Automatic three-dimensional reconstruction of fascicles in peripheral nerves from histological images

Abstract

Computational studies can be used to support the development of peripheral nerve interfaces, but currently use simplified models of nerve anatomy, which may impact the applicability of simulation results. To better quantify and model neural anatomy across the population, we have developed an algorithm to automatically reconstruct accurate peripheral nerve models from histological cross-sections. We acquired serial median nerve crosssections from human cadaveric samples, staining one set with hematoxylin and eosin (H&E) and the other using immunohistochemistry (IHC) with anti-neurofilament antibody. We developed a four-step processing pipeline involving registration, fascicle detection, segmentation, and reconstruction. We compared the output of each step to manual ground truths, and additionally compared the final models to commonly used extrusions, via intersection-over-union (IOU). Fascicle detection and segmentation required the use of a neural network and active contours in H&E-stained images, but only simple image processing methods for IHC-stained images. Reconstruction achieved an IOU of 0.42±0.07 for H&E and 0.37±0.16 for IHC images, with errors partially attributable to global misalignment at the registration step, rather than poor reconstruction. This work provides a quantitative baseline for fully automatic construction of peripheral nerve models. Our models provided fascicular shape and branching information that would be lost via extrusion.

Organ- and function-specific anatomical organization of vagal fibers supports fascicular vagus nerve stimulation

“…Deep-learning based algorithms have recently received attention in anatomically guided, medical image segmentation [ 90 ]. With regard to segmentation of anatomical features of nerves, deep-learning algorithms have been used on EM images, to resolve single fibers, and on ultrasound [ 91 ] and histological images [ 92 ], to resolve fascicles. To the best of our knowledge, this is the first use of convolutional neural networks on micro-CT and IHC data, to segment and extract anatomical features from micro-CT or IHC data in a user-assisted, semi-automated manner.…”

Enhancing the selective electrical activation of human vagal nerve fibers: a comparative computational modeling study with validation in a rat sciatic model

“…Another minor limitation of our simulations was the necessity of estimating the position of the vagus nerve within the neurovascular bundle, which was due to the limited resolution of the images obtained from the Visible Human Project. Future histologic studies could improve the precision of the model by extracting vagus nerve position data at regular intervals along the cervical vagus nerve, and then reconstructing the nerve as in situ [51]. Magnetic resonance neurography could also be performed to acquire in-vivo images of the vagus nerve within the cervical region; this could be done on multiple volunteers to allow for comparison between individuals.…”

Organ- and function-specific anatomical organization of the vagus nerve supports fascicular vagus nerve stimulation

“…Deep-learning based algorithms have recently received attention in anatomically guided, medical image segmentation [44]. With regard to segmentation of anatomical features of nerves, deep-learning algorithms have been used on EM images [45], with regard to single fibers, and on ultrasound [46] and histological images [47], with regard to fascicles. To the best of our knowledge, this is the first use of convolutional neural networks, in particular mask-RCNN, on micro-CT and IHC data, to automatically segment and extract anatomical features at the fascicle and single fiber level.…”