# Implementation of a Modified U-Net for Medical Image Segmentation on Edge Devices

arXiv: https://arxiv.org/abs/2206.02358 · HTML: https://mlsanity.com/paper/2206.02358/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 6 Jun 2022.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [U-Net and its variants for medical image segmentation: theory and applications](https://mlsanity.com/paper/2011.01118/) (2020)
- [Recurrent U-Net for Resource-Constrained Segmentation](https://mlsanity.com/paper/1906.04913/) (2019)
- [Automatic segmentation of MR brain images with a convolutional neural network](https://mlsanity.com/paper/1704.03295/) (2017)
- [Generative Adversarial Network for Medical Images (MI-GAN)](https://mlsanity.com/paper/1810.00551/) (2018)
- [R2U++: A Multiscale Recurrent Residual U-Net with Dense Skip Connections for Medical Image Segmentation](https://mlsanity.com/paper/2206.01793/) (2022)
- [Segmentation of Lungs in Chest X-Ray Image Using Generative Adversarial Networks](https://mlsanity.com/paper/2009.05752/) (2020)

## Built on by (most cited first, 6 of 6)

- [Using U-Net Network for Efficient Brain Tumor Segmentation in MRI Images](https://mlsanity.com/paper/2211.01885/) (2022)
- [Texture-Semantic Collaboration Network for ORSI Salient Object Detection](https://mlsanity.com/paper/2312.03548/) (2023)
- [Exploring Generalizable Distillation for Efficient Medical Image Segmentation](https://mlsanity.com/paper/2207.12995/) (2022)
- [A framework for dynamically training and adapting deep reinforcement learning models to different, low-compute, and continuously changing radiology deployment environments](https://mlsanity.com/paper/2306.05310/) (2023)
- [A Novel Framework using Intuitionistic Fuzzy Logic with U-Net and U-Net++ Architecture: A case Study of MRI Bain Image Segmentation](https://mlsanity.com/paper/2603.18042/) (2026)
- [How Far Can INRs Go? Cross-Domain Parameter-efficient INR-Based Semantic Segmentation for Brain MRI](https://mlsanity.com/paper/2609.31573/) (2026)

## Abstract (arXiv)

Deep learning techniques, particularly convolutional neural networks, have shown great potential in computer vision and medical imaging applications. However, deep learning models are computationally demanding as they require enormous computational power and specialized processing hardware for model training. To make these models portable and compatible for prototyping, their implementation on low-power devices is imperative. In this work, we present the implementation of Modified U-Net on Intel Movidius Neural Compute Stick 2 (NCS-2) for the segmentation of medical images. We selected U-Net because, in medical image segmentation, U-Net is a prominent model that provides improved performance for medical image segmentation even if the dataset size is small. The modified U-Net model is evaluated for performance in terms of dice score. Experiments are reported for segmentation task on three medical imaging datasets: BraTs dataset of brain MRI, heart MRI dataset, and Ziehl-Neelsen sputum smear microscopy image (ZNSDB) dataset. For the proposed model, we reduced the number of parameters from 30 million in the U-Net model to 0.49 million in the proposed architecture. Experimental results show that the modified U-Net provides comparable performance while requiring significantly lower resources and provides inference on the NCS-2. The maximum dice scores recorded are 0.96 for the BraTs dataset, 0.94 for the heart MRI dataset, and 0.74 for the ZNSDB dataset.