-ovarian carcinoma found that HRDPath inferred homologous recombination deficiency from pathology slides with an ...
Adversarial domain adaptation for false-positive reduction in hospital-to-robotic echocardiographic screening under limited target-domain data
Adversarial domain adaptation raised normal-case specificity on robotic echocardiograms from 65.7% to 89.3% without using robotic pathological cases, but validation ...
MSIPep prioritizes tumor peptides in leukemia and solid-tumor datasets
MSIPep combines immunopeptidomics, transcriptomics and deep learning to identify and computationally prioritize candidate tumor peptides in leukemia and solid-tumor datasets.
ADGB-ONet: an attention-driven gradient balancing operator network for scattering pressure field prediction
A computational study reports that ADGB-ONet achieved a 2.88% mean relative error when predicting scattered pressure fields, outperforming the compared ...
Photo-based AI classifies cavities and restorations in children’s primary molars
A multistage AI pipeline detected primary molars in children’s intraoral photographs and classified visible findings with 85.9% accuracy in a ...
An interpretable hierarchical deep learning framework for lung and colon cancer detection
A hierarchical deep-learning framework classified five lung and colon tissue classes with 98.50% accuracy on LC25000 and 82.01% on the ...
Hybrid deep-learning model shows favorable hourly PM2.5 prediction performance in modeling study
A Scientific Reports abstract describes a hybrid decomposition and deep-learning model that reported favorable accuracy and generalization performance for hourly ...
Mahabad Dam modeling study reports 80% lower mean absolute error for total nitrogen predictions
A Mahabad Dam modeling study reported an 80% reduction in mean absolute error and a rise in Willmott’s index from ...
Simulated hybrid framework identifies and localizes module-level faults in 3 × 5 photovoltaic array
A simulation study of a 3 × 5 photovoltaic array reported 99.76% topology-classification accuracy and 100% localization accuracy for two ...
Uncertainty-aware multimodal model evaluated for cervical-cell classification
An abstract reports that an uncertainty-aware proof-of-concept model classified 6,849 cervical-cell images with an AUC-ROC of 0.993, but synthetic auxiliary ...
POPULAR NEWS
-
Case Report Explores Caplacizumab in Late-Diagnosed Congenital Thrombotic Thrombocytopenic Purpura
-
Multitask Cambrian Model Improves Protein Melting Temperature Prediction
-
Vasopressors Exert Divergent Immunomodulatory Effects Across a Spectrum in Septic Shock
-
Study Identifies Key Drivers Shaping Salmonid Gill Microbiomes in Aquaculture