Medical Image Classification using Tensorflow

제공자:
Coursera Project Network
학습자는 이 안내 프로젝트에서 다음을 수행하게 됩니다.

Import and compile a Residual Convolutional Network (Resnet).

Train a Resnet to identify pleural effusion in chest x-ray (CXR) images.

Use the fully trained Resnet for inference functions identifying effusion.

Clock2 hours
Advanced고등
Cloud다운로드 필요 없음
Video분할 화면 동영상
Comment Dots영어
Laptop데스크톱 전용

The medical imaging industry is set to see 9 and a half billion dollars in growth in just a few years, mostly due to advances in AI imaging technologies. AI integration with medical imaging is expected to gain traction as it enables increased productivity, improved accuracy, and reduced errors in the diagnosis performed by technicians and radiologists. The use of AI will also automate the labor-intensive manual segmentation and enable technicians to identify abnormalities, in turn, accelerating the treatment process. Furthermore, AI platforms are also being developed for hospitals and health systems to help clinicians in making quick decisions and improving patient outcomes. Ultimately, this field of research will benefit from more minds refining the technology. This project will get you started in using Python and Tensorflow/Keras for advanced medical imaging. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

개발할 기술

  • tensorflow in production
  • image classification
  • health informatics analysis

단계별 학습

작업 영역이 있는 분할 화면으로 재생되는 동영상에서 강사는 다음을 단계별로 안내합니다.

  1. Preprocess medical imaging data

  2. Compile a neural network model -Part 1

  3. Compile a neural network model -Part 2

  4. Build and Train a Resnet Model to recognize lung effusion

  5. Making Predictions in Inference

안내형 프로젝트 진행 방식

작업 영역은 브라우저에 바로 로드되는 클라우드 데스크톱으로, 다운로드할 필요가 없습니다.

분할 화면 동영상에서 강사가 프로젝트를 단계별로 안내해 줍니다.

자주 묻는 질문

자주 묻는 질문

궁금한 점이 더 있으신가요? 학습자 도움말 센터를 방문해 보세요.