好色先生

好色先生

Explore the latest content from across our publications

Log In

Forgot Password?
Create New Account

Loading... please wait

Abstract Details

Morphometric Analysis of Peripheral Nerve through Deep Learning
General Neurology
S32 - General Neurology: Advances in Neurology: From the Clinic to the Bench (3:52 PM-4:03 PM)
003

Most neurological diseases produce one of two key pathological changes – axonal loss or demyelination – or a combination of the two. Therefore, studying these disorders requires rigorous quantification of myelin and axon pathology. Traditional manual quantification is time-consuming and may suffer from inter-observer variation. Deep-learning has been utilized to automate image analysis. The aim of the present study is to develop a Convolutional Neural Network (CNN) – based approach to segment images of mouse nerve.

To develop a method for nerve morphometric analysis through deep learning.

We used Keras, a deep-learning library, to create a CNN based on U-net architecture for improved localization of image features. Training data included 280 microscopic images of mouse sciatic nerve cross-sections paired with their respective segmentation masks obtained in previous studies of neuropathy mouse models.

After training, accuracy plateaued at 0.91 dice coefficient and the validation dice coefficient varied between 0.81 and 0.85. Compared to the manual method, the CNN-based automated method exhibited a 2.5% decrease of nerve fiber density, 4.2% lower axonal diameter, 2.0% larger myelin thickness, and 2.6% lower G-ratio. Distribution of myelinated fiber diameters was very similar between the two methods, thus no size of nerve fibers was disproportionately affected by the automation. After training, measurements took 16-20 minutes per image while manual segmentation took 65-76 minutes.

We have developed a CNN-based method to analyze nerve morphometrics. Previously acquired nerve images were used to train the model to recognize atypical myelin structures, including severe pathological changes. The trained model decreased analysis time with excellent accuracy in axonal density and g-ratio. We were not able to eliminate manual refinement of the automated segmentation product, but our data have provided alternative methods for improvement. Overall, greatly increased efficiency in the automation out-weighs minor limitations, thus justifying our confidence in its prospects. 
Authors/Disclosures
Daniel Moiseev
PRESENTER
Daniel Moiseev has nothing to disclose.
No disclosure on file
Jun Li, MD, PhD, FAAN (Harris Methodist Hospital) The institution of Dr. Li has received personal compensation in the range of $500-$4,999 for serving as a Consultant for FDA. The institution of Dr. Li has received research support from NIH. Dr. Li has a non-compensated relationship as a Associate Editor of ACTN journal with ANA that is relevant to AAN interests or activities.