Beta

nih-chestxray14-swin-clinical-report – AI Model by projectthinkings123 | AlphaNeural AI

You can deploy this model and start earning money today!

projectthinkings123/
nih-chestxray14-swin-clinical-report

Name: nih-chestxray14-swin-clinical-report
Availability: InStock

Views

No views yet

NIH ChestX-ray14 Swin Transformer — Clinical Report System

A medical AI project that uses a Swin Transformer to perform multi-label chest X-ray disease classification on the NIH ChestX-ray14 dataset.

The current repository contains the trained image-diagnosis model and the inference pipeline. The planned complete system will additionally accept clinical information and use an LLM/reasoning layer to generate a doctor-friendly clinical report.

Project Architecture

text

                         Doctor / User
                              |
                 +------------+------------+
                 |                         |
            Chest X-ray                Clinical Data
          PNG / JPG / DICOM          Text / PDF / Typed
                 |                         |
                 v                         v
       Swin Transformer              Clinical Data
       Image Diagnosis                Extraction
                 |                         |
                 |                         |
                 +-----------+-------------+
                             |
                             v
                    Fusion & Reasoning
                             |
                             v
                    LLM / Report Layer
                             |
              +--------------+--------------+
              |              |              |
              v              v              v
       Predicted Diseases  Confidence    Clinical
                           Scores         Reasoning
                             |
                             v
                    Doctor-friendly Report

Current status: The Swin Transformer image branch is trained and evaluated. The clinical-data and LLM report-generation branch is the next development stage.

Image Diagnosis Model

Model

Architecture: Swin Tiny Patch4 Window7 224
timm model: swin_tiny_patch4_window7_224
Framework: PyTorch
Pretraining: ImageNet pretrained weights were used during training
Input image size: 224 × 224
Number of classes: 15
Task: Multi-label classification
Output activation: Sigmoid
Loss: BCEWithLogitsLoss

During inference, the architecture is recreated without downloading pretrained weights and the trained best_model.pth checkpoint is loaded.

Dataset

The image model was trained on NIH ChestX-ray14.

The model predicts the following 15 classes:

text

Atelectasis
Cardiomegaly
Consolidation
Edema
Effusion
Emphysema
Fibrosis
Hernia
Infiltration
Mass
No Finding
Nodule
Pleural_Thickening
Pneumonia
Pneumothorax

The dataset itself is not included in this repository.

Model Performance

The trained model achieved:

Macro AUROC: 0.8386

This value was obtained from the test-set evaluation performed in the project Colab notebook.

Repository Structure

text

nih-chestxray14-swin-clinical-report/
│
├── best_model.pth
├── config.json
├── labels.json
├── model.py
├── inference.py
├── swin_chestxray14_training.ipynb
├── requirements.txt
└── README.md

File descriptions

File	Purpose
`best_model.pth`	Trained Swin Transformer weights
`model.py`	Recreates the Swin-Tiny architecture and loads the trained checkpoint
`inference.py`	Runs X-ray inference and returns disease probabilities/predictions
`labels.json`	Maps the 15 model outputs to disease names
`config.json`	Model and training configuration
`swin_chestxray14_training.ipynb`	Colab training/evaluation notebook
`requirements.txt`	Python dependencies
`README.md`	Project documentation

Installation

Install the required Python packages:

pip install -r requirements.txt

The main dependencies are:

text

torch
torchvision
timm
Pillow
numpy

Running Inference

Place a chest X-ray image in the working directory and run:

python inference.py path/to/xray.png

Or:

python inference.py path/to/xray.jpg

The default classification threshold is:

0.5

You can specify another threshold:

python inference.py path/to/xray.png --threshold 0.5

The model outputs:

Predicted disease labels
Probability for each of the 15 classes

Example output format:

text

Predicted Labels:
- Infiltration

Probabilities:
Atelectasis: 0.4172
Cardiomegaly: 0.0345
Consolidation: 0.0173
...
Infiltration: 0.1427
...

How Inference Works

text

Input Chest X-ray
       |
       v
Resize to 224 × 224
       |
       v
Image normalization
       |
       v
Swin Tiny Transformer
       |
       v
15 logits
       |
       v
Sigmoid
       |
       v
15 disease probabilities
       |
       v
Threshold = 0.5
       |
       v
Predicted labels

Because this is a multi-label classification problem, multiple diseases can be predicted for a single X-ray.

Clinical Data Integration — Planned System

The final project is intended to extend the image model with clinical information.

The planned workflow is:

text

Chest X-ray
     |
     v
Swin Transformer
     |
     v
Disease Predictions + Confidence Scores
                         \
                          \
                           +--> Fusion & Reasoning --> LLM
                          /
Clinical Data -----------/
     |
     v
Age / Symptoms / Vitals / Laboratory Information / Other

The clinical branch is intended to provide information such as:

Age
Symptoms
Vital signs
Laboratory results
Relevant clinical history
Other information supplied by the user/doctor

The LLM/report layer will use the model's predicted findings together with the available clinical information to produce a structured, doctor-friendly report.

Important: The clinical-data/LLM component is a planned extension and is not represented as being part of the current trained Swin model.

Important Notes

Model output is not a medical diagnosis

This project is a research/educational prototype. The model's predictions and generated reports should not be treated as a definitive medical diagnosis or as a replacement for a qualified medical professional.

NIH ChestX-ray14

The dataset is not distributed with this repository. Users must obtain and use the dataset according to its applicable terms and permissions.

Checkpoint

best_model.pth contains the trained model parameters. The model architecture is reconstructed by model.py before the checkpoint is loaded.

Development Roadmap

Completed

NIH ChestX-ray14 dataset preparation
Swin Tiny Transformer model
ImageNet-pretrained initialization during training
15-class multi-label classification
Model training
Checkpoint saving
Test-set evaluation
Macro AUROC evaluation
Inference pipeline
Hugging Face model repository

Clinical-data input pipeline
Clinical information extraction
Image + clinical-data fusion
LLM/reasoning layer
Structured clinical report generation
Explainability/visualization such as Grad-CAM
End-to-end application interface

Project Goal

The goal is to build a multimodal clinical-assistance prototype that combines:

text

Medical Image
      +
Clinical Information
      +
AI Reasoning
      |
      v
Structured, doctor-friendly report

The Swin Transformer serves as the image-diagnosis component, while the planned clinical and LLM components provide additional contextual reasoning and report generation.

projectthinkings123/nih-chestxray14-swin-clinical-report

NIH ChestX-ray14 Swin Transformer — Clinical Report System

Project Architecture

Image Diagnosis Model

Model

Dataset

Model Performance

Repository Structure

File descriptions

Installation

Running Inference

How Inference Works

Clinical Data Integration — Planned System

Important Notes

Model output is not a medical diagnosis

NIH ChestX-ray14

Checkpoint

Development Roadmap

Completed

Next

Project Goal

projectthinkings123/
nih-chestxray14-swin-clinical-report