UNet (and its variants) for Biomedical Image Segmentation
Sourodip Ghosh (~sourodip) |
Different traditional methods in Deep Learning are used to detect the particular type of class/category and therefore, produce an output label. However semantic segmentations are often cumbersome and time-consuming. First introduced by O Ronneberger in 2015 (UNet paper), UNet is since then, used as a primary tool in the field of biomedical image segmentation. Since 2015, there has been a lot of gradients of UNet, fine-tuned on the particular base architecture, like UNet++, Nas-Unet, Vanilla U-Net, etc.
The aim is to discuss these sophisticated approaches for solving the segmentation problems of these target classes. The layout is structured as follows:
- Introduction: A little bit of description about the origin of architectures to analyze biomedical imaging (5 min)
- Difference between U-Net and a little bit of tweak in the algorithms (4 min)
- Detection and segmentation: A step further after detection (4 min)
- Use case of UNet vs variations: Using a particular dataset [Brain MRI] to explain the functionality (4 min)
- Results: Evaluation parameters (3 min)
- Model diversity and reliability (5 min)
- Questions! (5 min)
Link to presentation: https://1drv.ms/p/s!AmZTbGBdPZo9jieoZjz-g9W2TORf?e=hjDTPQ
A little bit of basics in Machine Learning and Deep Learning is helpful. The rest would be covered in the course itself.
I am a senior year student, pursuing a Bachelor's in Technology, major in Electronics. I have been using Deep Learning for medical imaging for a while now. I have been publishing papers in the Biomedical image processing domain, using segmentation and analysis.
OCTx: Ensembled Deep Learning Model to Detect Retinal Disorders [IEEE 33rd International Symposium on Computer Based Medical Systems (CBMS)] [Accepted]
[Performance Comparison of CNN and ResNet50 for detection and classification of fruits: FruitX] [IEEE International Conference for Innovation in Technology 2020, Bangalore, India (INOCON 2020) [Accepted]
A novel approach to detect and classify fruits using ShuffleNet V2 [2nd IEEE Conference on Applied Signal Processing , ASPCON 2020] [Accepted]