Variable Generalization Performance of a Pre Trained Model to Diagnose Pneumonia from Chest Xrays Images

This study proposes a convolutional neural network model trained from scratch to classify and detect the presence of pneumonia from a collection of chest X-ray image samples. Unlike other methods that rely solely on transfer learning approaches or traditional handcrafted techniques to achieve a rema

Project Title

Variable Generalization Performance of a Pre Trained Model to Diagnose Pneumonia from Chest Xrays Images

Project Area of Specialization

Artificial Intelligence

Project Summary

This study proposes a convolutional neural network model trained from scratch to classify and detect the presence of pneumonia from a collection of chest X-ray image samples. Unlike other methods that rely solely on transfer learning approaches or traditional handcrafted techniques to achieve a remarkable classification performance, we constructed a convolutional neural network model from scratch to extract features from a given chest X-ray image and classify it to determine if a person is infected with pneumonia. This model could help mitigate the reliability and interpretability challenges often faced when dealing with medical imagery. Unlike other deep learning classification tasks with sufficient image repository, it is difficult to obtain a large amount of pneumonia dataset for this classification task; therefore, we deployed several data augmentation algorithms to improve the validation and classification accuracy of the CNN model and achieved remarkable validation accuracy.

Project Objectives

The risk of pneumonia is immense for many, especially in developing nations where billions face energy poverty and rely on polluting forms of energy. The WHO estimates that over 4 million premature deaths occur annually from household air pollution-related diseases including pneumonia. Over 150 million people get infected with pneumonia on an annual basis especially children under 5?years old. In such regions, the problem can be further aggravated due to the dearth of medical resources and personnel. For example, in Africa’s 57 nations, a gap of 2.3 million doctors and nurses exists. For these populations, accurate and fast diagnosis means everything. It can guarantee timely access to treatment and save much needed time and money for those already experiencing poverty.

Project Implementation Method

We present the detailed experiments and evaluation steps undertaken to test the effectiveness of the proposed model. Our experiments were based on a chest X-ray image dataset. We deployed Keras open-source deep learning framework with TensorFlow backend to build and train the convolutional neural network model. All experiments were run on a Dell T7400 Intel Xeon E5400  with an Nvidia GeForce GTX 660 GPU card of 2?GB

But Required Dell Optiplex 7050 MT Core i7 7th Generation Desktop Computer 32GB DDR4 1TB HDD 

GPU: NVIDIA GTX 1060 8GB

Dataset:

       The original dataset consists of three main folders (i.e., training, testing, and validation folders) and two subfolders containing pneumonia (P) and normal (N) chest X-ray images, respectively. A total of 5,219 X-ray images of anterior-posterior chests were carefully chosen from retrospective pediatric patients between 1 and 5?years old. The entire chest X-ray imaging was conducted as part of patients’ routine medical care. We rearranged the entire data into training and validation set only. A total of 3,722 images were allocated to the training set and 2,134 images were assigned to the validation set to improve validation accuracy.

Preprocessing and Augmentation:

        We employed several data augmentation methods to artificially increase the size and quality of the dataset. This process helps in solving overfitting problems and enhances the model’s generalization ability during training. The settings deployed in image augmentation 

Model:

         The overall architecture of the proposed CNN model which consists of two major parts: the feature extractors and a classifier. Each layer in the feature extraction layer takes its immediate preceding layer's output as input, and its output is passed as an input to the succeeding layers. The proposed architecture consists of the convolution, max-pooling, and classification layers combined together.

Input (200 x 200, 3)

Block 1 (200 x 200, 64) (200 x 200, 64)  Max Pool (100 x 100, 64)

Block 2 (100 x 100, 128) (100 x 100, 128) Max Pool (50 x 50, 128)

Block 3 (50 x 50, 256) (50 x 50, 256) (50 x 50, 256) Max Pool (25 x 25, 256)

Block 4 (25 x 25, 512) (25 x 25, 512) (25 x 25, 512)  Max Pool (12 x 12, 512) 

Block 5 (12 x 12, 512) (12 x 12, 512) (12 x 12, 512) Max Pool (6 x 6, 512) 

The classifier is placed at the far end of the proposed convolutional neural network (CNN) model. It is simply an artificial neural network (ANN) often referred to as a dense layer. This classifier requires individual features (vectors) to perform computations like any other classifier. Therefore, the output of the feature extractor (CNN part) is converted into feature vector for the classifiers. The classification layer contains a flattened layer, a dropout of size 0.5, two dense layers of size 512 a Softmax between the two dense layers and a sigmoid activation function that performs the classification tasks.

Benefits of the Project

We developed a model to detect and classify pneumonia from chest X-ray images taken from frontal views at high validation accuracy. The algorithm begins by transforming chest X-ray images into sizes smaller than the original. The next step involves the identification and classification of images by the convolutional neural network framework, which extracts features from the images and classifies them. Due to the effectiveness of the trained CNN model for identifying pneumonia from chest X-ray images, the validation accuracy of our model was significantly higher when compared with other approaches. To affirm the performance of the model, we repeated the training process of the model several times, each time obtaining the same results. To validate the performance of the trained model on different chest X-ray image sizes, we varied the sizes of the training and validation dataset and still obtained relatively similar results. This will go a long way in improving the health of at-risk children in energy-poor environments. The study was limited by the depth of data. With increased access to data and training of the model with radiological data from patients and nonpatients in different parts of the world, significant improvements can be made.

Technical Details of Final Deliverable

We have demonstrated how to classify positive and negative pneumonia data from a collection of X-ray images. We build our model from scratch, which separates it from other methods that rely heavily on transfer learning approach. In the future, this work will be extended to detect and classify X-ray images consisting of lung cancer and pneumonia. Distinguishing X-ray images that contain lung cancer and pneumonia has been a big issue in recent times, and our next approach will tackle this problem.

Final Deliverable of the Project

Software System

Core Industry

Health

Other Industries

Medical

Core Technology

Artificial Intelligence(AI)

Other Technologies

Others

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com