Pneumonia Classification Model

Information shown here should be verified against the original training artifacts.

Architecture

Deep Convolutional Neural Network

  • 8 Conv2D layers
  • 4 MaxPooling2D layers
  • 4 Dropout layers
  • 11 ReLU activations
  • 4 linear/dense layers
  • 4 BatchNormalization layers

Input & Output

Input shape: Unavailable until model loads

Output shape: Unavailable until model loads

Approximately 128 x 128 pixel Chest X-Ray images, unless the loaded model reports a different input shape.

Classes

  • Pneumonia-COVID-19
  • Normal
  • Pneumonia-Bacterial
  • Pneumonia-Viral

Reported Performance

Higher than 96% accuracy in the original implementation.

Reported accuracy refers to the original model evaluation and does not guarantee identical performance on external or clinical datasets.

Research Background

This application is a continued research implementation based on prior pneumonia Chest X-Ray classification studies by Anggi Muhammad Rifai and collaborators.

Rifai, A. M., Raharjo, S., Utami, E., & Ariatmanto, D. (2024). Analysis for diagnosis of pneumonia symptoms using chest X-ray based on MobileNetV2 models with image enhancement using white balance and contrast limited adaptive histogram equalization (CLAHE). Biomedical Signal Processing and Control, 90, 105857. https://doi.org/10.1016/j.bspc.2023.105857

Rifa'i, A. M., Utami, E., & Ariatmanto, D. (2022). Analysis for Diagnosis of Pneumonia Symptoms Using Chest X-Ray Based on Resnet-50 Models With Different Epoch. 2022 6th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), 471-476. https://doi.org/10.1109/ICITISEE57756.2022.10057805