A Deep Learning Based Cardiac Cine Segmentation Framework for Clinicians – Transfer Learning Application to 7T

Ankenbrand, Markus J.; Lohr, David; Schlötelburg, Wiebke; Reiter, Theresa; Wech, Tobias; Schreiber, Laura M.

doi:10.1101/2020.06.15.20131656

Cited by 4 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it will be interesting to observe in future studies how promising new coil concepts which have been tested successfully in large [53,54] and in other pilot studies [55][56][57][58] will further improve the image quality in clinical imaging. Additionally, the use of automated segmentation methods based on transfer learning might add to the application of CMR at 7T [59,60].…”

Section: Plos Onementioning

confidence: 99%

On the way to routine cardiac MRI at 7 Tesla - a pilot study on consecutive 84 examinations

et al. 2021

Self Cite

View full text Add to dashboard Cite

Introduction Cardiac magnetic resonance (CMR) at ultrahigh field (UHF) offers the potential of high resolution and fast image acquisition. Both technical and physiological challenges associated with CMR at 7T require specific hardware and pulse sequences. This study aimed to assess the current status and existing, publicly available technology regarding the potential of a clinical application of 7T CMR. Methods Using a 7T MRI scanner and a commercially available radiofrequency coil, a total of 84 CMR examinations on 72 healthy volunteers (32 males, age 19–70 years, weight 50–103 kg) were obtained. Both electrocardiographic and acoustic triggering were employed. The data were analyzed regarding the diagnostic image quality and the influence of patient and hardware dependent factors. 50 complete short axis stacks and 35 four chamber CINE views were used for left ventricular (LV) and right ventricular (RV), mono-planar LV function, and RV fractional area change (FAC). Twenty-seven data sets included aortic flow measurements that were used to calculate stroke volumes. Subjective acceptance was obtained from all volunteers with a standardized questionnaire. Results Functional analysis showed good functions of LV (mean EF 56%), RV (mean EF 59%) and RV FAC (mean FAC 52%). Flow measurements showed congruent results with both ECG and ACT triggering. No significant influence of experimental parameters on the image quality of the LV was detected. Small fractions of 5.4% of LV and 2.5% of RV segments showed a non-diagnostic image quality. The nominal flip angle significantly influenced the RV image quality. Conclusion The results demonstrate that already now a commercially available 7T MRI system, without major methods developments, allows for a solid morphological and functional analysis similar to the clinically established CMR routine approach. This opens the door towards combing routine CMR in patients with development of advanced 7T technology.

show abstract

Section: Plos Onementioning

confidence: 99%

On the way to routine cardiac MRI at 7 Tesla - a pilot study on consecutive 84 examinations

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The first case study addressed the problem of producing initial training data for a deep learning-based cardiac cine segmentation framework with transfer learning to 7 T [32]. On the one hand there is a public dataset of cardiac magnetic resonance images, the Data Science Bowl Cardiac Challenge (DSBCC) data [33].…”

Section: Case Study I: Model Suitabilitymentioning

confidence: 99%

“…More precisely, a model was demanded for segmentation of the heart in transversal ultra-high field MR images to improve B 0 shimming performance [36]. A model pre-trained on short-axis cine images at 7 T [32] was fine-tuned with very little additional data (90 images from 4 subjects). It was investigated how quickly the segmentation performance collapses when dataset characteristics differ to those of the training set.…”

Section: Case Study Ii: Model Robustnessmentioning

confidence: 99%

Sensitivity analysis for interpretation of machine learning based segmentation models in cardiac MRI

et al. 2021

Self Cite

View full text Add to dashboard Cite

Background Image segmentation is a common task in medical imaging e.g., for volumetry analysis in cardiac MRI. Artificial neural networks are used to automate this task with performance similar to manual operators. However, this performance is only achieved in the narrow tasks networks are trained on. Performance drops dramatically when data characteristics differ from the training set properties. Moreover, neural networks are commonly considered black boxes, because it is hard to understand how they make decisions and why they fail. Therefore, it is also hard to predict whether they will generalize and work well with new data. Here we present a generic method for segmentation model interpretation. Sensitivity analysis is an approach where model input is modified in a controlled manner and the effect of these modifications on the model output is evaluated. This method yields insights into the sensitivity of the model to these alterations and therefore to the importance of certain features on segmentation performance. Results We present an open-source Python library (misas), that facilitates the use of sensitivity analysis with arbitrary data and models. We show that this method is a suitable approach to answer practical questions regarding use and functionality of segmentation models. We demonstrate this in two case studies on cardiac magnetic resonance imaging. The first case study explores the suitability of a published network for use on a public dataset the network has not been trained on. The second case study demonstrates how sensitivity analysis can be used to evaluate the robustness of a newly trained model. Conclusions Sensitivity analysis is a useful tool for deep learning developers as well as users such as clinicians. It extends their toolbox, enabling and improving interpretability of segmentation models. Enhancing our understanding of neural networks through sensitivity analysis also assists in decision making. Although demonstrated only on cardiac magnetic resonance images this approach and software are much more broadly applicable.

show abstract

“…More precisely, a model was demanded for segmentation of the heart in transversal ultra-high eld MR images to improve B 0 shimming performance (33). A model pre-trained on short-axis cine images at 7T (29) was ne-tuned with very little additional data (90 images from 4 subjects). It was investigated how quickly the segmentation performance collapses when dataset characteristics differ to those of the training set.…”

Section: Case Study II -Model Robustnessmentioning

confidence: 99%

Sensitivity Analysis for Interpretation of Machine Learning Based Segmentation Models in Cardiac MRI

Ankenbrand

Shainberg

Hock

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Background Image segmentation is a common task in medical imaging e.g. for volumetry analysis in cardiac MRI. Artificial neural networks are used to automate this task with performance similar to manual operators. However, this performance is only achieved in the narrow tasks networks are trained on. Performance drops dramatically when data characteristics differ from the training set properties. Moreover, neural networks are commonly considered black boxes, because it is hard to understand how they make decisions and why they fail. Therefore, it is also hard to predict whether they will generalize and work well with new data. Results We show that sensitivity analysis is a suitable approach to answer practical questions regarding use and functionality of segmentation models. We also provide an open source Python library (misas), that facilitates the use of this method with arbitrary data and models. By enabling a better understanding of neural networks through sensitivity analysis it also assists in decision making. We demonstrate this in two case studies on cardiac magnetic resonance imaging.Conclusions Sensitivity analysis is a useful tool for deep learning developers as well as users such as clinicians. It extends their toolbox with a new tool that makes segmentation models more interpretable. Although demonstrated only on cardiac magnetic resonance images this approach and software are much more broadly applicable.

show abstract

A Deep Learning Based Cardiac Cine Segmentation Framework for Clinicians – Transfer Learning Application to 7T

Cited by 4 publications

References 33 publications

On the way to routine cardiac MRI at 7 Tesla - a pilot study on consecutive 84 examinations

On the way to routine cardiac MRI at 7 Tesla - a pilot study on consecutive 84 examinations

Sensitivity analysis for interpretation of machine learning based segmentation models in cardiac MRI

Sensitivity Analysis for Interpretation of Machine Learning Based Segmentation Models in Cardiac MRI

Contact Info

Product

Resources

About