Pneumonia Detection in Chest X-Rays using Transfer Learning and TPUs

Abstract

Pneumonia is a severe respiratory disease with potentially life-threatening consequences if not promptly diagnosed and treated. Chest X-rays are commonly employed for pneumonia detection, but interpreting the images can pose challenges. This study explores the efficacy of four popular transfer learning models, namely VGG16, ResNet, InceptionNet, and DenseNet, alongside a custom CNN model for this task. The model performance is evaluated using Mean Absolute Error (MAE) as the performance metric. The findings reveal that VGG16 outperforms the other transfer learning models, achieving the lowest MAE (66.19). To optimize the model training process, a distributed training strategy utilizing TensorFlow's TPU (Tensor Processing Unit) strategy is implemented. The custom CNN model is parallelized using TPU's multiple instances available over the cloud, enabling efficient computation parallelization and significantly reducing model training times. The experimental results demonstrate a remarkable decrease of 68.36% and 54.74% in model training times for the CNN model when trained using TPU compared to training on a CPU and GPU, respectively.

Efficient Deep Learning Approach for the Classification of Pneumonia in Infants from Chest X-Ray Images

“…While this study demonstrated machine learning's potential in medical imaging, its limitations lie in the necessity for extensive data augmentation to balance the dataset and optimize feature extraction, which can be resource-intensive and may not scale well in different clinical environments. The authors [24] delved into the utility of several advanced image recognition models to improve pneumonia detection from chest X-rays. This investigation deployed models like VGG16, ResNet, InceptionNet, and DenseNet, as well as a tailored CNN model.…”

Advancements in Dental Filling Detection Technologies and Strategies for Comprehensive Oral Health Care

“…Image segmentation of dental works is essential for proper patient treatment since there are various objects a medical practitioner would observe through this process, which would facilitate the former to successfully deal with the patient's issue. This study deploys the periapical view of the tooth from the detailed X-rays [5,6]. The aforementioned objects have been generalized into three main classes, namely Endodontic, Restoration, and Implant.…”

GPU Shader Analysis and Power Optimization Model

“…An algorithm based on Dynamic Voltage Frequency Scaling (DVFS) [3,4], is implemented to explore the characteristics confined to frame controlled rendering GPUs and reach desirable power savings. The workload of each frame is analyzed in the 3D scene by considering factors such as geometry [5,6], textures, pixels [7], and rasterization. This analysis helps in understanding computational intensity of each frame.…”