SkinAI Classifier | Advanced Skin Cancer Detection with Deep Learning

Project Overview

Advancing medical diagnosis through innovative AI technology and rigorous scientific research

Purpose

Design a deep learning model to classify various types of skin lesions, supporting dermatologists with AI-powered diagnostic assistance for improved accuracy and accessibility.

Impact: Enhanced diagnostic precision

Motivation

80,000 annual skin cancer cases in Canada

99% five-year survival rate with early detection

Only ~60% accuracy in visual examination

Limited dermatologist accessibility

Challenge: Bridging the diagnostic gap

Vision

A foundational step towards deployable applications that integrate seamlessly into clinical workflows, enhancing diagnostic efficiency and supporting healthcare professionals.

Future Applications:

• Clinical decision support systems
• Mobile diagnostic apps
• Telemedicine integration

Goal: Democratizing expert diagnosis

Project Impact

81.01%

Model Accuracy

10,015

Training Images

7

Lesion Types

ResNet-18

Architecture

Meet the Team

The minds behind SkinAI Classifier

Click on any team member to view their LinkedIn profile

Final Presentation

Watch our comprehensive presentation showcasing the development process, challenges, and achievements of the SkinAI Classifier

Technical Deep Dive

ResNet-18 Architecture

Input Layer

→

Conv Blocks

→

Skip Connections

→

FC Layer (7 outputs)

Pretrained ResNet-18 with reconfigured final fully connected layer for 7-class skin lesion classification

Classification Pipeline

📷

Input Images

Dermoscopic images

⚙️

Preprocessing

224x224 resize, normalization

🔄

Data Augmentation

Address class imbalance

🧠

ResNet-18 Model

Deep learning classification

📊

Prediction

7-class output

HAM10000 Dataset

Total Images: 10,015

Seven Diagnostic Categories:

• Melanocytic nevi (nv)
• Melanoma (mel)
• Benign keratosis-like lesions (bkl)
• Basal cell carcinoma (bcc)
• Actinic keratoses (akiec)
• Vascular lesions (vasc)
• Dermatofibroma (df)

Data Processing

Data Cleaning:

• Removed corrupt/duplicate images
• Handled null values
• Resized to 224x224 pixels
• Applied normalization

Training Configuration:

• Learning Rate: 0.001
• Batch Size: 32
• Epochs: 10
• Optimizer: Adam
• Loss: CrossEntropyLoss

Challenges Addressed:

• Class imbalance via augmentation
• Computational optimization
• Training time efficiency

Live Demo

Experience our skin cancer classification model in action. Upload an image and get real-time AI-powered diagnosis with confidence scores.

🧬

Live AI Classifier

Upload an image to get real-time predictions

Open in New Tab

Loading interactive demo...

📱 Upload Images

🧠 AI Analysis

📊 Instant Results

Model Performance

✓

84.9%

Training Accuracy

📊

81.01%

Validation Accuracy

⚡

0.45

Final Loss

🎯

7

Classification Classes

Performance Analysis

Model Strengths

✓ Strong performance on melanocytic nevi and melanoma
✓ Effective transfer learning from ImageNet pretrained weights
✓ Robust feature extraction with ResNet-18 architecture
✓ Efficient training with data augmentation

Areas for Improvement

→ Class imbalance in rare lesion types (DF, VASC, AKIEC)
→ Enhanced data augmentation for minority classes
→ Ensemble methods and deeper architectures
→ Clinical validation and deployment considerations

Reports

Research Impact

Advancing Medical AI

This project represents a significant step forward in applying deep learning to medical diagnosis, demonstrating the potential for AI to support healthcare professionals in critical decision-making processes. Our work contributes to the growing field of medical AI and showcases the practical application of convolutional neural networks in real-world healthcare scenarios.