The Use of Artificial Intelligence for the Classification of Craniofacial Deformities.

Positional cranial deformities are a common finding in toddlers, yet differentiation from craniosynostosis can be challenging. The aim of this study was to train convolutional neural networks (CNNs) to classify craniofacial deformities based on 2D images generated using photogrammetry as a radiation-free imaging technique. A total of 487 patients with photogrammetry scans were included in this retrospective cohort study: children with craniosynostosis (n = 227), positional deformities (n = 206), and healthy children (n = 54). Three two-dimensional images were extracted from each photogrammetry scan. The datasets were divided into training, validation, and test sets. During the training, fine-tuned ResNet-152s were utilized. The performance was quantified using tenfold cross-validation. For the detection of craniosynostosis, sensitivity was at 0.94 with a specificity of 0.85. Regarding the differentiation of the five existing classes (trigonocephaly, scaphocephaly, positional plagiocephaly left, positional plagiocephaly right, and healthy), sensitivity ranged from 0.45 (positional plagiocephaly left) to 0.95 (scaphocephaly) and specificity ranged from 0.87 (positional plagiocephaly right) to 0.97 (scaphocephaly). We present a CNN-based approach to classify craniofacial deformities on two-dimensional images with promising results. A larger dataset would be required to identify rarer forms of craniosynostosis as well. The chosen 2D approach enables future applications for digital cameras or smartphones.

3D-2D Distance Maps Conversion Enhances Classification of Craniosynostosis.

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 CNN-based 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.

Impact of data synthesis strategies for the classification of craniosynostosis.

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 are rare. Synthetic data could support or even replace clinical data for the classification of craniosynostosis, but this has never been studied systematically. Methods: We tested 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 is validated and tested on clinical data. Results: The combination of an SSM and a GAN achieved an accuracy of 0.960 and an F1 score of 0.928 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. Conclusions: Without a single clinical training sample, a CNN was able to classify head deformities with similar accuracy 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.

CNN-Based Classification of Craniosynostosis Using 2D Distance Maps.

Craniosynostosis is a condition associated with the premature fusion of skull sutures affecting infants. 3D photogrammetric scans are a promising alternative to computed tomography scans in cases of single suture or nonsyndromic synostosis for diagnostic imaging, but oftentimes diagnosis is not automated and relies on additional cephalometric measure-ments and the experience of the surgeon. We propose an alternative representation of the infant's head shape created from 3D photogrammetric surface scans as 2D distance maps. Those 2D distance maps rely on ray casting to extract distances from a center point to the head surface, arranging them into a 2D image grid. We use the distance map for an original convolutional neural network (CNN)-based classification approach, which is evaluated on a publicly available synthetic dataset for benchmarking and also tested on clinical data. Qualitative differences of different head shapes can be ob-served in the distance maps. The CNN-based classifier achieves accuracies of 100 % on the publicly available synthetic dataset and 98.86 % on the clinical test set. Our distance map approach demonstrates the diagnostic value of 3D photogrammetry and the possibility of automatic, CNN-based diagnosis. Future steps include the improvement of the mapping method and testing the CNN on more pathologies.

A Radiation-Free Classification Pipeline for Craniosynostosis Using Statistical Shape Modeling.

BACKGROUND: Craniosynostosis is a condition caused by the premature fusion of skull sutures, leading to irregular growth patterns of the head. Three-dimensional photogrammetry is a radiation-free alternative to the diagnosis using computed tomography. While statistical shape models have been proposed to quantify head shape, no shape-model-based classification approach has been presented yet. METHODS: We present a classification pipeline that enables an automated diagnosis of three types of craniosynostosis. The pipeline is based on a statistical shape model built from photogrammetric surface scans. We made the model and pathology-specific submodels publicly available, making it the first publicly available craniosynostosis-related head model, as well as the first focusing on infants younger than 1.5 years. To the best of our knowledge, we performed the largest classification study for craniosynostosis to date. RESULTS: Our classification approach yields an accuracy of 97.8 %, comparable to other state-of-the-art methods using both computed tomography scans and stereophotogrammetry. Regarding the statistical shape model, we demonstrate that our model performs similar to other statistical shape models of the human head. CONCLUSION: We present a state-of-the-art shape-model-based classification approach for a radiation-free diagnosis of craniosynostosis. Our publicly available shape model enables the assessment of craniosynostosis on realistic and synthetic data.

Reducing Line-of-Block Artifacts in Cardiac Activation Maps Estimated Using ECG Imaging: A Comparison of Source Models and Estimation Methods.

OBJECTIVE: To investigatecardiac activation maps estimated using electrocardiographic imaging and to find methods reducing line-of-block (LoB) artifacts, while preserving real LoBs. METHODS: Body surface potentials were computed for 137 simulated ventricular excitations. Subsequently, the inverse problem was solved to obtain extracellular potentials (EP) and transmembrane voltages (TMV). From these, activation times (AT) were estimated using four methods and compared to the ground truth. This process was evaluated with two cardiac mesh resolutions. Factors contributing to LoB artifacts were identified by analyzing the impact of spatial and temporal smoothing on the morphology of source signals. RESULTS: AT estimation using a spatiotemporal derivative performed better than using a temporal derivative. Compared to deflection-based AT estimation, correlation-based methods were less prone to LoB artifacts but performed worse in identifying real LoBs. Temporal smoothing could eliminate artifacts for TMVs but not for EPs, which could be linked to their temporal morphology. TMVs led to more accurate ATs on the septum than EPs. Mesh resolution had anegligible effect on inverse reconstructions, but small distances were important for cross-correlation-based estimation of AT delays. CONCLUSION: LoB artifacts are mainly caused by the inherent spatial smoothing effect of the inverse reconstruction. Among the configurations evaluated, only deflection-based AT estimation in combination with TMVs and strong temporal smoothing can prevent LoB artifacts, while preserving real LoBs. SIGNIFICANCE: Regions of slow conduction are of considerable clinical interest and LoB artifacts observed in non-invasive ATs can lead to misinterpretations. We addressed this problem by identifying factors causing such artifacts.

3D-Guided Face Manipulation of 2D Images for the Prediction of Post-Operative Outcome After Cranio-Maxillofacial Surgery.

Cranio-maxillofacial surgery often alters the aesthetics of the face which can be a heavy burden for patients to decide whether or not to undergo surgery. Today, physicians can predict the post-operative face using surgery planning tools to support the patient's decision-making. While these planning tools allow a simulation of the post-operative face, the facial texture must usually be captured by another 3D texture scan and subsequently mapped on the simulated face. This approach often results in face predictions that do not appear realistic or lively looking and are therefore ill-suited to guide the patient's decision-making. Instead, we propose a method using a generative adversarial network to modify a facial image according to a 3D soft-tissue estimation of the post-operative face. To circumvent the lack of available data pairs between pre- and post-operative measurements we propose a semi-supervised training strategy using cycle losses that only requires paired open-source data of images and 3D surfaces of the face's shape. After training on "in-the-wild" images we show that our model can realistically manipulate local regions of a face in a 2D image based on a modified 3D shape. We then test our model on four clinical examples where we predict the post-operative face according to a 3D soft-tissue prediction of surgery outcome, which was simulated by a surgery planning tool. As a result, we aim to demonstrate the potential of our approach to predict realistic post-operative images of faces without the need of paired clinical data, physical models, or 3D texture scans.

Comparison of Activation Times Estimation for Potential-Based ECG Imaging.

Activation times (AT) describe the sequence of cardiac depolarization and represent one of the most important parameters for analysis of cardiac electrical activity. However, estimation of ATs can be challenging due to multiple sources of noise such as fractionation or baseline wander. If ATs are estimated from signals reconstructed using electrocardiographic imaging (ECGI), additional problems can arise from over-smoothing or due to ambiguities in the inverse problem. Often, resulting AT maps show falsely homogeneous regions or artificial lines of block. As ATs are not only important clinically, but are also commonly used for evaluation of ECGI methods, it is important to understand where these errors come from. We present results from a community effort to compare methods for AT estimation on a common dataset of simulated ventricular pacings. ECGI reconstructions were performed using three different surface source models: transmembrane voltages, epi-endo potentials and pericardial potentials, all using 2nd-order Tikhonov and 6 different regularization parameters. ATs were then estimated by the community participants and compared to the ground truth. While the pacing site had the largest effect on AT correlation coefficients (CC larger for lateral than for septal pacings), there were also differences between methods and source models that were poorly reflected in CCs. Results indicate that artificial lines of block are most severe for purely temporal methods. Compared to the other source models, ATs estimated from transmembrane voltages are more precise and less prone to artifacts.