Robust head CT image registration pipeline for craniosynostosis skull correction surgery

Improving Cranial Vault Remodeling for Unilateral Coronal Craniosynostosis-Introducing Automated Surgical Planning

Study Design

Cranial vault remodeling (CVR) for unicoronal synostosis is challenging due to the asymmetric nature of the deformity. Computer-automated surgical planning has demonstrated success in reducing the subjectivity of decision making in CVR in symmetric subtypes. This proof of concept study presents a novel method using Boolean functions and image registration to automatically suggest surgical steps in asymmetric craniosynostosis.

Objective

The objective of this study is to introduce automated surgical planning into a CVR virtual workflow for an asymmetric craniosynostosis subtype.

Methods

Virtual workflows were developed using Geomagic Freeform Plus software. Hausdorff distances and color maps were used to compare reconstruction models to the preoperative model and a control skull. Reconstruction models were rated as high or low performing based on similarity to the normal skull and the amount of advancement of the frontal bone (FB) and supra-orbital bar (SOB). Fifteen partially and fully automated workflow iterations were carried out.

Results

FB and SOB advancement ranged from 3.08 to 10.48 mm, and -1.75 to 7.78 mm, respectively. Regarding distance from a normal skull, models ranged from .85 to 5.49 mm at the FB and 5.40 to 10.84 mm at the SOB. An advancement of 8.43 mm at the FB and 7.73 mm at the SOB was achieved in the highest performing model, and it differed to a comparative normal skull by .02 mm at the FB and .48 mm at the SOB.

Conclusions

This is the first known attempt at developing an automated virtual surgical workflow for CVR in asymmetric craniosynostosis. Key regions of interest were outlined using Boolean operations, and surgical steps were suggested using image registration. These techniques improved post-operative skull morphology.

Data-driven cranial suture growth model enables predicting phenotypes of craniosynostosis

We present the first data-driven pediatric model that explains cranial sutural growth in the pediatric population. We segmented the cranial bones in the neurocranium from the cross-sectional CT images of 2068 normative subjects (age 0-10 years), and we used a 2D manifold-based cranial representation to establish local anatomical correspondences between subjects guided by the location of the cranial sutures. We designed a diffeomorphic spatiotemporal model of cranial bone development as a function of local sutural growth rates, and we inferred its parameters statistically from our cross-sectional dataset. We used the constructed model to predict growth for 51 independent normative patients who had longitudinal images. Moreover, we used our model to simulate the phenotypes of single suture craniosynostosis, which we compared to the observations from 212 patients. We also evaluated the accuracy predicting personalized cranial growth for 10 patients with craniosynostosis who had pre-surgical longitudinal images. Unlike existing statistical and simulation methods, our model was inferred from real image observations, explains cranial bone expansion and displacement as a consequence of sutural growth and it can simulate craniosynostosis. This pediatric cranial suture growth model constitutes a necessary tool to study abnormal development in the presence of cranial suture pathology.

Joint Cranial Bone Labeling and Landmark Detection in Pediatric CT Images Using Context Encoding

Image segmentation, labeling, and landmark detection are essential tasks for pediatric craniofacial evaluation. Although deep neural networks have been recently adopted to segment cranial bones and locate cranial landmarks from computed tomography (CT) or magnetic resonance (MR) images, they may be hard to train and provide suboptimal results in some applications. First, they seldom leverage global contextual information that can improve object detection performance. Second, most methods rely on multi-stage algorithm designs that are inefficient and prone to error accumulation. Third, existing methods often target simple segmentation tasks and have shown low reliability in more challenging scenarios such as multiple cranial bone labeling in highly variable pediatric datasets. In this paper, we present a novel end-to-end neural network architecture based on DenseNet that incorporates context regularization to jointly label cranial bone plates and detect cranial base landmarks from CT images. Specifically, we designed a context-encoding module that encodes global context information as landmark displacement vector maps and uses it to guide feature learning for both bone labeling and landmark identification. We evaluated our model on a highly diverse pediatric CT image dataset of 274 normative subjects and 239 patients with craniosynostosis (age 0.63 ± 0.54 years, range 0-2 years). Our experiments demonstrate improved performance compared to state-of-the-art approaches.

Data-driven Normative Reference of Pediatric Cranial Bone Development

Available normative references of cranial bone development and suture fusion are incomplete or based on simplified assumptions due to the lack of large datasets. We present a fully data-driven normative model that represents the age- and sex-specific variability of bone shape, thickness, and density between birth and 10 years of age at every location of the calvaria.

Predictive Statistical Model of Early Cranial Development

OBJECTIVE

We present a data-driven method to build a spatiotemporal statistical shape model predictive of normal cranial growth from birth to the age of 2 years.

METHODS

The model was constructed using a normative cross-sectional computed tomography image dataset of 278 subjects. First, we propose a new standard representation of the calvaria using spherical maps to establish anatomical correspondences between subjects at the cranial sutures - the main areas of cranial bone expansion. Then, we model the cranial bone shape as a bilinear function of two factors: inter-subject anatomical variability and temporal growth. We estimate these factors using principal component analysis on the spatial and temporal dimensions, using a novel coarse-to-fine temporal multi-resolution approach to mitigate the lack of longitudinal images of the same patient.

RESULTS

Our model achieved an accuracy of 1.54 ± 1.05 mm predicting development on an independent longitudinal dataset. We also used the model to calculate the cranial volume, cephalic index and cranial bone surface changes during the first two years of age, which were in agreement with clinical observations.

SIGNIFICANCE

To our knowledge, this is the first data-driven and personalized predictive model of cranial bone shape development during infancy and it can serve as a baseline to study abnormal growth patterns in the population.

Test-retest validation of a cranial deformity index in unilateral coronal craniosynostosis

Unilateral coronal craniosynostosis (UCS) affects many infants resulting in abnormalities affecting the forehead and orbits. As a result, the deformity caused by UCS is very noticeable and there are several surgical treatment options available to normalize the head shape. However, there is a lack of consistently used outcome measures, resulting in difficulty assessing surgical outcomes and on-going debate over optimal treatments. Current techniques to quantify deformity in UCS are cumbersome, provide limited information, or are based on subjective assessments. In this study, a cranial deformity index was developed to quantify abnormality at the frontal bones for UCS that is accessible, user-friendly, and generates objective surface distance measurements. The cranial deformity index is defined as the Euclidean distance at the point of the largest deviation between the deformed skull compared to a reference skull. In addition, the index was successfully used to quantify post-operative changes in a single case of UCS that underwent corrective surgery. The reproducibility of the index was assessed using test-retest reliability and was demonstrated to be highly reproducible (ICC = 0.93). A user-friendly measurement index that is based on open-source software may be a valuable tool for surgical teams. In addition, this information can augment the consultation experience for patients and their families.