Partial Volume Segmentation of Brain MRI Scans of Any Resolution and Contrast

Billot, Benjamin; Robinson, Eleanor; Dalca, Adrian V.; Iglesias, Juan Eugenio

doi:10.1007/978-3-030-59728-3_18

Cited by 19 publications

(23 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we present SynthSeg, the first neural network to readily segment brain MRI scans of any contrast and resolution, without having to be retrained or fine-tuned (Figure 1). This work extends two of our recent articles about contrast-adaptiveness [80] and PV simulation [81] for segmentation of brain MRI scans. Here we substantially expand these works by building, for the first time, robustness to brain scans of any resolution (in addition to contrastinvariance), as well as adaptiveness to a wide range of subject populations.…”

Section: Contributionsupporting

confidence: 73%

SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining

Billot¹,

Greve²,

Puonti³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Despite advances in data augmentation and transfer learning, convolutional neural networks (CNNs) have difficulties generalising to unseen target domains. When applied to segmentation of brain MRI scans, CNNs are highly sensitive to changes in resolution and contrast: even within the same MR modality, decreases in performance can be observed across datasets. We introduce SynthSeg, the first segmentation CNN agnostic to brain MRI scans of any contrast and resolution. SynthSeg is trained with synthetic data sampled from a generative model inspired by Bayesian segmentation. Crucially, we adopt a domain randomisation strategy where we fully randomise the generation parameters to maximise the variability of the training data. Consequently, SynthSeg can segment preprocessed and unpreprocessed real scans of any target domain, without retraining or fine-tuning. Because SynthSeg only requires segmentations to be trained (no images), it can learn from label maps obtained automatically from existing datasets of different populations (e.g., with atrophy and lesions), thus achieving robustness to a wide range of morphological variability. We demonstrate SynthSeg on 5,500 scans of 6 modalities and 10 resolutions, where it exhibits unparalleled generalisation compared to supervised CNNs, test time adaptation, and Bayesian segmentation. The code and trained model are available at github.com/BBillot/SynthSeg.

show abstract

Section: Contributionsupporting

confidence: 73%

SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining

Billot¹,

Greve²,

Puonti³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Many of these tools require computationally expensive training on large datasets or are limited to specific applications, although new methods are being developed that are relevant to a broad range of tasks (Isensee et al, 2020). Another recent development is deep‐learning methods trained on synthetic data, which promise to generate accurate segmentation (Billot et al, 2020) and registration (Hoffmann et al, 2020) in seconds, without the usual requirements of large empirical training datasets. The runtime/quality trade‐off of these tools could be benchmarked using the tools presented here.…”

Section: Discussionmentioning

confidence: 99%

Rapid processing and quantitative evaluation of structural brain scans for adaptive multimodal imaging

Váša

Hobday

Stanyard

et al. 2021

Human Brain Mapping

View full text Add to dashboard Cite

Current neuroimaging acquisition and processing approaches tend to be optimised for quality rather than speed. However, rapid acquisition and processing of neuroimaging data can lead to novel neuroimaging paradigms, such as adaptive acquisition, where rapidly processed data is used to inform subsequent image acquisition steps. Here we first evaluate the impact of several processing steps on the processing time and quality of registration of manually labelled T1‐weighted MRI scans. Subsequently, we apply the selected rapid processing pipeline both to rapidly acquired multicontrast EPImix scans of 95 participants (which include T1‐FLAIR, T2, T2*, T2‐FLAIR, DWI and ADC contrasts, acquired in ~1 min), as well as to slower, more standard single‐contrast T1‐weighted scans of a subset of 66 participants. We quantify the correspondence between EPImix T1‐FLAIR and single‐contrast T1‐weighted scans, using correlations between voxels and regions of interest across participants, measures of within‐ and between‐participant identifiability as well as regional structural covariance networks. Furthermore, we explore the use of EPImix for the rapid construction of morphometric similarity networks. Finally, we quantify the reliability of EPImix‐derived data using test–retest scans of 10 participants. Our results demonstrate that quantitative information can be derived from a neuroimaging scan acquired and processed within minutes, which could further be used to implement adaptive multimodal imaging and tailor neuroimaging examinations to individual patients.

show abstract

“…While such models are very costly to train -in terms of time, computing power and energy -inference is very fast. Examples of relevant recent tools include SynthSeg for scan segmentation (Billot et al, 2020), voxelmorph for scan registration (Hoffmann et al, 2020) or FastSurfer, a deep learning analogue of Freesurfer which is particularly suitable for surface-based measures (Henschel et al, 2020). Additionally, EPImix scans could be super-resolved using image quality transfer tools, to improve scan resolution and likely increase correspondence to conventional single-contrast acquisitions (Iglesias et al, 2021).…”

Section: Active Acquisitionmentioning

confidence: 99%

Tissue volume estimation and age prediction using rapid structural brain scans

Hobday

Cole

Stanyard

et al. 2022

Preprint

View full text Add to dashboard Cite

The multicontrast EPImix sequence generates 6 contrasts, including a T1-weighted scan, in ~1 minute. EPImix shows comparable diagnostic performance to conventional scans under qualitative clinical evaluation, and similarities in simple quantitative measures including contrast intensity. However, EPImix scans have not yet been compared to standard MRI scans using established quantitative measures. In this study, we compared conventional and EPImix-derived T1-weighted scans of 64 healthy participants using tissue volume estimates and predicted brain-age. All scans were pre-processed using the SPM12 DARTEL pipeline, generating measures of grey matter, white matter and cerebrospinal fluid volume. Brain-age was predicted using brainageR, a Gaussian process regression model previously trained on a large sample of standard T1-weighted scans. Estimates of both global and voxel-wise tissue volume showed significantly similar results between standard and EPImix-derived T1-weighted scans. Brain-age estimates from both sequences were significantly correlated, although EPImix T1-weighted scans showed a systematic offset in predictions of chronological age. Supplementary analyses suggest that this is likely caused by the reduced field-of-view of EPImix scans, and the use of a brain-age model trained using conventional T1-weighted scans. However, this systematic error can be corrected using additional regression of T1-predicted brain-age onto EPImix-predicted brain-age. Finally, retest EPImix scans acquired for 10 participants demonstrated high test-retest reliability in all evaluated quantitative measurements. Quantitative analysis of EPImix scans holds potential to reduce scanning time, increasing participant comfort and reducing cost, as well as to support automation of scanning, utilising active learning for faster and individually-tailored (neuro)imaging.

show abstract

Partial Volume Segmentation of Brain MRI Scans of Any Resolution and Contrast

Cited by 19 publications

References 30 publications

SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining

SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining

Rapid processing and quantitative evaluation of structural brain scans for adaptive multimodal imaging

Tissue volume estimation and age prediction using rapid structural brain scans

Contact Info

Product

Resources

About