Hemibrain growth as a biomarker for whole-brain growth.
Authors
Affiliations (4)
Affiliations (4)
- 1Department of Electrical Engineering, Pennsylvania State University, University Park, Pennsylvania.
- 2Department of Neurosurgery, Yale University, New Haven, Connecticut.
- 3Department of Neurosurgery, University of Utah, Salt Lake City, Utah; and.
- 4Division of Neurosurgery, Department of Surgery, The Hospital for Sick Children, University of Toronto, Ontario, Canada.
Abstract
Accurate estimation of CSF and brain volume is an important component in evaluating hydrocephalus treatments, including shunt and endoscopic third ventriculostomy procedures. While MRI-based segmentation typically provides precise measurements, metallic artifacts from implanted shunts in patients with hydrocephalus can impede accurate volume determination. This study introduces a method for assessing brain growth in hydrocephalus patients using artifact-affected MR images and presents an efficient, automated AI-based pipeline for hemibrain segmentation and subsequent volume assessment. This study utilizes imaging data from the Endoscopic versus Shunt Treatment of Hydrocephalus in Infants trial. Pre- and postoperative T2-weighted MR images were obtained in 75 patients. Hemibrain growth curves for the artifact-free hemisphere are proposed to assess postoperative brain growth in MR images with metallic shunt artifacts. An AI-based hemibrain volume estimation pipeline was developed, consisting of a brain/CSF segmentation model and a hemibrain mask generator. Segmentation labels, including left/right hemibrain masks and brain/CSF segmentation maps, were created. The AI pipeline was trained and validated using a manually segmented data subset. The volumes of left and right brain hemispheres after surgery were calculated and analyzed. Postoperative hemisphere volume ratios approached the normal ratio and remained constant over time, confirming the feasibility of using hemibrain measurements as proxies for whole-brain volume assessment in the presence of metallic artifacts. Additionally, the AI-based pipeline demonstrated high accuracy in generating hemibrain masks and segmenting brain/CSF, effectively automating the process of hemibrain volume estimation. Hemibrain volume estimation of the unaffected hemisphere offers a feasible method for assessing brain growth over time. This process can be automated using a highly accurate AI pipeline, providing a valuable tool for monitoring brain growth in pediatric hydrocephalus patients with shunts.