Skip to main content
Springer Nature Link
Log in

A computer-aid multi-task light-weight network for macroscopic feces diagnosis

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The abnormal traits and colors of feces typically indicate that the patients are probably suffering from tumor or digestive-system diseases. Thus a fast, accurate and automatic health diagnosis system based on feces is urgently necessary for improving the examination speed and reducing the infection risk. The rarity of the pathological images would deteriorate the accuracy performance of the trained models. In order to alleviate this problem, we employ augmentation and over-sampling to expand the samples of the classes that have few samples in the training batch. In order to achieve an impressive recognition performance and leverage the latent correlation between the traits and colors of feces pathological samples, a multi-task network is developed to recognize colors and traits of the macroscopic feces images. The parameter number of a single multi-task network is generally much smaller than the total parameter number of multiple single-task networks, so the storage cost is reduced. The loss function of the multi-task network is the weighted sum of the losses of the two tasks. In this paper, the weights of the tasks are determined according to their difficulty levels that are measured by the fitted linear functions. The sufficient experiments confirm that the proposed method can yield higher accuracies, and the efficiency is also improved.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Abdulnabi AH, Wang G, Lu J et al (2015) Multi-task CNN model for attribute prediction. IEEE Trans Multimedia 17(11):1949–1959. https://doi.org/10.1109/TMM.2015.2477680

    Article  Google Scholar 

  2. Alomari YM, Abdullah S, Huda SN et al (2014) Automatic detection and quantification of WBCs and RBCs using iterative structured circle detection algorithm. Comput Math Methods Med 2014:979302. https://doi.org/10.1155/2014/979302

    Article  MATH  Google Scholar 

  3. Alsmirat MA, AI-Alem F, AI-Ayyoub M et al (2019) Impact of digital fingerprint image quality on the fingerprint recognition accuracy. Multimed Tools Appl 28:3649–3688. https://doi.org/10.1007/s11042-017-5537-5

    Article  Google Scholar 

  4. Baldoumas G, Peschos D, Tatsis G, Chronopoulos SK, Christofilakis V, Kostarakis P, Varotsos P, Sarlis NV, Skordas ES, Bechlioulis A, Michalis LK, Naka KK (2019) A prototype photoplethysmography electronic device that distinguishes congestive heart failure from healthy individuals by applying natural time analysis. Electronics 8(11):1288. https://doi.org/10.3390/electronics8111288

    Article  Google Scholar 

  5. Bao J, Luo L, Zhang Y, Yang K, Peng C, Peng J, Li R (2021) Half quadratic splitting method combined with convolution neural network for blind image deblurring. Multimed Tools Appl 80:3489–3504. https://doi.org/10.1007/s11042-020-09821-6

    Article  Google Scholar 

  6. Bergquist R, Johansen MV, Utzinger J (2009) Diagnostic dilemmas in helminthology: what tools to use and when. Trends Parasitol 25(4):151–156. https://doi.org/10.1016/j.pt.2009.01.004

    Article  Google Scholar 

  7. Berhe N, Medhin G, Erko B, Smith T, Gedamu S, Bereded D, Moore R, Habte E, Redda A, Gebre-Michael T, Gundersen SG (2004) Variations in helminth faecal egg counts in Kato-Katz thick smears and their implications in assessing infection status with Schistosoma mansoni. Acta Trop 92(3):205–212. https://doi.org/10.1016/j.actatropica.2004.06.011

    Article  Google Scholar 

  8. Black CJ, Ford AC (2020) Global burden of irritable bowel syndrome: trends, predictions and risk factors. Nat Rev Gastroenterol Hepatol 16:473–486. https://doi.org/10.1038/s41575-020-0286-8

    Article  Google Scholar 

  9. Carvalho AOF, Silva AC, Paiva AC et al (2017) Lung-nodule classification based on computed tomography using taxonomic diversity indexes and an SVM. J Signal Process Syst 87(2):179–196. https://doi.org/10.1007/s11265-016-1134-5

    Article  Google Scholar 

  10. Caselli F, Ninno AD, Reale R et al (2020) A Bayesian approach for coincidence resolution in microfluidic impedance cytometry, IEEE trans. Biomed Eng 68:340–349. https://doi.org/10.1109/TBME.2020.2995364

    Article  Google Scholar 

  11. Chang S, Chen X, Duan J et al (2020) A CNN hybrid ring artifact reduction algorithm for CT images. IEEE Trans Plasma Sci. https://doi.org/10.1109/TRPMS.2020.2983391

  12. Charoensuk L, Subrungruang I, Mungthin M, Pinlaor S, Suwannahitatorn P (2019) Comparison of stool examination techniques to detect Opisthorchis viverrini in low intensity infection. Acta Trop 191:13–16. https://doi.org/10.1016/j.actatropica.2018.12.018

    Article  Google Scholar 

  13. Chen H, Zhang Y, Kalra MK, Lin F, Chen Y, Liao P, Zhou J, Wang G (2017) Low-dose CT with a residual encoder-decoder convolutional neural network. IEEE Trans Med Imaging 36(12):2524–2535. https://doi.org/10.1109/TMI.2017.2715284

    Article  Google Scholar 

  14. Cheng J (2018) Sparse range-constrained learning and its application for medical image grading. IEEE Trans Med Imaging 37(12):2729–2738. https://doi.org/10.1109/TMI.2018.2851607

    Article  Google Scholar 

  15. Chu J, Guo Z, Leng L (2018) Object detection based on multi-layer convolution feature fusion and online hard example mining. IEEE Access 6(1):19959–19967. https://doi.org/10.1109/ACCESS.2018.2815149

    Article  Google Scholar 

  16. Du X, Lin L, Wang X et al (2019) Automatic classification of cells in microscopic fecal images using convolutional neural networks. Biosci Rep 39(4):BSR20182100. https://doi.org/10.1042/BSR20182100

    Article  Google Scholar 

  17. Esposito C, Ficco M, Gupta BB (2021) Blockchain-based authentication and authorization for smart city applications. Inf Process Manag 58(2):102468. https://doi.org/10.1016/j.ipm.2020.102468

    Article  Google Scholar 

  18. Eun H, Kim D, Jung C, Kim C (2018) Single-view 2D CNNs with fully automatic non-nodule categorization for false positive reduction in pulmonary nodule detection. Comput Methods Prog Biomed 165:215–224. https://doi.org/10.1016/j.cmpb.2018.08.012

    Article  Google Scholar 

  19. Ginneken BV, Frangi AF, Staal J et al (2002) Active shape model segmentation with optimal features. IEEE Trans Med Imaging 21(8):924–933. https://doi.org/10.1109/TMI.2002.803121

    Article  Google Scholar 

  20. Gu Y, Shen M, Yang J, Yang GZ (2019) Reliable label-efficient learning for biomedical image recognition. IEEE Trans Biomed Eng 66(9):2423–2432. https://doi.org/10.1109/TBME.2018.2889915

    Article  Google Scholar 

  21. Hachuel D, Jha A, Estrin D et al (2019) Augmenting gastrointestinal health: a deep learning approach to human stool recognition and characterization in macroscopic images. Gastroenterology 156(6):S-937. https://doi.org/10.1016/S0016-5085(19)39304-7

    Article  Google Scholar 

  22. He K, Zhang X, Ren S et al. (2016) Deep residual learning for image recognition, In Proceedings of Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 770–778

  23. Hu C, Wang Y (2020) An efficient CNN model based on object-level attention mechanism for casting defects detection on radiography images. IEEE Trans Ind Electron 67(12):10922–10930. https://doi.org/10.1109/TIE.2019.2962437

    Article  Google Scholar 

  24. Huang L, Jiang H, Li S, Bai Z, Zhang J (2020) Two stage residual CNN for texture denoising and structure enhancement on low dose CT image. Comput Methods Prog Biomed 184:105115. https://doi.org/10.1016/j.cmpb.2019.105115

    Article  Google Scholar 

  25. Jodeiri A, Zoroofi RA, Hiasa Y, Takao M, Sugano N, Sato Y, Otake Y (2020) Fully automatic estimation of pelvic sagittal inclination from anterior-posterior radiography image using deep learning framework. Comput Methods Prog Biomed 184:105282. https://doi.org/10.1016/j.cmpb.2019.105282

    Article  Google Scholar 

  26. Kermany DS, Goldbaum M, Cai W, Valentim CCS, Liang H, Baxter SL, McKeown A, Yang G, Wu X, Yan F, Dong J, Prasadha MK, Pei J, Ting MYL, Zhu J, Li C, Hewett S, Dong J, Ziyar I, … Zhang K (2018) Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172(5):1122–1131. https://doi.org/10.1016/j.cell.2018.02.010

    Article  Google Scholar 

  27. Kinross JM, Mason SE, Mylonas G, Darzi A (2020) Next-generation robotics in gastrointestinal surgery. Nat Rev Gastroenterol Hepatol 17:430–440. https://doi.org/10.1038/s41575-020-0290-z

    Article  Google Scholar 

  28. Kumar A, Kim J, Lynodon D et al (2016) An ensemble of fine-tuned convolutional neural networks for medical image classification. IEEE J Biomed Health Inform 21(1):31–40. https://doi.org/10.1109/JBHI.2016.2635663

    Article  Google Scholar 

  29. Leng L, Teoh ABJ (2015) Alignment-free row-co-occurrence cancelable palmprint fuzzy vault. Pattern Reocgnit 48(7):2290–2303. https://doi.org/10.1016/j.patcog.2015.01.021

    Article  Google Scholar 

  30. Leng L, Li M, Kim C, Bi X (2017) Dual-source discrimination power analysis for multi-instance contactless palmprint recognition. Multimed Tools Appl 76(1):333–354. https://doi.org/10.1007/s11042-015-3058-7

    Article  Google Scholar 

  31. Leng L, Yang Z, Kim K et al (2020) A light-weight practical framework for feces detection and trait recognition. Sensors 20(9):2644. https://doi.org/10.3390/s20092644

    Article  Google Scholar 

  32. Li Q, Li S, Liu X, He Z, Wang T, Xu Y, Guan H, Chen R, Qi S, Wang F (2020) FecalNet: automated detection of visible components in human feces using deep learning. Med Phys 47:4212–4222. https://doi.org/10.1002/mp.14352

    Article  Google Scholar 

  33. Liu M, Zhang J, Adeli E, Shen D (2018) Joint classification and regression via deep multi-task multi-channel learning for Alzheimer's disease diagnosis. IEEE Trans Biomed Eng 66(5):1943–1952. https://doi.org/10.1109/TBME.2018.2869989

    Article  Google Scholar 

  34. Liu J, Chen F, Pan C, Zhu M, Zhang X, Zhang L, Liao H (2018) A cascaded deep convolutional neural network for joint segmentation and genotype prediction of brainstem gliomas. IEEE Trans Biomed Eng 65(9):1943–1952. https://doi.org/10.1109/TBME.2018.2845706

    Article  Google Scholar 

  35. Liu J, Zhang Y, Zhao Q, Lv T, Wu W, Cai N, Quan G, Yang W, Chen Y, Luo L, Shu H, Coatrieux JL (2019) Deep iterative reconstruction estimation (DIRE): approximate iterative reconstruction estimation for low dose CT imaging. Phys Med Biol 64(13):135007. https://doi.org/10.1088/1361-6560/ab18db

    Article  Google Scholar 

  36. Mao R, Qiu Y, He JS, Tan JY, Li XH, Liang J, Shen J, Zhu LR, Chen Y, Iacucci M, Ng SC, Ghosh S, Chen MH (2020) Manifestations and prognosis of gastrointestinal and liver involvement in patients with COVID-19: a systematic review and meta-analysis. The Lancet Gastroen Hepatol 5(7):667–678. https://doi.org/10.1016/S2468-1253(20)30126-6

    Article  Google Scholar 

  37. Masud M, Gaba GS, Alqahtani S et al (2020) A lightweight and robust secure key establishment for internet of medical thins in COVID-19 patients care. IEEE Internet Things. https://doi.org/10.1109/JIOT.2020.3047662

  38. Nkamgang OT, Tchiotsop D, Fotsin HB, Talla PK, Louis Dorr V, Wolf D (2019) Automatic the clinical stools exam using image processing integrated in an expert system. Inform Med Unlocked 15:100165. https://doi.org/10.1016/j.imu.2019.100165

    Article  Google Scholar 

  39. Pollastri F, Bolelli F, Paredes R, Grana C (2020) Augmenting data with GANs to segment melanoma skin lesions. Multimed Tools Appl 79:15575–15592. https://doi.org/10.1007/s11042-019-7717-y

    Article  Google Scholar 

  40. Qureshi MNI, Oh J, Lee B (2017) 3D-CNN based discrimination of schizophrenia using resting-state fMRI. Artif Intell Med 98:10–17. https://doi.org/10.1016/j.artmed.2019.06.003

    Article  Google Scholar 

  41. Reena MR, Ameer PM (2020) Localization and recognition of leukocytes in peripheral blood: a deep learning approach. Comput Biol Med 126:104034. https://doi.org/10.1016/j.compbiomed.2020.104034

    Article  Google Scholar 

  42. Savelli B, Bria A, Molinara M, Marrocco C, Tortorella F (2020) A multi-context CNN ensemble for small lesion detection. Artif Intell Med 103:101749. https://doi.org/10.1016/j.artmed.2019.101749

    Article  Google Scholar 

  43. Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958

    MathSciNet  MATH  Google Scholar 

  44. Su A, He X, Zhao X (2021) JPEG steganalysis based on ResNeXt with gauss partial derivative filters. Multimed Tools Appl 80:3349–3366. https://doi.org/10.1007/s11042-020-09350-2

    Article  Google Scholar 

  45. Tajbakhsh N, Shin JY, Gurudu SR, Hurst RT, Kendall CB, Gotway MB, Liang J (2016) Convolutional neural networks for medical image analysis: full training or fine tuning. IEEE Trans Med Imaging 35(5):1299–1312. https://doi.org/10.1109/TMI.2016.2535302

    Article  Google Scholar 

  46. Tewari A, Gupta BB (2017) Cryptanalysis of novel ultra-lightweight mutual authentication protocol for IoT devices using RFID tags. J Supercomput 73:1085–1102. https://doi.org/10.1007/s11227-016-1849-x

    Article  Google Scholar 

  47. Tian C, Xu Y, Zuo W (2020) Image denoising using deep CNN with batch renormalization. Neural Netw 121:461–473. https://doi.org/10.1016/j.neunet.2019.08.022

    Article  Google Scholar 

  48. Wang G, Deng Z, Choi KS (2016) Tracking missing data in community health studies using additive LS-SVM classifier. IEEE J Biomed Health Inform 22(2):579–587. https://doi.org/10.1109/JBHI.2016.2634587

    Article  Google Scholar 

  49. Wong WJ, Lai SH (2020) Multi-task CNN for restoring corrupted fingerprint images. Pattern Reocgnit 101:107203. https://doi.org/10.1016/j.patcog.2020.107203

    Article  Google Scholar 

  50. Yang W, Zhong L, Chen Y, Lin L, Lu Z, Liu S, Wu Y, Feng Q, Chen W (2018) Predicting CT images from MRI data through feature matching with learned nonlinear local descriptors. IEEE Trans Med Imaging 37(4):977–987. https://doi.org/10.1109/TMI.2018.2790962

    Article  Google Scholar 

  51. Yang Z, Leng L, Kim BG (2019) StoolNet for color classification of stool medical images. Electronics 8(12):1464. https://doi.org/10.3390/electronics8121464

    Article  Google Scholar 

  52. Yu C, Li J, Li X, Ren X, Gupta BB (2018) Four-image encryption scheme based on quaternion Fresnel transform, chaos and computer generated hologram. Multimed Tools Appl 77:4585–4608. https://doi.org/10.1007/s11042-017-4637-6

    Article  Google Scholar 

  53. Zhang Y, Chu J, Leng L, Miao J (2020) Mask-refined R-CNN: a network for refining object details in instance segmentation. Sensors 20(4):1010. https://doi.org/10.3390/s20041010

    Article  Google Scholar 

Download references

Acknowledgements

This research was funded by the National Natural Science Foundation of China (61866028, 61866025, 61663031, 62162045), Key Program Project of Research and Development (Jiangxi Provincial Department of Science and Technology) (20192BBE50073).

Author information

Authors and Affiliations

  1. School of Software, Nanchang Hangkong University, Nanchang, 330063, People’s Republic of China

    Ziyuan Yang, Lu Leng & Jun Chu

  2. College of Computer Science, Sichuan University, Chengdu, 610065, People’s Republic of China

    Ziyuan Yang

  3. School of Electrical and Electronic Engineering, College of Engineering, Yonsei University, Seoul, 120749, Republic of Korea

    Lu Leng

  4. School of Information Engineering, Nanchang Hangkong University, Nanchang, 330063, People’s Republic of China

    Ming Li

Authors
  1. Ziyuan Yang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Lu Leng
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Ming Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Jun Chu
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Lu Leng.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, Z., Leng, L., Li, M. et al. A computer-aid multi-task light-weight network for macroscopic feces diagnosis. Multimed Tools Appl 81, 15671–15686 (2022). https://doi.org/10.1007/s11042-022-12565-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12565-0

Keywords