Inception block based Residual Auto Encoder For Lung Segmentation
| Autor: | R Adarsh, S. Deivalakshmi, R. Pandeeswari, Gadipudi Amarnageswarao |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
business.industry
Computer science Deep learning Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Image segmentation respiratory system Residual medicine.disease Autoencoder respiratory tract diseases 030218 nuclear medicine & medical imaging 03 medical and health sciences ComputingMethodologies_PATTERNRECOGNITION 0302 clinical medicine medicine Segmentation Artificial intelligence business Lung cancer 030217 neurology & neurosurgery Block (data storage) |
| Zdroj: | 2020 4th International Conference on Computer, Communication and Signal Processing (ICCCSP). |
| Popis: | Lung segmentation from a CT image is the integral process required to diagnose lung related diseases. To reduce the difficulties in manual lung segmentation and to support pulmonologists in diagnosing diseases like lung cancer, we find a necessity of efficient segmentation technique. One efficient technique of use is training a deep learning model which performs segmentation. In this work, an Inception block based residual path auto encoder is recommended and implemented to successfully segment lung from CT images. This model is trained and evaluated using Kaggle Lung dataset. It is shown to have better performance metrics compared to the state-of-the-art alternatives. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|