Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “multimodal data”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4Linked to original sources
PubMed2004

Dyslexia: the possible benefit of multimodal integration of fMRI- and EEG-data.

Biological research about dyslexia has been conducted using various neuroimaging methods like functional Magnetic Resonance Imaging (fMRI) or Electroencephalography (EEG). Since language functions are characterized by both distributed network activities and speed of processing within milliseconds, high temporal as well as high spatial resolution of activation profiles are of interest: "where" can dyslexia specific activations be detected and "when" do language processes start to diverge between dyslexics and controls? Due to the network character of language processing, fMRI-constrained distributed source models based on EEG-data were computed for multimodal data integration. First single-case results show that this method could be a promising approach for the understanding of a repeatedly described experimental finding for dyslexia like that of an overactivation in inferior frontal language areas. Multimodal data analysis for the subjects presented here could probably demonstrate that inferior frontal overactivations are the consequence of a phonological deficit and could represent ongoing articulation processes used to solve phonologically challenging tasks.

Adolescent↗
PubMed1996

Statistics for investigation of multimodal MR imaging data and an application to multiple sclerosis patients.

Magnetic resonance spectroscopy can image axonal damage specifically based on changes in N-acetyl aspartate (NAA), a neuronal marker. We have developed statistical methods for multimodal analysis of MR spectroscopic images. These methods, which are extensions of mixed-effect models, have allowed us to quantify differences in images from different subgroups of patients with multiple sclerosis (MS) and to determine the dependence of chemical pathology on clinical disability, duration of disease and lesions on T2-weighted MRI. Statistical power was improved by using all reliable resonance intensities in the spectroscopic images while taking into consideration the intra-subject correlations. We studied 17 normal subjects, 14 patients with relapsing remitting (RR) MS and 21 patients with chronic progressive (CP) MS. The ratio of resonance intensities of N-acetylaspartate over creatine (Cr) was found to be significantly lower than normal in normal appearing white matter (NAWM) of both RR and CP patients (19.6% in RR, 28.8% in CP), NAA/Cr was decreased even more in MS plaques than in NAWM (44.2% in RR, 17.7% in CP), NAA/Cr was correlated with clinical disability (p < 0.02) and disease duration (p < 0.1). Our results suggest that, in this setting, MRS reflects accumulated neuronal loss or damage and can be used as a measure of disease severity. The methods developed provide opportunities to evaluate the relationship between inflammation, demyelination, axonal loss and clinical disability in future studies.

Aspartic Acid↗
PubMed2004

Managing atypical antipsychotic-associated weight gain: 12-month data on a multimodal weight control program.

BACKGROUND: The purpose of this study was to test prospectively the feasibility and efficacy of a multimodal weight control program for over-weight and obese severely mentally ill adults who had gained weight while taking atypical antipsychotic medications. METHOD: Thirty-one subjects with schizophrenia or schizoaffective disorder (DSM-IV), on treatment with atypical antipsychotics, participated in a 52-week, multimodal weight control program that incorporated nutrition, exercise, and behavioral interventions. The primary outcomes were measures of body mass index (BMI) and weight. A variety of secondary outcomes, including hemoglobin A(1c) level, systolic and diastolic blood pressure, and cholesterol level, were compared from baseline to endpoint. Weight and BMI changes in the intervention group were also compared with changes in 20 nonintervention patients ("usual care" group) who were contemporaneously treated in the same clinics. RESULTS: Twenty of the 31 subjects in the intervention group completed the program. Statistically significant pre-post improvements in weight (p <.02), BMI (p <.02), hemoglobin A(1c) levels (p <.001), diastolic (p <.001) and systolic (p <.05) blood pressure, exercise level (p <.003), nutrition knowledge (p <.0001), and stage of change (exercise [p <.0001] and weight [p <.008]) were seen in the intervention group. Patients attended a mean of 69% of the sessions during the year of the program. Weight and BMI also decreased significantly (p =.01) in the intervention group compared with the "usual care" group, who gained weight during the observation period. CONCLUSIONS: Individuals with schizophrenia and schizoaffective disorder were willing to attend, and benefited from, a weight control program that focused on nutrition, exercise, and motivation. The program resulted in clinically significant reductions in weight, BMI, and other risk factors for long-term poor health, including hemoglobin A(1c). In contrast, patients who did not receive the weight control intervention continued to gain weight.

Adult↗
PubMed2004

A 3D interactive multimodal viewer as data mining tool for the Visible Human Dataset color image histograms.

An on-line virtual three-dimensional immersive environment to navigate through colorimetric characterization of the Visible Human Dataset (VHD) cryosectional cross-section color images is introduced. Real-time analysis of color component characteristics of a user defined set of VHD images is now possible. This is a potentially useful resource to many developers working on the VHD raw data, however it could be used in medical education.

Female↗
PubMed2026

Unifying multimodal single-cell data with a mixture-of-experts &#x3b2;-variational autoencoder framework.

Multimodal single-cell assays profile complementary layers of cell state, but integration is complicated by modality mismatch, sparsity, and uneven cohort coverage. Here, we present Unified Variational Inference (UniVI), a scalable mixture-of-experts &#x3b2;-variational autoencoder that learns a shared latent space while preserving modality-specific structure. UniVI couples modality-specific encoders/decoders with a shared latent prior and a symmetric cross-modal alignment objective, enabling consistent integration of paired measurements without curated feature-link graphs or preannotated reference atlases; optional supervised heads can be added when labels are available. Across paired RNA-protein (CITE-seq) and RNA-chromatin (10x Genomics Multiome, SHARE-seq) data spanning human PBMCs and mouse back skin-a nonhematopoietic tissue with continuous differentiation hierarchies-UniVI produces coherent embeddings, improves label transfer, and enables cross-modal reconstruction and denoising. Extending to trimodal measurements, UniVI maintains robust three-way alignment among RNA, chromatin accessibility, and surface proteins (TEA-seq), and accommodates DNA methylation in a paired scNMT-seq mouse gastrulation proof-of-concept under beta-binomial likelihoods. Performance degrades gracefully under severe cell type imbalance and in the presence of modality-exclusive populations. In an acute myeloid leukemia mosaic design, a paired RNA-protein bridge anchors independent RNA-only and protein+genotype cohorts, revealing genotype-associated neighborhoods that sharpen with mutation-aware fine-tuning. UniVI thus provides a flexible, interpretable framework for multimodal integration across paired, trimodal, and mosaic study designs and supports practical reference-to-query projection in partially observed studies.

Journal Article↗
PubMed1997

Dorfman-Berbaum-Metz method for statistical analysis of multireader, multimodality receiver operating characteristic data: validation with computer simulation.

RATIONALE AND OBJECTIVES: The authors examined the relationship between the critical P value (alpha) and the empirical type I error rate when using the Dorfman-Berbaum-Metz (DMB) method for analysis of variance in multireader, multimodality receiver operating characteristic (ROC) data. METHODS: The authors developed a linear mixed-effect model to generate continuous, normally distributed random decision variables containing multiple sources (components) of variation. A range of magnitudes for these variance components was used to stimulate experiments in which multiple readers (three or five) read imaged obtained with two modalities from the same set of cases with no re-reading. Three binormal population ROC curves, with areas of 0.962, 0.855, and 0.702, were included. Case-sample sizes ranged from 50 to 400, and either 50% or 10% of cases were actually positive. For each experiment, 2,000 data sets were analyzed by the computer program, and the proportion of 2,000 modality differences that was found to be statistically significant at an alpha level of .05 was tubulated. RESULTS: The test for modality difference performed well for the low and intermediate ROC curves, even with small case samples. For the high ROC curve, the small-sample results were conservative. No relationship between observed type I error rate and the magnitude of data correlation was evident. CONCLUSION: For typical ROC curves, the DBM method is robust in testing for modality effects in the null case, given a sufficient sample size. Instructions for obtaining a free copy of the software are given.

Analysis of Variance↗
PubMed2000

A data fusion environment for multimodal and multi-informational neuronavigation.

OBJECTIVE: Part of the planning and performance of neurosurgery consists of determining target areas, areas to be avoided, landmark areas, and trajectories, all of which are components of the surgical script. Nowadays, neurosurgeons have access to multimodal medical imaging to support the definition of the surgical script. The purpose of this paper is to present a software environment developed by the authors that allows full multimodal and multi-informational planning as well as neuronavigation for epilepsy and tumor surgery. MATERIALS AND METHODS: We have developed a data fusion environment dedicated to neuronavigation around the Surgical Microscope Neuronavigator system (Carl Zeiss, Oberkochen, Germany). This environment includes registration, segmentation, 3D visualization, and interaction-applied tools. It provides the neuronavigation system with the multimodal information involved in the definition of the surgical script: lesional areas, sulci, ventricles segmented from magnetic resonance imaging (MRI), vessels segmented from magnetic resonance angiography (MRA), functional areas from magneto-encephalography (MEG), and functional magnetic resonance imaging (fMRI) for somatosensory, motor, or language activation. These data are considered to be relevant for the performance of the surgical procedure. The definition of each entity results from the same procedure: registration to the anatomical MRI data set (defined as the reference data set), segmentation, fused 3D display, selection of the relevant entities for the surgical step, encoding in 3D surface-based representation, and storage of the 3D surfaces in a file recognized by the neuronavigation software (STP 3.4, Leibinger; Freiburg, Germany). RESULTS: Multimodal neuronavigation is illustrated with two clinical cases for which multimodal information was introduced into the neuronavigation system. Lesional areas were used to define and follow the surgical path, sulci and vessels helped identify the anatomical environment of the surgical field, and, finally, MEG and fMRI functional information helped determine the position of functional high-risk areas. CONCLUSION: In this short evaluation, the ability to access preoperative multi-functional and anatomical data within the neuronavigation system was a valuable support for the surgical procedure.

Adult↗
PubMed2026

Bayesian inference of lineage trees by joint analysis of single-cell multimodal lineage-tracing data with BiLinT.

The advent of single-cell lineage-tracing technologies has enabled the simultaneous profiling of gene expression and lineage barcodes. However, accurate, high-resolution reconstruction of cell lineage trees remains challenging because most existing approaches treat these modalities separately and therefore fail to fully exploit their complementary information. Here we present BiLinT, a Bayesian framework that jointly models multimodal single-cell lineage-tracing data for lineage tree reconstruction. BiLinT integrates barcode evolution (a continuous-time Markov chain) with gene expression dynamics (an Ornstein-Uhlenbeck process) within a unified probabilistic model. Across synthetic and real data sets, BiLinT provides accurate lineage-tree reconstruction and reveals differentiation-associated clonal structure and developmental fate biases.

Journal Article↗
PubMed2025

miss-SNF: a multimodal patient similarity network integration approach to handle completely missing data sources.

MOTIVATION: Precision medicine leverages patient-specific multimodal data to improve prevention, diagnosis, prognosis, and treatment of diseases. Advancing precision medicine requires the non-trivial integration of complex, heterogeneous, and potentially high-dimensional data sources, such as multi-omics and clinical data. In the literature, several approaches have been proposed to manage missing data, but are usually limited to the recovery of subsets of features for a subset of patients. A largely overlooked problem is the integration of multiple sources of data when one or more of them are completely missing for a subset of patients, a relatively common condition in clinical practice. RESULTS: We propose miss-Similarity Network Fusion (miss-SNF), a novel general-purpose data integration approach designed to manage completely missing data in the context of patient similarity networks. miss-SNF integrates incomplete unimodal patient similarity networks by leveraging a non-linear message-passing strategy borrowed from the SNF algorithm. miss-SNF is able to recover missing patient similarities and is "task agnostic", in the sense that can integrate partial data for both unsupervised and supervised prediction tasks. Experimental analyses on nine cancer datasets from The Cancer Genome Atlas (TCGA) demonstrate that miss-SNF achieves state-of-the-art results in recovering similarities and in identifying patients subgroups enriched in clinically relevant variables and having differential survival. Moreover, amputation experiments show that miss-SNF supervised prediction of cancer clinical outcomes and Alzheimer's disease diagnosis with completely missing data achieves results comparable to those obtained when all the data are available. AVAILABILITY AND IMPLEMENTATION: miss-SNF code, implemented in R, is available at https://github.com/AnacletoLAB/missSNF.

Humans↗
PubMed2006

The multimod application framework: a rapid application development tool for computer aided medicine.

This paper describes a new application framework (OpenMAF) for rapid development of multimodal applications in computer-aided medicine. MAF applications are multimodal in data, in representation, and in interaction. The framework supports almost any type of biomedical data, including DICOM datasets, motion-capture recordings, or data from computer simulations (e.g. finite element modeling). The interactive visualization approach (multimodal display) helps the user interpret complex datasets, providing multiple representations of the same data. In addition, the framework allows multimodal interaction by supporting the simultaneous use of different input-output devices like 3D trackers, stereoscopic displays, haptics hardware and speech recognition/synthesis systems. The Framework has been designed to run smoothly even on limited power computers, but it can take advantage of all hardware capabilities. The Framework is based on a collection of portable libraries and it can be compiled on any platform that supports OpenGL, including Windows, MacOS X and any flavor of Unix/linux.

Humans↗
PubMed2026

Data-centric, robust, and explainable multimodal deep learning for clinical decision support: A systematic review.

PURPOSE: Multimodal deep learning is increasingly proposed for clinical decision support (CDS) under a "data-centric" framing that prioritizes label quality, missing-modality robustness, distribution shift, calibration, and explainability. Prior reviews have examined multimodal medical AI, CDS, and data-centric methods separately, but none address their intersection. We mapped the modalities, fusion strategies, and data-centric and explainability techniques used in this recent literature, quantified how often each is implemented rather than merely mentioned, assessed deployment-relevant evidence (external validation, clinical-outcome measurement, equity), and formally appraised study-level risk of bias. METHODS: Following the PRISMA 2020 statement (PROSPERO CRD420261427815; registered retrospectively), we screened 150 records and included primary, clinical, multimodal studies that applied machine or deep learning to a decision-support task and reported at least one quantitative result. Two reviewers screened and extracted data with consensus adjudication. Each study was coded against pre-specified operational definitions, separating implemented or empirically evaluated techniques from those only mentioned. Study-level risk of bias was assessed with PROBAST + AI. Synthesis was narrative. RESULTS: Thirty-one studies met inclusion; 30 (97%) were published between 2024 and 2026, with a median of three modalities (range 2-6), most commonly structured EHR (71%) and imaging (39%). Data-centric techniques were frequently reported (74-84% across label-noise, distribution-shift, calibration, missing-modality and class-imbalance handling; equity 61%). However, external validation was reported in only 4/31 studies (13%), a clinical or provider outcome in 3/31 (10%), and no study reported routine deployment. Overall risk of bias was high in 27/31 studies (87%), driven by the analysis domain. CONCLUSION: Within this recent, self-selected slice of the field, technical robustness and explainability techniques are widely reported but rarely validated out-of-distribution or against clinical outcomes, and the underlying evidence is at high risk of bias. Progress requires external multi-site validation, clinical-outcome measurement, formal bias appraisal, and adherence to AI reporting standards (e.g., TRIPOD + AI) before deployment can be justified.

Deep Learning↗
PubMed1993

Data fusion in medical imaging: merging multimodal and multipatient images, identification of structures and 3D display aspects.

Data fusion in medical imaging can be seen into two ways (i) multisensors fusion of anatomical and functional information and (ii) interpatient data fusion by means of warping models. These two aspects set the methodological framework necessary to perform anatomical modelling especially when concerning the modelling of brain structures. The major relevance of the work presented here concerns the interpretation of multimodal 3D neuro-anatomical data bases. Three types of data fusion problems are considered in this paper. The first one concerns the problem of data combination which includes multimodal registration (multisensor fusion applied to CT, MRI, DSA, PET, SPECT, or MEG). In particular, the problem of warping patient data to an anatomical atlas is reviewed and a solution is proposed. The second problem of data fusion addressed in this paper is the identification of anatomical structures by means of image analysis methods. Two techniques have been developed. The first one deals with the analysis of image geometrical features to end up with the determination of a fuzzy mask to label the structure of interest. The second technique consists of labelling major cerebral structures by means of statistical image features associated with relaxation techniques. Finally, the paper presents a review of up to date 3D display techniques with a special emphasis on volume rendering and 3D display of combined data.

Algorithms↗
PubMed2026

MethylModes: computationally efficient detection of multimodal distributions in DNA methylation data.

SUMMARY: MethylModes is an R package and Shiny application to identify multimodal distributions in human DNA methylation at individual CpG sites. Multimodal distributions, which can be the result of nearby genetic variation, environmental exposures, or assay artifacts, are susceptible to confounding and important to identify for methylation analysis. MethylModes is easily incorporated into existing quality control pipelines of array-based DNA methylation data. The underlying algorithm uses kernel smoothing of probe-level data to locate the number and location of peaks. The algorithm can be parallelized across probes for efficient implementation at genome-scale. We provide a case study implementation of MethylModes in the Health and Retirement Study as well as the Airwave Health Monitoring Study. AVAILABILITY AND IMPLEMENTATION: MethylModes is available on GitHub at https://github.com/lutiffan/methylModes as an R package wrapping an R Shiny application. We include a toy dataset to validate installation. The codebase is also published on Zenodo at https://doi.org/10.5281/zenodo.17448517.

DNA Methylation↗
PubMed2005

Advanced multimodal visualisation of clinical gait and fluoroscopy analyses in the assessment of total knee replacement.

Traditional gait and fluoroscopy analysis of human movement are largely utilised but are still limited in registration, integration, synchronisation and visualisation capabilities. The present work exploits the features of a recently developed software tool based on multimodal display (Data Manager developed within the EU-funded project 'Multimod') in an exemplary clinical case. Standard lower limb gait analysis, comprising segment position, ground reaction force and EMG data collection, and three-dimensional fluoroscopy analysis at the replaced joint were performed in a total knee replacement patient while ascending stairs. Clinical information such as X-rays and standard scores were also available. Data Manager was able to import all this variety of data and to structure these in an original hierarchical tree. Bone and prosthesis component models were registered to corresponding marker position data for effective three-dimensional animations. These were also synchronised with corresponding standard video sequences. Animations, video, time-histories of collected and also processed data were shown in various combinations, according to specific interests of the bioengineering and medical professionals expected to observe and to interpret this large amount of data. This software tool demonstrated to be a valuable means to enhance representation and interpretation of measurements coming from human motion analysis. In a single software, a thorough and effective clinical and biomechanical analysis of human motion was performed.

Arthroplasty, Replacement, Knee↗
PubMed2025

Generative AI Models in Time-Varying Biomedical Data: Scoping Review.

BACKGROUND: Trajectory modeling is a long-standing challenge in the application of computational methods to health care. In the age of big data, traditional statistical and machine learning methods do not achieve satisfactory results as they often fail to capture the complex underlying distributions of multimodal health data and long-term dependencies throughout medical histories. Recent advances in generative artificial intelligence (AI) have provided powerful tools to represent complex distributions and patterns with minimal underlying assumptions, with major impact in fields such as finance and environmental sciences, prompting researchers to apply these methods for disease modeling in health care. OBJECTIVE: While AI methods have proven powerful, their application in clinical practice remains limited due to their highly complex nature. The proliferation of AI algorithms also poses a significant challenge for nondevelopers to track and incorporate these advances into clinical research and application. In this paper, we introduce basic concepts in generative AI and discuss current algorithms and how they can be applied to health care for practitioners with little background in computer science. METHODS: We surveyed peer-reviewed papers on generative AI models with specific applications to time-series health data. Our search included single- and multimodal generative AI models that operated over structured and unstructured data, physiological waveforms, medical imaging, and multi-omics data. We introduce current generative AI methods, review their applications, and discuss their limitations and future directions in each data modality. RESULTS: We followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines and reviewed 155 articles on generative AI applications to time-series health care data across modalities. Furthermore, we offer a systematic framework for clinicians to easily identify suitable AI methods for their data and task at hand. CONCLUSIONS: We reviewed and critiqued existing applications of generative AI to time-series health data with the aim of bridging the gap between computational methods and clinical application. We also identified the shortcomings of existing approaches and highlighted recent advances in generative AI that represent promising directions for health care modeling.

Artificial Intelligence↗
PubMed2026

Longitudinal Clinical, Physiological, and Molecular Profiling of Female Patients With Metastatic Cancer: Protocol and Feasibility of a Multicenter High-Definition Oncology Study.

PURPOSE: A substantial proportion of patients receiving genomically matched therapies do not achieve clinical benefit, underscoring the influence of nongenetic factors on cancer outcomes. High-Definition Oncology (HDO) proposes integrating longitudinal, multimodal patient data-spanning clinical, molecular, physiological, and behavioral domains-to enable truly individualized cancer care. This manuscript describes the HDO study design, framework, and feasibility results in women with metastatic cancer. METHODS: We initiated a prospective, multicenter observational study (HDO study; ClinicalTrials.gov identifier: NCT06590506) enrolling 300 female patients with newly diagnosed metastatic breast, lung, or colorectal cancer. Here, we report the study design, standardized workflows, prespecified feasibility criteria, and early internal pilot results. Eleven data modalities are collected longitudinally, including tumor and germline genomics, germline epigenomics, gut microbiome, blood and stool metabolomics and proteomics, exposome characterization, wearable-derived physiological monitoring, digital footprint assessment, medical imaging, and patient-reported outcomes. Standardized workflows govern clinical procedures, data acquisition, biospecimen processing, and quality control across all participating sites. RESULTS: Feasibility was evaluated in the first 30 participants (10% of planned accrual). Patients completed 100% of scheduled clinical visits, 97.4% of planned plasma collections, 80.7% of stool samples, and all tumor biopsies. Wearable devices captured activity, heart rate, sleep, and blood oxygen saturation data during 95.0%, 84.2%, 90.6%, and 70.7% of total patient-days, respectively. Biospecimens met predefined quality control metrics across all molecular modalities. Engagement with mobile applications for pain and emotion reporting exceeded 80%. CONCLUSION: The HDO study demonstrates the feasibility of comprehensive, longitudinal, multimodal data collection in women with metastatic cancer. This internal pilot establishes an integrated framework for future analyses aimed at characterizing disease trajectories, defining molecular and physiological determinants of outcomes, and developing patient-specific computational models.

Humans↗
PubMed2026

Big data in multiple sclerosis.

PURPOSE OF REVIEW: This review summarizes recent key advancements in multiple sclerosis (MS) achieved through the utilization of big data from diverse sources and advanced analytical techniques. RECENT FINDINGS: Real-world evidence (RWE) derived from MS big data has significantly enhanced treatment strategies, redefined the concept of disease progression, refined prognostic models, and facilitated personalized medicine. RWE has highlighted the long-term benefits of early intensive treatment compared to escalation strategies, the unfavorable risk profile associated with treatment de-escalation and the importance of managing treatments during pregnancy. Additionally, it has revealed similarities and differences in the effectiveness and safety of specific high-efficacy therapies, as well as key predictors for switching treatments. RWE has also emphasized the central role of progression independent of relapse activity as a significant driver of disability and predictor of unfavorable long-term outcomes in both adult and pediatric onset MS. A data-driven approach utilizing artificial intelligence and big data has established a comprehensive framework for understanding the disease's evolution. Multimodal big data frameworks - encompassing clinical data, MRI, genomics, biomarkers, and app-based metrics - have demonstrated their ability to enhance diagnostic performance and risk stratification in MS. SUMMARY: Big data approaches are transforming MS research and clinical practice by providing stronger RWE to guide therapeutic decision-making, refining models of disease progression, and developing more precise prognostic tools.

Humans↗
PubMed1997

Demonstration of accuracy and clinical versatility of mutual information for automatic multimodality image fusion using affine and thin-plate spline warped geometric deformations.

This paper applies and evaluates an automatic mutual information-based registration algorithm across a broad spectrum of multimodal volume data sets. The algorithm requires little or no pre-processing, minimal user input and easily implements either affine, i.e. linear or thin-plate spline (TPS) warped registrations. We have evaluated the algorithm in phantom studies as well as in selected cases where few other algorithms could perform as well, if at all, to demonstrate the value of this new method. Pairs of multimodal gray-scale volume data sets were registered by iteratively changing registration parameters to maximize mutual information. Quantitative registration errors were assessed in registrations of a thorax phantom using PET/CT and in the National Library of Medicine's Visible Male using MRI T2-/T1-weighted acquisitions. Registrations of diverse clinical data sets were demonstrated including rotate-translate mapping of PET/MRI brain scans with significant missing data, full affine mapping of thoracic PET/CT and rotate-translate mapping of abdominal SPECT/CT. A five-point thin-plate spline (TPS) warped registration of thoracic PET/CT is also demonstrated. The registration algorithm converged in times ranging between 3.5 and 31 min for affine clinical registrations and 57 min for TPS warping. Mean error vector lengths for rotate-translate registrations were measured to be subvoxel in phantoms. More importantly the rotate-translate algorithm performs well even with missing data. The demonstrated clinical fusions are qualitatively excellent at all levels. We conclude that such automatic, rapid, robust algorithms significantly increase the likelihood that multimodality registrations will be routinely used to aid clinical diagnoses and post-therapeutic assessment in the near future.

Abdomen↗