Accurate compensation of brain deformation is critical for reliable image-guided neurosurgery. Surgical manipulation and tumor resection induce tissue motion, causing preoperative planning images to become misaligned with the intraoperative anatomy. In this review, we examine data-driven methods developed between 2020 and 2025 for brain deformation registration and modeling, with a particular focus on learning-based approaches. A comprehensive literature search was conducted in PubMed, IEEE Xplore, Scopus, and Web of Science using predefined inclusion and exclusion criteria for computational methods addressing brain deformation in neurosurgical imaging, resulting in 46 eligible studies. We provide a unified analysis of methodological strategies, including deep learning-based image registration, direct deformation field regression, synthesis-driven multimodal alignment, resection-aware architectures for handling missing correspondences, and hybrid models integrating biomechanical priors. We also examine dataset utilization, evaluation metrics, validation protocols, and the assessment of uncertainty and generalization across studies. While learning-based methods demonstrate promising accuracy and computational efficiency, current approaches remain limited by out-of-distribution robustness, standardized benchmarking, interpretability, and readiness for clinical deployment. Our review highlights these gaps and outlines future directions toward more robust, generalizable, and clinically translatable solutions for neurosurgical guidance. By organizing recent advances and critically assessing evaluation practices, this work provides a comprehensive reference for researchers and clinicians working on data-driven registration and modeling of brain deformation.

We propose a deep mixture of multimodal hierarchical variational auto-encoders called MMHVAE that synthesizes missing images from observed images in different modalities. MMHVAE's design focuses on tackling four challenges: (i) creating a complex latent representation of multimodal data to generate high-resolution images; (ii) encouraging the variational distributions to estimate the missing information needed for cross-modal image synthesis; (iii) learning to fuse multimodal information in the context of missing data; (iv) leveraging dataset-level information to handle incomplete data sets at training time. Extensive experiments are performed on the challenging problem of pre-operative brain multi-parametric magnetic resonance and intra-operative ultrasound imaging.

We introduce MHVAE, a deep hierarchical variational autoencoder (VAE) that synthesizes missing images from various modalities. Extending multi-modal VAEs with a hierarchical latent structure, we introduce a probabilistic formulation for fusing multi-modal images in a common latent representation while having the flexibility to handle incomplete image sets as input. Moreover, adversarial learning is employed to generate sharper images. Extensive experiments are performed on the challenging problem of joint intra-operative ultrasound (iUS) and Magnetic Resonance (MR) synthesis. Our model outperformed multi-modal VAEs, conditional GANs, and the current state-of-the-art unified method (ResViT) for synthesizing missing images, demonstrating the advantage of using a hierarchical latent representation and a principled probabilistic fusion operation. Our code is publicly available.

Lung ultrasound (LUS) is an important imaging modality used by emergency physicians to assess pulmonary congestion at the patient bedside. B-line artifacts in LUS videos are key findings associated with pulmonary congestion. Not only can the interpretation of LUS be challenging for novice operators, but visual quantification of B-lines remains subject to observer variability. In this work, we investigate the strengths and weaknesses of multiple deep learning approaches for automated B-line detection and localization in LUS videos. We curate and publish,BEDLUS, a new ultrasound dataset comprising 1,419 videos from 113 patients with a total of 15,755 expert-annotated B-lines. Based on this dataset, we present a benchmark of established deep learning methods applied to the task of B-line detection. To pave the way for interpretable quantification of B-lines, we propose a novel “single-point” approach to B-line localization using only the point of origin. Our results show that (a) the area under the receiver operating characteristic curve ranges from 0.864 to 0.955 for the benchmarked detection methods, (b) within this range, the best performance is achieved by models that leverage multiple successive frames as input, and (c) the proposed single-point approach for B-line localization reaches an F$_{1}$-score of 0.65, performing on par with the inter-observer agreement. The dataset and developed methods can facilitate further biomedical research on automated interpretation of lung ultrasound with the potential to expand the clinical utility.

Creating 3D computer models is a difficult, time consuming task. Existing systems capable of providing detailed, expressive models of sufficient quality for Hollywood or CAD can be labor intensive and complex, thus limiting creativity and the availability of good 3D models. During the past few years, several systems have been presented that address some of these limitations by using distance fields to represent and create models. The author presents the latest advancements to the Kizamu system and several new design paradigms that can make use of distance fields for creating and editing 3D geometry.

This paper presents Kizamu, a computer-based sculpting system for creating digital characters for the entertainment industry. Kizamu incorporates a blend of new algorithms, significant technical advances, and novel user interaction paradigms into a system that is both powerful and unique.

Adaptively Sampled Distance Fields (ADFs) are a unifying representation of shape that integrate numerous concepts in computer graphics including the representation of geometry and volume data and a broad range of processing operations such as rendering, sculpting, level-of-detail management, surface offsetting, collision detection, and color gamut correction. Its structure is uncomplicated and direct, but is especially effective for quality reconstruction of complex shapes, e.g., artistic and organic forms, precision parts, volumes, high order functions, and fractals. We characterize one implementation of ADFs, illustrating its utility on two diverse applications: 1) artistic carving of fine detail, and 2) representing and rendering volume data and volumetric effects. Other applications are briefly presented.

In volume graphics, objects are represented by arrays or clusters of sampled 3D data. A volumetric object representation is necessary in computer modeling whenever interior structure affects an object's behavior or appearance. However, existing volumetric representations are not sufficient for modeling the behaviors expected in applications such as surgical simulation, where interactions between both rigid and deformable objects and the cutting, tearing, and repairing of soft tissues must be modeled in real time. Three-dimensional voxel arrays lack the sense of connectivity needed for complex object deformation, while finite element models and mass-spring systems require substantially reduced geometric resolution for interactivity and they can not be easily cut or carved interactively. This paper discusses a linked volume representation that enables physically realistic modeling of object interactions such as: collision detection, collision response, 3D object deformation, and interactive object modification by carving, cutting, tearing, and joining. The paper presents a set of algorithms that allow interactive manipulation of linked volumes that have more than an order of magnitude more elements and considerably more flexibility than existing methods. Implementation details, results from timing tests, and measurements of material behavior are presented.

An algorithm is presentedthatenables fast deformation of volumetric objects.Using this algorithm, rigid, defm-rnable,elastic and plastic materialscan be modeled by adjusting deformation limits for individual elements.An interactivesystem thatcombines the deformation algorithm with collision deteetion and an energy minimizing elastic relaxation step is described.Using this system, objects containing up to-125,000 elements have b deformed intem~tivelyon an-SGI Indy.-.

Article Design galleries: a general approach to setting parameters for computer graphics and animation Share on Authors: J. Marks MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MA MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MAView Profile , B. Andalman Harvard Univ. Harvard Univ.View Profile , P. A. Beardsley MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MA MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MAView Profile , W. Freeman MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MA MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MAView Profile , S. Gibson MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MA MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MAView Profile , J. Hodgins Georgia Tech. Georgia Tech.View Profile , T. Kang CMU CMUView Profile , B. Mirtich MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MA MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MAView Profile , H. Pfister MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MA MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MAView Profile , W. Ruml MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MA MERL - A Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge, MAView Profile , K. Ryall Harvard Univ. Harvard Univ.View Profile , J. Seims Univ. of Washington Univ. of WashingtonView Profile , S. Shieber Harvard Univ. Harvard Univ.View Profile Authors Info & Claims SIGGRAPH '97: Proceedings of the 24th annual conference on Computer graphics and interactive techniquesAugust 1997 Pages 389–400https://doi.org/10.1145/258734.258887Online:03 August 1997Publication History 346citation2,992DownloadsMetricsTotal Citations346Total Downloads2,992Last 12 Months156Last 6 weeks16 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

We present a new approach to radiosity simulation that uses perceptually‐based measures to control the generation of view‐independent radiosity solutions. This enables computational effort to be moved away from areas that are deemed to have a visually insignificant effect on the solution's appearance, into those that are more noticeable. We achieve this with an a‐priori estimate of the real‐world adaptation luminance, and use a tone‐reproduction operator to transform luminance values to display colours during the solution process. The distance between two colours in a perceptually‐uniform colour space is then used as a numerical measure of their perceived difference. We describe an oracle that stops patch refinement once the difference between successive levels of elements becomes perceptually unnoticeable. We also show how the perceived importance of any potential shadow falling across a receiving element can be determined. This is then used to control the number of rays that are cast during visibility computations, giving reductions of almost 93% in the total number of rays required for a solution without any significant loss in image quality. Finally, we discuss how perceptual knowledge can be used to optimise the element mesh for faster interactive display and to save memory during computation.