# Shape constrained CNN for segmentation guided prediction of myocardial shape and pose parameters in cardiac MRI

arXiv: https://arxiv.org/abs/2203.01089 · HTML: https://mlsanity.com/paper/2203.01089/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 61 references that are in the map.
- First posted on arXiv 2 Mar 2022.

## Builds on (most cited first, 29 of 29)

- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge](https://mlsanity.com/paper/1811.02629/) (2018)
- [Ladder Variational Autoencoders](https://mlsanity.com/paper/1602.02282/) (2016)
- [Boundary loss for highly unbalanced segmentation](https://mlsanity.com/paper/1812.07032/) (2018)
- [A Deep Learning Framework for Unsupervised Affine and Deformable Image Registration](https://mlsanity.com/paper/1809.06130/) (2018)
- [Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networks](https://mlsanity.com/paper/1904.10030/) (2019)
- [Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation](https://mlsanity.com/paper/1705.08302/) (2017)
- [Shape-Aware Organ Segmentation by Predicting Signed Distance Maps](https://mlsanity.com/paper/1912.03849/) (2019)
- [Fully Convolutional Multi-scale Residual DenseNets for Cardiac Segmentation and Automated Cardiac Diagnosis using Ensemble of Classifiers](https://mlsanity.com/paper/1801.05173/) (2018)
- [DeepSSM: A Deep Learning Framework for Statistical Shape Modeling from Raw Images](https://mlsanity.com/paper/1810.00111/) (2018)
- [Studying Robustness of Semantic Segmentation under Domain Shift in cardiac MRI](https://mlsanity.com/paper/2011.07592/) (2020)
- [Cardiac Segmentation from LGE MRI Using Deep Neural Network Incorporating Shape and Spatial Priors](https://mlsanity.com/paper/1906.07347/) (2019)
- [Explainable Anatomical Shape Analysis through Deep Hierarchical Generative Models](https://mlsanity.com/paper/1907.00058/) (2019)
- [Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow](https://mlsanity.com/paper/1811.03433/) (2018)
- [Learning Shape Priors for Robust Cardiac MR Segmentation from Multi-view Images](https://mlsanity.com/paper/1907.09983/) (2019)
- [Shape-Aware Complementary-Task Learning for Multi-Organ Segmentation](https://mlsanity.com/paper/1908.05099/) (2019)
- [Joint Left Atrial Segmentation and Scar Quantification Based on a DNN with Spatial Encoding and Shape Attention](https://mlsanity.com/paper/2006.13011/) (2020)
- [Cardiac MRI Segmentation with Strong Anatomical Guarantees](https://mlsanity.com/paper/1907.02865/) (2019)
- [A Distance Map Regularized CNN for Cardiac Cine MR Image Segmentation](https://mlsanity.com/paper/1901.01238/) (2019)
- [Probabilistic 3D surface reconstruction from sparse MRI information](https://mlsanity.com/paper/2010.02041/) (2020)
- [3D Cardiac Shape Prediction with Deep Neural Networks: Simultaneous Use of Images and Patient Metadata](https://mlsanity.com/paper/1907.01913/) (2019)
- [PC-U Net: Learning to Jointly Reconstruct and Segment the Cardiac Walls in 3D from CT Data](https://mlsanity.com/paper/2008.08194/) (2020)
- [Direct Multitype Cardiac Indices Estimation via Joint Representation and Regression Learning](https://mlsanity.com/paper/1705.09307/) (2017)
- [Shape Constrained CNN for Cardiac MR Segmentation with Simultaneous Prediction of Shape and Pose Parameters](https://mlsanity.com/paper/2010.08952/) (2020)
- [Left Ventricle Segmentation and Quantification from Cardiac Cine MR Images via Multi-task Learning](https://mlsanity.com/paper/1809.10221/) (2018)
- [A Deep Learning based Fast Signed Distance Map Generation](https://mlsanity.com/paper/2005.12662/) (2020)
- [Anatomy-Aware Cardiac Motion Estimation](https://mlsanity.com/paper/2008.07579/) (2020)
- [Left Ventricle Quantification Using Direct Regression with Segmentation Regularization and Ensembles of Pretrained 2D and 3D CNNs](https://mlsanity.com/paper/1908.04181/) (2019)

## Built on by (most cited first, 2 of 2)

- [A new method incorporating deep learning with shape priors for left ventricular segmentation in myocardial perfusion SPECT images](https://mlsanity.com/paper/2206.03603/) (2022)
- [Shape-intensity knowledge distillation for robust medical image segmentation](https://mlsanity.com/paper/2409.17503/) (2024)

## Abstract (arXiv)

Semantic segmentation using convolutional neural networks (CNNs) is the state-of-the-art for many medical image segmentation tasks including myocardial segmentation in cardiac MR images. However, the predicted segmentation maps obtained from such standard CNN do not allow direct quantification of regional shape properties such as regional wall thickness. Furthermore, the CNNs lack explicit shape constraints, occasionally resulting in unrealistic segmentations. In this paper, we use a CNN to predict shape parameters of an underlying statistical shape model of the myocardium learned from a training set of images. Additionally, the cardiac pose is predicted, which allows to reconstruct the myocardial contours. The integrated shape model regularizes the predicted contours and guarantees realistic shapes. We enforce robustness of shape and pose prediction by simultaneously performing pixel-wise semantic segmentation during training and define two loss functions to impose consistency between the two predicted representations: one distance-based loss and one overlap-based loss. We evaluated the proposed method in a 5-fold cross validation on an in-house clinical dataset with 75 subjects and on the ACDC and LVQuan19 public datasets. We show the benefits of simultaneous semantic segmentation and the two newly defined loss functions for the prediction of shape parameters. Our method achieved a correlation of 99% for left ventricular (LV) area on the three datasets, between 91% and 97% for myocardial area, 98-99% for LV dimensions and between 80% and 92% for regional wall thickness.