IP Indian Journal of Anatomy and Surgery of Head, Neck and Brain
Official Publication of Khyati Education And Research Foundation
Official Publication of Khyati Education And Research Foundation
Print ISSN: 2581-5210
Online ISSN: 2581-5229
CODEN : IIJAAL
IP Indian Journal of Anatomy and Surgery of Head, Neck and Brain (IJASHNB) open access, peer-reviewed quarterly journal publishing since 2015 and is published under the Khyati Education and Research Foundation (KERF), is registered as a non-profit society (under the society registration act, 1860), Government of India with the vision of various accredited vocational courses in healthcare, education, paramedical, yoga, publication, teaching and research activity, with the aim of faster and better dissemination of knowledge, we will be publishing more...Original Article
Author Details :
Volume : 10, Issue : 4, Year : 2024
Article Page : 92-96
https://doi.org/10.18231/j.ijashnb.2024.020
Abstract
Medical image segmentation is a pertinent issue, with deep learning being a leading solution. However, the demand for a substantial number of fully annotated images for training extensive models can be a hurdle, particularly for applications with diverse images, such as brain tumors, which can manifest in various sizes and shapes. In contrast, the recent Feature Learning from Image Markers (FLIM) methodology, which incorporates an expert in the learning process, has proven to be effective. This approach generates compact networks requiring only a few images to train the convolutional layers without backpropagation. In our study, we implement the interactive—technique for image collection plus neural-nets-training with reference to F.L.I.M, exploring the user’s knowledge. The results underscore the efficacy of our methodology, as we were able to select a small set of images to train the encoder of a U-shaped network, achieving performance on par with manual selection and even surpassing the same U-shaped network trained by backpropagation with all training images. Index Terms—Deep Learning, Brain, Tumor, Segmentation, Interactive Machine Learning.
Keywords: Brain, Tumor, Segmentation, Interactive Machine Learning
How to cite : Raju V R, Brain tumor segmentation network: A study through interactive image selection and neural-nets training method. IP Indian J Anat Surg Head Neck Brain 2024;10(4):92-96
This is an Open Access (OA) journal, and articles are distributed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 License, which allows others to remix, tweak, and build upon the work non-commercially, as long as appropriate credit is given and the new creations are licensed under the identical terms.
