SkillAgentSearch skills...

Isic2018

Results of Task 3 ISIC 2018 Challenge to detect Melanoma

Install / Use

/learn @naneja/Isic2018
About this skill

Quality Score

0/100

Supported Platforms

Universal

README

ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection

This repository presents results of our work to detect Melanoma by Skin Lesion Analysis.

About ISIC

The International Skin Imaging Collaboration (ISIC) is an international effort to improve melanoma diagnosis, sponsored by the International Society for Digital Imaging of the Skin (ISDIS). The ISIC Archive contains the largest publicly available collection of quality controlled dermoscopic images of skin lesions.

The goal of this challenge is to help participants develop image analysis tools to enable the automated diagnosis of melanoma from dermoscopic images.

This challenge is broken into three separate tasks: Task 1: Lesion Segmentation
Task 2: Lesion Attribute Detection Task 3: Disease Classification

Ours results are for Task 3: Disease Classification

Possible disease categories are:

| Sr.No. | Disease | |:-------------:|:-------------:| | 1 | Melanoma | | 2 | Melanocytic nevus | | 3 | Basal cell carcinoma | | 4 | Actinic keratosis / Bowen’s disease (intraepithelial carcinoma) | | 5 | Benign keratosis (solar lentigo / seborrheic keratosis / lichen planus-like keratosis) | | 6 | Dermatofibroma | | 7 | Vascular lesion |

Results

Following Graphs show Model Accuracy for Training and Testing Phase; Model Loss for Training and Testing Phase; and Computation Time for Training the model and Training plus Tresting the model.

model

Model Accuracy, Model Loss, and Training Time is available at model

Class wise probabilities for each valid image is available at Valid Results

Class wise probabilities for each test image is available at Test Results

Our position at ISIC Live Challenge Leaderboards at the time of uploading the results for Task 3 is 23 and we are working to improve the results.

Sanity Check

Following are five random images that were picked and detected one of the disease categories by our model

Pred1 Pred2 Pred3 Pred4 Pred5

Dataset Size

Below is the Training Dataset consisting of 10,015 images for different disease categories

| Sr.No. | Disease | Training Files | |:-------------:|:-------------:|:-------------:| | 1 | Melanoma | 1113 | | 2 | Melanocytic nevus | 6705 | | 3 | Basal cell carcinoma | 514 | | 4 | Actinic keratosis / Bowen’s disease (intraepithelial carcinoma) | 327 | | 5 | Benign keratosis (solar lentigo / seborrheic keratosis / lichen planus-like keratosis) | 1099 | | 6 | Dermatofibroma | 115 | | 7 | Vascular lesion | 142 |

Project Members

Dr. Nagender Aneja, http://ResearchID.co/naneja

Dr. Sandhya Aneja, http://expert.ubd.edu.bn/sandhya.aneja

Feedback

Please submit your feedback to (nanejaATgmail or nanejaATieee.org).

Related Skills

View on GitHub
GitHub Stars10
CategoryDevelopment
Updated2mo ago
Forks2

Languages

Jupyter Notebook

Security Score

75/100

Audited on Feb 9, 2026

No findings