# mwasifanwar/mediscanai architecture

> Architecture diagram of the GitHub repository mwasifanwar/mediscanai, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-11-05). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/mwasifanwar/mediscanai
- Repository: https://github.com/mwasifanwar/mediscanai

## Overview

##### Project Type and Purpose
- This is a full-stack, deep-learning–driven medical image diagnosis assistant (“MediScan AI”) with both a web interface (Flask) and a CLI. It ingests multi-modal inputs (images + clinical metadata), runs them through a custom PyTorch model (multi-branch image & clinical encoders + fusion + classifier), produces explainable outputs (Grad-CAM), and can be trained and deployed in Dockerized environments.

##### File-Structure & Architectural Clues
- Top-level:
- app/ (Flask web server entry point, models, utils)
- train.py, inference.py (CLI entrypoints)
- data/ (sample-data generator)
- config.yaml (system and model parameters)
- tests/ (unit tests)
- app/models: multimodal_model.py (feature encoders + fusion + classifier) & explainable_ai.py (Grad-CAM module)
- app/utils: config management, data loading, preprocessing
- External build/deploy hints: requirements.txt, Docker, Gunicorn

##### README Insights
- Multi-branch architecture: image encoder (ResNet/DenseNet) + clinical encoder (MLP) → feature fusion → multi-head classifier
- Workflow: data ingestion (DICOM/PNG/JPEG) → preprocessing → multi-modal processing → explainability (Grad-CAM)
- Deployment: Flask REST API, optional React frontend, Docker containerization, Gunicorn WSGI

##### Diagramming Conventions
- Blue rectangles for “Compute Services” (Flask API, Model Service, Training Engine)
- Orange parallelograms for “Clients” (Browser/React, CLI)

##### Final Advice
- Be exhaustive: include all major directories/modules as components
- Multi-modal fusion and explainability path
- Keep component names matching file names (e.g., app/utils/data_loader.py → “Data Loader”)

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Client Layer
    subgraph "Client Layer"
        direction TB
        Browser["Browser UI\n(React)"]:::client
        CLI_infer["CLI Inference\ninference.py"]:::client
        CLI_train["CLI Training\ntrain.py"]:::client
    end

    %% Server Layer in Docker
    subgraph "Server Layer"
        direction TB
        Docker["Docker Container\n(port 5000)"]:::docker
        subgraph "Gunicorn WSGI + Flask API"
            direction TB
            FlaskAPI["Flask API\n(app/main.py)"]:::service
        end
        subgraph "Application Layer"
            direction TB
            ConfigManager["Config Manager\n(app/utils/config.py)"]:::service
            Preprocessor["Preprocessor & Data Loader\n(app/utils/data_loader.py)\n(app/utils/preprocess.py)"]:::service
        end
        subgraph "Model Inference Service"
            direction TB
            ImageEncoder["Image Encoder\n(ResNet/DenseNet)"]:::compute
            ClinicalEncoder["Clinical Encoder\n(MLP)"]:::compute
            Fusion["Feature Fusion\n(app/models/multimodal_model.py)"]:::compute
            Classifier["Classifier"]:::compute
            Explainability["Grad-CAM Module\n(app/models/explainable_ai.py)"]:::compute
        end
        subgraph "Storage / Artifacts"
            direction TB
            SampleData["Sample Data\n(data/)"]:::storage
            Checkpoints["Checkpoints\n(models/)"]:::storage
            ConfigFile["Configuration File\n(config.yaml)"]:::storage
        end
    end

    %% Connections - Inference
    Browser -->|HTTP JSON| FlaskAPI
    CLI_infer -->|CLI call| FlaskAPI
    FlaskAPI -->|load params| ConfigManager
    FlaskAPI -->|raw data| Preprocessor
    ConfigManager -->|config params| Preprocessor
    Preprocessor -->|image tensor| ImageEncoder
    Preprocessor -->|metadata| ClinicalEncoder
    ImageEncoder -->|features| Fusion
    ClinicalEncoder -->|features| Fusion
    Fusion <-->|"feature concat"| Classifier
    Classifier -->|predictions| Explainability
    Explainability -->|Grad-CAM maps| FlaskAPI
    FlaskAPI -->|HTTP JSON + images| Browser
    FlaskAPI -->|CLI output| CLI_infer

    %% Connections - Training
    CLI_train -->|start training| Preprocessor
    Preprocessor -->|tensors| Fusion
    Fusion -->|loss & grads| Checkpoints
    ConfigManager -->|training params| CLI_train

    %% Storage interactions
    SampleData -->|reads sample| Preprocessor
    Checkpoints -->|load weights| Explainability
    ConfigFile -->|loaded by| ConfigManager

    %% Click Events
    click CLI_infer "https://github.com/mwasifanwar/mediscanai/blob/main/inference.py"
    click CLI_train "https://github.com/mwasifanwar/mediscanai/blob/main/train.py"
    click FlaskAPI "https://github.com/mwasifanwar/mediscanai/blob/main/app/main.py"
    click Preprocessor "https://github.com/mwasifanwar/mediscanai/blob/main/app/utils/data_loader.py"
    click Preprocessor "https://github.com/mwasifanwar/mediscanai/blob/main/app/utils/preprocess.py"
    click ConfigManager "https://github.com/mwasifanwar/mediscanai/blob/main/app/utils/config.py"
    click ConfigFile "https://github.com/mwasifanwar/mediscanai/blob/main/config.yaml"
    click Fusion "https://github.com/mwasifanwar/mediscanai/blob/main/app/models/multimodal_model.py"
    click Explainability "https://github.com/mwasifanwar/mediscanai/blob/main/app/models/explainable_ai.py"
    click SampleData "https://github.com/mwasifanwar/mediscanai/blob/main/data/sample_data.py"

    %% Styles
    classDef client fill:#ffa500,stroke:#333,stroke-width:1px
    classDef service fill:#6495ED,stroke:#333,stroke-width:1px
    classDef compute fill:#ADD8E6,stroke:#333,stroke-width:1px
    classDef storage fill:#8FBC8F,stroke:#333,stroke-width:1px
    classDef docker fill:#f0e68c,stroke:#333,stroke-width:1px
```
