A tissue-fraction estimation-based segmentation method for quantitative dopamine transporter SPECT

Abstract

Quantitative measures of uptake in the caudate, putamen, and globus pallidus in dopamine transporter (DaT) brain SPECT have potential as biomarkers for the severity of Parkinson disease. This potential is critical for clinical care and research. Reliable quantification of uptake requires accurate segmentation of these regions. However, segmentation is challenging in DaT SPECT due to partial-volume effects, system noise, physiological variability, and the small size of these regions. To address these challenges, we propose an estimation-based approach to segmentation. This approach estimates the posterior mean of the fractional volume occupied by caudate, putamen, and globus pallidus within each voxel of a 3D SPECT image. The estimate is obtained by minimizing a cost function based on the binary cross-entropy loss between the true and estimated fractional volumes over a population of SPECT images, where the distribution of the true fractional volumes is obtained from magnetic resonance (MR) images from clinical populations. The proposed method accounts for both the sources of partial-volume effects in SPECT, namely the limited system resolution and tissue-fraction effects. The method was implemented using an encoder-decoder network and evaluated using realistic clinically guided SPECT simulation studies, where the ground-truth fractional volumes of caudate, putamen, and globus pallidus were known. The method significantly outperformed all other considered segmentation methods, including a U-net-based method, and yielded accurate segmentation with dice similarity coefficients of ∼ 0.80 for all regions. The method was relatively insensitive to the changes in voxel size. Further, the method was relatively robust up to ±10 • of patient head tilt along transaxial, sagittal, and coronal planes. Overall, the results demonstrate the efficacy of the proposed method to yield accurate fully automated segmentation of caudate, putamen, and globus pallidus in 3D DaT-SPECT images.

A physics and learning-based transmission-less attenuation compensation method for SPECT

“…In this work, we evaluated our method in the context of myocardial perfusion SPECT. SPECT has multiple other clinical applications, such as in assessment of neurodegenerative disorders [31], [42] , and in imaging-based dosimetry [43][44][45] . Our method is general and the results motivate developing and evaluating the proposed method for those applications.…”

“…For this purpose, we used a virtual imaging trial (VIT) framework. As has been shown in several studies, including those evaluating SPECT methods [27]- [31] , the VIT framework evaluates the performance of a method against known ground truth by providing the ability to accurately model in vivo anatomical and physiological properties and imaging system characteristics, incorporate population variability, and generate multiple scan realizations of the same patient to evaluate reproducibility. Even more importantly, this is all done in silico, which is inexpensive and enables optimizing the method before conducting clinical studies.…”

Task-based assessment of binned and list-mode SPECT systems

“…In DaT-SPECT, the goal is to estimate the activity in the caudate and putamen regions. The boundaries for these regions can be obtained by either segmenting these regions, [21][22][23] or from other imaging modalities, such as MRI. 24 Thus, the ROI can be defined.…”

Learning Fuzzy Clustering for SPECT/CT Segmentation via Convolutional Neural Networks

“…In nuclear medicine, various ConvNets-based studies have investigated their use for image segmentation. For instance, Liu et al [12] designed a ConvNet for dopamine transporter brain SPECT segmentation that estimates the posterior mean of the fractional volume within each voxel. Built upon the idea of fusing multimodality information, Guo et al [13], and Li et al [14] incorporated computed tomography (CT) images in training the ConvNet for improved lesion delineation in Positron emission tomography (PET).…”