Deep Learned Esophageal Contraction Vigor Classification on High-resolution Manometry Images

HE Fuli; DAI Yuzhuo; LI Zhaoying; SU Ri; CAO Cong; WANG Jiaoju; DAI Liaoyuan; HOU Muzhou; WANG Zheng

doi:10.11999/JEIT210909

Volume 44 Issue 1

Jan. 2022

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2022 > 44(1): 78-88

HE Fuli, DAI Yuzhuo, LI Zhaoying, SU Ri, CAO Cong, WANG Jiaoju, DAI Liaoyuan, HOU Muzhou, WANG Zheng. Deep Learned Esophageal Contraction Vigor Classification on High-resolution Manometry Images[J]. Journal of Electronics & Information Technology, 2022, 44(1): 78-88. doi: 10.11999/JEIT210909

Citation:

HE Fuli, DAI Yuzhuo, LI Zhaoying, SU Ri, CAO Cong, WANG Jiaoju, DAI Liaoyuan, HOU Muzhou, WANG Zheng. Deep Learned Esophageal Contraction Vigor Classification on High-resolution Manometry Images[J]. Journal of Electronics & Information Technology, 2022, 44(1): 78-88. doi: 10.11999/JEIT210909

Citation:

HE Fuli, DAI Yuzhuo, LI Zhaoying, SU Ri, CAO Cong, WANG Jiaoju, DAI Liaoyuan, HOU Muzhou, WANG Zheng. Deep Learned Esophageal Contraction Vigor Classification on High-resolution Manometry Images[J]. Journal of Electronics & Information Technology, 2022, 44(1): 78-88. doi: 10.11999/JEIT210909

PDF( 7539 KB)

Deep Learned Esophageal Contraction Vigor Classification on High-resolution Manometry Images

doi: 10.11999/JEIT210909

1.
School of Mathematics and Statistics, Central South University, Changsha 410083, China
2.
Science and Engineering School, Hunan First Normal University, Changsha 410205, China
3.
Hunan Computer Users Association, Changsha 410205, China

Funds: Graduate Student Innovation Foundation of Central South University (2020zzts362), The Natural Science Foundation of Hunan Province (2020JJ4105)

Received Date: 2021-08-31
Accepted Date: 2021-12-20
Rev Recd Date: 2021-11-30

Available Online: 2021-12-27

Publish Date: 2022-01-10

Abstract

Abstract

As the gold standard for the detection of Esophageal Motility Disorder(EMD), High-Resolution Manometry(HRM) is widely used in clinical tests to assist doctors in diagnosis. The amount of HRM images explodes with an increase in the prevalence rate, and the diagnostic process of EMD is complicated, both of which may lead to misdiagnosis of EMD in clinic. To improve the accuracy of the diagnosis of EMD, we hope to build a Computer Aided Diagnosis(CAD) system to assist doctors in analyzing HRM images automatically. Since the abnormality of esophageal contraction vigor is an important basis for diagnosis of EMD, in this paper, a Deep Learning(DL) model(PoS-ClasNet) is proposed to classify esophageal contraction vigor, which lays the foundation for machine to diagnose EMD instead of manual in the future. PoS-ClasNet, as a multi-task Convolutional Neural Network(CNN), is formed by PoSNet and S-ClassNet. The former is used to detect and extract swallowing frames in HRM images, while the latter identifies the type of contraction vigor based on esophageal swallowing characteristics. 4,000 expert-labeled HRM images are used for the experiment, among which the images of training set, verification set and test set accounted for 70%, 20% and 10%. On the test set, the classification accuracy of esophageal contraction vigor classifier PoS-ClasNet is as high as 93.25%, meanwhile the precision rate and the recall rate are 93.39% and 93.60% respectively. The experimental results show PoS-ClasNet can well adapt to the features of HRM image, with the outstanding accuracy and robustness in the task of intelligent diagnosis of esophageal contraction vigor. If the proposed model is used to assist doctors in clinical prevention, diagnosis and treatment, it will bring enormous social benefits.
- High-Resolution Manometry (HRM),
- Esophageal contraction vigor,
- Deep Learning (DL),
- Convolutional Neural Network (CNN)

FullText(HTML)

References(32)

References

[1]	BOWERS S P. Esophageal motility disorders[J]. Surgical Clinics of North America, 2015, 95(3): 467–482. doi: 10.1016/j.suc.2015.02.003
[2]	ZAMBITO G, ROETHER R, KERN B, et al. Is barium esophagram enough? Comparison of esophageal motility found on barium esophagram to high resolution manometry[J]. The American Journal of Surgery, 2021, 221(3): 575–577. doi: 10.1016/j.amjsurg.2020.11.028
[3]	KUNIEDA K, FUJISHIMA I, WAKABAYASHI H, et al. Relationship between tongue pressure and pharyngeal function assessed using high-resolution manometry in older dysphagia patients with sarcopenia: A pilot study[J]. Dysphagia, 2021, 36(1): 33–40. doi: 10.1007/s00455-020-10095-1
[4]	李飞, 王美峰, 汤玉蓉, 等. 《食管动力障碍的测压(第4版芝加哥分类)》更新点解读[J]. 中华消化杂志, 2021, 41(7): 492–497. doi: 10.3760/cma.j.cn311367-20210323-00173
[5]	PANDOLFINO J E, FOX M R, BREDENOORD A J, et al. High-resolution manometry in clinical practice: Utilizing pressure topography to classify oesophageal motility abnormalities[J]. Neurogastroenterology & Motility, 2009, 21(8): 796–806. doi: 10.1111/j.1365-2982.2009.01311.x
[6]	SAWADA A, GUZMAN M, NIKAKI K, et al. Identification of different phenotypes of esophageal reflux hypersensitivity and implications for treatment[J]. Clinical Gastroenterology and Hepatology, 2021, 19(4): 690–698.E2. doi: 10.1016/j.cgh.2020.03.063
[7]	KAHRILAS P J, BREDENOORD A J, FOX M, et al. The Chicago Classification of esophageal motility disorders, v3.0[J]. Neurogastroenterology & Motility, 2015, 27(2): 160–174. doi: 10.1111/nmo.12477
[8]	GYAWALI C P. High resolution manometry: The Ray Clouse legacy[J]. Neurogastroenterology & Motility, 2012, 24(S1): 2–4. doi: 10.1111/j.1365-2982.2011.01836.x
[9]	SCHMIDHUBER J. Deep learning in neural networks[J]. Neural Networks, 2015, 61: 85–117. doi: 10.1016/j.neunet.2014.09.003
[10]	LECUN Y, BENGIO Y, and HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436–444. doi: 10.1038/nature14539
[11]	KOU Wenjun, CARLSON D A, BAUMANN A J, et al. A deep-learning-based unsupervised model on esophageal manometry using variational autoencoder[J]. Artificial Intelligence in Medicine, 2021, 112: 102006. doi: 10.1016/j.artmed.2020.102006
[12]	CARLSON D A, KOU Wenjun, ROONEY K P, et al. Achalasia subtypes can be identified with functional luminal imaging probe (FLIP) panometry using a supervised machine learning process[J]. Neurogastroenterology & Motility, 2021, 33(3): e13932. doi: 10.1111/nmo.13932
[13]	侯晓华. 消化道高分辨率测压图谱[M]. 北京: 科学出版社, 2014. HOU Xiaohua. High Resolution Manometry in Digestive Tract[M]. Beijing: Science Press, 2014.
[14]	RENA Y. High-resolution esophageal manometry: Interpretation in clinical practice[J]. Current Opinion in Gastroenterology, 2017, 33(4): 301–309. doi: 10.1097/MOG.0000000000000369
[15]	BREDENOORD A J and SMOUT A J. High-resolution manometry of the esophagus: More than a colorful view on esophageal motility?[J]. Expert Review of Gastroenterology & Hepatology, 2007, 1(1): 61–69. doi: 10.1586/17474124.1.1.61
[16]	LI Zewen, LIU Fan, YANG Wenjie, et al. A survey of convolutional neural networks: Analysis, applications, and prospects[J]. IEEE Transactions on Neural Networks and Learning Systems, To be published.
[17]	GU Jiuxiang, WANG Zhenhua, KUEN J, et al. Recent advances in convolutional neural networks[J]. Pattern Recognition, 2018, 77: 534–377. doi: 10.1016/j.patcog.2017.10.013
[18]	SARVAMANGALA D R and KULKARNI R V. Convolutional neural networks in medical image understanding: A survey[J]. Evolutionary Intelligence, 2021(4): 1–22. doi: 10.1007/s12065-020-00540-3
[19]	MOHAPATRA S, SWARNKAR T, and DAS J. Deep Convolutional Neural Network in Medical Image Processing[M]. BALAS V E, MISHRA B K, and KUMAR R. Handbook of Deep Learning in Biomedical Engineering. Amsterdam: Academic Press, 2021: 25–60.
[20]	LITJENS G, KOOI T, BEJNORDI B E, et al. A survey on deep learning in medical image analysis[J]. Medical Image Analysis, 2017, 42: 60–88. doi: 10.1016/j.media.2017.07.005
[21]	GREENSPAN H, VAN GINNEKEN B, and SUMMERS R M. Guest editorial deep learning in medical imaging: Overview and future promise of an exciting new technique[J]. IEEE Transactions on Medical Imaging, 2016, 35(5): 1153–1159. doi: 10.1109/TMI.2016.2553401
[22]	JANOWCZYK A and MADABHUSHI A. Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases[J]. Journal of Pathology Informatics, 2016, 7: 29. doi: 10.4103/2153-3539.186902
[23]	RONNEBERGER O, FISCHER P, and BROX T. U-Net: Convolutional networks for biomedical image segmentation[C]. Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 2015: 234–241.
[24]	SIMONYAN K and ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv: 1409.1556, 2014.
[25]	GIRSHICK R. Fast R-CNN[C]. Proceedings of 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 1440–1448.
[26]	REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137–1149. doi: 10.1109/TPAMI.2016.2577031
[27]	ZHANG Ziang, WU Chengdong, COLEMAN S, et al. DENSE-INception U-net for medical image segmentation[J]. Computer Methods and Programs in Biomedicine, 2020, 192: 105395. doi: 10.1016/j.cmpb.2020.105395
[28]	WANG Zheng, MENG Yu, WENG Futian, et al. An effective CNN method for fully automated segmenting subcutaneous and visceral adipose tissue on CT scans[J]. Annals of Biomedical Engineering, 2020, 48(1): 312–328. doi: 10.1007/s10439-019-02349-3
[29]	DROZDZAL M, VORONTSOV E, CHARTRAND G, et al. The importance of skip connections in biomedical image segmentation[C]. Proceedings of the 1st International Workshop on Large-Scale Annotation of Biomedical Data and Expert Label Synthesis, Athens, Greece, 2016: 179–187.
[30]	IOFFE S and SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]. Proceedings of the 32nd International Conference on International Conference on Machine Learning, Lille, France, 2015: 448–456.
[31]	HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification[C]. Proceedings of 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 1026–1034.
[32]	KINGMA D P and BA J. Adam: A method for stochastic optimization[C]. Proceedings of the 3rd International Conference on Learning Representations, San Diego, USA, 2014.