# Leveraging Global Binary Masks for Structure Segmentation in Medical Images

arXiv: https://arxiv.org/abs/2205.09107 · HTML: https://mlsanity.com/paper/2205.09107/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 38 references that are in the map.
- First posted on arXiv 13 May 2022.

## Builds on (most cited first, 14 of 14)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation](https://mlsanity.com/paper/1603.05959/) (2016)
- [Visual Interpretability for Deep Learning: a Survey](https://mlsanity.com/paper/1802.00614/) (2018)
- [Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation](https://mlsanity.com/paper/1705.08302/) (2017)
- [Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge](https://mlsanity.com/paper/1902.07880/) (2019)
- [SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2108.06227/) (2021)
- [Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-supervised Learning](https://mlsanity.com/paper/2102.10680/) (2021)
- [Post-DAE: Anatomically Plausible Segmentation via Post-Processing with Denoising Autoencoders](https://mlsanity.com/paper/2006.13791/) (2020)
- [Semi-supervised Task-driven Data Augmentation for Medical Image Segmentation](https://mlsanity.com/paper/2007.05363/) (2020)
- [ConvNet-Based Localization of Anatomical Structures in 3D Medical Images](https://mlsanity.com/paper/1704.05629/) (2017)
- [Visualizing Convolutional Neural Networks to Improve Decision Support for Skin Lesion Classification](https://mlsanity.com/paper/1809.03851/) (2018)
- [How Can CNNs Use Image Position for Segmentation?](https://mlsanity.com/paper/2005.03463/) (2020)

## Built on by (most cited first, 1 of 1)

- [Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels](https://mlsanity.com/paper/2209.13476/) (2022)

## Abstract (arXiv)

Deep learning (DL) models for medical image segmentation are highly influenced by intensity variations of input images and lack generalization due to primarily utilizing pixels' intensity information for inference. Acquiring sufficient training data is another challenge limiting models' applications. We proposed to leverage the consistency of organs' anatomical shape and position information in medical images. We introduced a framework leveraging recurring anatomical patterns through global binary masks for organ segmentation. Two scenarios were studied.1) Global binary masks were the only model's (i.e. U-Net) input, forcing exclusively encoding organs' position and shape information for segmentation/localization.2) Global binary masks were incorporated as an additional channel functioning as position/shape clues to mitigate training data scarcity. Two datasets of the brain and heart CT images with their ground-truth were split into (26:10:10) and (12:3:5) for training, validation, and test respectively. Training exclusively on global binary masks led to Dice scores of 0.77(0.06) and 0.85(0.04), with the average Euclidian distance of 3.12(1.43)mm and 2.5(0.93)mm relative to the center of mass of the ground truth for the brain and heart structures respectively. The outcomes indicate that a surprising degree of position and shape information is encoded through global binary masks. Incorporating global binary masks led to significantly higher accuracy relative to the model trained on only CT images in small subsets of training data; the performance improved by 4.3-125.3% and 1.3-48.1% for 1-8 training cases of the brain and heart datasets respectively. The findings imply the advantages of utilizing global binary masks for building generalizable models and to compensate for training data scarcity.