# thanushamh/medical-image-classification-multicancer architecture

> Architecture diagram of the GitHub repository thanushamh/medical-image-classification-multicancer, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-05). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/thanushamh/medical-image-classification-multicancer
- Repository: https://github.com/thanushamh/medical-image-classification-multicancer

## Overview

This notebook implements a deep-learning workflow for classifying medical images into eight cancer types. The documented stages include preprocessing and normalization, augmentation, training a CNN from scratch, and transfer learning with ResNet50 followed by fine-tuning. The fine-tuned model is evaluated with accuracy, precision, recall, F1-score, and a confusion matrix. The dataset is external and is not included in the repository. No notebook source excerpts were available, so the relationships shown here are based only on the README.

Main entry points: [`Multi_Cancer_Medical_Image_Classification.ipynb`](https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb) (Preprocessing)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_preparation["Image Preparation"]
  node_preprocessing["Preprocessing"]
  node_augmentation["Data Augmentation"]
end

subgraph group_modeling["Model Training"]
  node_cnn["Scratch CNN"]
  node_resnet["ResNet50 Transfer"]
  node_finetuning["Fine-Tuning"]
end

subgraph group_evaluation["Evaluation"]
  node_evaluation["Model Evaluation"]
  node_metrics["Classification Metrics"]
end

node_analyst(("Analyst"))
node_dataset[("Kaggle Image Dataset")]

node_analyst -->|"classifies images"| node_preprocessing
node_dataset -->|"provides images"| node_preprocessing
node_preprocessing -->|"prepares images"| node_augmentation
node_augmentation -->|"augments training"| node_cnn
node_augmentation -->|"augments training"| node_resnet
node_preprocessing -->|"normalizes inputs"| node_cnn
node_preprocessing -->|"normalizes inputs"| node_resnet
node_resnet -->|"fine-tunes layers"| node_finetuning
node_finetuning -->|"evaluates model"| node_evaluation
node_evaluation -->|"reports scores"| node_metrics

click node_preprocessing "https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb"
click node_augmentation "https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb"
click node_cnn "https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb"
click node_resnet "https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb"
click node_finetuning "https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb"
click node_evaluation "https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb"
click node_metrics "https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_preprocessing,node_augmentation toneBlue
class node_cnn,node_resnet,node_finetuning,node_dataset toneAmber
class node_evaluation,node_metrics toneMint
class node_analyst toneIndigo
```

## Components

### Image Preparation

- [Preprocessing](https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb): `Multi_Cancer_Medical_Image_Classification.ipynb`
- [Data Augmentation](https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb): `Multi_Cancer_Medical_Image_Classification.ipynb`

### Model Training

- [Scratch CNN](https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb): `Multi_Cancer_Medical_Image_Classification.ipynb`
- [ResNet50 Transfer](https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb): `Multi_Cancer_Medical_Image_Classification.ipynb`
- [Fine-Tuning](https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb): `Multi_Cancer_Medical_Image_Classification.ipynb`

### Evaluation

- [Model Evaluation](https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb): `Multi_Cancer_Medical_Image_Classification.ipynb`
- [Classification Metrics](https://github.com/thanushamh/medical-image-classification-multicancer/blob/main/Multi_Cancer_Medical_Image_Classification.ipynb): `Multi_Cancer_Medical_Image_Classification.ipynb`

### Other components

- **Analyst**
- **Kaggle Image Dataset**

## Connections

- Analyst → Preprocessing: classifies images (evidence: `README`)
- Kaggle Image Dataset → Preprocessing: provides images (evidence: `README`)
- Preprocessing → Data Augmentation: prepares images (evidence: `README`)
- Data Augmentation → Scratch CNN: augments training (evidence: `README`)
- Data Augmentation → ResNet50 Transfer: augments training (evidence: `README`)
- Preprocessing → Scratch CNN: normalizes inputs (evidence: `README`)
- Preprocessing → ResNet50 Transfer: normalizes inputs (evidence: `README`)
- ResNet50 Transfer → Fine-Tuning: fine-tunes layers (evidence: `README`)
- Fine-Tuning → Model Evaluation: evaluates model (evidence: `README`)
- Model Evaluation → Classification Metrics: reports scores (evidence: `README`)
