IEICE TRANSACTIONS on Information
Brain Tumor Classification using Under-Sampled k-Space Data: A Deep Learning Approach
Summary :
We assess how well the recently created MRI reconstruction technique, Multi-Resolution Convolutional Neural Network (MRCNN), performs in the core medical vision field (classification). The primary goal of MRCNN is to identify the best k-space undersampling patterns to accelerate the MRI. In this study, we use the Figshare brain tumor dataset for MRI classification with 3064 T1-weighted contrast-enhanced MRI (CE-MRI) over three categories: meningioma, glioma, and pituitary tumors. We apply MRCNN to the dataset, which is a method to reconstruct high-quality images from under-sampled k-space signals. Next, we employ the pre-trained VGG16 model, which is a Deep Neural Network (DNN) based image classifier to the MRCNN restored MRIs to classify the brain tumors. Our experiments showed that in the case of MRCNN restored data, the proposed brain tumor classifier achieved 92.79% classification accuracy for a 10% sampling rate, which is slightly higher than that of SRCNN, MoDL, and Zero-filling methods have 91.89%, 91.89%, and 90.98% respectively. Note that our classifier was trained using the dataset consisting of the images with full sampling and their labels, which can be regarded as a model of the usual human diagnostician. Hence our results would suggest MRCNN is useful for human diagnosis. In conclusion, MRCNN significantly enhances the accuracy of the brain tumor classification system based on the tumor location using under-sampled k-space signals.
- Publication
- IEICE TRANSACTIONS on Information Vol.E106-D No.11 pp.1831-1841
- Publication Date
- 2023/11/01
- Publicized
- 2023/08/15
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2022EDP7198
- Type of Manuscript
- PAPER
- Category
- Artificial Intelligence, Data Mining
Authors
Tania SULTANA
Kyushu University
Sho KUROSAKI
Kyushu University
Yutaka JITSUMATSU
Tokyo Institute of Technology
Shigehide KUHARA
Kyorin University
Jun'ichi TAKEUCHI
Kyushu University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Tania SULTANA, Sho KUROSAKI, Yutaka JITSUMATSU, Shigehide KUHARA, Jun'ichi TAKEUCHI, "Brain Tumor Classification using Under-Sampled k-Space Data: A Deep Learning Approach" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 11, pp. 1831-1841, November 2023, doi: 10.1587/transinf.2022EDP7198.
Abstract: We assess how well the recently created MRI reconstruction technique, Multi-Resolution Convolutional Neural Network (MRCNN), performs in the core medical vision field (classification). The primary goal of MRCNN is to identify the best k-space undersampling patterns to accelerate the MRI. In this study, we use the Figshare brain tumor dataset for MRI classification with 3064 T1-weighted contrast-enhanced MRI (CE-MRI) over three categories: meningioma, glioma, and pituitary tumors. We apply MRCNN to the dataset, which is a method to reconstruct high-quality images from under-sampled k-space signals. Next, we employ the pre-trained VGG16 model, which is a Deep Neural Network (DNN) based image classifier to the MRCNN restored MRIs to classify the brain tumors. Our experiments showed that in the case of MRCNN restored data, the proposed brain tumor classifier achieved 92.79% classification accuracy for a 10% sampling rate, which is slightly higher than that of SRCNN, MoDL, and Zero-filling methods have 91.89%, 91.89%, and 90.98% respectively. Note that our classifier was trained using the dataset consisting of the images with full sampling and their labels, which can be regarded as a model of the usual human diagnostician. Hence our results would suggest MRCNN is useful for human diagnosis. In conclusion, MRCNN significantly enhances the accuracy of the brain tumor classification system based on the tumor location using under-sampled k-space signals.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDP7198/_p
Copy
@ARTICLE{e106-d_11_1831,
author={Tania SULTANA, Sho KUROSAKI, Yutaka JITSUMATSU, Shigehide KUHARA, Jun'ichi TAKEUCHI, },
journal={IEICE TRANSACTIONS on Information},
title={Brain Tumor Classification using Under-Sampled k-Space Data: A Deep Learning Approach},
year={2023},
volume={E106-D},
number={11},
pages={1831-1841},
abstract={We assess how well the recently created MRI reconstruction technique, Multi-Resolution Convolutional Neural Network (MRCNN), performs in the core medical vision field (classification). The primary goal of MRCNN is to identify the best k-space undersampling patterns to accelerate the MRI. In this study, we use the Figshare brain tumor dataset for MRI classification with 3064 T1-weighted contrast-enhanced MRI (CE-MRI) over three categories: meningioma, glioma, and pituitary tumors. We apply MRCNN to the dataset, which is a method to reconstruct high-quality images from under-sampled k-space signals. Next, we employ the pre-trained VGG16 model, which is a Deep Neural Network (DNN) based image classifier to the MRCNN restored MRIs to classify the brain tumors. Our experiments showed that in the case of MRCNN restored data, the proposed brain tumor classifier achieved 92.79% classification accuracy for a 10% sampling rate, which is slightly higher than that of SRCNN, MoDL, and Zero-filling methods have 91.89%, 91.89%, and 90.98% respectively. Note that our classifier was trained using the dataset consisting of the images with full sampling and their labels, which can be regarded as a model of the usual human diagnostician. Hence our results would suggest MRCNN is useful for human diagnosis. In conclusion, MRCNN significantly enhances the accuracy of the brain tumor classification system based on the tumor location using under-sampled k-space signals.},
keywords={},
doi={10.1587/transinf.2022EDP7198},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - Brain Tumor Classification using Under-Sampled k-Space Data: A Deep Learning Approach
T2 - IEICE TRANSACTIONS on Information
SP - 1831
EP - 1841
AU - Tania SULTANA
AU - Sho KUROSAKI
AU - Yutaka JITSUMATSU
AU - Shigehide KUHARA
AU - Jun'ichi TAKEUCHI
PY - 2023
DO - 10.1587/transinf.2022EDP7198
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2023
AB - We assess how well the recently created MRI reconstruction technique, Multi-Resolution Convolutional Neural Network (MRCNN), performs in the core medical vision field (classification). The primary goal of MRCNN is to identify the best k-space undersampling patterns to accelerate the MRI. In this study, we use the Figshare brain tumor dataset for MRI classification with 3064 T1-weighted contrast-enhanced MRI (CE-MRI) over three categories: meningioma, glioma, and pituitary tumors. We apply MRCNN to the dataset, which is a method to reconstruct high-quality images from under-sampled k-space signals. Next, we employ the pre-trained VGG16 model, which is a Deep Neural Network (DNN) based image classifier to the MRCNN restored MRIs to classify the brain tumors. Our experiments showed that in the case of MRCNN restored data, the proposed brain tumor classifier achieved 92.79% classification accuracy for a 10% sampling rate, which is slightly higher than that of SRCNN, MoDL, and Zero-filling methods have 91.89%, 91.89%, and 90.98% respectively. Note that our classifier was trained using the dataset consisting of the images with full sampling and their labels, which can be regarded as a model of the usual human diagnostician. Hence our results would suggest MRCNN is useful for human diagnosis. In conclusion, MRCNN significantly enhances the accuracy of the brain tumor classification system based on the tumor location using under-sampled k-space signals.
ER -
English
