Translator Disclaimer
18 July 2018 Understanding the learned behavior of customized convolutional neural networks toward malaria parasite detection in thin blood smear images
Author Affiliations +
Abstract
Convolutional neural networks (CNNs) have become the architecture of choice for visual recognition tasks. However, these models are perceived as black boxes since there is a lack of understanding of the learned behavior from the underlying task of interest. This lack of transparency is a serious drawback, particularly in applications involving medical screening and diagnosis since poorly understood model behavior could adversely impact subsequent clinical decision-making. Recently, researchers have begun working on this issue and several methods have been proposed to visualize and understand the behavior of these models. We highlight the advantages offered through visualizing and understanding the weights, saliencies, class activation maps, and region of interest localizations in customized CNNs applied to the challenge of classifying parasitized and uninfected cells to aid in malaria screening. We provide an explanation for the models’ classification decisions. We characterize, evaluate, and statistically validate the performance of different customized CNNs keeping every training subject’s data separate from the validation set.
© 2018 Society of Photo-Optical Instrumentation Engineers (SPIE) 2329-4302/2018/$25.00 © 2018 SPIE
Sivaramakrishnan Rajaraman, Kamolrat Silamut, Md. A. Hossain, Ilker Ersoy, Richard J. Maude, Stefan Jaeger, George R. Thoma, and Sameer K. Antani "Understanding the learned behavior of customized convolutional neural networks toward malaria parasite detection in thin blood smear images," Journal of Medical Imaging 5(3), 034501 (18 July 2018). https://doi.org/10.1117/1.JMI.5.3.034501
Received: 7 March 2018; Accepted: 25 June 2018; Published: 18 July 2018
JOURNAL ARTICLE
11 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Saliency location based on color contrast
Proceedings of SPIE (April 15 2014)
Recognition as translating images into text
Proceedings of SPIE (January 09 2003)

Back to Top