[논문]A Parallel Deep Convolutional Neural Network for Alzheimer's disease classification on PET/CT brain images

Baydargil, Husnu Baris; Park, Jangsik; Kang, Do-Young; Kang, Hyun; Cho, Kook

doi:10.3837/tiis.2020.09.001

A Parallel Deep Convolutional Neural Network for Alzheimer's disease classification on PET/CT brain images 원문보기

KSII Transactions on internet and information systems : TIIS, v.14 no.9, 2020년, pp.3583 - 3597

Baydargil, Husnu Baris (Department of Electric Electronic and Communication Engineering, Kyungsung University) , Park, Jangsik (Department of Electric Electronic and Communication Engineering, Kyungsung University) , Kang, Do-Young (Department of Nuclear Medicine, Dong-a University College of Medicine, Dong-A University Hospital) , Kang, Hyun (Institute of Convergence Bio-Health, Dong-A University) , Cho, Kook (College of General Education, Dong-A University)

Abstract ▼ AI-Helper

In this paper, a parallel deep learning model using a convolutional neural network and a dilated convolutional neural network is proposed to classify Alzheimer's disease with high accuracy in PET/CT images. The developed model consists of two pipelines, a conventional CNN pipeline, and a dilated convolution pipeline. An input image is sent through both pipelines, and at the end of both pipelines, extracted features are concatenated and used for classifying Alzheimer's disease. Complimentary abilities of both networks provide better overall accuracy than single conventional CNNs in the dataset. Moreover, instead of performing binary classification, the proposed model performs three-class classification being Alzheimer's disease, mild cognitive impairment, and normal control. Using the data received from Dong-a University, the model performs classification detecting Alzheimer's disease with an accuracy of up to 95.51%.

주제어

표/그림 (16)

그림 Fig. 1. Amyloid-positive (left) and amyloid-negative (right) images using PET scans are used in the diagnosis of Alzheimer's disease.
그림 Fig. 2. Standard operations performed by the model down both pipelines.
그림 Fig. 3. The architecture of the proposed model. The top pipeline is a regular CNN with eight layers with each specific layer operations highlighted in Fig. 2. The bottom pipeline is dilated CNN with eight identical layers except that in this pipeline, dilation operation is used. In both pipelines, fully-connected layers are obtained, concatenated together, and this layer is connected to the classification layer with softmax operation.
그림 Fig. 4. Sample images from the dataset. Left image AD, middle one MCI, and the right image is the NC case. Image slices were taken from the same slice number of different patient's images (60th slice out of 110).
표 Table 1. The dataset information with the total number of images and the total number of patients for each designated class.
그림 Fig. 5. Flowchart of the method for creating sagittal and coronal axes using the axial images.
그림 Fig. 6. An example of created coronal images with AD, MCI, and NC, respectively. The slices are taken from the same 𝑖^th image of a person.
그림 Fig. 7. An example of created sagittal images with AD, MCI, and NC, respectively. The slices are taken from the same 𝑖^th image of a person.
표 Table 2. The total number of images that are used for training images after the bicubic interpolation process.
표 Table 3. The total number of images in the dataset after the data augmentation is applied.
그림 Fig. 8. The model's accuracy and loss value change through the epochs during the training. It can be seen that 120 epochs were sufficient for optimized accuracy and loss value.
그림 Fig. 9. Activation maps of the model for a test image for the AD case. The left box is the convolutional pipeline, and the right box is the dilated convolution pipeline. It can be seen that the activated areas for the test image complement each other; meaning, the dilated pipeline can capture features not obtained by convolutional pipeline, and vice versa.
그림 Fig. 10. Activation maps of the model for a test image for the MCI case.
그림 Fig. 11. Activation maps of the model for a test image for the NC case.
표 Table 4. Accuracy comparison between the developed model and other state-of-the-art classification models.
표 Table 5. Trainable parameter comparison between the proposed model and the benchmark models. The model has a large number of parameters.

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

제안 방법

Unfortunately, AD is only classified at its later stage, and earlier detection may only help slow the progression of cognitive decline, so it’s vital to be able to detect AD at its earlier stages. In this paper, a new proposed very deep parallel CNN which takes in three classes AD, MCI, and normal control (NC), and is capable of extracting different features of the same input data, concatenate these features and provide higher classification accuracy. The dataset used was provided with the collaborating Dong-a University Department of Nuclear Medicine.
In this paper, a parallel deep learning CNN model is proposed that is both capable of performing accurately in a given dataset, and computationally more efficient than similar very deep models such as VGG16. Convolutional and dilated convolutional pipelines work complementary with each other in extracting features the other pipeline cannot, which provides higher accuracy.
The development of radiotracers to visualize Aβ plaques in the brain has become an active area of AD research. In this work, FBB brain PET imaging data was used to develop and validate the proposed model.
Structural differences in the brain were identified through such research, to show the difference between a healthy brain and a brain that’s affected by AD.
In this paper, a parallel pipeline CNN model that uses both convolution operation and dilated convolution operation is proposed. The model extracts two distinct, but complementary image features that are spatially complementary to each other for each given brain image. One pipeline consists of conventional layers, whereas the other pipeline consists of dilated convolutional layers.
The proposed model is a parallel deep CNN that is designed to extract different abstract color-based spatial information using convolutional and dilated convolutional layers, and concatenate these extracted abstract information to achieve higher accuracy. While one pipeline is a standard 8-layer-deep CNN with normal convolutions, the other pipeline is an 8-layer-deep CNN with dilated convolutions [25].
The proposed model was able to extract more useful information from created sagittal images than the original axial images. This means that the spatial information carried in the sagittal plane is found to be more useful for the proposed model to perform classification more accurately.
Other axes, namely sagittal and coronal axes also carry spatial information in their relevant planes about plaque formations in the brain, which can be used to train the model. Thus, in this work, the proposed model was also tested to see how it would perform with other axes of the brain, sagittal, and coronal. Using the bicubic interpolation method, sagittal and coronal axes were created.

대상 데이터

In this paper, a new proposed very deep parallel CNN which takes in three classes AD, MCI, and normal control (NC), and is capable of extracting different features of the same input data, concatenate these features and provide higher classification accuracy. The dataset used was provided with the collaborating Dong-a University Department of Nuclear Medicine.
One pipeline consists of conventional layers, whereas the other pipeline consists of dilated convolutional layers. The extracted features coming from two pipelines are concatenated to be used in the classification stage The proposed model is trained with the dataset that is obtained from Dong-A University Department of Nuclear Medicine, using PET/CT images.

이론/모형

Stochastic gradient descent with momentum optimization algorithm was used for the proposed model. The training data is also split with training and cross-validation in 8:2 proportions.
The proposed model was compared with other well-known state-of-the-art models such as VGG16 [32], GoogLeNet Inception v4 [33], ResNet50 [34], and a sparse autoencoder specifically developed for AD classification in [35]. The results show that the proposed model outperforms all the comparison models by a large margin.

참고문헌 (35)

Alzheimer's Association, "2019 Alzheimer's disease facts and figures," Alzheimer's & Dementia, vol. 15, pp. 321-387, 2019.
R. Brookmeyer, E. Johnson, K. Ziegler-Graham and H.M. Arrighi, "Forecasting the global burden of Alzheimer's disease," Alzheimer's & Dementia, vol. 3, no. 3, pp. 186-191, July 2007.

상세보기
G. Frisoni, N.C. Fox, C. Jack, P. Scheltens and P. Thompson, "The clinical use of structural MRI in Alzheimer's disease," Nature Reviews Neurology, vol. 6, no.3, pp. 67-77, February 2010.
G. Litjens, T. Kooi, B.E. Bejnordi, A.A.A. Setio, F. Ciompi, M. Ghafoorian, J.A. van der Laak, B. Van Ginneken and C.I. Sanchez, "A survey on deep learning in medical image analysis," Medical Image Analysis, vol. 42, pp. 60-88, December 2017.

상세보기
J. Yanase and E. Triantaphyllou, "A systematic survey of computer-aided diagnosis in medicine: Past and present developments," Expert Systems with Applications, vol. 138, pp. 112821, December 2019.
A. Tufail, C. Rudisill. C. Egan, V.V. Kapetanakis, S. Vega-Salas, C.G. Owen, A. Lee, V. Louw, J. Anderson, G. Liew, L. Bolter, S. Srivinas, M. Nittala, S. Sadda, P. Taylor, and A.R. Rudnicka, "Automated Diabetic Retinopathy Image Assessment Software: Diagnostic Accuracy and Cost-Effectiveness Compared with Human Graders," Ophthalmology, Vol. 124, no. 3, pp. 343-351, March 2017.
Y. Fan, S.M. Resnick, X. Wu and C. Davatzikos, "Structural and functional biomarkers of prodromal Alzheimer's disease: a high-dimensional pattern classification study," Neuroimage, vol. 41, no. 2, pp. 277-285, June 2008.

상세보기
K. Hu, Y. Wang, K. Chen, L. Hou and X. Zhang, "Multi-scale features extraction from baseline structure MRI for MCI patient classification and AD early diagnosis," Neurocomputing, vol. 175, pp. 132-145, October 2016.

상세보기
R. Filiphovych, and C. Davatzikos and Initiative ADN et. al., "Semi-supervised pattern classification of medical images: application to mild cognitive impairment (MCI)," Neuroimage, vol. 55, no. 3, pp. 1109-1119, April 2011.

상세보기
A.K. Ambastha, "Neuroanatomical characterization of Alzheimer's disease using deep learning," Journal of National University of Singapore, October 2015.
K.R. Gray, R. Wolz, R.A. Heckermann, P. Aljabar, A. Hammers, D. Rueckert and Initiative ADN et. al., "Multi-region analysis of longitudinal FDG-PET for classification for the Alzheimer's disease," Neuroimage, vol. 60, no. 1, pp. 221-229, March 2012.
C. Davatzikos, P. Bhatt, L.M. Shaw, K.N. Batmangehelich and J.Q. Trojanowski, "Prediction of MCI to AD conversion, via MRI, CSF biomarkers, and pattern classification," Neurobiology of Aging, vol. 32 no.12, pp. 2322.e19-2322.e27, December 2011.
H, Suk, C.Y. Wee and D. Shen, "Discriminative group sparse representation for mild cognitive impairment classification," in Proc. of 4th Int. work-shop on machine learning in medical imaging, vol. 8134, pp.131-138, September 2013.
R.J. Perrin, A.M. Fagan and D.M. Holtzman, "Multimodal techniques for diagnosis and prognosis of Alzheimer's disease," Nature, vol. 461, no. 7266, pp. 916-922, October 2009.

상세보기
H. Choi and K.H. Jin, "Predicting cognitive decline with deep learning of brain metabolism and amyloid imaging," Behavioural Brain Research, vol. 344, pp. 103-109, February 2018.

상세보기
M. Liu, J. Zhang, E. Adeli and D. Shen, "Landmark-based deep multi-instance learning for brain disease diagnosis," Medical Image Analysis, vol. 43, pp. 157-168, October 2017.
J. Islam and Y. Zhang, "Brain MRI analysis for Alzheimer's disease diagnosis using an emsemble system of deep convolutional neural networks," Brain Informatics, vol. 5, no. 2, May 2018.
A. Gupta, M. Ayhan and A. Maida, "Natural image bases to represent neuroimaging data," in Proc. of the 30th Int. Conf. on machine learning, vol. 28, pp. 987-994, June 2013.
A. Payan and G. Montana, "Predicting Alzheimer's disease; a neuroimaging study with 3D convolutional networks," in Proc. of 4th Int. Conf. on Pattern Recognition Applications and Methods, vol. 2, February 2015.
T. Brosch, R. Tam and Initiative ADN et. al., "Manifold learning of brain MRIs by deep learning," in Proc. of the Int. Conf. on Medical Image Computing and Computer-assisted Intervention, vol. 16, pp. 633-640, 2013.
H.I. Suk, S.W. Lee, D. Shen and Initiative ADN et. al., "Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis," Neuroimage, vol. 101, pp. 569-582, November 2014.
H.I. Suk and D. Shen, "Deep learning-based feature representation for AD/MCI classification," in Proc. of Int. Conf. on Medical Image Computing and Computer-assisted Intervention, vol. 16, pp. 583-590, September 2013.
H.I. Suk, S.W. Lee, D. Shen and Initiative ADN et. al., "Latent feature representation with stacked auto-encoder for AD/MCI diagnosis," Brain Structure and Function, vol. 220, no. 2, pp. 841-859, March 2013.
D. Cardenas-Pena, D. Collazos-Huertas and G. Castellanos-Dominguez, "Centered kernel alignment enhancing neural network pretraining for MRI-based dementia diagnosis," Computational and Mathematical Methods in Medicine, vol. 2016, pp. 1-10, January 2016.
Y. Fisher and V. Koltun, "Multi-Scale Context Aggregation by Dilated Convolutions," in Proc. of the Int. Conf. on Learning Representations, May 2016.
S. Ioffe and C. Szegedy, "Batch normalization: accelerating deep network training by reducing internal covariate shift," in Proc of the Int. Conf. on Machine Learning, pp. 448-456, July 2015.
N. Srivastava, G.E. Hinton, A. Krizhevsky, I. Sutskever and R. Salakhundinov, "Dropout: a simple way to prevent neural networks from overfitting," Machine Learning, vol. 15, no. 1, pp. 1929-1958, June 2014.
G. Huang, Z.Liu, L. Van der Mateen and K.Q. Weinberger, "Densely connected convolutional networks," in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 2261-2269, July 2017.
A. Krizhevsky, I. Sutskever and G.E. Hinton, "Imagenet classification with deep convolutional neural networks," Advances in neural information processing systems, vol. 25, no. 2, pp. 1097-1105, December 2012.
M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G.S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghenmawat, I. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Jozefowicz, L. Kaser, M. Kudlur, J. Levenberg, D. Mane, R. Monga, S. Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Viegas, O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu and X. Zheng, "Tensorflow: Large-scale machine learning on heterogeneous systems," 2015. https://www.tensorflow.org
F. Chollet et. al., "Keras," 2015. https://github.com/keras-team/keras
K. Simonyan and A. Sizzerman, "Very deep convolutional networks for large-scale image recognition," in Proc. of 3rd Int. Conf. on Machine Learning, May 2015.
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. E. Reed, D. Anguelov, D. Erhan, V. Vanhoucke and A. Rabinovich, "Going Deeper with Convolutions," in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1-9, June 2015.
K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp.770-778, July 2016.
D. Jha and G.R. Kwon, "Alzheimer's Disease Detection Using Sparse Autoencoder, Scale Conjugate Gradient and Softmax Output Layer with Fine Tuning," Int. Journal of Machine Learning and Computing, vol. 7, no. 1, pp. 13-17, February 2017.

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증