https://arxiv.org/api/dwhVbShzlybn0bNlppcv+Dbqz14 2026-09-18T20:59:14Z 25 15 0 http://arxiv.org/abs/2608.16535v1 2026-08-17T13:11:48Z

Manual cephalometric landmark annotation is important for craniofacial assessment but is labor-intensive and difficult to scale. We introduce CephViT, a Vision Transformer-based model for automated 2D lateral cephalometric landmark localization, and evaluate its use in downstream skeletal malocclusion classification. CephViT was trained and benchmarked on a public lateral cephalogram dataset, achieving a mean radial error of 1.28 +/- 1.42 mm and a successful detection rate of 92.0% at 3.0 mm. Because the private evaluation cohort consisted of 3D CBCT scans, lateral cephalogram-like digitally reconstructed radiographs (DRRs) were generated from each volume and used as 2D inputs to the landmark localization model. Landmark coordinates were normalized into a common coordinate frame, and skeletal malocclusion classification was performed using landmarks shared between the reference and DRR-based pipelines. Classification performance using DRR-localized landmarks was comparable to that obtained using manually annotated reference landmarks, with accuracies of 70.0% and 68.3%, respectively. These results support the feasibility of automated cephalometric analysis on CBCT-derived DRRs for skeletal malocclusion assessment.

2026-08-17T13:11:48Z Accepted for presentation at the ODIN 2026 Workshop, held in conjunction with MICCAI 2026 Benjamin Hou Konstantinia Almpani Janice S. Lee Zhiyong Lu http://arxiv.org/abs/2606.19867v4 2026-09-09T10:49:42Z

Computed Tomography (CT) is essential for diagnosing pediatric craniofacial abnormalities, yet poses radiation risks to developing anatomies. Reconstructing 3D CT from sparse bi-planar X-rays offers a low-dose alternative but is severely ill-posed. Existing methods employ geometry-agnostic feature lifting, naively projecting 2D features into 3D without explicit spatial modeling, causing depth ambiguity and degraded osseous boundaries. We present PSCT-Net, a geometry-aware framework with differentiable back-projection. Differentiable back-projection establishes a spatially faithful volumetric prior, alleviating depth ambiguity. An Attention-Guided Projection (AGP-3D) module then learns non-linear voxel-wise correspondences between 2D regions and 3D locations. A Bidirectional Mamba (BiM-3D) module captures long-range volumetric dependencies with linear complexity. We further curate a private institutional pediatric skull CT cohort, PedSkull-CT, comprising normal and pathological cases for internal evaluation, addressing the gap in adult-centric, trunk-focused datasets. Project page and code are available at https://dydevelop.github.io/PSCT-Net/.

2026-06-18T07:26:32Z Accepted for publication at the 29th International Conference on Medical Image Computing and Computer-Assisted Intervention PedAItrics Workshop (MICCAIw 2026) Dong Yeong Kim Jaewon Choi Youmin Shin JunGyu Lee Myeongseop Kim Jinwook Choi Joo Whan Kim Young-Gon Kim http://arxiv.org/abs/2606.16573v1 2026-06-15T11:19:10Z

This work addresses the computational problem of generating reproducible projection-space observations from heterogeneous anatomical scenes whose components may undergo independent spatial transformations. We propose a transformation-driven framework for synthetic projection imaging from multimodal anatomical data and demonstrate it on mandibular-motion scenarios. In contrast to conventional Digitally Reconstructed Radiograph (DRR) approaches primarily designed for registration, projection realism, or rendering efficiency, the proposed formulation treats projection imaging as an observation process operating on an explicitly represented anatomical scene. Independently transformable volumetric and surface-based anatomical objects are embedded within a shared scene representation and propagated directly into projection space through explicit transformations. Projection geometry, acquisition modelling, material interpretation, and image presentation remain explicitly separated, enabling controlled exploration of methodological assumptions while preserving reproducibility and direct comparability between generated projections. Particular emphasis is placed on transformation-driven anatomical scenarios relevant to craniofacial analysis, including mandibular motion and therapeutic repositioning. Using a shared anatomical reference scene composed of CT/CBCT volumes, segmented structures, surface models, and auxiliary anatomical or therapeutic objects, the framework enables generation of directly comparable VirtualRTG projections from multiple anatomical configurations while preserving identical imaging assumptions. Rather than aiming at fully physically faithful radiographic simulation, the proposed approach provides a controllable and reproducible methodological environment for studying anatomy--projection relationships, motion observability, and transformation-aware imaging workflows.

2026-06-15T11:19:10Z 36 pages, 11 figures Dariusz Pojda Krzysztof Domino Michał Tarnawski Agnieszka Anna Tomaka http://arxiv.org/abs/2606.09699v1 2026-06-08T16:20:35Z

The state-of-the-art generative models, such as CycleGAN, Pix2Pix, and diffusion models have demonstrated remarkable performance in the face generation task. However, they fail to effectively capture cross-modality semantic information in craniofacial reconstruction when translating from the skull (x-ray) to the face (optical) domain, due to a mismatch in the alignment of structural identity across modalities. To address this issue, we propose Cranio-Diff, a diffusion-based framework for cross-domain cranio-facial reconstruction from 2D X-ray skull images. The proposed approach integrates skull-conditioned structural guidance through ControlNet with biometric text conditioning to generate a face which is more semantically and structurally aligned with the given skull. The proposed Cranio-diff method is evaluated on skull-face dataset obtained from X-ray scans of 120 subjects in lateral and frontal views. To enable controlled evaluation, each face image is synthesised across three age groups (25, 45, 65) and three BMI variations of -10%, baseline and +10%, yielding 4320 paired samples. To the best of our knowledge, this is the only X-ray-face dataset with this magnitude. Extensive experiments showed that the proposed method outperforms recent existing approaches in both generated image quality and retrieval task. Finally, to evaluate the performance of our proposed method, we have evaluated the quality of the generated image using FID, IS, SSIM, LPIPS, PSNR and ArcFace score. Additionally, retrieval performance is evaluated using recall@k, mAP@k and MRR@k. Obtained experimental results demonstrate that the proposed method can be used as an alternate tool in providing aid in forensic investigations.

2026-06-08T16:20:35Z 14 pages, 7 figures, BMVC 2026 conference Ravi Shankar Prasad Naresh Gurjar Shashank Baghel Chirag Dinesh Singh http://arxiv.org/abs/2605.20827v1 2026-05-20T07:20:56Z

Panoramic radiograph (PR) is fundamentally used in routine dental care, but it inherently provides only a two-dimensional (2D) projection of complex three-dimensional (3D) craniofacial anatomy. Most existing learning-based methods attempt to computationally recover this 3D information by directly regressing native cone-beam computed tomography (CBCT) volumes from PR. However, this direct mapping requires the model to simultaneously learn common anatomical structures and patient-specific morphological variations. This entangled formulation makes the ill-posed 2D-to-3D inverse problem highly ambiguous, often producing over-smoothed reconstructions with blurred anatomical boundaries. To address this, we propose HyDAR-Pano3D, a two-stage framework that reformulates PR-to-CBCT reconstruction as a disentangled anatomical recovery problem. In Stage 1, a dual-encoder network integrates radiographic features with SAM-derived semantic priors to reconstruct an arch-normalized canonical volume. In Stage 2, an Anatomical Restoration Network predicts a prior-constrained structured deformation field to map this canonical volume back to the native space, restoring individual morphological variations. Experiments on three large-scale datasets show that HyDAR-Pano3D significantly outperforms baseline methods ($p < 0.05$), achieving a 25.76 dB PSNR, 85.70\% SSIM, and an 83.83\% overall anatomical Dice score. The synthesized volumes successfully support downstream segmentation of whole teeth (82.4\% Dice) and the inferior alveolar canal (72.2\% Dice), demonstrating that our disentangled approach preserves clinically relevant structures to enable robust anatomy-aware assessment when CBCT data is unavailable.

2026-05-20T07:20:56Z 10 pages Yaoyao Yue Jérôme Schmid Xiaoshuang Li Eduardo Delamare Jinman Kim http://arxiv.org/abs/2602.13535v1 2026-02-14T00:22:03Z

Metallic plating systems composed of titanium and its alloys remain the standard treatment for craniofacial bony fixation but may require secondary removal due to infection, implant migration, or discomfort. Thus, biodegradable metallic implants may eliminate complications and secondary procedures while maintaining structural integrity. Our previous work demonstrated the fabrication of immiscible Fe-AZ31 composites via additive manufacturing with improved degradation kinetics over pure Iron. This study aimed to evaluate the in vitro and in vivo biocompatibility of Fe-AZ31 composites for potential craniofacial fixation applications. Pure iron (Fe), Mg alloy (AZ31) and Fe-AZ31 samples were fabricated for extract-based cytotoxicity testing using HFF-1 fibroblasts, L929 fibroblasts and hFOB osteoblasts. Metal extracts were prepared at a 3 cm^2/mL surface-to-volume ratio in complete media at 37C and cell viability was measured by live/dead assay after 24 and 72h exposure. For in vivo evaluation, Fe-AZ31, Fe, and Ti plates were implanted subcutaneously in wild type mice for 6 weeks, 3 and 6 months. Implant degradation, histologic response, hematology, and serum biochemistry were assessed. Fe-AZ31 extracts demonstrated >70% cell viability across all cell types at both timepoints with normal cell morphology and adhesion, whereas AZ31 extracts caused marked cytotoxicity associated with pronounced alkalization (pH 10). In vivo, Fe-AZ31 implants exhibited gradual surface corrosion accompanied by mild, transient inflammation and minimal capsule formation over time. No systemic toxicity was observed. Hematology and serum biochemistry remained within physiological limits. Additively manufactured Fe-AZ31 composites demonstrate acceptable biocompatibility and favorable tissue responses, supporting their development as resorbable metallic fixation devices for craniofacial reconstruction.

2026-02-14T00:22:03Z Xue Dong Samuel Medina Sai Pratyush Akula Abby Chopoorian Fuchsman Matthew W. Liao Sophia Salingaros Atieh Moridi Jason A. Spector http://arxiv.org/abs/2512.19560v1 2025-12-22T16:42:58Z

Early detection of developmental disorders can be aided by analyzing infant craniofacial morphology, but modeling infant faces is challenging due to limited data and frequent spontaneous expressions. We introduce BabyFlow, a generative AI model that disentangles facial identity and expression, enabling independent control over both. Using normalizing flows, BabyFlow learns flexible, probabilistic representations that capture the complex, non-linear variability of expressive infant faces without restrictive linear assumptions. To address scarce and uncontrolled expressive data, we perform cross-age expression transfer, adapting expressions from adult 3D scans to enrich infant datasets with realistic and systematic expressive variants. As a result, BabyFlow improves 3D reconstruction accuracy, particularly in highly expressive regions such as the mouth, eyes, and nose, and supports synthesis and modification of infant expressions while preserving identity. Additionally, by integrating with diffusion models, BabyFlow generates high-fidelity 2D infant images with consistent 3D geometry, providing powerful tools for data augmentation and early facial analysis.

2025-12-22T16:42:58Z Antonia Alomar Mireia Masias Marius George Linguraru Federico M. Sukno Gemma Piella http://arxiv.org/abs/2512.05920v1 2025-12-05T17:56:44Z

Orthognathic surgery is a crucial intervention for correcting dentofacial skeletal deformities to enhance occlusal functionality and facial aesthetics. Accurate postoperative facial appearance prediction remains challenging due to the complex nonlinear interactions between skeletal movements and facial soft tissue. Existing biomechanical, parametric models and deep-learning approaches either lack computational efficiency or fail to fully capture these intricate interactions. To address these limitations, we propose Neural Implicit Craniofacial Model (NICE) which employs implicit neural representations for accurate anatomical reconstruction and surgical outcome prediction. NICE comprises a shape module, which employs region-specific implicit Signed Distance Function (SDF) decoders to reconstruct the facial surface, maxilla, and mandible, and a surgery module, which employs region-specific deformation decoders. These deformation decoders are driven by a shared surgical latent code to effectively model the complex, nonlinear biomechanical response of the facial surface to skeletal movements, incorporating anatomical prior knowledge. The deformation decoders output point-wise displacement fields, enabling precise modeling of surgical outcomes. Extensive experiments demonstrate that NICE outperforms current state-of-the-art methods, notably improving prediction accuracy in critical facial regions such as lips and chin, while robustly preserving anatomical integrity. This work provides a clinically viable tool for enhanced surgical planning and patient consultation in orthognathic procedures.

2025-12-05T17:56:44Z Jiawen Yang Yihui Cao Xuanyu Tian Yuyao Zhang Hongjiang Wei http://arxiv.org/abs/2509.24577v1 2025-09-29T10:34:13Z

Building a joint face-skull morphable model holds great potential for applications such as remote diagnostics, surgical planning, medical education, and physically based facial simulation. However, realizing this vision is constrained by the scarcity of paired face-skull data, insufficient registration accuracy, and limited exploration of reconstruction and clinical applications. Moreover, individuals with craniofacial deformities are often overlooked, resulting in underrepresentation and limited inclusivity. To address these challenges, we first construct a dataset comprising over 200 samples, including both normal cases and rare craniofacial conditions. Each case contains a CT-based skull, a CT-based face, and a high-fidelity textured face scan. Secondly, we propose a novel dense ray matching registration method that ensures topological consistency across face, skull, and their tissue correspondences. Based on this, we introduce the 3D Bidirectional Face-Skull Morphable Model (BFSM), which enables shape inference between the face and skull through a shared coefficient space, while also modeling tissue thickness variation to support one-to-many facial reconstructions from the same skull, reflecting individual changes such as fat over time. Finally, we demonstrate the potential of BFSM in medical applications, including 3D face-skull reconstruction from a single image and surgical planning prediction. Extensive experiments confirm the robustness and accuracy of our method. BFSM is available at https://github.com/wang-zidu/BFSM

2025-09-29T10:34:13Z Under review Zidu Wang Meng Xu Miao Xu Hengyuan Ma Jiankuo Zhao Xutao Li Xiangyu Zhu Zhen Lei http://arxiv.org/abs/2508.18031v2 2026-06-20T11:40:58Z

Craniofacial reconstruction in forensics is one of the processes to identify victims of crime and natural disasters. Identifying an individual from their remains plays a crucial role when all other identification methods fail. Traditional methods for this task, such as clay-based craniofacial reconstruction, require expert domain knowledge and are a time-consuming process. At the same time, other probabilistic generative models like the statistical shape model or the Basel face model fail to capture the skull and face cross-domain attributes. Looking at these limitations, we propose a generic framework for craniofacial reconstruction from 2D X-ray images. Here, we used various generative models (i.e., CycleGANs, cGANs, etc) and fine-tune the generator and discriminator parts to generate more realistic images in two distinct domains, which are the skull and face of an individual. This is the first time where 2D X-rays are being used as a representation of the skull by generative models for craniofacial reconstruction. We have evaluated the quality of generated faces using FID, IS, and SSIM scores. Finally, we have proposed a retrieval framework where the query is the generated face image and the gallery is the database of real faces. By experimental results, we have found that these generative models can be used as an assisting tool for craniofacial identifications in forensic science.

2025-08-25T13:52:59Z 15 pages, 20 figures Ravi Shankar Prasad Dinesh Singh http://arxiv.org/abs/2507.08329v1 2025-07-11T05:49:12Z

Craniofacial reconstruction in forensic science is crucial for the identification of the victims of crimes and disasters. The objective is to map a given skull to its corresponding face in a corpus of faces with known identities using recent advancements in computer vision, such as deep learning. In this paper, we presented a framework for the identification of a person given the X-ray image of a skull using convolutional Siamese networks for cross-domain identity representation. Siamese networks are twin networks that share the same architecture and can be trained to discover a feature space where nearby observations that are similar are grouped and dissimilar observations are moved apart. To do this, the network is exposed to two sets of comparable and different data. The Euclidean distance is then minimized between similar pairs and maximized between dissimilar ones. Since getting pairs of skull and face images are difficult, we prepared our own dataset of 40 volunteers whose front and side skull X-ray images and optical face images were collected. Experiments were conducted on the collected cross-domain dataset to train and validate the Siamese networks. The experimental results provide satisfactory results on the identification of a person from the given skull.

2025-07-11T05:49:12Z 7 pages, 12 figures, Pattern Recognition Letters Ravi Shankar Prasad Dinesh Singh http://arxiv.org/abs/2101.04303v2 2021-03-17T21:58:11Z

Craniomaxillofacial reconstruction with patient-specific customized craniofacial implants (CCIs) is most commonly performed for large-sized skeletal defects. Because the exact size of skull resection may not be known prior to the surgery, in the single-stage cranioplasty, a large CCI is prefabricated and resized intraoperatively with a manual-cutting process provided by a surgeon. The manual resizing, however, may be inaccurate and significantly add to the operating time. This paper introduces a fast and non-contact approach for intraoperatively determining the exact contour of the skull resection and automatically resizing the implant to fit the resection area. Our approach includes four steps: First, a patient's defect information is acquired by a 3D scanner. Second, the scanned defect is aligned to the CCI by registering the scanned defect to the reconstructed CT model. Third, a cutting toolpath is generated from the contour of the scanned defect. Lastly, the large CCI is resized by a cutting robot to fit the resection area according to the given toolpath. To evaluate the resizing performance of our method, six different resection shapes were used in the cutting experiments. We compared the performance of our method to the performances of surgeon's manual resizing and an existing technique which collects the defect contour with an optical tracking system and projects the contour on the CCI to guide the manual modification. The results show that our proposed method improves the resizing accuracy by 56% compared to the surgeon's manual modification and 42% compared to the projection method.

2021-01-12T05:36:43Z Submitted to ICRA 2021 Shuya Liu Wei-Lun Huang Chad Gordon Mehran Armand http://arxiv.org/abs/1911.08008v2 2020-02-19T23:23:21Z

Three-dimensional Morphable Models (3DMMs) are powerful statistical tools for representing the 3D shapes and textures of an object class. Here we present the most complete 3DMM of the human head to date that includes face, cranium, ears, eyes, teeth and tongue. To achieve this, we propose two methods for combining existing 3DMMs of different overlapping head parts: i. use a regressor to complete missing parts of one model using the other, ii. use the Gaussian Process framework to blend covariance matrices from multiple models. Thus we build a new combined face-and-head shape model that blends the variability and facial detail of an existing face model (the LSFM) with the full head modelling capability of an existing head model (the LYHM). Then we construct and fuse a highly-detailed ear model to extend the variation of the ear shape. Eye and eye region models are incorporated into the head model, along with basic models of the teeth, tongue and inner mouth cavity. The new model achieves state-of-the-art performance. We use our model to reconstruct full head representations from single, unconstrained images allowing us to parameterize craniofacial shape and texture, along with the ear shape, eye gaze and eye color.

2019-11-18T23:58:34Z 18 pages, 18 figures, submitted to Transactions on Pattern Analysis and Machine Intelligence (TPAMI) on the 9th of October as an extension paper of the original oral CVPR paper : arXiv:1903.03785 Stylianos Ploumpis Evangelos Ververas Eimear O' Sullivan Stylianos Moschoglou Haoyang Wang Nick Pears William A. P. Smith Baris Gecer Stefanos Zafeiriou http://arxiv.org/abs/1801.05694v1 2018-01-17T14:54:39Z

CBCT images suffer from acute shading artifacts primarily due to scatter. Numerous image-domain correction algorithms have been proposed in the literature that use patient-specific planning CT images to estimate shading contributions in CBCT images. However, in the context of radiosurgery applications such as gamma knife, planning images are often acquired through MRI which impedes the use of polynomial fitting approaches for shading correction. We present a new shading correction approach that is independent of planning CT images. Our algorithm is based on the assumption that true CBCT images follow a uniform volumetric intensity distribution per material, and scatter perturbs this uniform texture by contributing cupping and shading artifacts in the image domain. The framework is a combination of fuzzy C-means coupled with a neighborhood regularization term and Otsu's method. Experimental results on artificially simulated craniofacial CBCT images are provided to demonstrate the effectiveness of our algorithm. Spatial non-uniformity is reduced from 16% to 7% in soft tissue and from 44% to 8% in bone regions. With shading-correction, thresholding based segmentation accuracy for bone pixels is improved from 85% to 91% when compared to thresholding without shading-correction. The proposed algorithm is thus practical and qualifies as a plug and play extension into any CBCT reconstruction software for shading correction.

2018-01-17T14:54:39Z 15 pages, published in CMBEBIH 2017 Proceedings of the International Conference on Medical and Biological Engineering 2017 Awais Ashfaq Jonas Adler 10.1007/978-981-10-4166-2_81 http://arxiv.org/abs/physics/0610167v1 2006-10-21T18:20:56Z

The aim of craniofacial reconstruction is to produce a likeness of a face from the skull. Few works in computerized assisted facial reconstruction have been done in the past, due to poor machine performances and data availability, and major works are manually reconstructions. In this paper, we present an approach to build 3D statistical models of the skull and the face with soft tissues from the skull of one individual. Results on real data are presented and seem promising.

2006-10-21T18:20:56Z Proceedings of the Fourth International Symposium on Image and Signal Processing and Analysis ISPA'2005 IEEE (Ed.) (2005) 365-370 Maxime Berar LIS Michel Desvignes LIS Gérard Bailly ICP Yohan Payan TIMC - IMAG