ScaffoldNet: Detecting and Classifying Biomedical Polymer-Based\n Scaffolds via a Convolutional Neural Network

2018/05/17 by Darlington Akogo, Akogo, Darlington Ahiale, Xavier‐Lewis Palmer +1
Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Infrastructure Maintenance and Monitoring

paper · pdf · doi:10.48550/arxiv.1805.08702

openalex publication_date 2018/05/17 · openalex created_date 2022/09/07 · openalex updated_date 2026/07/28

Abstract

We developed a Convolutional Neural Network model to identify and classify\nAirbrushed (alternatively known as Blow-spun), Electrospun and Steel Wire\nscaffolds. Our model ScaffoldNet is a 6-layer Convolutional Neural Network\ntrained and tested on 3,043 images of Airbrushed, Electrospun and Steel Wire\nscaffolds. The model takes in as input an imaged scaffold and then outputs the\nscaffold type (Airbrushed, Electrospun or Steel Wire) as predicted\nprobabilities for the 3 classes. Our model scored a 99.44% Accuracy,\ndemonstrating potential for adaptation to investigating and solving complex\nmachine learning problems aimed at abstract spatial contexts, or in screening\ncomplex, biological, fibrous structures seen in cortical bone and fibrous\nshells.\n

Related

• Rapid prediction of lab-grown tissue properties using deep learning
• Rapid prediction of organisation in engineered corneal, glial and fibroblast tissues using machine learning and biophysical models
• Evaluating Deep Convolutional Neural Networks for Material\n Classification
• The effectiveness of data augmentation in porous substrate, nanowire, fiber and tip images at the level of deep learning intelligence
• Parameters, Properties, and Process: Conditional Neural Generation of Realistic SEM Imagery Towards ML-assisted Advanced Manufacturing