Self-supervised Skull Reconstruction in Brain CT Images with Decompressive Craniectomy

Matzkin, Franco; Newcombe, Virginia; Stevenson, Susan; Khetani, Aneesh; Newman, Tom; Digby, Richard; Stevens, Andrew R; Glocker, Ben; Ferrante, Enzo

doi:10.1007/978-3-030-59713-9_38

Cited by 19 publications

(17 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pretext and downstream tasks may be the same. For example, a CNN was trained to reconstruct a skull bone flap by simulating craniectomies on CT scans [17]. Lesions simulated in chest CT of healthy subjects were used to train models for nodule detection, improving accuracy compared to training on a smaller dataset of real lesions [25].…”

Section: Related Workmentioning

confidence: 99%

A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections

et al. 2021

View full text Add to dashboard Cite

Purpose Accurate segmentation of brain resection cavities (RCs) aids in postoperative analysis and determining follow-up treatment. Convolutional neural networks (CNNs) are the state-of-the-art image segmentation technique, but require large annotated datasets for training. Annotation of 3D medical images is time-consuming, requires highly trained raters and may suffer from high inter-rater variability. Self-supervised learning strategies can leverage unlabeled data for training. Methods We developed an algorithm to simulate resections from preoperative magnetic resonance images (MRIs). We performed self-supervised training of a 3D CNN for RC segmentation using our simulation method. We curated EPISURG, a dataset comprising 430 postoperative and 268 preoperative MRIs from 430 refractory epilepsy patients who underwent resective neurosurgery. We fine-tuned our model on three small annotated datasets from different institutions and on the annotated images in EPISURG, comprising 20, 33, 19 and 133 subjects. Results The model trained on data with simulated resections obtained median (interquartile range) Dice score coefficients (DSCs) of 81.7 (16.4), 82.4 (36.4), 74.9 (24.2) and 80.5 (18.7) for each of the four datasets. After fine-tuning, DSCs were 89.2 (13.3), 84.1 (19.8), 80.2 (20.1) and 85.2 (10.8). For comparison, inter-rater agreement between human annotators from our previous study was 84.0 (9.9). Conclusion We present a self-supervised learning strategy for 3D CNNs using simulated RCs to accurately segment real RCs on postoperative MRI. Our method generalizes well to data from different institutions, pathologies and modalities. Source code, segmentation models and the EPISURG dataset are available at https://github.com/fepegar/resseg-ijcars.

show abstract

Section: Related Workmentioning

confidence: 99%

A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Recently, we have proposed [11] a simple virtual craniectomy procedure which enables training different deep learning models in a self-supervised way, given a dataset composed of full skulls. In this work, we compared two different approaches: direct estimation of the implant, or reconstruct-and-subtract (RS) strategies where the full skull is first reconstructed, and then the original image is subtracted from it to generate a difference map.…”

Section: Introductionmentioning

confidence: 99%

“…In this work, based on the conclusions from [11], we employ a direct estimation method that operates on full skulls which are rigidly registered to an atlas and resampled to an intermediate resolution. Aligning the images allow us to work in a common space which simplifies the reconstruction task.…”

Section: Introductionmentioning

confidence: 99%

“…We adapt the virtual craniectomy procedure to account for more realistic flap shapes, similar to the ones introduced in the AutoImplant challenge. Moreover, we propose to incorporate anatomical priors into the standard direct estimation model introduced in [11] by feeding the registered skull atlas as an extra image channel. Previous works [8] have shown that incorporating approximate shape priors as additional image channels is a simple yet effective way to increase the anatomical plausibility of the segmentations, since it provides supplementary context information to the network.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cranial Implant Design via Virtual Craniectomy with Shape Priors

Matzkin¹,

Newcombe²,

Glocker³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Cranial implant design is a challenging task, whose accuracy is crucial in the context of cranioplasty procedures. This task is usually performed manually by experts using computer-assisted design software. In this work, we propose and evaluate alternative automatic deep learning models for cranial implant reconstruction from CT images. The models are trained and evaluated using the database released by the AutoImplant challenge, and compared to a baseline implemented by the organizers. We employ a simulated virtual craniectomy to train our models using complete skulls, and compare two different approaches trained with this procedure. The first one is a direct estimation method based on the UNet architecture. The second method incorporates shape priors to increase the robustness when dealing with out-of-distribution implant shapes. Our direct estimation method outperforms the baselines provided by the organizers, while the model with shape priors shows superior performance when dealing with out-of-distribution cases. Overall, our methods show promising results in the difficult task of cranial implant design.

show abstract

“…In addition, Shi & Chen 22 proposed a convolutional neural network of the autoencoder 9,10,11 structure with an auxiliary path to predict the 3D implant from inpainting 2D slices of different axes. Matzkin et al 23 used a 3D version of the standard U-Net architecture 6 to compare two different approaches: direct estimation of the implant, and the reconstruct-and-subtract strategy, where the complete skull is first reconstructed, and then the defective model is subtracted from it to generate the implant. Before training, all the images were registered to an atlas space which is constructed by averaging several healthy head CT images.…”

mentioning

confidence: 99%

Three-Dimensional Deep Learning to Automatically Generate Cranial Implant Geometry

Chang

Yang

2021

Preprint

View full text Add to dashboard Cite

We present a 3D deep learning framework that can generate a complete cranial model using a defective one. The Boolean subtraction between these two models automatically generates the geometry of the implant required for surgical reconstruction. There is little or no need for post-processing to eliminate noise in the implant model generated by the proposed approach. The framework can be used to meet the repair needs of cranial imperfections caused by trauma, congenital defects, plastic surgery, or tumor resection. Traditional implant design methods for skull reconstruction rely on the mirror operation. However, these approaches have great limitations when the defect crosses the plane of symmetry or the patient's skull is asymmetrical. The proposed deep learning framework is based on an enhanced three-dimensional autoencoder. Each training sample for the framework is a pair consisting of a cranial model converted from CT images and a corresponding model with simulated defects on it. Our approach can learn the spatial distribution of the upper part of normal cranial bones and use flawed cranial data to predict its complete geometry. Empirical research on simulated defects and actual clinical applications shows that our framework can meet most of the requirements of cranioplasty.

show abstract

Self-supervised Skull Reconstruction in Brain CT Images with Decompressive Craniectomy

Cited by 19 publications

References 15 publications

A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections

A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections

Cranial Implant Design via Virtual Craniectomy with Shape Priors

Three-Dimensional Deep Learning to Automatically Generate Cranial Implant Geometry

Contact Info

Product

Resources

About