Brain ventricle parcellation using a deep neural network: Application to patients with ventriculomegaly

Abstract

Numerous brain disorders are associated with ventriculomegaly, including both neuro-degenerative diseases and cerebrospinal fluid disorders. Detailed evaluation of the ventricular system is important for these conditions to help understand the pathogenesis of ventricular enlargement and elucidate novel patterns of ventriculomegaly that can be associated with different diseases. One such disease is normal pressure hydrocephalus (NPH), a chronic form of hydrocephalus in older adults that causes dementia. Automatic parcellation of the ventricular system into its sub-compartments in patients with ventriculomegaly is quite challenging due to the large variation of the ventricle shape and size. Conventional brain labeling methods are time-consuming and often fail to identify the boundaries of the enlarged ventricles. We propose a modified 3D U-Net method to perform accurate ventricular parcellation, even with grossly enlarged ventricles, from magnetic resonance images (MRIs). We validated our method on a data set of healthy controls as well as a cohort of 95 patients with NPH with mild to severe ventriculomegaly and compared with several state-of-the-art segmentation methods. On the healthy data set, the proposed network achieved mean Dice similarity coefficient (DSC) of 0.895 ± 0.03 for the ventricular system. On the NPH data set, we achieved mean DSC of 0.973 ± 0.02, which is significantly ( p < 0.005) higher than four state-of-the-art segmentation methods we compared with. Furthermore, the typical processing time on CPU-base implementation of the proposed method is 2 min, which is much lower than the several hours required by the other methods. Results indicate that our method provides: 1) highly robust parcellation of the ventricular system that is comparable in accuracy to state-of-the-art methods on healthy controls; 2) greater robustness and significantly more accurate results on cases of ventricular enlargement; and 3) a tool that enables computation of novel imaging biomarkers for dilated ventricular spaces that characterize the ventricular system.

Systematic and Comprehensive Automated Ventricle Segmentation on Ventricle Images of the Elderly Patients: A Retrospective Study

“…Shao et al mentioned in their brain ventricle parcellation work that the proposed network was also robust to white matter hyperintensities (WMH), which were often associated with NPH and located adjacent to the lateral ventricles. WMH can sometimes negatively affect the outcome of automated segmentation algorithms (Shao et al, 2019). Similarly, some of our patients were also NPH patients, and they had white matter hyperintensities around their lateral ventricles.…”

“…The segmented ventricles can also serve as the reference in determining the spatial position of the infarct, which can provide useful information for treatment planning (Poh et al, 2012). Accurate and automated segmentation and labeling tools enable more sophisticated evaluations of the ventricular system in neurodegenerative diseases, cerebrospinal fluid disorders, as well as in normal aging (Shao et al, 2019). Various diseases affect the size and morphology of the ventricles, and knowledge of the normal and abnormal ventricular system is essential in understanding various pathological states.…”

“…In some automated ventricle segmentation methods, pathological ventricles were not included (Huff et al, 2019), but pathological ventricles are common in the elderly, especially in patients with acquired hydrocephalus, because they may have brain trauma, brain tumors, subarachnoid hemorrhage, and it becomes extremely difficult to delineate the ventricle from these patients. Previous literature also reported the segmentation of the ventricle of idiopathic Normal Pressure Hydrocephalus (iNPH) patients (Shao et al, 2019). These patients are prone to segmentation failure due to the enlarged ventricle.…”

“…Therefore, when we need the volume of the ventricle, and the volume of the ventricle is measurable, then we should use it (Ambarki et al, 2010). Because of this, research on ventricle segmentation methods has brought much attention, and researchers have continuously optimized algorithms to make better and more accurate estimation (Chen et al, 2009;Coupe et al, 2011;Kempton et al, 2011;Poh et al, 2012;Qiu et al, 2015;Tang et al, 2015Tang et al, , 2018Qian et al, 2017;Cherukuri et al, 2018;Shao et al, 2019;Dubost et al, 2020).…”

“…Therefore, the developed automated ventricle segmentation methods were rarely interchangeable. Moreover, various algorithms might perform differently in segmenting different sections of the ventricles (Chen et al, 2009;Coupe et al, 2011;Shao et al, 2019;Dubost et al, 2020). Most previous machine learning (including deep learning) based studies were developed using images with a slice thickness of <3 mm, because at the same scanning distance, the smaller of the image thickness, the more images could be obtained, which could be more conducive for machine/deep learning algorithms to extract more image features (Xia et al, 2004;Coupe et al, 2011;Kempton et al, 2011).…”