Neuropathy Classification of Corneal Nerve Images Using Artificial Intelligence

الموضوعات

علوم تطبيقية وتكنولوجية

الملخص

Nerve variations in the human cornea have been associated with alterations inthe neuropathy state of a patient suffering from chronic diseases. For some diseases,such as diabetes, detection of neuropathy prior to visible symptoms is important,whereas for others, such as multiple sclerosis, early prediction of disease worsening iscrucial. As current methods fail to provide early diagnosis of neuropathy, in vivocorneal confocal microscopy enables very early insight into the nerve damage byilluminating and magnifying the human cornea. This non-invasive method captures asequence of images from the corneal sub-basal nerve plexus. Current practices ofmanual nerve tracing and classification impede the advancement of medical research inthis domain. Since corneal nerve analysis for neuropathy is in its initial stages, there isa dire need for process automation.To address this limitation, we seek to automate the two stages of this process:nerve segmentation and neuropathy classification of images. For nerve segmentation,we compare the performance of two existing solutions on multiple datasets to select theappropriate method and proceed to the classification stage. Consequently, we approachneuropathy classification of the images through artificial intelligence using AdaptiveNeuro-Fuzzy Inference System, Support Vector Machines, Naïve Bayes and k-nearestneighbors. We further compare the performance of machine learning classifiers withdeep learning. We ascertained that nerve segmentation using convolutional neural networks provided a significant improvement in sensitivity and false negative rate byat least 5% over the state-of-the-art software. For classification, ANFIS yielded the bestclassification accuracy of 93.7% compared to other classifiers. Furthermore, for thisproblem, machine learning approaches performed better in terms of classificationaccuracy than deep learning.

روابط وملفات

التعريف والنوع

رقم الوثيقة

ffbb1c2e-8cda-4581-8f11-540df2e3dee0

رقم العقد

0

نوع الوسائط

Crawler

نوع المحتوى

الرسائل العلمية

صيغة المصدر

رسائل ماجيستير

نوع الملف

pdf text

أسماء الملفات

2018420_1.pdf

بيانات النشر

ألقاب المؤلفين

[{"name_ar":" Tooba Salahuddin","title_ar":"اعداد","title_en":"Preparation"},{"name_ar":"Uvais Ahmed Qidwai","title_ar":"اشراف","title_en":"Supervision"},{"name_ar":"سمية المديد","title_ar":"اشراف","title_en":"Supervision"}]

اللغة

English

المصدر والدورية

اسم المصدر

Neuropathy Classification of Corneal Nerve Images Using Artificial Intelligence

المحتوى والصفحات

عدد الصفحات

0

إشراف وإعداد

الإشراف

Uvais Ahmed Qidwai, سمية المديد

الإعداد

Tooba Salahuddin

الاقتباسات الببليوغرافية