Computerized Classification Method for 1p/19q Codeletion in Low-Grade Glioma on Brain MRI Using Multi-Scale 3D-CNNs with Attention Mechanism

被引：0

作者：

Tanaka D. ^{[1
]}

Hizukuri A. ^{[1
]}

Nakayama R. ^{[1
]}

机构：

[1] Graduate School of Science and Engineering, Ritsumeikan University, 1-1-1, Nojihigashi, Shiga, Kusatsu

来源：

IEEJ Transactions on Electronics, Information and Systems | 2022年 / 142卷 / 05期

关键词：

1p/19q codeletion; attention mechanism; attention pooling; brain MRI; low-grade glioma;

D O I：

10.1541/ieejeiss.142.550

中图分类号：

学科分类号：

摘要：

The purpose of this study was to develop a computerized classification method for low-grade gliomas (LGGs) with/without 1p/19q codeletion on brain MRI using multi-scale 3D-convolutional neural networks (Multi-scale 3D-CNNs) with an attention mechanism that analyzes only the tumor region. Our database consisted of brain T2-weighted MRI images for 159 patients (102 LGGs with 1p/19q codeletion and 57 LGGs without it) from The Cancer Imaging Archive. The proposed method was constructed from a feature extractor, an attention mechanism, and a perception branch. In the feature extractor, the feature maps were extracted from input images. The attention mechanism generated the attention maps focusing on a tumor region from those feature maps. The feature maps on the tumor region were then obtained using an attention pooling with the attention maps. In the perception branch, the likelihood of LGG with 1p/19q codeletion was evaluated based on the feature maps of the tumor region. The classification accuracy, the sensitivity, the specificity, and the area under the receiver operating characteristic curve for the proposed method were 78.0%, 82.4%, 70.2%, and 0.838, showing a significant improvement when compared with the multi-scale 3D-CNNs without the attention mechanism (69.8%, 75.5%, 59.6%, and 0.717; p = 0.001). © 2022 The Institute of Electrical Engineers of Japan.

引用

页码：550 / 556

页数：6

共 23 条

[1]

Ichimura K., Arita H., Narita Y., Genetic Basis for the Development of Adult Gliomas, Jpn J Neurosurg, 23, 7, pp. 532-540, (2014)

[2]

Nitta M., Komori T., Outline and Problems of the WHO 2016 Classification of Tumors of the Central Nervous System, Jpn J Neurosurg, 26, 11, pp. 782-791, (2017)

[3]

Cairncross G., Wang M., Shaw E., Jenkins R., Brachman D., Buckner J., Fink K., Souhami L., Laperriere N., Curran W., Mehta M., Phase Ⅲ trial of chemoradiotherapy for anaplastic oligodendroglioma: long-term results of RTOG 9402, J Clin Oncol, 31, 3, pp. 337-343, (2013)

[4]

van den Bent M. J., Baumert B., Erridge S. C., Et al., Interim results from the CATNON trial (EORIC study 26053-22054) of treatment with concurrent and adjuvant temozolomide for 1p/19q non-co-deleted anaplastic glioma: a phase 3, randomized, open-label intergroup study, Lancet, 390, pp. 1645-1653, (2017)

[5]

Ruff M. W., Uhm J., Anaplastic Glioma: Treatment Approaches in the Era of Molecular Diagnostics, Curr Treat Options Oncol, 19, 12, (2018)

[6]

Miki S., Ichimura K., Narita Y., How to understand the Results of Basic Glioma Genome Sequence Data, Jpn J Neurosurg, 26, 11, pp. 806-816, (2017)

[7]

Gonzalez S. R., Zemmoura I., Tauber C., Deep Convolutional Neural Network to predict 1p19q co-deletion and IDH1 mutation status from MRI in Low Grade Gliomas, International Conference on Pattern Recognition Systems (ICPRS), (2019)

[8]

Akkus Z., Ali I., Sedlar J., Agrawal J. P., Parney I. F., Giannini C., Erickson B. J., Predicting Deletion of Chromosomal Arms 1p/19q in Low-Grade Gliomas from MR Images Using Machine Intelligence, J Digit Imaging, 30, pp. 469-476, (2017)

[9]

Decuyper M., Bonte S., Deblaere K., Holen R. V., Automated MRI based pipeline for glioma segmentation and prediction of grade, IDH mutation and 1p19q co-deletion, Computerized Medical Imaging and Graphics, 88, pp. 1-9, (2021)

[10]

Yogananda C. G. B., Shah B. R., Yu F. F., Pinho M. C., Nalawade S. S., Murugesan G. K., Wagner B. C., Mickey B., Patel T. R., Fei B., Madhuranthakam A. J., Maldjian J. A., A novel fully automated MRI-based deep-learning method for classification of 1p/19q co-deletion status in brain gliomas, Neuro-Oncology Advances, 2, 4, pp. iv42-iv48, (2020)

← 1 2 3 →