Multi-Modal Segmentation of 3d Brain Scans Using Neural Networks

Zopes, Jonathan; Platscher, Moritz; Paganucci, Silvio; Federau, Christian

doi:10.26226/morressier.5f5a58d42c3338b5c13cd116

Cited by 3 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, to create the final, clinically relevant summary of lesion distribution. Since these two purposes applied, respectively, to the FLAIR and the T1 modality, which have different constraints, two separate models were actually trained (Figure 3), because we would not benefit from having a single multi‐modal model (Zopes et al, 2021) here.…”

Section: Methodsmentioning

confidence: 99%

Higher‐resolution quantification of white matter hypointensities by large‐scale transfer learning from 2D images on the JPSC‐AD cohort

Thyreau

Tatewaki

Chen

et al. 2022

Human Brain Mapping

View full text Add to dashboard Cite

White matter lesions (WML) commonly occur in older brains and are quantifiable on MRI, often used as a biomarker in Aging research. Although algorithms are regularly proposed that identify these lesions from T2‐fluid‐attenuated inversion recovery (FLAIR) sequences, none so far can estimate lesions directly from T1‐weighted images with acceptable accuracy. Since 3D T1 is a polyvalent and higher‐resolution sequence, it could be beneficial to obtain the distribution of WML directly from it. However a serious difficulty, both for algorithms and human, can be found in the ambiguities of brain signal intensity in T1 images. This manuscript shows that a cross‐domain ConvNet (Convolutional Neural Network) approach can help solve this problem. Still, this is non‐trivial, as it would appear to require a large and varied dataset (for robustness) labelled at the same high resolution (for spatial accuracy). Instead, our model was taught from two‐dimensional FLAIR images with a loss function designed to handle the super‐resolution need. And crucially, we leveraged a very large training set for this task, the recently assembled, multi‐sites Japan Prospective Studies Collaboration for Aging and Dementia (JPSC‐AD) cohort. We describe the two‐step procedure that we followed to handle such a large number of imperfectly labeled samples. A large‐scale accuracy evaluation conducted against FreeSurfer 7, and a further visual expert rating revealed that WML segmentation from our ConvNet was consistently better. Finally, we made a directly usable software program based on that trained ConvNet model, available at https://github.com/bthyreau/deep-T1-WMH .

show abstract

Section: Methodsmentioning

confidence: 99%

Higher‐resolution quantification of white matter hypointensities by large‐scale transfer learning from 2D images on the JPSC‐AD cohort

Thyreau

Tatewaki

Chen

et al. 2022

Human Brain Mapping

View full text Add to dashboard Cite

show abstract

“…To obtain the anatomical segmentations, we use FreeSurfer as our reference tool (Fischl et al, 2002), and follow (Zopes et al, 2020) to obtain the segmentation masks. The total processing time for the 2027 healthy and 449 stroke cases is of the order of a few hours.…”

Section: Datamentioning

confidence: 99%

Image Translation for Medical Image Generation -- Ischemic Stroke Lesions

Platscher¹,

Zopes²,

Federau³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Deep learning-based automated disease detection and segmentation algorithms promise to accelerate and improve many clinical processes. However, such algorithms require vast amounts of annotated training data, which are typically not available in a medical context, e.g., due to data privacy concerns, legal obstructions, and non-uniform data formats. Synthetic databases of annotated pathologies could provide the required amounts of training data. Here, we demonstrate with the example of ischemic stroke that a significant improvement in lesion segmentation is feasible using deep learning-based data augmentation. To this end, we train different image-to-image translation models to synthesize diffusionweighted magnetic resonance images (DWIs) of brain volumes with and without stroke lesions from semantic segmentation maps. In addition, we train a generative adversarial network to generate synthetic lesion masks. Subsequently, we combine these two components to build a large database of synthetic stroke DWIs. The performance of the various generative models is evaluated using a U-Net which is trained to segment stroke lesions on a clinical test set. We compare the results to human expert inter-reader scores. For the model with the best performance, we report a maximum Dice score of 82.6%, which significantly outperforms the model trained on the clinical images alone (74.8%), and also the inter-reader Dice score of two human readers of 76.9%. Moreover, we show that for a very limited database of only 10 or 50 clinical cases, synthetic data can be used to pre-train the segmentation algorithms, which ultimately yields an improvement by a factor of as high as 8 compared to a setting where no synthetic data is used.

show abstract