How well do U-Net-based segmentation trained on adult cardiac magnetic resonance imaging data generalise to rare congenital heart diseases for surgical planning?

Sven Koehler, Animesh Tandon, Tarique Hussain, Heiner Latus, Thomas Pickardt, Samir Sarikouch, Philipp Beerbaum, Franz G Greil, Sandy Engelhardt, Ivo Wolf

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Planning the optimal time of intervention for pulmonary valve replacement surgery in patients with the congenital heart disease Tetralogy of Fallot (TOF) is mainly based on ventricular volume and function according to current guidelines. Both of these two biomarkers are most reliably assessed by segmentation of 3D cardiac magnetic resonance (CMR) images. In several grand challenges in the last years, U-Net architectures have shown impressive results on the provided data. However, in clinical practice, data sets are more diverse considering individual pathologies and image properties derived from different scanner properties. Additionally, specific training data for complex rare diseases like TOF is scarce. For this work, 1) we assessed the accuracy gap when using a publicly available labelled data set (the Automatic Cardiac Diagnosis Challenge (ACDC) data set) for training and subsequent applying it to CMR data of TOF patients and vice versa and 2) whether we can achieve similar results when applying the model to a more heterogeneous data base. Multiple deep learning models were trained with four-fold cross validation. Afterwards they were evaluated on the respective unseen CMR images from the other collection. Our results confirm that current deep learning models can achieve excellent results (left ventricle dice of 0.951±0.003/0.941±0.0007 train/validation) within a single data collection. But once they are applied to other pathologies, it becomes apparent how much they overfit to the training pathologies (dice score drops between 0.072±0.001 for the left and 0.165±0.001 for the right ventricle).

Original languageEnglish (US)
Title of host publicationMedical Imaging 2020
Subtitle of host publicationImage-Guided Procedures, Robotic Interventions, and Modeling
EditorsBaowei Fei, Cristian A. Linte
PublisherSPIE
ISBN (Electronic)9781510633971
DOIs
StatePublished - 2020
EventMedical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling - Houston, United States
Duration: Feb 16 2020Feb 19 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11315
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceMedical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling
CountryUnited States
CityHouston
Period2/16/202/19/20

Keywords

  • Cardiac magnet resonance imaging (CMR)
  • Deep learning
  • Generalisation
  • Machine learning for surgical applications
  • Semantic segmentation
  • Tetralogy of Fallot
  • U-Net

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'How well do U-Net-based segmentation trained on adult cardiac magnetic resonance imaging data generalise to rare congenital heart diseases for surgical planning?'. Together they form a unique fingerprint.

  • Cite this

    Koehler, S., Tandon, A., Hussain, T., Latus, H., Pickardt, T., Sarikouch, S., Beerbaum, P., Greil, F. G., Engelhardt, S., & Wolf, I. (2020). How well do U-Net-based segmentation trained on adult cardiac magnetic resonance imaging data generalise to rare congenital heart diseases for surgical planning? In B. Fei, & C. A. Linte (Eds.), Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling [113151K] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11315). SPIE. https://doi.org/10.1117/12.2550651