Perelman School of Medicine at the University of Pennsylvania

Section for Biomedical Image Analysis (SBIA)

Header Image



COMPARE Classification Of Morphological Patterns using Adaptive Regional Elements

COMPARE is a method for classification of structural brain magnetic resonance (MR) images, which is a combination of deformation-based morphometry and machine learning methods. Before running classification, a morphological representation of the anatomy of interest is obtained from structural MR brain images using a high-dimensional mass-preserving template warping method [1, 2]. Regions that display strong correlations between tissue volumes and classification (clinical) variables learned from training samples are extracted using a watershed segmentation algorithm. To achieve robustness to outliers, the regional smoothness of the correlation map is estimated by a cross-validation strategy. A volume increment algorithm is then applied to these regions to extract regional volumetric features. To improve efficiency and generalization ability of the classification, a feature selection technique using Support Vector Machine-based criteria is used to select the most discriminative features, according to their effect on the upper bound of the leave-one-out generalization error. Finally, SVM-based classification is applied using the best set of features, and it is tested using a leave-one-out cross-validation strategy. Although the algorithm is designed for structural brain image classification, it is readily applicable for functional brain image classification with proper feature images.

For more details visit COMPARE.

GONDOLA: Generative-Discriminative Basis Learning

This software implements Generative-Discriminative Basis Learning (GONDOLA), GONDOLA provides a generative method to reduce the dimensionality of medical images while using class labels. It produces basis vectors that are useful for classification and also clinically interpretable. When provided with two sets of labeled images as input, the software outputs features saved in the Weka Attribute-Relation File Format (ARFF) and a MATLAB data file. The program can also save basis vectors as NIfTI-1 images. Scripts are provided to find and build an optimal classifier using Weka. The software can also be used for semi-supervised cases in which a number of subjects do not have class labels.

For more details visit GONDOLA.

LIBRA: Laboratory for Individualized Breast Radiodensity Assessment

LIBRA, "Laboratory for Individualized Breast Radiodensity Assessment", is a fully-automated breast density estimation software solution for digital mammography that has been designed with multi-vendor, multi-presentation compatibility in mind. Originally validated on raw and processed GE Senographe images, it has since been extended to be compatible with Hologic, Inc. Selenia and Siemens Mammomat mammograms and has been internally validated on over 30,000 screening exams. Designed for ease-of-use, LIBRA is currently distributed as a stand-alone executable for systems running 64-bit Windows OS; the original Matlab 2013a source code is also provided as a platform-independent solution. With the option to run either a command-line or interactive interface, LIBRA is easy to incorporate into breast density studies.

For more details visit LIBRA.

MOE: Mixture of Experts**

In many studies, the main objective is to compare two groups of individuals, i.e. between normal controls and patients, with the assumption that disease affects all subjects in a uniform, homogeneous fashion. In other words, each affected individual is assumed to possess the same pattern of abnormality. This approach conflicts with what is observed in clinical assessments, which point to inherently multi-dimensional symptoms or cognitive changes that reflect a broad “spectrum” of changes associated with disease or developmental and maturational processes. To address this issue, present Mixture of Experts (MOE), a method that explicitly models and captures heterogeneous patterns of change in the affected group relative to a reference group of controls.

For more details visit MOE.

ODVBA: Optimally-Discriminative Voxel-based Analysis**

This software implements ODVBA, which is used to determine the optimal spatially adaptive smoothing of images, followed by applying a voxel-based group analysis. Voxel-based Analysis and Statistical Parametric Mapping (VBA-SPM) of imaging data have offered the potential to analyze structural and functional data in great spatial detail, without the need to define a priori regions of interest (ROIs) and assumptions. Gaussian smoothing of images is an important step in VBA-SPM; it accounts for registration errors and integrates imaging signals from a region around each voxel being analyzed. However, it has also become a limitation of VBA-SPM based methods, since it is often chosen empirically, non-optimally, and lacks spatial adaptivity to the shape and spatial extent of the region of interest.

For more details visit ODVBA.

PHI Estimator: Peritumoral Heterogeneity Index

The Peritumoral Heterogeneity Index (PHI) Estimator is a lightweight tool built towards the following goals:

  1. Perform quantitative pattern analysis of the spatial heterogeneity of peritumoral perfusion imaging dynamics, retrieved from Dynamic Susceptibility Contrast Magnetic Resonance Imaging (DSC-MRI) data.
  2. Evaluate the imaging biomarker of the Epidermal Growth Factor Receptor variant III (EGFRvIII) mutation status, in individual patients diagnosed with Glioblastoma.

For more details visit PHI Estimator


SCPLearn: Identification of Sparse Connectivity Patterns in rsfMRI**

This software is used to calculate Sparse Connectivity Patterns (SCPs) from resting state fMRI connectivity data. SCPs consist of those regions whose between-region connectivity co-varies across subjects. This algorithm was developed as a complementary approach to existing network identification methods.

For more details visit SCPLearn.

**Please visit our NITRC page and/or contact us with questions about any former software packages**



DRAMMS: Deformable Registration via Attribute Matching and Mutual-Saliency Weighting

DRAMMS, "Deformable Registration via Attribute Matching and Mutual-Saliency Weighting", is a deformable image registration software designed for 2D-to-2D and 3D-to-3D image registrations.

Some typical applications include,

  • Cross-subject registration of the same organ (can be brain, breast, cardiac, etc);
  • Mono- and Multi-modality registration (MRI, CT, histology);
  • Longitudinal registration (pediatric brain growth, cancer development, etc);
  • Registration under partial missing correspondences (small lesions, tumors, histological cuts).

DRAMMS is a UNIX/Linux/Mac command-line tool. It is fully automatic and easy to use --- users input two images, and DRAMMS will output registered image and deformations. No need for pre-segmentation of any structures, no need for any prior knowledge, and no need for human initialization or intervention.

For more details visit DRAMMS


DTI-DROID: Deformable Registration using Orientation and Intensity Descriptors

Diffusion tensor (DT) imaging is a relatively new magnetic resonance imaging method, which has emerged during the past few years as a potentially powerful way of understanding connectivity in the brain. DT imaging is based on measurements of microscopic diffusion of water molecules, which provides insight into homogeneous white matter and indicates the direction of nerve bundles. Since brain connectivity is important in studying brain development, aging, and disease processes, DTI is bound to play an important role in these scientific areas. Spatial normalization of tensor fields pose difficulties not previously considered in deformable registration methods of scalar images. In addition to the tensor's relocation to the template space, the orientation of each tensor has to be properly adjusted, which implies that the actual measurement on each voxel is both displaced and changed by the spatial transformation. Moreover, the reorientation of a tensor relies on the shape of the tensor in relation to the deformation field direction at that location. Therefore, the same deformation field prescribes a different re-orientation for different tensors. The DTIGUI performs spatial normalization on DTI human brain images to facilitate subsequent statistical analysis (such as voxel based analysis or group averaging).

For more details visit DTI-DROID


PORTR: Pre-Operative and post-Recurrence brain Tumor Registration

PORTR is a software package designed for determining the optimal deformation between pre-operative and post-recurrence scans by finding the minimum of an energy function, which is based on the concept of symmetric registration.

For more details visit PORTR



 — GLISTR: GLioma Image SegmenTation and Registration

Automatic segmentation and atlas normalization of brain tumor images are extremely challenging and clinically important tasks. We have developed a package for GLioma Image SegmenTation and Registration (GLISTR) for such specific goals. This method performs both spatial normalization of the brain tumor images into an originally healthy atlas, and segmentation of multi-channel MR images into six tissue types: tumor, necrosis, edema, cerebrospinal fluid, gray and white matters. The method introduces a glioma growth diffusion-reaction model into the segmentation procedure, and estimates the tissue labels, warping parameters and the diffusion-reaction model parameters in an EM framework. The tumor embedding in the atlas space is intended for subject-specific modification of the originally healthy into an atlas with tumor and edema priors. It introduces mass-effect and diffusion of (artificial) glioma cells into the healthy tissues. This greatly improves the registration performance by allowing the inferred deformation field to be smooth.

For more details please visit GLISTR


 — GLISTRboost

GLISTRboost describes our proposed method for segmenting low- and high-grade gliomas in multimodal magnetic resonance imaging (MRI) volumes.The proposed approach is based on a hybrid generative-discriminative model. Firstly, a generative approach of a joint segmentation-registration scheme based on an Expectation-Maximization framework, that incorporates a glioma growth model, is used to segment the brain scans into tumor and healthy tissue labels. Secondly, a discriminative, gradient boosting multi-class classification, scheme is used to refine tumor labels based on information from multiple patients. Lastly, a probabilistic Bayesian strategy is employed to further refine and finalize the tumor segmentation based on patient-specific intensity statistics from the multiple modalities.Note that this is the winning method of the Multimodal Brain Tumor Image Segmentation (BRATS) Challenge, held in conjunction with the Medical Image Computing and Computer Assisted Intervention (MICCAI) conference in Technische Universitaet Muenchen (TUM) in Munich (Germany) - October 2015.

For more details please visit GLISTRboost

GraSP: A graph-based parcellation tool originally developed for the functional parcellation of the cortex.

GraSP is a graph-based parcellation software.GraSP was initially developed for parcellating the cortex into functionally coherent regions, based on their Pearson correlation [1], as shown in Figure 1, that presents different cortical parcellations of the left hemisphere. However, the software can handle any graph, such as volumetric parcellation as well.

For more details please visit GraSP


MASS: Multi Atlas Skull Stripping

Multi Atlas Skull Stripping (MASS), is a software package designed for robust and accurate brain extraction, applicable for both individual as well as large population studies. MASS is implemented as a Unix command-line tool. It is fully automatic and easy to use — users input an image, and MASS will output the extracted brain and the associated brain mask.

For more details please visit MASS


MUSE: MUlti-atlas region Segmentation utilizing Ensembles of registration algorithms and parameters, and locally optimal atlas selection

MUSE generates a large ensemble of candidate labels in the target image space using multiple atlases, registration algorithms and smoothness values for these algorithms. The ensemble is then fused into a final segmentation. 

For more details please visit MUSE


WMLS: White Matter Lesion Segmentation

White matter lesions (WML) are brain abnormalities that appear in different brain diseases, such as multiple sclerosis (MS), head injury, vascular disease particularly related to hypertension possibly diabetes, and some forms of dementia. Their incidence also increases with normal aging. MRI is routinely used as surrogate in the study of WMLs, as MRI signal changes reflect certain aspects of the underlying brain pathology. Out of the many available MRI acquisition protocols, T1-w and T2-w, PD, and FLAIR are among the most commonly used to evaluate white matter lesion load in the brain. Computer analysis methods have started to complement expert-readings of these images, as they may improve throughput and consistency, in addition to providing more accurate quantitative measures of WML. Computer analysis is even more critical in longitudinal studies that involve relatively small changes in WML, thereby rendering it advantageous, if not necessary, to use unbiased computer-assisted segmentation methods to detect WMLs and assess their longitudinal change.

For more details please visit: WMLS



Atrophy Simulation

This software package is used to simulate brain images with local growth/atrophy within a prescribed spherical region. Specifically, given an input image and its segmented image, the location of the center of the spherical region, and the radius of that sphere, it simulates new images that have tissue growth or shrinkage within that pre-specified brain region according to given rates (atrophy for rates less than one and growth for rates greater than one). The algorithm uses an iterative procedure that tries to achieve the given level of volumetric change for brain tissues within the region, by seeking a smooth deformation field, whose Jacobian determinants match the prescribed volume change rate within the region. Note that in the current software, the simulation of growth or atrophy for brain tissue requires that the input spherical region has to cover some CSF or background regions.

For more details please visit Atrophy Simulation


 — BASIS: Build system And Software Implementation Standard

This meta-project, not specifically related to the analysis of medical images, aims at reducing and standardizing our software development and maintenance efforts. Many more recent software packages distributed by us are build upon this software package.

For more details please visit BASIS

 — Brain Anatomy Simulator: Statistically-based Simulation of Deformations: Brain Anatomy Simulator Using Statistical Shape Modeling

This package estimates the statistical properties of high-dimensional deformation fields, which are produced by deformable registration packages like HAMMER, and then uses the estimates statistics to simulate brain images with very high degree of realism.

For more details please visit Brain Anatomy Simulator

 — Brain Tumor Viewer

BrainTumorViewer (BTV) is a lightweight viewer, built for fast and simple interaction with MRI image volumes.

For more details please visit Brain Tumor Viewer

 — CaPTk: Cancer Imaging Phenomics Toolkit

CaPTk is a software platform for analysis of radiographic cancer images, currently focusing on brain, breast, and lung cancer. CaPTk integrates advanced, validated tools performing various aspects of medical image analysis, that have been developed in the context of active clinical research studies and collaborations toward addressing real clinical needs. With emphasis given in its use as a very lightweight and efficient viewer, and with no prerequisites for substantial computational background, CaPTk aims to facilitate the swift translation of advanced computational algorithms into routine clinical quantification, analysis, decision making, and reporting workflow. Its long-term goal is providing widely used technology that leverages the value of advanced imaging analytics in cancer prediction, diagnosis and prognosis, as well as in better understanding the biological mechanisms of cancer development.

For more details please visit CaPTk


For resources and more information please visit our CBICA NITRC page

SBIA Software
Section for Biomedical Image Analysis (SBIA)
3700 Hamilton Walk
Richards Building, 7th Flr
Philadelphia, PA 19104