Sudhakar Chelikani

An Integrated Approach to Segmentation and Nonrigid Registration for Application in Image-Guided Pelvic Radiotherapy

External beam radiotherapy (EBRT) has become the preferred options for nonsurgical treatment of prostate cancer and cervix cancer. In order to deliver higher doses to cancerous regions within these pelvic structures (i.e. prostate or cervix) while maintaining or lowering the doses to surrounding non-cancerous regions, it is critical to account for setup variation, organ motion, anatomical changes due to treatment and intra-fraction motion. In previous work, manual segmentation of the soft tissues is performed and then images are registered based on the manual segmentation. In this paper, we present an integrated automatic approach to multiple organ segmentation and nonrigid constrained registration, which can achieve these two aims simultaneously. The segmentation and registration steps are both formulated using a Bayesian framework, and they constrain each other using an iterative conditional model strategy. We also propose a new strategy to assess cumulative actual dose for this novel integrated algorithm, in order to both determine whether the intended treatment is being delivered and, potentially, whether or not a plan should be adjusted for future treatment fractions. Quantitative results show that the automatic segmentation produced results that have an accuracy comparable to manual segmentation, while the registration part significantly outperforms both rigid and nonrigid registration. Clinical application and evaluation of dose delivery show the superiority of proposed method to the procedure currently used in clinical practice, i.e. manual segmentation followed by rigid registration.

Constrained non-rigid registration for use in image-guided adaptive radiotherapy

A constrained non-rigid registration (CNRR) algorithm for use in prostate image-guided adaptive radiotherapy is presented in a coherent mathematical framework. The registration algorithm is based on a global rigid transformation combined with a series of local injective non-rigid multi-resolution cubic B-spline Free Form Deformation (FFD) transformations. The control points of the FFD are used to non-rigidly constrain the transformation to the prostate, rectum, and bladder. As well, the control points are used to rigidly constrain the transformation to the estimated position of the pelvis, left femur, and right femur. The algorithm was tested with both 3D conformal radiotherapy (3DCRT) and intensity-modulated radiotherapy (IMRT) dose plan data sets. The 3DCRT dose plan set consisted of 10 fan-beam CT (FBCT) treatment-day images acquired from four different patients. The IMRT dose plan set consisted of 32 cone-beam CT (CBCT) treatment-day images acquired from 4 different patients. The CNRR was tested with different combinations of anatomical constraints and each test significantly outperformed both rigid and non-rigid registration at aligning constrained bones and critical organs. The CNRR results were used to adapt the dose plans to account for patient positioning errors as well as inter-day bone motion and intrinsic organ deformation. Each adapted dose plan improved performance by lowering radiation distribution to the rectum and bladder while increasing or maintaining radiation distribution to the prostate.

Optimizing Compton camera geometries

Compton cameras promise to improve the characteristics of nuclear medicine imaging, wherein mechanical collimation is replaced with electronic collimation. This leads to huge gains in sensitivity and, consequently, a reduction in the radiation dosage that needs to be administered to the patient. Design modifications that improve the sensitivity invariably compromise resolution. The scope of the current project was to determine an optimal design and configuration of a Compton camera that strikes a balance between these two properties. Transport of the photon flux from the source to the detectors was simulated with the camera geometry serving as the parameter to be optimized. Two variations of the Boltzmann photon transport equation, with and without photon polarization, were employed to model the flux. Doppler broadening of the energy spectra was also included. The simulation was done in a Monte Carlo framework using GEANT4. Two clinically relevant energies, 140 keV and 511 keV, corresponding to 99mTc and 18F were simulated. The gain in the sensitivity for the Compton camera over the conventional camera was 100 fold. Neither Doppler broadening nor polarization had any significant effect on the sensitivity of the camera. However, the spatial resolution of the camera was affected by these processes. Doppler broadening had a deleterious effect on the spatial resolution, but polarization improved the resolution when accounted for in the reconstruction algorithm.

Simultaneous Nonrigid Registration, Segmentation, and Tumor Detection in MRI Guided Cervical Cancer Radiation Therapy

External beam radiation therapy (EBRT) for the treatment of cancer enables accurate placement of radiation dose on the cancerous region. However, the deformation of soft tissue during the course of treatment, such as in cervical cancer, presents significant challenges for the delineation of the target volume and other structures of interest. Furthermore, the presence and regression of pathologies such as tumors may violate registration constraints and cause registration errors. In this paper, automatic segmentation, nonrigid registration and tumor detection in cervical magnetic resonance (MR) data are addressed simultaneously using a unified Bayesian framework. The proposed novel method can generate a tumor probability map while progressively identifying the boundary of an organ of interest based on the achieved nonrigid transformation. The method is able to handle the challenges of significant tumor regression and its effect on surrounding tissues. The new method was compared to various currently existing algorithms on a set of 36 MR data from six patients, each patient has six T2-weighted MR cervical images. The results show that the proposed approach achieves an accuracy comparable to manual segmentation and it significantly outperforms the existing registration algorithms. In addition, the tumor detection result generated by the proposed method has a high agreement with manual delineation by a qualified clinician.

Integrated segmentation and nonrigid registration for application in prostate image-guided radiotherapy

Many current image-guided radiotherapy (IGRT) systems incorporate an in-room cone-beam CT (CBCT) with a radiotherapy linear accelerator for treatment day imaging. Segmentation of key anatomical structures (prostate and surrounding organs) in 3DCBCT images as well as registration between planning and treatment images are essential for determining many important treatment parameters. Due to the image quality of CBCT, previous work typically uses manual segmentation of the soft tissues and then registers the images based on the manual segmentation. In this paper, an integrated automatic segmentation/constrained nonrigid registration is presented, which can achieve these two aims simultaneously. This method is tested using 24 sets of real patient data. Quantitative results show that the automatic segmentation produces results that have an accuracy comparable to manual segmentation, while the registration part significantly outperforms both rigid and non-rigid registration. Clinical application also shows promising results.

Constrained non-rigid registration using Lagrange multipliers for application in prostate radiotherapy

This paper presents a novel free-form deformation registration algorithm with non-rigid constraints to capture the transformation between the planning day and treatment day CT images used for external beam radiotherapy for prostate cancer. The non-rigid registration is constrained to the predetermined motion of segmented soft tissues, and the constrained optimization problem is solved by the method of Lagrange multipliers. The ultimate goal is for the nonrigid transformation to be used to update the radiotherapy plan to take into account soft tissue deformation. The performance of this hard-constrained nonrigid registration (H-CNRR) algorithm has been compared to those achieved using rigid, fully non-rigid, and soft-constrained nonrigid registration (S-CNRR). The results clearly indicate that this Lagrange multipliers based hard-constrained nonrigid registration algorithm presented in this paper performed better at capturing the motion of the constrained organs.1

A unified framework for joint segmentation, nonrigid registration and tumor detection: application to MR-guided radiotherapy

Image guided external beam radiation therapy (EBRT) for the treatment of cancer enables accurate placement of radiation dose to the cancerous region. However, the deformation of soft tissue during the course of treatment, such as in cervical cancer, presents significant challenges. Furthermore, the presence of pathologies such as tumors may violate registration constraints and cause registration errors. In this paper, we present a unified MAP framework that performs automatic segmentation, nonrigid registration and tumor detection simultaneously. It can generate a tumor probability map while progressively identifing the boundary of an organ of interest based on the achieved transformation. We demonstrate the approach on a set of 30 T2-weighted MR images, and the results show that the approach performs better than similar methods which separate the registration and segmentation problems. In addition, the detection result generated by the proposed method has a high agreement with the manual delineation by a qualified clinician.

A Constrained Non-rigid Registration Algorithm for Use in Prostate Image-Guided Radiotherapy

A constrained non-rigid registration (CNRR) algorithm for use in updating prostate external beam image-guided radiotherapy treatment plans is presented in this paper. The developed algorithm is based on a multi-resolution cubic B-spline FFD transformation and has been tested and verified using 3D CT images from 10 sets of real patient data acquired from 4 different patients on different treatment days. The registration can be constrained to any combination of the prostate, rectum, bladder, pelvis, left femur, and right femur. The CNRR was tested with 5 different combinations of constraints and each test significantly outperformed both rigid and non-rigid registration at aligning constrained bones and critical organs. The CNRR was then used to update the treatment plans to account for articulated, rigid bone motion and non-rigid organ deformation. Each updated treatment plan outperformed the original treatment plan by increasing radiation dosage to the prostate and lowering radiation dosage to the rectum and bladder.

A CONSTRAINED NON-RIGID REGISTRATION ALGORITHM FOR APPLICATION IN PROSTATE RADIOTHERAPY

This paper presents a novel free-form deformation registration algorithm with non-rigid constraints to capture the transformation between the planning day and treatment day CT images used for external beam radiotherapy for prostate cancer. The algorithm is constrained to the predetermined motion of a segmented organ, which is described by an injective free-form deformation (FFD) based on B-splines. The end goal is for the injective transformation to be used to update the radiotherapy plan to take into account bone and soft tissue deformation. The results of the algorithm have been compared to those achieved using rigid and fully non-rigid registration. The results clearly indicate that the constrained non-rigid registration algorithm presented in this paper performed much better at capturing the motion of the constrained organ, the bladder in this case, than the rigid or fully non-rigid registration algorithms.

Voxel-based logistic analysis of PPMI control and Parkinson's disease DaTscans

ABSTRACT A comprehensive analysis of the Parkinsons Progression Markers Initiative (PPMI) Dopamine Transporter Single Photon Emission Computed Tomography (DaTscan) images is carried out using a voxel‐based logistic lasso model. The model reveals that sub‐regional voxels in the caudate, the putamen, as well as in the globus pallidus are informative for classifying images into control and PD classes. Further, a new technique called logistic component analysis is developed. This technique reveals that intra‐population differences in dopamine transporter concentration and imperfect normalization are significant factors influencing logistic analysis. The interactions with handedness, sex, and age are also evaluated. HighlightsVoxel‐wise analysis of PPMI Control and Parkinsons DaTscan images gives accurate classification and identifies voxels that are informative.New analysis called Logistic Principal Components reveals sources of variation in control and PD images that affect classification.Logistic features are related to MDS‐UPDRS scores.Logistic features interact with sex and age, but not with handedness.