Tahreema N. Matin

Non-local shape descriptor: a new similarity metric for deformable multi-modal registration

Deformable registration of images obtained from different modalities remains a challenging task in medical image analysis. This paper addresses this problem and proposes a new similarity metric for multi-modal registration, the non-local shape descriptor. It aims to extract the shape of anatomical features in a non-local region. By utilizing the dense evaluation of shape descriptors, this new measure bridges the gap between intensity-based and geometric feature-based similarity criteria. Our new metric allows for accurate and reliable registration of clinical multi-modal datasets and is robust against the most considerable differences between modalities, such as non-functional intensity relations, different amounts of noise and non-uniform bias fields. The measure has been implemented in a non-rigid diffusion-regularized registration framework. It has been applied to synthetic test images and challenging clinical MRI and CT chest scans. Experimental results demonstrate its advantages over the most commonly used similarity metric - mutual information, and show improved alignment of anatomical landmarks.

MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration

Deformable registration of images obtained from different modalities remains a challenging task in medical image analysis. This paper addresses this important problem and proposes a modality independent neighbourhood descriptor (MIND) for both linear and deformable multi-modal registration. Based on the similarity of small image patches within one image, it aims to extract the distinctive structure in a local neighbourhood, which is preserved across modalities. The descriptor is based on the concept of image self-similarity, which has been introduced for non-local means filtering for image denoising. It is able to distinguish between different types of features such as corners, edges and homogeneously textured regions. MIND is robust to the most considerable differences between modalities: non-functional intensity relations, image noise and non-uniform bias fields. The multi-dimensional descriptor can be efficiently computed in a dense fashion across the whole image and provides point-wise local similarity across modalities based on the absolute or squared difference between descriptors, making it applicable for a wide range of transformation models and optimisation algorithms. We use the sum of squared differences of the MIND representations of the images as a similarity metric within a symmetric non-parametric Gauss-Newton registration framework. In principle, MIND would be applicable to the registration of arbitrary modalities. In this work, we apply and validate it for the registration of clinical 3D thoracic CT scans between inhale and exhale as well as the alignment of 3D CT and MRI scans. Experimental results show the advantages of MIND over state-of-the-art techniques such as conditional mutual information and entropy images, with respect to clinically annotated landmark locations.

Imaging of the pleura.

Pleural disease is a problem of global significance which causes significant morbidity and mortality. Pleural disease is usually first suspected on chest x‐ray but further imaging, often ultrasound, is usually required as part of the diagnostic work‐up. Complex imaging with computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET)‐CT are less often performed but are routinely required in patients with mesothelioma and occasionally required in patients with pleural infection and other pleural diseases. Cross‐sectional imaging may be used to suggest the diagnosis of pleural disease, quantify disease severity, guide biopsy, and even predict prognosis. This review will focus on the contributions of CT, MRI, and PET to the management of pleural disease with discussion of their relative strengths and weaknesses. J. Magn. Reson. Imaging 2010;32:1275–1286.

Interventional radiology of pleural diseases.

Image‐guided pleural procedures are important in both the diagnosis and management of pleural disease. Pleural aspiration, biopsy and drainage are all proven to be safer and more efficacious using image guidance. The aim of this article is to review common image‐guided pleural techniques and the evidence base for their application in clinical practice.

Pulmonary lobe segmentation from CT images using fissureness, airways, vessels and multilevel B-splines

Lobe detection from CT images is a challenging segmentation problem with important respiratory health care applications, including surgical planning and regional image analysis. We present a fully automated method for segmenting the pulmonary lobes. We first build a lobar approximation by applying a watershed transform to a vesselness density filter, using seed points generated from segmentation and analysis of the bronchial tree. We then apply a fissureness filter, which combines Hessian-based detection of planar structures with suppression of locally fissure-like points on the boundaries of the pulmonary vasculature. Finally, we fit a smooth multi-level B-spline curve through the fissureness maxima and extrapolate to the lung boundaries. Our method addresses several limitations of similar work, namely it is robust to incomplete fissures and vessels crossing the lobar boundaries, and it is computationally efficient and does not require training. We provide validation using fissure landmarks manually placed on 10 lung cancer datasets by a pulmonary clinician.

Chronic Obstructive Pulmonary Disease: Lobar Analysis with Hyperpolarized 129Xe MR Imaging

Purpose To compare lobar ventilation and apparent diffusion coefficient (ADC) values obtained with hyperpolarized xenon 129 (129Xe) magnetic resonance (MR) imaging to quantitative computed tomography (CT) metrics on a lobar basis and pulmonary function test (PFT) results on a whole-lung basis in patients with chronic obstructive pulmonary disease (COPD). Materials and Methods The study was approved by the National Research Ethics Service Committee; written informed consent was obtained from all patients. Twenty-two patients with COPD (Global Initiative for Chronic Obstructive Lung Disease stage II-IV) underwent hyperpolarized 129Xe MR imaging at 1.5 T, quantitative CT, and PFTs. Whole-lung and lobar 129Xe MR imaging parameters were obtained by using automated segmentation of multisection hyperpolarized 129Xe MR ventilation images and hyperpolarized 129Xe MR diffusion-weighted images after coregistration to CT scans. Whole-lung and lobar quantitative CT-derived metrics for emphysema and bronchial wall thickness were calculated. Pearson correlation coefficients were used to evaluate the relationship between imaging measures and PFT results. Results Percentage ventilated volume and average ADC at lobar 129Xe MR imaging showed correlation with percentage emphysema at lobar quantitative CT (r = -0.32, P < .001 and r = 0.75, P < .0001, respectively). The average ADC at whole-lung 129Xe MR imaging showed moderate correlation with PFT results (percentage predicted transfer factor of the lung for carbon monoxide [Tlco]: r = -0.61, P < .005) and percentage predicted functional residual capacity (r = 0.47, P < .05). Whole-lung quantitative CT percentage emphysema also showed statistically significant correlation with percentage predicted Tlco (r = -0.65, P < .005). Conclusion Lobar ventilation and ADC values obtained from hyperpolarized 129Xe MR imaging demonstrated correlation with quantitative CT percentage emphysema on a lobar basis and with PFT results on a whole-lung basis.

Piecewise-diffeomorphic registration of 3D CT/MR pulmonary images with sliding conditions

In this paper, we present a new algorithm to register 3D multimodal images with sliding conditions in a diffeomorphic framework. Our driving motivation is to define one-to-one mappings between CT/MR pulmonary volumes acquired from patients with empyema. The main problem to overcome is that the pulmonary motion, which can be large, presents sliding conditions at the thoracic cage boundary. Our algorithm is therefore piecewise-diffeomorphic as it ensures the definition of one-to-one mappings with discontinuous deformations at the location of the sliding conditions. Its performance is demonstrated on 14 CT/MR image volumes of the chest. Results show that the estimated deformations are similar to those obtained using free-form deformations, with the additional property to ensure the invertibility of the deformations and to explicitly model the sliding motion at the thoracic cage boundary.

Regional lung ventilation estimation based on supervoxel tracking.

In the case of lung cancer, an assessment of regional lung function has the potential to guide more accurate radiotherapy treatment. This could spare well-functioning parts of the lungs, as well as be used for follow up. In this paper we present a novel approach for regional lung ventilation estimation from dynamic lung CT imaging, which might be used during radiotherapy planning. Our method combines a supervoxel-based image representation with deformable image registration, performed between peak breathing phases, for which we track changes in intensity of previously extracted supervoxels. Such a region-oriented approach is expected to be more physiologically consistent with lung anatomy than previous methods relying on voxel-wise relationships, as it has the potential to mimic the lung anatomy. Our results are compared with static ventilation images acquired from hyperpolarized Xenon129 MRI. In our study we use three patient datasets consisting of 4DCT and XeMRI. We achieve higher correlation (0.487) compared to the commonly used method for estimating ventilation performed in a voxel-wise manner (0.423) on average based on global correlation coefficients. We also achieve higher correlation values for our method when ventilated/non-ventilated regions of lungs are investigated. The increase of the number of layers of supervoxels further improves our results, with one layer achieving 0.393, compared to 0.487 for 15 layers. Overall, we have shown that our method achieves higher correlation values compared to the previously used approach, when correlated with XeMRI.

Fast dynamic ventilation MRI of hyperpolarized 129 Xe using spiral imaging.

To develop and optimize a rapid dynamic hyperpolarized 129Xe ventilation (DXeV) MRI protocol and investigate the feasibility of capturing pulmonary signal‐time curves in human lungs.

Learning-Based Multi-atlas Segmentation of the Lungs and Lobes in Proton MR Images

Delineation of the lung and lobar anatomy in MR images is challenging due to the limited image contrast and the absence of visible interlobar fissures. Here we propose a novel automated lung and lobe segmentation method for pulmonary MR images. This segmentation method employs prior information of the lungs and lobes extracted from CT in the form of multiple MRI atlases, and adopts a learning-based atlas-encoding scheme, based on random forests, to improve the performance of multi-atlas segmentation. In particular, we encode each CT-derived MRI atlas by training an atlas-specific random forest for each structure of interest. In addition to appearance features, we also extract label context features from the registered atlases to introduce additional information to the non-linear mapping process. We evaluated our proposed framework on 10 clinical MR images acquired from COPD patients. It outperformed state-of-the-art approaches in segmenting the lungs and lobes, yielding a mean Dice score of 95.7%.