Hey, y’all! I started writing about network architectures useful for medical image segmentation i.e. UNet and its variants. In the first article, I had covered basic UNet and 3D UNet. You can find that here. In this article, I'm going to go over Attention UNet.

Photo by JJ Ying on Unsplash

Attention UNet

Fully convolutional neural networks (FCNNs) like UNet outperform traditional approaches in medical image analysis. This is mainly attributed to the fact that (I) domain-specific image features are learned using stochastic gradient descent (SGD) optimization, (II) learned kernels are shared across all pixels and (III) image convolution operations exploit the structural information in medical images well…

Photo by Uriel SC on Unsplash

Medical image segmentation is an important area in medical image analysis and is necessary for diagnosis, monitoring, and treatment. The deep learning-based methods have achieved superior performance compared to traditional methods in medical image segmentation tasks. I'm going to go over UNet and several other architectures that are derived from UNet and are used for medical image segmentation.

Basic UNet

Any UNet has 2 parts:

  1. Contracting Path [Encoder] (left side)
  2. Expansive Path [Decoder](right side).

The encoder/contracting path follows the typical architecture of a convolutional network. It extracts feature maps from the image. It has repeated application of two 3x3 convolutions (unpadded convolutions)…

Photo by Alina Grubnyak on Unsplash

Domain adaptation is an important topic in recent studies on deep learning, that aims to recover performance degradation when applying the neural networks to new testing domains. SIFA also called Synergistic Image and Feature Adaptation is a novel unsupervised domain adaptation framework that effectively tackles the problem of domain shift.


Deep CNNs (DCNNs) face a problem of performance degradation while encountering domain shift i.e., attempting to apply the learned models on testing data (target domain) that have different distributions from the training data (source domain). …

I have been working on a Covid CT dataset from Kaggle containing 20 CT scans of patients diagnosed with COVID-19 as well as segmentation of lungs and infections made by experts. My goal was to build a segmentation model using UNet. Due to fewer images (only 20 ;P), I had to perform data augmentation after which, I had 3200 images and masks in the training dataset. On passing these to the Dataloader and training the model, it took 1.5 hrs to run a single epoch and the GPU was barely being used.

After digging a bit, I found on Kaggle

Shambhavi Malik

Biomed and DL enthusiast (IIT BHU ‘23)

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store