An artificial intelligent diagnostic system on mobile Android terminals for cholelithiasis by lightweight convolutional neural network

English version

Autoři: Shanchen Pang ^aff001; Shuo Wang ^aff001; Alfonso Rodríguez-Patón ^aff002; Pibao Li ^aff003; Xun Wang ^aff001
Působiště autorů: College of Computer and Communication Engineering, China University of Petroleum, Qingdao, Shandong, China ^aff001; Departamento de Inteligencia Artificial, Universidad Politécnica de Madrid, Campus de Montegancedo, Boadilla del Monte, Madrid, Spain ^aff002; Department of Intensive Care Unit, Shandong Provincial Third Hospital, Jinan, Shandong, China ^aff003
Vyšlo v časopise: PLoS ONE 14(9)
Kategorie: Research Article
prolekare.web.journal.doi_sk: https://doi.org/10.1371/journal.pone.0221720

Souhrn

Artificial intelligence (AI) tools have been applied to diagnose or predict disease risk from medical images with recent data disclosure actions, but few of them are designed for mobile terminals due to the limited computational power and storage capacity of mobile devices. In this work, a novel AI diagnostic system is proposed for cholelithiasis recognition on mobile devices with Android platform. To this aim, a data set of CT images of cholelithiasis is firstly collected from The Third Hospital of Shandong Province, China, and then we technically use histogram equalization to preprocess these CT images. As results, a lightweight convolutional neural network is obtained in a constructive way to extract cholelith features and recognize gallstones. In terms of implementation, we compile Java and C++ to adapt to the application of deep learning algorithm on mobile devices with Android platform. Noted that, the training task is completed offline on PC, but cholelithiasis recognition tasks are performed on mobile terminals. We evaluate and compare the performance of our MobileNetV2 with MobileNetV1, Single Shot Detector (SSD), YOLOv2 and original SSD (with VGG-16) as feature extractors for object detection. It is achieved that our MobileNetV2 achieve similar accuracy rate, about 91% with the other four methods, but the number of parameters used is reduced from 36.1M (SSD 300, SSD512), 50.7M (Yolov2) and 5.1M (MobileNetV1) to 4.3M (MobileNetV2). The complete process on testing mobile devices, including Virtual machine, Xiaomi 7 and Htc One M8 can be controlled within 4 seconds in recognizing cholelithiasis as well as the degree of the disease.

Klíčová slova:

Biology and life sciences – Engineering and technology – Research and analysis methods – Neuroscience – Computer and information sciences – Anatomy – Medicine and health sciences – Diagnostic medicine – Mathematical and statistical techniques – Gastroenterology and hepatology – Imaging techniques – Neuroimaging – Diagnostic radiology – Radiology and imaging – Tomography – Mathematical functions – Computed axial tomography – Neural networks – Convolution – Liver – Biliary system – Gallbladder – Biliary disorders – Cholelithiasis – Computer vision – Target detection – Digital imaging – Grayscale

Zdroje

1. AI diagnostics need attention, Nature, 2018, https://www.nature.com/articles/d41586-018-03067-x

2. Lester V. Bergman/Getty, https://www.nature.com/articles/d41586-018-03067-x

3. Hoffman Ronald L. Intelligent medicine: A Guide to optimizing health and preventing illness for the raby-boomer generation. Simon Schuster, New York, 1997.

4. Viana-Ferreira C, Ribeiro L, Matos S, Costa C. Pattern recognition for cache management in distributed medical imaging environments. International Journal of Computer Assisted Radiology & Surgery, 2015, 11 (2):1–10.

5. Meyer-Baese A, Schmid V. Pattern Recognition and Signal Analysis in Medical Imaging. Pattern Recognition & Signal Analysis in Medical Imaging, 2014:135–149. doi: 10.1016/B978-0-12-409545-8.00005-4

6. Litjens G, Kooi T, Bejnordi BE, Aaa S, Ciompi F. A survey on deep learning in medical image analysis. Medical Image Analysis, 2017, 42 (9):60–88. doi: 10.1016/j.media.2017.07.005

7. Lundin J, Dumont G. Medical mobile technologies–what is needed for a sustainable and scalable implementation on a global scale?. Global health action, 2017, 10(sup3): 1344046. doi: 10.1080/16549716.2017.1344046

8. Rodriguez CS, Fischer G. The Linux Kernel Primer: A Top-down Approach for x86 and PowerPC Architectures. Pearson Education, India, 2006.

9. Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5MB model size. International Conference on Learning Representations, Toulon, 2017.

10. Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. Computer Vision and Pattern Recognition, Hawaii, 2017.

11. Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun. ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. Computer Vision and Pattern Recognition, Hawaii, 2017.

12. Franois Chollet. Xception: Deep Learning with Depth-wise Separable Convolutions. Computer Vision and Pattern Recognition, Hawaii, 2017.

13. Dawei Li, Xiaolong Wang, Deguang Kong. DeepRebirth: Accelerating Deep Neural Network Execution on Mobile Devices. American Association for Artificial Intelligence, New Orleans, 2018.

14. Song Han, Huizi Mao, William J. Dally. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. ICLR, The Commonwealth of Puerto Rico, 2016.

15. Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. Ssd: Single shot multibox detector. In ECCV, 2016. 7.

16. Joseph Redmon and Ali Farhadi. Yolo9000: Better, faster, stronger. arXiv preprint arXiv:1612.08242, 2016. 7.

17. Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. CoRR, abs/1409.1556, 2014. 1, 7.

18. Kim YT. Contrast enhancement using brightness preserving bi-histogram equalization. IEEE Transactions on Consumer Electronics, 2002, 43 (1):1–8.

19. Zhang Baochang, Gao Yongsheng, Zhao Sanqiang, et al. Local derivative pattern versus local binary pattern: face recognition with high-order local pattern descriptor. IEEE Transactions on Image Processing, 2010, 19 (2):533–544. doi: 10.1109/TIP.2009.2035882

20. Dalal N, Triggs B. Histograms of oriented gradients for human detection. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, 1:886-893.

21. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 2012: 1097–1105.

22. Bradski G. The OpenCV Library. Dr Dobbs Journal of Software Tools, 2000, 25(11):384–386.

23. Song Tao, Liu Xiyu, Zhao Yuzhen, Zhang Xingyi, Spiking Neural P Systems with White Hole Neurons, IEEE Trans on Nanobioscience, 2016, 15(7) 666–673. doi: 10.1109/TNB.2016.2598879

24. Song Tao, Zheng Pan Wong Dennis Mouling, Wang Xun, Design of Logic Gates Using Spiking Neural P Systems with Homogeneous Neurons and Astrocytes-like Control, Information Sciences, 372, 2016, Pages 380–391 doi: 10.1016/j.ins.2016.08.055

25. Song Tao, Rodríguez-Patón Alfonso, Zheng Pan, Zeng Xiangxiang, Spiking Neural P Systems With Colored Spikes, IEEE Transactions on Cognitive and Developmental Systems, 2018. doi: 10.1109/TCDS.2017.2785332

26. Song Tao, Wang Xun, Zheng Pan Li Xin, A programming triangular DNA origami for doxorubicin loading and delivering to target ovarian cancer cells, Oncotaget, 2018

27. Song Tao, Zeng Xiangxiang, Zheng Pan, Jiang Min, Rodríguez-Patón Alfonso, A Parallel Workflow Pattern Modelling Using Spiking Neural P Systems With Colored Spikes, IEEE Transactions on Nanobioscience.

28. Song Tao, Pang Shanchen, Hao Shaohua, Rodríguez-Patón Alfonso, Zheng Pan, A Parallel Image Skeletonizing Method Using Spiking Neural P Systems with Weights, Neural Processing Letters.

29. Song Tao, Pan Linqiang, Wu Tingfang, Zheng Pan, Wong M. L. Dennis and Rodríguez-Patón Alfonso, Spiking Neural P Systems with Learning Functions, IEEE Trans Nanobioscience, 2019. doi: 10.1109/TNB.2019.2896981

30. Wang Xun, Zheng Pan, Ma Tongmao, Song Tao, Computing with Bacteria Conjugation: Small Universal Systems, Moleculer, 2018, 2018, 23(6), 1307 doi: 10.3390/molecules23061307

31. Yuan S, Deng G, Feng Q, et al. Multi-Objective Evolutionary Algorithm Based on Decomposition for Energy-aware Scheduling in Heterogeneous Computing Systems[J]. Journal of Universal Computer Science, 2017, 23(7): 636–651.

32. Pang Shanchen, Ding Tong, Rodríguez-Patón Alfonso, Song Tao, Zheng Pan, A Parallel Bioinspired Framework for Numerical Calculations Using Enzymatic P System with an Enzymatic Environment.

33. Chun-Hsien Lu; Chih-Sheng Lin; Hung-Lin Chao; Jih-Sheng Shen; Pao-Ann Hsiung, Reconfigurable multi-core architecture—a plausible solution to the von Neumann performance bottleneck, International Journal of Adaptive and Innovative Systems (IJAIS), 2015 Vol.2 No.3, pp.217–231.

34. Militello Carmelo; Vitabile Salvatore; Rundo Leonardo; Gagliardo Cesare; Salerno Sergio, An edge-driven 3D region-growing approach for upper airway morphology and volume evaluation in patients with Pierre Robin sequence, International Journal of Adaptive and Innovative Systems (IJAIS), 2015 Vol.2 No.3, pp.232–253. doi: 10.1504/IJAIS.2015.074406

35. Gowri R.; Kanmani S., Self-adaptive agent-based tutoring system, International Journal of Adaptive and Innovative Systems (IJAIS), 2015 Vol.2 No.3, pp.197–216. doi: 10.1504/IJAIS.2015.074398

36. Pham Hai Van; Moore Philip; Thi My Loc Nguyen, A knowledge-based consultancy system using ICT Newhouse indicators with reasoning techniques for consultants in e-learning, International Journal of Adaptive and Innovative Systems (IJAIS), 2015 Vol.2 No.3, pp.254–266. doi: 10.1504/IJAIS.2015.074410

An artificial intelligent diagnostic system on mobile Android terminals for cholelithiasis by lightweight convolutional neural network

Souhrn

Klíčová slova:

Zdroje

PLOS One

Aktuální možnosti diagnostiky a léčby litiáz