Preprint Article Version 1 This version is not peer-reviewed

Implementation of Regional-CNN and SSD Machine Learning Object Detection Architectures for the Real Time Analysis of Blood Borne Pathogens in Dark Field Microscopy

Version 1 : Received: 6 July 2018 / Approved: 6 July 2018 / Online: 6 July 2018 (14:38:52 CEST)

How to cite: Fleury, D.; Fleury, A. Implementation of Regional-CNN and SSD Machine Learning Object Detection Architectures for the Real Time Analysis of Blood Borne Pathogens in Dark Field Microscopy. Preprints 2018, 2018070119 (doi: 10.20944/preprints201807.0119.v1). Fleury, D.; Fleury, A. Implementation of Regional-CNN and SSD Machine Learning Object Detection Architectures for the Real Time Analysis of Blood Borne Pathogens in Dark Field Microscopy. Preprints 2018, 2018070119 (doi: 10.20944/preprints201807.0119.v1).

Abstract

The emerging use of visualization techniques in pathology and microbiol- ogy  has  been  accelerated  by  machine  learning  (ML)  approaches  towards image preprocessing, classification, and feature extraction in an increasingly complex series of datasets. Modern Convolutional Neural Network (CNN) architectures have developed into an umbrella of vast image reinforcement and recognition methods, including a combined classification-localization of single/multi-object featured images. As a subtype neural network, CNN cre- ates a rapid order of complexity by initially detecting borderlines, edges, and colours in images for  dataset  construction,  eventually capable in mapping intricate  objects  and  conformities.  This  paper  investigates  the  disparities between Tensorflow object detection APIs, exclusively, Single Shot Detector (SSD) Mobilenet V1 and the Faster RCNN Inception V2 model, to sample computational  drawbacks in accuracy-precision vs. real  time visualization capabilities. The situation of rapid ML medical image analysis is theoretically framed in regions with limited access to pathology and disease prevention departments  (e.g.  3rd  world  and  impoverished  countries).  Dark  field  mi- croscopy datasets of an initial 62  XML-JPG annotated training  files were processed under Malaria and Syphilis classes. Model trainings were halted as soon as loss values were regularized and converged.

Subject Areas

Convolutional Neural Network,Single Shot Detector, Regional Convolutional Neural Network, Machine Learning, Visualization-Localization

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.