Abstract Single Photon Emission Computed Tomography (SPECT) imaging has the potential to acquire information about areas of concerns in a non-invasive manner. Until now, however, deep learning based classification of SPECT images is still not studied yet. To examine the ability of convolutional neural networks on classifying whole-body SPECT bone scan images, in this work, we propose three different two-class classifiers based on the classical Visual Geometry Group (VGG) model. The proposed classifiers are able to automatically identify that whether or not a SPECT image include lesions via classifying this image into categories. Specifically, a pre-processing method is proposed to convert each SPECT file into an image via balancing difference of the detected uptake between SPECT files, normalizing elements of each file into an interval, and splitting an image into batches. Second, different strategies were introduced into the classical VGG16 model to develop classifiers by minimizing the number of parameters as many as possible. Lastly, a group of clinical whole-body SPECT bone scan files were utilized to evaluate the developed classifiers. Experiment results show that our classifiers are workable for automated classification of SPECT images, obtaining the best values of 0.838, 0.929, 0.966, 0.908 and 0.875 for accuracy, precision, recall, F-1 score and AUC value, respectively.

References

[1] Chen B., Deng W., and Du J., “Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, pp. 4021-4030, 2017.

[2] Figueiras R., Goh V., Padhani A., Naveira A., Caamaño A., and Martin C., “The Role of Functional Imaging in Colorectal Cancer,” American Journal of Roentgenology, vol. 195, no. 1, pp. 54-66, 2010.

[3] Fukushima K., “Neocognitron: A Hierarchical Neural Network Capable of Visual Pattern Recognition,” Neural Networks, vol. 1, no. 2, pp. 119-130, 1988.

[4] Haidekker M., Nuclear Imaging Medical Imaging Technology, Springer, 2013.

[5] Huang G., Liu Z., Maaten LVD., and Weinberger K., “Densely Connected Convolutional Networks,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, pp. 2261-2269, 2017.

[6] Iizuka T., Fukasawa M., and Kameyama M., “Deep-Learning-Based Imaging Classification Identified Cingulate Island Sign in Dementia with Lewy Bodies,” Scientific Reports, vol. 9, no. 1, pp. 8944, 2019.

[7] Ker J., Wang L., Rao J., and Lim T., “Deep Learning Applications in Medical Image Analysis,” IEEE Access, vol. 6, pp. 9375-9389, 2018.

[8] Li X., Zhong A., Lin M, Guo N., Sitek A., Ye J., Thrall J., and Li Q., “Self-paced Convolutional Neural Network for Computer Aided Detection in Medical Imaging Analysis,” in Proceedings International Workshop on Machine Learning in Medical Imaging, Quebec, pp. 212-219, 2017.

[9] Litjens G., Kooi T., Bejnordi B., Setio A., Ciompi F., Ghafoorian M., Laak J., Ginneken B., and Sánchez C., “A Survey on Deep Learning in Medical Image Analysis,” Medical Image Analysis, vol. 42, no. 9, pp. 60-88, 2017.

[10] Ma L., Ma C., Liu Y., Wang X., and Xie W., “Diagnosis of Thyroid Diseases Using SPECT Mages Based On Convolutional Neural Network,” Journal of Medical Imaging and Health Informatics, vol. 8, no. 8, pp. 1684-1689, 2018.

[11] Ma L., Ma C., Liu Y., and Wang X., “Thyroid Diagnosis from SPECT Images Using Convolutional Neural Network with Optimization,” Computational Intelligence and Neuroscience, pp. 1-11, 2019.

[12] Martinez-Murcia F., Górriz J., Ramírez J., and Ortiz A., “Convolutional Neural Networks for Neuroimaging in Parkinson’s Disease: Is Preprocessing Needed?,” International Journal of Neural Systems, vol. 28, no. 10, pp. 1850035, 2018.

[13] Martinez-Murcia F., Ortiz A., Górriz J., et al., “A 3D Convolutional Neural Network Approach for The Diagnosis of Parkinson’s Disease,” in Proceedings International Work-Conference on the Interplay Between Natural and Artificial Computation, Corunna, pp. 324-333, 2017.

[14] Nair V., Hinton G., and Thorsten J., “Rectified linear Units Improve Restricted Boltzmann Machines,” in Proceedings International Conference on Machine Learning, Haifa, pp. 807-814, 2010.

[15] Ortiz A., Munilla J., Martínez-Ibañez M., Górriz J., Ramírez J., and Salas-Gonzalez D., “Parkinson’s Disease Detection Using Isosurfaces-Based Features and Convolutional Neural Networks,” Frontiers in Neuroinformatics, vol. 13, pp. 48, 2019.

[16] Ramakrishnan D. and Radhakrishnan K., “Applying Deep Convolutional Neural Network (DCNN) Algorithm in The Cloud Autonomous Vehicles Traffic,” The International Arab Journal of Information Technology, vol. 19, no. 2, pp. 186-194, 2022.

[17] Ravi D., Wong C., Deligianni F., Berthelot M., Andreu-Perez J., Lo B., Yang G., “Deep learning for Health Informatics,” IEEE Journal of Biomedical and Health Informatics, vol. 21, no. 1, pp. 4-21, 2017.

[18] Shen D., Wu G., and Suk H., “Deep Learning in Medical Image Analysis,” Annual Review of Biomedical Engineering, vol. 19, pp. 221-248, 2017.

[19] Simonyan K. and Zisserman A., “Very Deep Convolutional Networks for Large-Scale Image Recognition,” arXiv 2014, arXiv:1409.1556, 2014.

[20] Spier N., Christoph R., Rupprecht C., Navab N., Baust M., and Nekolla S., “Defect Detection in Cardiac SPECT Using Graph-Based Convolutional Neural Networks,” Journal of 8 The International Arab Journal of Information Technology, Vol. 20, No. 1, January 2023 Nuclear Medicine, vol. 59, no. 1, pp. 1541, 2018.

[21] Tian J., Liu G., Gu S., JUZ., Liu J., and GU D., “Deep Learning in Medical Image Analysis and its Challenges,”Acta Automatica Sinica, vol. 44, no. 3, pp. 401-424, 2018. Qiang Lin received his Ph.D. in computer science and technology from Northwestern Polytechnical University, China in 2014. He is currently a Professor with the School of Mathematics and Computer Science, Northwest Minzu University. His research interest includes medical image computing, pervasive computing, intelligent information processing, and human behavior sensing. Zhengxng Man received his M.S. in computer software and theory from Lanzhou University, China in 2005. He is currently a Professor with the School of Mathematics and Computer Science, Northwest Minzu University. His research interest includes medical image computing, software design, and intelligent information processing. Yongchun Cao received his M.S. in computer application technology from University of Science and Technology of China, China in 2002. He is currently a Professor with the School of Mathematics and Computer Science, Northwest Minzu University. His research interest includes medical image computing, intelligent information processing, and human behavior sensing. Haijun Wang received his chief physician in imaging and nuclear medicine in 2021. He is currently a director and Professor of Nuclear Medicine Department, Gansu Provincial Hospital. His research interest includes imaging diagnosis and radionuclide therapy.