Deep Learning Guided Partitioned Shape Model for Anterior Visual Pathway Segmentation

Abstract

Analysis of cranial nerve systems, such as the anterior visual pathway (AVP), from MRI sequences is challenging due to their thin long architecture, structural variations along the path, and low contrast with adjacent anatomic structures. Segmentation of a pathologic AVP (e.g., with low-grade gliomas) poses additional challenges. In this work, we propose a fully automated partitioned shape model segmentation mechanism for AVP steered by multiple MRI sequences and deep learning features. Employing deep learning feature representation, this framework presents a joint partitioned statistical shape model able to deal with healthy and pathological AVP. The deep learning assistance is particularly useful in the poor contrast regions, such as optic tracts and pathological areas. Our main contributions are: 1) a fast and robust shape localization method using conditional space deep learning, 2) a volumetric multiscale curvelet transform-based intensity normalization method for robust statistical model, and 3) optimally partitioned statistical shape and appearance models based on regional shape variations for greater local flexibility. Our method was evaluated on MRI sequences obtained from 165 pediatric subjects. A mean Dice similarity coefficient of 0.779 was obtained for the segmentation of the entire AVP (optic nerve only =0.791 ) using the leave-one-out validation. Results demonstrated that the proposed localized shape and sparse appearance-based learning approach significantly outperforms current state-of-the-art segmentation approaches and is as robust as the manual segmentation.

Deep Learning for Health Informatics

“…It is different than other methods because it does not require a locally linear manifold space. Mansoor et al [54] developed a fully automated shape model segmentation mechanism for the analysis of cranial nerve systems. The deep learning approach outperforms conventional methods particularly in regions with low contrast, such as optic tracts and areas with pathology.…”

Variability and reproducibility in deep learning for medical image segmentation

“…In Table 2 , we can see that the main strategy is to use a convolutional neural network (CNN) or recurrent neural network (RNN) architecture (91% of the methods) for segmentation (these architectures are types of DL models 14 ). Two articles 51 , 58 test several different DL architectures in their frameworks (5 for 51 and 2 for 58 ).…”

Optic pathway glioma volume predicts retinal axon degeneration in neurofibromatosis type 1

“…MRI segmentation and volumetric analysis was performed as previously described. 9,16 Briefly, both optic nerves, the optic chiasm, and the proximal portion of the optic tracts were manually segmented using the MRI sequence. Segmentation of the optic tracts was limited to 10 millimeters beyond the chiasm as reliable visualization beyond this point was variable among patients.…”

“…To address this barrier, our laboratory is developing novel processing algorithms that combine multiple sequence types to permit accurate AVP segmentation. 16 We limited our study to children with OPGs secondary to NF1 as their imaging features and factors used to make treatment decisions can be different from sporadic OPGs. 2 Sporadic OPGs cause more severe and frequent events of vision loss.…”