Publication: Deep learning-based osteosarcoma mri image classification system
| datacite.subject.fos | oecd::Engineering and technology::Electrical engineering, Electronic engineering, Information engineering | |
| dc.contributor.author | Ravichandran, Moaneezza | |
| dc.date.accessioned | 2024-02-28T07:46:34Z | |
| dc.date.available | 2024-02-28T07:46:34Z | |
| dc.date.issued | 2022-07-01 | |
| dc.description.abstract | Radiomics is an emerging and evolve extensively with the advancements in Artificial Intelligence (AI) field. Radiomics is important in quantitative image analysis from medical image to extract imaging information for clinical application in large scale. The development of quantitative imaging methods along with machine learning has enabled the opportunity to move data science research towards translation for more personalized cancer treatments. Classifying model of MRI medical images for identification of existence of osteosarcoma using convolutional neural network (CNN) is proposed in this thesis. The objective of the study is to develop a suitable deep learning algorithm for radiomics feature extraction and image classification using MRI medical image. Pretrained network of ResNet-50 is fine-tuned to customize last few layers to perform the required task with small dataset. Classification of MRI image is achieved with accuracy of 97.4603%. The system is not feasible as the system is only able to classify two different types of images which documented in 2 different subfolders but not able to classify accordingly based feature extraction of the osteosarcoma MRI images. Index Terms—radiomics, osteosarcoma, deep learning, medical image. | |
| dc.identifier.uri | https://erepo.usm.my/handle/123456789/18507 | |
| dc.language.iso | en | |
| dc.title | Deep learning-based osteosarcoma mri image classification system | |
| dc.type | Resource Types::text::report | |
| dspace.entity.type | Publication | |
| oairecerif.author.affiliation | Universiti Sains Malaysia |