Comparison of a Hybrid Mixture Model and a CNN for the Segmentation of Myocardial Pathologies in Delayed Enhancement MRI

Huellebrand, Markus; Ivantsits, Matthias; Zhang, Hannu; Kohlmann, Peter; Kuhnigk, Jan-Martin; Küehne, Titus; Schönberg, Stefan O.; Hennemuth, Anja

doi:10.1007/978-3-030-68107-4_32

Cited by 4 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared the results of our proposed network to different previous methods used in the EMIDEC challenge, enclosing Feng et al [ 42 ], Huellebrand et al [ 44 ], Yang et al [ 46 ], Zhang [ 47 ], Camarasa et al [ 41 ], Zhou et al [ 48 ], and Girum et al [ 43 ]. The LV myocardium, scar, and MVO were segmented using those methods from the same test dataset.…”

Section: Resultsmentioning

confidence: 99%

“…The segmented myocardium area from the anatomical network is further used to refine the pathological network’s segmentation, thus producing the final four-class segmentation output. Huellebrand et al [ 44 ] compared a hybrid mixture model approach with two U-Net segmentations. The proposed mixture model is inspired by [ 45 ] and is suited to EMIDEC data.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

An Improved 3D Deep Learning-Based Segmentation of Left Ventricular Myocardial Diseases from Delayed-Enhancement MRI with Inclusion and Classification Prior Information U-Net (ICPIU-Net)

Brahim

Arega

Boucher

et al. 2022

Sensors

View full text Add to dashboard Cite

Accurate segmentation of the myocardial scar may supply relevant advancements in predicting and controlling deadly ventricular arrhythmias in subjects with cardiovascular disease. In this paper, we propose the architecture of inclusion and classification of prior information U-Net (ICPIU-Net) to efficiently segment the left ventricle (LV) myocardium, myocardial infarction (MI), and microvascular-obstructed (MVO) tissues from late gadolinium enhancement magnetic resonance (LGE-MR) images. Our approach was developed using two subnets cascaded to first segment the LV cavity and myocardium. Then, we used inclusion and classification constraint networks to improve the resulting segmentation of the diseased regions within the pre-segmented LV myocardium. This network incorporates the inclusion and classification information of the LGE-MRI to maintain topological constraints of pathological areas. In the testing stage, the outputs of each segmentation network obtained with specific estimated parameters from training were fused using the majority voting technique for the final label prediction of each voxel in the LGE-MR image. The proposed method was validated by comparing its results to manual drawings by experts from 50 LGE-MR images. Importantly, compared to various deep learning-based methods participating in the EMIDEC challenge, the results of our approach have a more significant agreement with manual contouring in segmenting myocardial diseases.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

An Improved 3D Deep Learning-Based Segmentation of Left Ventricular Myocardial Diseases from Delayed-Enhancement MRI with Inclusion and Classification Prior Information U-Net (ICPIU-Net)

Brahim

Arega

Boucher

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…For data pre-processing and the training of models for the slice-wise segmentation of cardiac structures, we use the Redleaf framework, which allows the integration of inference methods directly in the MeVisLab based applications. U-nets are trained for the segmentation of the relevant structures such as RV, LV, and myocardium ( 44 ). These segmentations form the basis for the extraction of typical radiomics features and image-based cardiac biomarkers as suggested in Section Introduction.…”

Section: Methodsmentioning

confidence: 99%

A Collaborative Approach for the Development and Application of Machine Learning Solutions for CMR-Based Cardiac Disease Classification

Huellebrand

Ivantsits

Tautz

et al. 2022

Front. Cardiovasc. Med.

Self Cite

View full text Add to dashboard Cite

The quality and acceptance of machine learning (ML) approaches in cardiovascular data interpretation depends strongly on model design and training and the interaction with the clinical experts. We hypothesize that a software infrastructure for the training and application of ML models can support the improvement of the model training and provide relevant information for understanding the classification-relevant data features. The presented solution supports an iterative training, evaluation, and exploration of machine-learning-based multimodal data interpretation methods considering cardiac MRI data. Correction, annotation, and exploration of clinical data and interpretation of results are supported through dedicated interactive visual analytics tools. We test the presented concept with two use cases from the ACDC and EMIDEC cardiac MRI image analysis challenges. In both applications, pre-trained 2D U-Nets are used for segmentation, and classifiers are trained for diagnostic tasks using radiomics features of the segmented anatomical structures. The solution was successfully used to identify outliers in automatic segmentation and image acquisition. The targeted curation and addition of expert annotations improved the performance of the machine learning models. Clinical experts were supported in understanding specific anatomical and functional characteristics of the assigned disease classes.

show abstract

“…The first one omits the inter-slice correlation, i.e. all the tissues are segmented from single slices whether the framework is one-stage or two-stage ( [20,12,51,8]). The second one only takes 3D inputs while the data format organization is different.…”

Section: U-net-based Encoding-decoding Modelsmentioning

confidence: 99%

“…Apart from the U-Net-based models that most challengers employed, a mixture model was proposed by [20] for the scar segmentation. The application of the mixture model on the cardiac MRI was inspired by the work of [15].…”

Section: Mixture Model For the Scar Segmentationmentioning

confidence: 99%

Deep Learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge

Lalande¹,

Chen²,

Pommier³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

A key factor for assessing the state of the heart after myocardial infarction (MI) is to measure whether the myocardium segment is viable after reperfusion or revascularization therapy. Delayed enhancement-MRI or DE-MRI, which is performed several minutes after injection of the contrast agent, provides high contrast between viable and nonviable myocardium and is therefore a method of choice to evaluate the extent of MI. To automatically assess myocardial status, the results of the EMIDEC challenge that focused on this task are presented in this paper. The challenge's main objectives were twofold. First, to evaluate if deep learning methods can distinguish between normal and pathological cases. Second, to automatically calculate the extent of myocardial infarction. The publicly available database consists of 150 exams divided into 50 cases with normal MRI after injection of a contrast agent and 100 cases with myocardial infarction (and then with a hyperenhanced area on DE-MRI), whatever their inclusion in the cardiac emergency department. Along with MRI, clinical characteristics are also provided. The obtained results issued from several works show that the automatic classification of an exam is a reachable task (the best method providing an accuracy of 0.92), and the automatic segmentation of the myocardium is possible. However, the segmentation of the diseased area needs to be improved, mainly due to the small size of these areas and the lack of contrast with the surrounding structures.

show abstract

Comparison of a Hybrid Mixture Model and a CNN for the Segmentation of Myocardial Pathologies in Delayed Enhancement MRI

Cited by 4 publications

References 11 publications

An Improved 3D Deep Learning-Based Segmentation of Left Ventricular Myocardial Diseases from Delayed-Enhancement MRI with Inclusion and Classification Prior Information U-Net (ICPIU-Net)

An Improved 3D Deep Learning-Based Segmentation of Left Ventricular Myocardial Diseases from Delayed-Enhancement MRI with Inclusion and Classification Prior Information U-Net (ICPIU-Net)

A Collaborative Approach for the Development and Application of Machine Learning Solutions for CMR-Based Cardiac Disease Classification

Deep Learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge

Contact Info

Product

Resources

About