Comparison of wavelet transformations to enhance convolutional neural network performance in brain tumor segmentation

BMC Medical Informatics and Decision Making

Mohamadreza Hajiabadi¹  Azadeh Bashiri²  Hassan Emami³  Behrouz Alizadeh Savareh⁴ 

[1] Brain and Spinal Cord Injury Research Center, Neuroscience Institute, Tehran University of Medical Sciences, Tehran, Iran;Department of Health Information Management, School of Health Management and Information Sciences, Health Human Resources Research Center, Clinical Education Research Center, Shiraz University of Medical Sciences, Shiraz, Iran;Faculty of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran;National Agency for Strategic Research in Medical Education, Tehran, Iran;Shiraz University of Medical Sciences, Shiraz, Iran;

关键词: Brain;    Tumor;    Segmentation;    MRI;    Convolutional neural network;   

DOI  :  10.1186/s12911-021-01687-4

来源: Springer

【 摘 要 】

Introduction and goal to backgroundDue to the importance of segmentation of MRI images in identifying brain tumors, various methods including deep learning have been introduced for automatic brain tumor segmentation. On the other hand, using a combination of methods can improve their performance. Among them is the use of wavelet transform as an auxiliary element in deep networks. The analysis of the requirements of such combinations has been addressed in this study.MethodIn this developmental study, different wavelet functions were used to compress brain MRI images and finally as an auxiliary element in improving the performance of the convolutional neural network in brain tumor segmentation.ResultsBased on the results of the tests performed, the Daubechies1 function was most effective in enhancing network performance in segmenting MRI images and was able to balance the performance and computational overload.ConclusionChoosing the wavelet function to optimize the performance of a convolutional neural network should be based on the requirements of the problem, also taking into account some considerations such as computational load, processing time, and performance of the wavelet function in optimizing CNN output in the intended task.

【 授权许可】

CC BY