Nerve Fiber Segmentation in Bright-Field Microscopy Images of Skin Biopsies Using Deep Learning

Diagnosis of patients suffering from small-fiber neuropathy is a challenging task and requires accurate measurement of the density of nerve fibers crossing the dermal-epidermal junction in the skin. Currently this is typically done by expert manual counting in microscopy images of sliced and stained skin biopsies. It is a rather subjective and labor-intensive process that would benefit greatly from more automated approaches. Previously we have explored classical image processing methods for this, with very limited success. Here we explore the potential of convolutional neural networks and deep learning for the task. The results of preliminary experiments show the networks perform close to the expert and outperform novices and our previous method.

[1]  Catharina G. Faber,et al.  Small-fibre neuropathies—advances in diagnosis, pathophysiology and management , 2012, Nature Reviews Neurology.

[2]  Hanchuan Peng,et al.  V3D enables real-time 3D visualization and quantitative analysis of large-scale biological image data sets , 2010, Nature Biotechnology.

[3]  Kazuyuki Tamura,et al.  A semi-automated analysis method of small sensory nerve fibers in human skin-biopsies , 2010, Journal of Neuroscience Methods.

[4]  E. Wilder-Smith,et al.  Small fiber neuropathy: Getting bigger! , 2016, Muscle & nerve.

[5]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[6]  L. Padua,et al.  New technologies for the assessment of neuropathies , 2017, Nature Reviews Neurology.

[7]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[8]  Andreas C. Themistocleous,et al.  The clinical approach to small fibre neuropathy and painful channelopathy , 2014, Practical Neurology.

[9]  Alexey Shvets,et al.  TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation , 2018, Computer-Aided Analysis of Gastrointestinal Videos.

[10]  D. Sène.  Small fiber neuropathy: Diagnosis, causes, and treatment. , 2017, Joint, bone, spine : revue du rhumatisme.

[11]  P. Sonneveld,et al.  Chemotherapy-induced peripheral neuropathies in hematological malignancies , 2014, Journal of Neuro-Oncology.

[12]  A G Valdecasas,et al.  On the extended depth of focus algorithms for bright field microscopy. , 2001, Micron.

[13]  J. Valls-Solé,et al.  European Federation of Neurological Societies/Peripheral Nerve Society Guideline on the use of skin biopsy in the diagnosis of small fiber neuropathy. Report of a joint task force of the European Fe‐deration of Neurological Societies and the Peripheral Nerve Society , 2010, European journal of neurology.

[14]  Dimitri Van De Ville,et al.  Model-Based 2.5-D Deconvolution for Extended Depth of Field in Brightfield Microscopy , 2008, IEEE Transactions on Image Processing.

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Claudia Sommer,et al.  A semi‐automated method to assess intraepidermal nerve fibre density in human skin biopsies , 2016, Histopathology.

[17]  P. Dyck.  Incidence and prevalence of small-fiber neuropathy: A survey in the Netherlands , 2014, Neurology.

[18]  G. Wasner,et al.  Neuropathic pain: diagnosis, pathophysiological mechanisms, and treatment , 2010, The Lancet Neurology.

[19]  Eugenio Culurciello,et al.  LinkNet: Exploiting encoder representations for efficient semantic segmentation , 2017, 2017 IEEE Visual Communications and Image Processing (VCIP).