Abstract:

Introduction: Photogrammetric surface scans provide a radiation-free option to assess and classify craniosynostosis. Due to the low prevalence of craniosynostosis and high patient restrictions, clinical data is rare. Synthetic data could support or even replace clinical data for the classification of craniosynostosis, but this has never been studied systematically. Methods: We test the combinations of three different synthetic data sources: a statistical shape model (SSM), a generative adversarial network (GAN), and image-based principal component analysis for a convolutional neural network (CNN)-based classification of craniosynostosis. The CNN is trained only on synthetic data, but validated and tested on clinical data. Results: The combination of a SSM and a GAN achieved an accuracy of more than 0.96 and a F1-score of more than 0.95 on the unseen test set. The difference to training on clinical data was smaller than 0.01. Including a second image modality improved classification performance for all data sources. Conclusion: Without a single clinical training sample, a CNN was able to classify head deformities as accurate as if it was trained on clinical data. Using multiple data sources was key for a good classification based on synthetic data alone. Synthetic data might play an important future role in the assessment of craniosynostosis.

Abstract:

Objective: Diagnosis of craniosynostosis using photogrammetric 3D surface scans is a promising radiation-free alternative to traditional computed tomography. We propose a 3D surface scan to 2D distance map conversion enabling the usage of the first convolutional neural networks (CNNs)-based classification of craniosynostosis. Benefits of using 2D images include preserving patient anonymity, enabling data augmentation during training, and a strong under-sampling of the 3D surface with good classification performance.Methods: The proposed distance maps sample 2D images from 3D surface scans using a coordinate transformation, ray casting, and distance extraction. We introduce a CNNbased classification pipeline and compare our classifier to alternative approaches on a dataset of 496 patients. We investigate into low-resolution sampling, data augmentation, and attribution mapping.Results: Resnet18 outperformed alternative classifiers on our dataset with an F1-score of 0.964 and an accuracy of 98.4 %. Data augmentation on 2D distance maps increased performance for all classifiers. Under-sampling allowed 256-fold computation reduction during ray casting while retaining an F1-score of 0.92. Attribution maps showed high amplitudes on the frontal head.Conclusion: We demonstrated a versatile mapping approach to extract a 2D distance map from the 3D head geometry increasing classification performance, enabling data augmentation during training on 2D distance maps, and the usage of CNNs. We found that low-resolution images were sufficient for a good classification performance.Significance: Photogrammetric surface scans are a suitable craniosynostosis diagnosis tool for clinical practice. Domain transfer to computed tomography seems likely and can further contribute to reducing ionizing radiation exposure for infants.

Abstract:

The application of machine learning approachesin medical technology is gaining more and more attention.Due to the high restrictions for collecting intraoperative patientdata, synthetic data is increasingly used to support the trainingof artificial neural networks. We present a pipeline to createa statistical shape model (SSM) using 28 segmented clinicalliver CT scans. Our pipeline consists of four steps: data pre-processing, rigid alignment, template morphing, and statisti-cal modeling. We compared two different template morphingapproaches: Laplace-Beltrami-regularized projection (LBRP)and nonrigid iterative closest points translational (N-ICP-T)and evaluated both morphing approaches and their corre-sponding shape model performance using six metrics. LBRPachieved a smaller mean vertex-to-nearest-neighbor distances(2.486±0.897 mm) than N-ICP-T (5.559±2.413 mm). Gen-eralizationand specificity errors for LBRP were consistentlylower than those of N-ICP-T. The first principal componentsof the SSM showed realistic anatomical variations. The perfor-mance of the SSM was comparable to a state-of-the-art model.

Abstract:

Introduction: 3D surface scan-based diagnosis of craniosynostosis is a promising radiation-free alternative to traditional diagnosis using computed tomography. The cra- nial index (CI) and the cranial vault asymmetry index (CVAI) are well-established clinical parameters that are widely used. However, they also have the benefit of being easily adaptable for automatic diagnosis without the need of extensive prepro- cessing.Methods: We propose a multi-height-based classification ap- proach that uses CI and CVAI in different height layers and compare it to the initial approach using only one layer. We use ten-fold cross-validation and test seven different classi- fiers. The dataset of 504 patients consists of three types of craniosynostosis and a control group consisting of healthy and non-synostotic subjects.Results: The multi-height-based approach improved classifica- tion for all classifiers. The k-nearest neighbors classifier scored best with a mean accuracy of 89 % and a mean F1-score of 0.75.Conclusion: Taking height into account is beneficial for the classification. Based on accepted and widely used clinical pa- rameters, this might be a step towards an easy-to-understand and transparent classification approach for both physicians and patients.

Abstract:

This work investigates into radiation-free classification of craniosynostosis with an additional focus on including data augmentation and using synthetic data as a replacement for clinical data.Motivation: Craniosynostosis is a condition affecting infants and leads to head deformities. Diagnosis using radiation-free 3D surface scans is a promising alter- native to traditional computed tomography (CT) imaging. Clinical data are only sparsely available due to the low prevalence and difficulties in anonymization. This work addresses these challenges by proposing new classification algorithms for craniosynostosis, by creating synthetic data for the scientific community, and by demonstrating that it is possible to fully replace clinical data with synthetic data without losing classification performance.Methods: A statistical shape model (SSM) of craniosynostosis patients is created and made publicly available. A 3D-2D conversion from the 3D mesh geometry to a 2D image is proposed which enables the usage of convolutional neural net- works (CNNs) and data augmentation in the image domain. Three classification approaches (based on cephalometric measurements, based on an SSM, and based on the 2D images using a CNN) to distinguish between three types of craniosynos- tosis and a control group are proposed and evaluated. Finally, the clinical training data are fully replaced with synthetic data by an SSM and a generative adversarial network (GAN).Results: The proposed CNN classification outperformed competing approaches on a clinical dataset of 496 subjects and achieved an F1-score of 0.964. Data augmen- tation increased the F1-score to 0.975. Attribution maps of the classification decision showed high amplitudes on parts of the head associated with craniosynostosis. Replacing the clinical data with synthetic data created by an SSM and a GAN still yielded an F1-score of more than 0.95 without the model having seen a single clinical subject.Conclusion: The proposed conversion of 3D geometry to a 2D encoded image improved performance to existing classifiers and enabled data augmentation during training. Using an SSM and a GAN, clinical training data could be replaced with synthetic data. This work improves existing diagnostic approaches on radiation-free recordings and demonstrates the usability of synthetic data which makes clinical applications more objective, interpretable, and less expensive.