Overview / Usage

Medical Image Processing - Pneumonia classification

Pneumonia is a prevalent respiratory infection that requires accurate and timely diagnosis for effective treatment. In our project, we utilized SYCL, a programming model based on standard C++, for the classification of pneumonia in medical image processing. SYCL served as the foundation for our pneumonia classification project, leveraging the power of heterogeneous hardware architectures, such as CPUs, GPUs, and FPGAs.With SYCL, we optimized our classification algorithms for parallel processing, enabling faster and more accurate diagnosis

This project was a part of Intel One Api challenge - 2023 hosted by Intel and Hack2skill.This project was awarded the Runner up position in the Same.

Methodology / Approach

Please ensure you have the following dependencies installed on your system:

• Intel® oneAPI Base Toolkit – it provides the environment for compiling for DPC++/ SYCL libraries

• SYCL – it provides process parallelism which makes the diagnosis efficient and effective

• oneDNN – Neural Network Classifier for pneumonia prediction

• Opencv - it is used for data preprocessing

Technologies Used

oneAPI Deep Neural Network Library (oneDNN) is an open-source cross-platform performance library of basic building blocks for deep learning applications. oneDNN is part of oneAPI. The library is optimized for Intel(R) Architecture Processors, Intel Graphics, and Arm* 64-bit Architecture (AArch64)-based processors. oneDNN has experimental support for the following architectures: NVIDIA* GPU, AMD* GPU, OpenPOWER* Power ISA (PPC64), IBMz* (s390x), and RISC-V.

oneDNN is intended for deep learning applications and framework developers interested in improving application performance on CPUs and GPUs. Deep learning practitioners should use one of the applications enabled with oneDNN.

Repository

https://github.com/vis465/oneDNN

Other links

• git (https://github.com/vis465/oneDNN)