ISIC-2018
PulseAugur coverage of ISIC-2018 — every cluster mentioning ISIC-2018 across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New U-Net variant improves boundary accuracy in dermoscopic image segmentation
Researchers have developed EA-LiteUNet, a novel U-Net variant designed for precise segmentation of dermoscopic images, particularly focusing on boundary accuracy. The architecture incorporates boundary-aware representat…
-
Tree-NET framework enhances medical image segmentation efficiency
Researchers have developed Tree-NET, a novel framework designed to improve the accuracy and efficiency of 2D medical image segmentation. This approach utilizes dual bottleneck supervision, applying feature compression a…
-
New Graph-Based Model Improves Skin Lesion Diagnosis Accuracy
Researchers have developed a novel graph-based multiple instance learning framework that integrates both implicit and explicit relational biases for improved image classification. The approach begins with an EfficientNe…
-
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…
-
New method enhances medical image segmentation for skin lesions
Researchers have developed PEFT-MedSAM, a parameter-efficient fine-tuning method for the Medical Segment Anything Model (MedSAM) to improve the segmentation of skin lesions in dermoscopic images. This technique freezes …
-
New Chaos-SSL Framework Enhances Medical Image Classification
Researchers have introduced Chaos-SSL, a novel two-stage framework designed to improve medical image classification by addressing the limitations of standard self-supervised learning methods. The framework utilizes 1D c…
-
New chaotic self-supervision boosts medical image classification accuracy
Researchers have developed a new self-supervised learning strategy called the Chaotic Denoising Autoencoder (CDAE) for medical image classification. Unlike methods that use masking, CDAE applies chaotic transformations …
-
New method improves AI model safety post-hoc with targeted error correction
Researchers have developed a post-hoc error correction method to enhance the safety of machine learning models in critical applications. This technique employs a dual-classifier GBDT pipeline to differentiate between ro…
-
RABC-Net achieves high accuracy in annotation-free skin lesion segmentation
Researchers have developed RABC-Net, a novel system for segmenting skin lesions in dermoscopy images that does not require pixel-level manual annotations for training. The system incorporates reliability learning and ad…