# Multi-class probabilistic atlas-based whole heart segmentation method in cardiac CT and MRI

arXiv: https://arxiv.org/abs/2102.01822 · HTML: https://mlsanity.com/paper/2102.01822/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 68 references that are in the map.
- First posted on arXiv 3 Feb 2021.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation](https://mlsanity.com/paper/1908.10454/) (2019)
- [Semi-Supervised Learning with Ladder Networks](https://mlsanity.com/paper/1507.02672/) (2015)
- [Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge](https://mlsanity.com/paper/1902.07880/) (2019)
- [Dual-Teacher: Integrating Intra-domain and Inter-domain Teachers for Annotation-efficient Cardiac Segmentation](https://mlsanity.com/paper/2007.06279/) (2020)
- [DSNet: Automatic Dermoscopic Skin Lesion Segmentation](https://mlsanity.com/paper/1907.04305/) (2019)
- [MvMM-RegNet: A new image registration framework based on multivariate mixture model and neural network estimation](https://mlsanity.com/paper/2006.15573/) (2020)
- [CFUN: Combining Faster R-CNN and U-net Network for Efficient Whole Heart Segmentation](https://mlsanity.com/paper/1812.04914/) (2018)
- [Dilated Convolutional Neural Networks for Cardiovascular MR Segmentation in Congenital Heart Disease](https://mlsanity.com/paper/1704.03669/) (2017)
- [Multi-Planar Deep Segmentation Networks for Cardiac Substructures from MRI and CT](https://mlsanity.com/paper/1708.00983/) (2017)

## Built on by (most cited first, 4 of 4)

- [Continual atlas-based segmentation of prostate MRI](https://mlsanity.com/paper/2311.00548/) (2023)
- [AVP-AP: Self-supervised Automatic View Positioning in 3D cardiac CT via Atlas Prompting](https://mlsanity.com/paper/2504.05966/) (2025)
- [Super-Resolution Generative Adversarial Networks based Video Enhancement](https://mlsanity.com/paper/2505.10589/) (2025)
- [MCSeg: Pre-training and Fine-tuning Volumetric Pyramid Transformer for Multi-modal Cardiac Image Segmentation](https://mlsanity.com/paper/2608.30371/) (2026)

## Abstract (arXiv)

Accurate and robust whole heart substructure segmentation is crucial in developing clinical applications, such as computer-aided diagnosis and computer-aided surgery. However, segmentation of different heart substructures is challenging because of inadequate edge or boundary information, the complexity of the background and texture, and the diversity in different substructures' sizes and shapes. This article proposes a framework for multi-class whole heart segmentation employing non-rigid registration-based probabilistic atlas incorporating the Bayesian framework. We also propose a non-rigid registration pipeline utilizing a multi-resolution strategy for obtaining the highest attainable mutual information between the moving and fixed images. We further incorporate non-rigid registration into the expectation-maximization algorithm and implement different deep convolutional neural network-based encoder-decoder networks for ablation studies. All the extensive experiments are conducted utilizing the publicly available dataset for the whole heart segmentation containing 20 MRI and 20 CT cardiac images. The proposed approach exhibits an encouraging achievement, yielding a mean volume overlapping error of 14.5 % for CT scans exceeding the state-of-the-art results by a margin of 1.3 % in terms of the same metric. As the proposed approach provides better-results to delineate the different substructures of the heart, it can be a medical diagnostic aiding tool for helping experts with quicker and more accurate results.