Balance Graphs: An Aid for Studying Convolutional Neural Networks

Lyell Embery, Eva Ignatious, Sami Azam, Miriam Jonkman, Friso De Boer

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in Proceedingspeer-review

Abstract

Deep Learning Neural Networks offer a powerful tool to process visual data and to make decisions, but a limitation is its black box nature which offers low transparency to human examiners. This hurdle presents a particular challenge in using Neural Networks in safety-critical systems, which require high performance and transparency such as medical diagnosis of life-threatening diseases. This paper seeks to build and test a neural network for grading gliomas of comparable function and complexity to others in the field, then to apply Data Visualisation techniques to render the internal workings of the NN more understandable to a human observer. The purpose is to develop a system that can classify brain tumors into low-grade gliomas (LGG) and high-grade gliomas (HGG), to aid with diagnosis and prognosis The Brain Tumor Segmentation Challenge 2020 (BraTS2020) data set was used, with data categorised based on a combination of grade assigned in BraTS2020, and the labels in the segmentation data. As some categories are over-represented, methods were employed to ensure a better balance between different categories. Data augmentation was used to expand the limited number of scans in the BraTS2020. A 3D convolution neural network (CNN) was constructed to grade gliomas. With the method developed in this paper, an accuracy of 94.1% was achieved. A newly devised method to visually represent the weights of a convolution is explored. These graphs, called 'weight graphs' allow convolutions to be condensed into a visual medium. The weight graph is designed for easy visual interpretation of the weights assigned within a particular convolution. To overcome the limitations of weight graphs, an alternate graph was devised, called a balance graph, because it shows the overall balance of weights in a kernel, allowing for a quick impression of what effect a single kernel has. It is demonstrated that Balance Graphs improve the accessibility and transparency of the of the weights in convolution layers.

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE/ACIS 24th International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2022
EditorsShu-Ching Chen, Her-Terng Yau, Roland Stenzel, Hsiung-Cheng Lin
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages132-139
Number of pages8
ISBN (Electronic)9798350310412
DOIs
Publication statusPublished - 2022
Event24th IEEE/ACIS International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2022 - Taichung, Taiwan, Province of China
Duration: 7 Dec 20229 Dec 2022

Publication series

NameProceedings - 2022 IEEE/ACIS 24th International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2022

Conference

Conference24th IEEE/ACIS International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2022
Country/TerritoryTaiwan, Province of China
CityTaichung
Period7/12/229/12/22

Fingerprint

Dive into the research topics of 'Balance Graphs: An Aid for Studying Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this