HAM10000
PulseAugur coverage of HAM10000 — every cluster mentioning HAM10000 across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New method enhances fairness in medical AI by analyzing feature attribution
Researchers have developed a new method called joint output-attribution regularization to improve fairness in medical image classification models. This technique goes beyond simply ensuring equal outcomes across demogra…
-
New audit method tests melanoma AI classifiers with diffusion counterfactuals
Researchers have developed a novel method for auditing melanoma classifiers using diffusion models to generate counterfactual examples. This approach aims to rigorously test the concept-based explanations of these class…
-
Brain-Inspired Engram Memory Network Enhances AI Explainability
Researchers have developed an Engram Memory Network (EMN), a novel AI model inspired by the human memory system, to improve the explainability and reliability of prototype-based AI. The EMN utilizes a Hopfield-inspired …
-
YOLO26 study finds minimal preprocessing optimal for skin lesion analysis
A new study published on arXiv explores the impact of dermoscopic preprocessing techniques on skin lesion classification and segmentation using the YOLO26 model. The research, which controlled for data leakage by ensuri…
-
Dermoscopic preprocessing offers no consistent benefit for YOLO26 skin lesion analysis
A study evaluating dermoscopic preprocessing techniques for skin lesion analysis found that handcrafted preprocessing methods did not consistently improve the performance of a fixed YOLO26 segmentation model. When using…
-
MOXIE framework reveals multiple explanations for biomedical image classifiers
Researchers have developed MOXIE, an evolutionary framework designed to uncover multiple alternative explanations for biomedical image classifier predictions. Unlike methods that provide a single explanation based on a …
-
CNNs Compared for Melanoma Detection Across Image Types
A new research paper evaluates the effectiveness of several pre-trained convolutional neural networks (CNNs) for melanoma detection using both dermatoscopic and histopathological images. The study utilized datasets such…
-
BruNet framework achieves state-of-the-art bruise segmentation
Researchers have developed BruNet, a novel framework for segmenting bruises in medical images, addressing the challenges of limited data and variable appearance. This framework utilizes a ViT-based visual encoder, such …
-
EcoFair framework optimizes edge AI energy efficiency for medical diagnostics
Researchers have developed EcoFair, a novel inference framework designed to optimize energy efficiency in edge AI systems, particularly for medical applications like dermatology. This framework addresses the challenge o…
-
New research explores federated learning advancements in privacy, efficiency, and robustness · 9 sources tracked
Multiple research papers published on arXiv explore advancements in federated learning, focusing on improving its efficiency, privacy, and robustness. One paper analyzes the convergence of sequential federated learning …
-
Dermatology AI generalization gap linked more to disease shift than skin tone
A new study published on arXiv investigates the generalization gap in dermatology AI models, specifically examining whether poor performance is due to underrepresentation of skin tones or shifts in disease distribution.…
-
Cross-validation improves hyperparameter tuning for medical image AI
A new research paper explores hyperparameter optimization (HPO) for deep learning image classifiers, particularly in medical imaging where small datasets are common. The study compared three HPO protocols: fixed holdout…
-
Soft-Attention mechanism boosts skin cancer classification in deep neural networks
Researchers have demonstrated that incorporating a Soft-Attention mechanism into deep neural network architectures can significantly improve their performance in classifying skin lesions. By enabling networks to focus o…
-
New neuromorphic architecture enhances skin lesion classification on edge devices
Researchers have developed QANA, a novel quantization-aware neuromorphic architecture designed for skin lesion classification on resource-constrained devices. This architecture improves the conversion process from CNNs …
-
New ensemble deep learning framework enhances skin lesion classification accuracy
Researchers have developed a new deep learning framework for classifying skin lesions from medical images. This framework combines a vision transformer model, MaxViT-Tiny, with two convolutional neural network models, C…
-
New AI framework enhances skin lesion classification with uncertainty and explainability
Researchers have developed a new framework for classifying skin lesions that combines deep ensemble learning with uncertainty quantification and explainability techniques. This approach uses multiple models, including v…
-
EulerLoRA enhances parameter-efficient fine-tuning with stochasticity
Researchers have developed EulerLoRA, a novel extension of the Low-Rank Adaptation (LoRA) technique for parameter-efficient fine-tuning. Unlike standard LoRA, EulerLoRA introduces stochasticity to generate multiple pred…
-
AI model for skin cancer classification improved with robust data augmentation
Researchers have explored data augmentation techniques to enhance the robustness of dermoscopic skin lesion classifiers against domain shifts. Their study, utilizing a ConvNeXt-Large backbone and the ISIC Archive with D…
-
New PLCRD framework enables mask-free skin lesion classification
Researchers have developed a novel framework called Privileged Lesion-Context Relational Distillation (PLCRD) for skin lesion classification. This method uses lesion segmentation masks only during the training phase, al…
-
FedProIn framework enhances federated learning for medical imaging
Researchers have developed FedProIn, a novel framework designed to improve federated learning in medical imaging by addressing client drift. This approach utilizes learnable class prototypes to capture shared semantic s…