Artificial intelligence for automatic cerebral ventricle segmentation and volume calculation: a clinical tool for the evaluation of pediatric hydrocephalus

Abstract

OBJECTIVEImaging evaluation of the cerebral ventricles is important for clinical decision-making in pediatric hydrocephalus. Although quantitative measurements of ventricular size, over time, can facilitate objective comparison, automated tools for calculating ventricular volume are not structured for clinical use. The authors aimed to develop a fully automated deep learning (DL) model for pediatric cerebral ventricle segmentation and volume calculation for widespread clinical implementation across multiple hospitals.METHODSThe study cohort consisted of 200 children with obstructive hydrocephalus from four pediatric hospitals, along with 199 controls. Manual ventricle segmentation and volume calculation values served as “ground truth” data. An encoder-decoder convolutional neural network architecture, in which T2-weighted MR images were used as input, automatically delineated the ventricles and output volumetric measurements. On a held-out test set, segmentation accuracy was assessed using the Dice similarity coefficient (0 to 1) and volume calculation was assessed using linear regression. Model generalizability was evaluated on an external MRI data set from a fifth hospital. The DL model performance was compared against FreeSurfer research segmentation software.RESULTSModel segmentation performed with an overall Dice score of 0.901 (0.946 in hydrocephalus, 0.856 in controls). The model generalized to external MR images from a fifth pediatric hospital with a Dice score of 0.926. The model was more accurate than FreeSurfer, with faster operating times (1.48 seconds per scan).CONCLUSIONSThe authors present a DL model for automatic ventricle segmentation and volume calculation that is more accurate and rapid than currently available methods. With near-immediate volumetric output and reliable performance across institutional scanner types, this model can be adapted to the real-time clinical evaluation of hydrocephalus and improve clinician workflow.

AI-based medical e-diagnosis for fast and automatic ventricular volume measurement in patients with normal pressure hydrocephalus

“…The automatic ventricle segmentation method can overcome the limitations of the manual segmentation method [ 10 ]. It is an efficient and rapid ventricle segmentation method [ 12 , 23 ]. The most important thing is that it can significantly shorten the operation time [ 24 ]; this lays a solid foundation for the direct measurement of the ventricle volume in large-scale clinical practice.…”

“…In the past, researchers manually segmented the ventricle to calculate the volume. But this method needs to be based on professional knowledge [ 10 , 11 ] and is very time- and energy-consuming [ 12 – 14 ]. More importantly, it is prone to human errors [ 15 ].…”

“…So, our purpose is based on CT and MRI images of NPH patients, using machine learning methods, to achieve efficient and accurate automatic measurement of the ventricular volume of NPH patients. This will lay a solid foundation for the development of a large sample of the ventricular volume of NPH patients, and it will also help clinicians quickly and accurately assess the ventricular condition of NPH patients [ 12 , 14 , 27 ].…”

Progression in Neuroimaging of Normal Pressure Hydrocephalus

“…Quon et al achieved a deep learning model for automatic ventricle segmentation and volume calculation ( 34 ). They built a complex neural network that takes T2-weighted MRI images as input and produced satisfying accuracy in volume calculation with more rapid processing speed.…”

Update on establishing and managing an overnight emergency radiology division

“…Interest in radiology applications for AI has skyrocketed over the past few years [35]. Although emergency radiology may benefit from other types of AI such as automatic segmentation of structures [36], ventricular volume measurements for hydrocephalus [37], predicting ED patient volume-which is a driver of ED imaging volume [26,38]-or for protocolling studies [39], the main applications for the ED are for diagnosis [40]. This currently takes the form of flagging studies for worklist prioritization or as a double-check to catch radiologist errors (i.e., "misses") rather than as a radiologist replacement [41].…”