Skin Cancer Classification
14 papers with code • 1 benchmarks • 1 datasets
ISIC 2020 Challenge Dataset
Most implemented papers
Knowledge Transfer for Melanoma Screening with Deep Learning
learningtitans/isbi2017-part3
•
•
Knowledge transfer impacts the performance of deep learning -- the state of the art for image classification tasks, including automated melanoma screening.
Skin Lesion Synthesis with Generative Adversarial Networks
alceubissoto/gan-skin-lesion
•
•
Skin cancer is by far the most common type of cancer.
Data Augmentation for Skin Lesion Analysis
fabioperez/skin-data-augmentation
•
•
In this work, we investigate the impact of 13 data augmentation scenarios for melanoma classification trained on three CNNs (Inception-v4, ResNet, and DenseNet).
Skin Cancer Segmentation and Classification with NABLA-N and Inception Recurrent Residual Convolutional Networks
Several DL architectures have been proposed for classification, segmentation, and detection tasks in medical imaging and computational pathology.
Deep neural network or dermatologist?
KyleYoung1997/DNNorDermatologist
•
•
We show that despite high accuracy, the models will occasionally assign importance to features that are not relevant to the diagnostic task.
Melanoma Detection using Adversarial Training and Deep Transfer Learning
hasibzunair/adversarial-lesions
•
•
Journal of Physics in Medicine and Biology 2020
In the first stage, we leverage the inter-class variation of the data distribution for the task of conditional image synthesis by learning the inter-class mapping and synthesizing under-represented class samples from the over-represented ones using unpaired image-to-image translation.
Model Patching: Closing the Subgroup Performance Gap with Data Augmentation
HazyResearch/model-patching
•
•
ICLR 2021
Particularly concerning are models with inconsistent performance on specific subgroups of a class, e. g., exhibiting disparities in skin cancer classification in the presence or absence of a spurious bandage.
Semi-Supervised Federated Peer Learning for Skin Lesion Classification
With few annotated data, FedPerl is on par with a state-of-the-art method in skin lesion classification in the standard setup while outperforming SSFLs and the baselines by 1. 8% and 15. 8%, respectively.
Enabling Data Diversity: Efficient Automatic Augmentation via Regularized Adversarial Training
Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks' generalization performance.
Soft-Attention Improves Skin Cancer Classification Performance
skrantidatta/Attention-based-Skin-Cancer-Classification
•
•
Soft-Attention mechanism enables a neural network toachieve this goal.
