Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Variation of the Performance of Machine-Learning Based Image Classifier in Automated Detection of Itch-Induced Scratch

Version 1 : Received: 18 January 2020 / Approved: 19 January 2020 / Online: 19 January 2020 (03:13:48 CET)

How to cite: Liu, C.; Yan, S.; Wu, X.; Zhang, Z.; Li, W. Variation of the Performance of Machine-Learning Based Image Classifier in Automated Detection of Itch-Induced Scratch. Preprints 2020, 2020010205 (doi: 10.20944/preprints202001.0205.v1). Liu, C.; Yan, S.; Wu, X.; Zhang, Z.; Li, W. Variation of the Performance of Machine-Learning Based Image Classifier in Automated Detection of Itch-Induced Scratch. Preprints 2020, 2020010205 (doi: 10.20944/preprints202001.0205.v1).

Abstract

A 'little brother' of pain, itch is an unpleasant sensation that creates a specific urge to scratch. To date, various machine-learning based image classifiers (MBICs) have been proposed for quantitative analysis of itch-induced scratch behaviour of laboratory animals in an automated, non-invasive, inexpensive and real-time manner. In spite of MBICs' advantages, the overall performances (accuracy, sensitivity and specificity) of current MBIC approaches remains inconsistent, with their values varying from ~50% to ~99%, for which the reasons underlying have yet to be investigated further, both computationally and experimentally. To look into the variation of the performance of MBICs in automated detection of itch-induced scratch, this article focuses on the experimental data recording step, and reports here for the first time that MBICs' overall performance is inextricably linked to the sharpness of experimentally recorded video of laboratory animal scratch behaviour. This article furthermore demonstrates for the first time that a linearly correlated relationship exists between video sharpness and overall performance (accuracy and specificity, but not sensitivity) of MBICs, and highlight the primary role of experimental data recording in rapid, accurate and consistent quantitative assessment of laboratory animal itch.

Subject Areas

itch; scratch; automated real-time detection; machine-learning based image classifier; image sharpness

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.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.