Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/3987
Full metadata record
DC FieldValueLanguage
dc.contributor.authorPaul, Indraneel-
dc.contributor.authorSahu, Adyasha-
dc.contributor.authorDas, Pradeep Kumar-
dc.contributor.authorMeher, Sukadev-
dc.date.accessioned2023-03-23T09:59:15Z-
dc.date.available2023-03-23T09:59:15Z-
dc.date.issued2023-03-
dc.identifier.citationInternational Conference on Innovation in Technology (INOCON),Bengaluru, Karnataka, India, 03rd - 05th March 2023en_US
dc.identifier.urihttp://hdl.handle.net/2080/3987-
dc.descriptionCopyright belongs to proceeding publisheren_US
dc.description.abstractDeep convolutional neural networks (DCNNs) have been extensively studied for different types of detection and classification in the field of biomedical image processing. Many of them have produced results that are on par with or even better than those of radiologists and neurologists. But, the challenge to get good results from such DCNNs is the requirement of large dataset. In this paper, a unique single-model based approach for classifying brain tumours on small dataset is presented in this study. A modified DCNN called the RegNetY-3.2G is used, integrated with regularization DropOut and DropBlock to prevent over-fitting. Furthermore, an improved augmentation technique called the RandAugment is used to lessen the problem of small dataset. Lastly, MWNL (Multi-Weighted New Loss) method and end to end CLS (cumulative learning strategy) is used to address the problem of unequal size of sample, complexity in the classification and to lessen the effect of aberrant samplesen_US
dc.subjectBrain Tumoren_US
dc.subjectDeep Learningen_US
dc.subjectMachine Learningen_US
dc.subjectData Augmentationen_US
dc.subjectConvolutional Neural Networken_US
dc.subjectMRIen_US
dc.titleDeep Convolutional Neural Network-based Automatic Detection of Brain Tumouren_US
dc.typeArticleen_US
Appears in Collections:Conference Papers

Files in This Item:
File Description SizeFormat 
2023_INOCON_IPaul_Deep.pdf944.47 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.