Tirth27/Skin-Cancer-Classification-using-Deep-Learning
Classify Skin cancer from the skin lesion images using Image classification. The dataset for the project is obtained from the Kaggle SIIM-ISIC-Melanoma-Classification competition.
Implements a CNN-based Computer-Aided Diagnosis system that classifies nine skin cancer types using ensembled patient demographic metadata alongside lesion images. Addresses severe class imbalance (1.76% malignant in 2020 dataset) by combining SIIM-ISIC data from 2018-2020 competitions, and provides a web interface accepting DICOM and JPEG formats with real-time inference to reduce diagnostic turnaround from weeks to days.
168 stars. No commits in the last 6 months.
Stars
168
Forks
54
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 16, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Tirth27/Skin-Cancer-Classification-using-Deep-Learning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Michael-OvO/Skin-Burn-Detection-Classification
Highly Accurate and Efficient Burn detection and Classification trained with Deep Learning Model
aevri/mel
Tools to help identify new and changing moles on the skin with the goal of early detection of...
ImageMarkup/isic-archive
International Skin Imaging Collaboration: Melanoma Project
samhaswon/skin_segmentation
This repository details the various methods I have attempted for skin segmentation.
lrsoenksen/SPL_UD_DL
A reported 96,480 people were diagnosed with melanoma in the United States in 2019, leading to...