Segmentation and labeling of the ventricular system in patients with normal pressure hydrocephalus

Normal pressure hydrocephalus (NPH) affects older adults and is thought to be caused by obstruction of the normal flow of cerebrospinal fluid (CSF) leading to the expansion of the brain ventricles. NPH typically presents with cognitive impairment, gait dysfunction, and urinary incontinence, and may account for more than five percent of all cases of dementia.

Unlike most other causes of dementia, NPH can potentially be treated and the neurological dysfunction reversed by shunt surgery or endoscopic third ventriculostomy (ETV), which drain excess CSF. However, a major diagnostic challenge remains to robustly identify shunt-responsive NPH patients from patients with enlarged ventricles due to other neurodegenerative diseases, such as Alzheimer's and Parkinson's diseases.

Currently, radiologists grade the severity of NPH by detailed examination and measurement of the ventricles based on stacks of 2D magnetic resonance images (MRIs). We have developed a new method to automatically segment and label different compartments of the ventricular system in NPH patients from MRIs (see publications below).

While this task has been achieved in healthy subjects, the ventricles in NPH are both enlarged and deformed, causing current algorithms to fail. Comparison with state-of-the-art segmentation techniques demonstrates substantial improvements in labeling the enlarged ventricles using our methods, indicating that these strategies may be viable options for the diagnosis and characterization of NPH. The methods are also applicable to other neurodegenerative diseases, such as Alzheimer’s disease; a condition considered in the differential diagnosis of NPH.

Publications from this project include:

Atlason HE, Love A, Robertsson V, Blitz AM, Sigurdsson S, et al. (2022), "A joint ventricle and WMH segmentation from MRI for evaluation of healthy and pathological changes in the aging brain". PLOS ONE 17(9): e0274212. https://doi.org/10.1371/journal.pone.0274212

Muhan Shao, Shuo Han, Aaron Carass, Xian Li, Ari M. Blitz, Jaehoon Shin, Jerry. L. Prince, and Lotta. M. Ellingsen, "Brain ventricle parcellation using a deep neural network: Application to patients with ventriculomegaly," NeuroImage: Clinical, vol. 23, pp. 101871, doi.org/10.1016/j.nicl.2019.101871, 2019.

Hans Atlason, Muhan Shao, Viðar Róbertsson, Sigurður Sigurðsson, Vilmundur Guðnason, Jerry L. Prince, Lotta M. Ellingsen, "Large-scale parcellation of the ventricular system using convolutional neural networks," Proc. SPIE Medical Imaging 2019: Biomedical Applications in Molecular, Structural, and Functional Imaging, Vol. 10953, https://doi.org/10.1117/12.2514590, 2019.

Muhan Shao, Shuo Han, Aaron Carass, Xiang Li, Ari M. Blitz, Jerry L. Prince, Lotta M. Ellingsen, "Shortcomings of Ventricle Segmentation Using Deep Convolutional Networks , Understanding and Interpreting Machine Learning in Medical Image Computing Applications - First International Workshops MLCN 2018, DLF 2018, and iMIMIC 2018, Held in Conjunction with MICCAI 2018, Proceedings (pp. 79-86). (Lecture Notes in Computer Science, Vol. 11038 LNCS). Springer Verlag. https://doi.org/10.1007/978-3-030-02628-8_9, 2018.

Muhan Shao, Aaron Carass, Xiang Li, Blake E. Dewey, Ari M. Blitz, Jerry L. Prince, Lotta M. Ellingsen, "Multi-atlas segmentation of the hydrocephalus brain using an adaptive ventricles atlas," Proc. SPIE 10578, Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging, 105780F (March 2018), https://doi.org/10.1117/12.2295613, 2018.

Jeffrey Glaister, Muhan Shao, Xiang Li, Aaron Carass, Snehashis Roy, Ari M. Blitz, Jerry L. Prince, Lotta M. Ellingsen, "Deformable model reconstruction of the subarachnoid space," Proc. SPIE 10574, Medical Imaging 2018: Image Processing, 1057431 (March 2018), https://doi.org/10.1117/12.2293633, 2018.

Aaron Carass, Muhan Shao, Xiang Li, Blake E. Dewey, Ari M. Blitz, Snehashis Roy, Dzung L. Pham, Jerry L. Prince and, Lotta M. Ellingsen. “Whole brain parcellation with pathology: Validation on ventriculomegaly patients.” In: Patch-Based Techniques in Medical Imaging: Third International Workshop, Patch-MI 2017, Held in Conjunction with MICCAI 2017. Springer International Publishing; p. 20-28, 2017.

Lotta M. Ellingsen, Snehashis Roy, Aaron Carass, Ari M. Blitz, Dzung L. Pham, Jerry L. Prince. “Segmentation and labeling of the ventricular system in normal pressure hydrocephalus using patch-based tissue classification and multi-atlas labeling.” 2016 SPIE Conference on Medical Imaging, San Diego, California, USA, 27. Feb.-3. March 2016.

See other publications here: Google Scholar.