Robust automated segmentation of white matter hyperintensities (WMHs) in different datasets (domains) is highly challenging due to differences in acquisition (scanner, sequence), population (WMH amount and location) and limited availability of manual segmentations to train supervised algorithms. In this work we explore various domain adaptation techniques such as transfer learning and domain adversarial learning methods, including domain adversarial neural networks and domain unlearning, to improve the generalisability of our recently proposed triplanar ensemble network, which is our baseline model. We used datasets with variations in intensity profile, lesion characteristics and acquired using different scanners. For the source domain, we considered a dataset consisting of data acquired from 3 different scanners, while the target domain consisted of 2 datasets. We evaluated the domain adaptation techniques on the target domain datasets, and additionally evaluated the performance on the source domain test dataset for the adversarial techniques. For transfer learning, we also studied various training options such as minimal number of unfrozen layers and subjects required for fine-tuning in the target domain. On comparing the performance of different techniques on the target dataset, domain adversarial training of neural network gave the best performance, making the technique promising for robust WMH segmentation.

Comparison of domain adaptation techniques for white matter hyperintensity segmentation in brain MR images / Sundaresan, V.; Zamboni, G.; Dinsdale, N. K.; Rothwell, P. M.; Griffanti, L.; Jenkinson, M.. - In: MEDICAL IMAGE ANALYSIS. - ISSN 1361-8415. - 74:(2021), pp. 1-12. [10.1016/j.media.2021.102215]

Comparison of domain adaptation techniques for white matter hyperintensity segmentation in brain MR images

Zamboni G.;
2021

Abstract

Robust automated segmentation of white matter hyperintensities (WMHs) in different datasets (domains) is highly challenging due to differences in acquisition (scanner, sequence), population (WMH amount and location) and limited availability of manual segmentations to train supervised algorithms. In this work we explore various domain adaptation techniques such as transfer learning and domain adversarial learning methods, including domain adversarial neural networks and domain unlearning, to improve the generalisability of our recently proposed triplanar ensemble network, which is our baseline model. We used datasets with variations in intensity profile, lesion characteristics and acquired using different scanners. For the source domain, we considered a dataset consisting of data acquired from 3 different scanners, while the target domain consisted of 2 datasets. We evaluated the domain adaptation techniques on the target domain datasets, and additionally evaluated the performance on the source domain test dataset for the adversarial techniques. For transfer learning, we also studied various training options such as minimal number of unfrozen layers and subjects required for fine-tuning in the target domain. On comparing the performance of different techniques on the target dataset, domain adversarial training of neural network gave the best performance, making the technique promising for robust WMH segmentation.
2021
74
1
12
Comparison of domain adaptation techniques for white matter hyperintensity segmentation in brain MR images / Sundaresan, V.; Zamboni, G.; Dinsdale, N. K.; Rothwell, P. M.; Griffanti, L.; Jenkinson, M.. - In: MEDICAL IMAGE ANALYSIS. - ISSN 1361-8415. - 74:(2021), pp. 1-12. [10.1016/j.media.2021.102215]
Sundaresan, V.; Zamboni, G.; Dinsdale, N. K.; Rothwell, P. M.; Griffanti, L.; Jenkinson, M.
File in questo prodotto:
File Dimensione Formato  
Sundaresan2021_Comparison_Domain_adaptation_for_WMH_segmentation.pdf

Open access

Tipologia: Versione pubblicata dall'editore
Dimensione 3.18 MB
Formato Adobe PDF
3.18 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1253061
Citazioni
  • ???jsp.display-item.citation.pmc??? 2
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 6
social impact