Classification of brain tumours in MR images using deep spatiospatial models

被引:38
|
作者
Chatterjee, Soumick [1 ,2 ,3 ]
Nizamani, Faraz Ahmed [4 ]
Nurnberger, Andreas [2 ,3 ,5 ]
Speck, Oliver [5 ,6 ,7 ]
机构
[1] Otto von Guericke Univ, Biomed Magnet Resonance, Magdeburg, Germany
[2] Otto von Guericke Univ, Data & Knowledge Engn Grp, Magdeburg, Germany
[3] Otto von Guericke Univ, Fac Comp Sci, Magdeburg, Germany
[4] Otto von Guericke Univ, Inst Med Engn, Magdeburg, Germany
[5] Ctr Behav Brain Sci, Magdeburg, Germany
[6] German Ctr Neurodegenerat Dis, Magdeburg, Germany
[7] Leibniz Inst Neurobiol, Magdeburg, Germany
关键词
D O I
10.1038/s41598-022-05572-6
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
A brain tumour is a mass or cluster of abnormal cells in the brain, which has the possibility of becoming life-threatening because of its ability to invade neighbouring tissues and also form metastases. An accurate diagnosis is essential for successful treatment planning, and magnetic resonance imaging is the principal imaging modality for diagnosing brain tumours and their extent. Deep Learning methods in computer vision applications have shown significant improvement in recent years, most of which can be credited to the fact that a sizeable amount of data is available to train models, and the improvements in the model architectures yield better approximations in a supervised setting. Classifying tumours using such deep learning methods has made significant progress with the availability of open datasets with reliable annotations. Typically those methods are either 3D models, which use 3D volumetric MRIs or even 2D models considering each slice separately. However, by treating one spatial dimension separately or by considering the slices as a sequence of images over time, spatiotemporal models can be employed as "spatiospatial" models for this task. These models have the capabilities of learning specific spatial and temporal relationships while reducing computational costs. This paper uses two spatiotemporal models, ResNet (2+1)D and ResNet Mixed Convolution, to classify different types of brain tumours. It was observed that both these models performed superior to the pure 3D convolutional model, ResNet18. Furthermore, it was also observed that pre-training the models on a different, even unrelated dataset before training them for the task of tumour classification improves the performance. Finally, Pre-trained ResNet Mixed Convolution was observed to be the best model in these experiments, achieving a macro F1-score of 0.9345 and a test accuracy of 96.98%, while at the same time being the model with the least computational cost.
引用
收藏
页数:11
相关论文
共 50 条
  • [1] Classification of brain tumours in MR images using deep spatiospatial models
    Soumick Chatterjee
    Faraz Ahmed Nizamani
    Andreas Nürnberger
    Oliver Speck
    [J]. Scientific Reports, 12
  • [2] Classification of brain tumours from MR images with an enhanced deep learning approach using densely connected convolutional network
    Prakash, R. Meena
    Kumari, R. Shantha Selva
    Valarmathi, K.
    Ramalakshmi, K.
    [J]. COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION, 2023, 11 (02): : 266 - 277
  • [3] Classification of brain tumors from MR images using deep transfer learning
    Polat, Ozlem
    Gungen, Cahfer
    [J]. JOURNAL OF SUPERCOMPUTING, 2021, 77 (07): : 7236 - 7252
  • [4] Classification of brain tumors from MR images using deep transfer learning
    Özlem Polat
    Cahfer Güngen
    [J]. The Journal of Supercomputing, 2021, 77 : 7236 - 7252
  • [5] Application of deep transfer learning for automated brain abnormality classification using MR images
    Talo, Muhammed
    Baloglu, Ulas Baran
    Yildirim, Ozal
    Acharya, U. Rajendra
    [J]. COGNITIVE SYSTEMS RESEARCH, 2019, 54 : 176 - 188
  • [6] A Deep Transfer Learning Based Architecture for Brain Tumor Classification Using MR Images
    Badjie, Bakary
    Ulker, Ezgi Deniz
    [J]. INFORMATION TECHNOLOGY AND CONTROL, 2022, 51 (02): : 332 - 344
  • [7] Comparison of deep learning models for brain tumor classification using MRI images
    Cinar, Necip
    Kaya, Buket
    Kaya, Mehmet
    [J]. 2022 INTERNATIONAL CONFERENCE ON DECISION AID SCIENCES AND APPLICATIONS (DASA), 2022, : 1382 - 1385
  • [8] Using neural networks to automatically detect brain tumours in MR images
    Dickson, S
    Thomas, BT
    Goddard, P
    [J]. INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 1997, 8 (01) : 91 - 99
  • [9] Deep Learning Architectures for the Analysis and Classification of Brain Tumors in MR Images
    Osorio-Barone, A.
    Contreras-Ortiz, S. H.
    [J]. 16TH INTERNATIONAL SYMPOSIUM ON MEDICAL INFORMATION PROCESSING AND ANALYSIS, 2020, 11583
  • [10] Detection and Classification of Artifacts in Structural Brain MR Images Using Deep Convolutional Neural Networks
    Sujit, S.
    Gabr, R.
    Coronado, I.
    Narayana, P.
    [J]. MEDICAL PHYSICS, 2019, 46 (06) : E386 - E387