Abstract
Medical Imaging Computer Aided Diagnosis (CAD) systems could support physicians in several fields and recently are also applied in histopathology. The goal of this work is to design and test a novel CAD system module for the discrimination between glomeruli with a sclerotic and non-sclerotic condition, through the elaboration of histological images. The dataset was constituted by 26 kidney biopsies coming from 19 donors with Periodic Acid Schiff (PAS) staining. Preparation, digital acquisition and glomeruli annotations have been conducted by experts from the Department of Emergency and Organ Transplantation (DETO) of the University of Bari Aldo Moro (Italy). Starting from the annotated Regions Of Interest (ROIs), several feature extraction techniques were evaluated. Feature reduction and shallow artificial neural network were used for discriminating between the glomeruli classes. The mean and the best performances of the best ANN architecture were evaluated on an independent dataset. Metric comparison and analysis were performed to face the unbalanced dataset problem. Results on the test set asses that the proposed workflow, from the feature extraction to the supervised ANN approach, is consistent and reveals good performance in discriminating sclerotic and non-sclerotic glomeruli.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wolfe, R.A., Ashby, V.B., Milford, E.L., Ojo, A.O., Ettenger, R.E., Agodoa, L.Y.C., et al.: Comparison of mortality in all patients on dialysis, patients on dialysis awaiting transplantation, and recipients of a first cadaveric transplant. N. Engl. J. Med. (2002). https://doi.org/10.1056/nejm199912023412303
Port, F.K., Wolfe, R.A., Mauger, E.A., Berling, D.P., Jiang, K.: Comparison of survival probabilities for dialysis patients vs cadaveric renal transplant recipients. JAMA J. Am. Med. Assoc. (1993). https://doi.org/10.1001/jama.1993.03510110079036
Cecka, J.M.: The UNOS Scientific Renal Transplant Registry–ten years of kidney transplants. Clin. Transpl. 1–14 (1997)
United Network for Organ Sharing: United Network for Organ Sharing. Annual Report (2004)
Perico, N., Ruggenenti, P., Scalamogna, M., Remuzzi, G.: Tackling the shortage of donor kidneys: how to use the best that we have (2003). https://doi.org/10.1159/000072055
Moore, P.S., Farney, A.C., Sundberg, A.K., Rohr, M.S., Hartmann, E.L., Iskandar, S.S., et al.: Dual kidney transplantation: a case-control comparison with single kidney transplantation from standard and expanded criteria donors (2007). https://doi.org/10.1097/01.tp.0000266579.11595.95
Remuzzi, G., Grinyò, J., Ruggenenti, P., Beatini, M., Cole, E.H., Milford, E.L., et al.: Early experience with dual kidney transplantation in adults using expanded donor criteria. Double Kidney Transplant Group (DKG). J. Am. Soc. Nephrol. 10, 2591–2598 (1999)
Karpinski, J., Lajoie, G., Cattran, D., Fenton, S., Zaltzman, J., Cardella, C., et al.: Outcome of kidney transplantation from high-risk donors is determined by both structure and function. Transplantation (1999). https://doi.org/10.1097/00007890-199904270-00013
Remuzzi, G., Ruggenenti, P.: Renal transplantation: single or dual for donors aging  ≥60 years? Transplantation (2003). https://doi.org/10.1097/00007890-200005270-00002
Bevilacqua, V., Pietroleonardo, N., Triggiani, V., Brunetti, A., Di Palma, A.M., Rossini, M., et al.: An innovative neural network framework to classify blood vessels and tubules based on Haralick features evaluated in histological images of kidney biopsy. Neurocomputing 228, 143–153 (2017). https://doi.org/10.1016/j.neucom.2016.09.091
Bevilacqua, V., Buongiorno, D., Carlucci, P., Giglio, F., Tattoli, G., Guarini, A., et al.: A supervised CAD to support telemedicine in hematology. In: Proceedings of the International Joint Conference on Neural Networks (2015). https://doi.org/10.1109/ijcnn.2015.7280464
Bevilacqua, V., et al.: Retinal fundus biometric analysis for personal identifications. In: Huang, D.-S., Wunsch, D.C., Levine, D.S., Jo, K.-H. (eds.) ICIC 2008. LNCS (LNAI), vol. 5227, pp. 1229–1237. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-85984-0_147
Kotyk, T., Dey, N., Ashour, A.S., Balas-Timar, D., Chakraborty, S., Ashour, A.S., et al.: Measurement of glomerulus diameter and Bowman’s space width of renal albino rats. Comput. Methods Programs Biomed. 126, 143–153 (2016). https://doi.org/10.1016/J.CMPB.2015.10.023
Zhao, Y., Black, E.F., Marini, L., McHenry, K., Kenyon, N., Patil, R., et al.: Automatic glomerulus extraction in whole slide images towards computer aided diagnosis. In: 2016 IEEE 12th International Conference on e-Science (e-Science), pp. 165–174. IEEE (2016). https://doi.org/10.1109/escience.2016.7870897
Chan, T.F., Vese, L.A.: Active contours without edges. IEEE Trans. Image Process. (2001). https://doi.org/10.1109/83.902291
Lloyd, S.: Least squares quantization in PCM. IEEE Trans. Inf. Theory 28, 129–137 (1982)
Simon, O., Yacoub, R., Jain, S., Tomaszewski, J.E., Sarder, P.: Multi-radial LBP features as a tool for rapid glomerular detection and assessment in whole slide histopathology images OPEN, 8, 2032 (2018). https://doi.org/10.1038/s41598-018-20453-7
Matthews, B.W.: Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochim. Biophys. Acta (BBA)-Protein Struct. 405, 442–451 (1975)
Chicco, D.: Ten quick tips for machine learning in computational biology (2017). https://doi.org/10.1186/s13040-017-0155-3
Song, B., Zhang, G., Zhu, W., Liang, Z.: ROC operating point selection for classification of imbalanced data with application to computer-aided polyp detection in CT colonography. Int. J. Comput. Assist. Radiol. Surg. (2014). https://doi.org/10.1007/s11548-013-0913-8
Bevilacqua, V., et al.: A novel deep learning approach in haematology for classification of leucocytes. In: Esposito, A., Faundez-Zanuy, M., Morabito, F.C., Pasero, E. (eds.) WIRN 2017 2017. SIST, vol. 103, pp. 265–274. Springer, Cham (2019). https://doi.org/10.1007/978-3-319-95095-2_25
Brunetti, A., Buongiorno, D., Trotta, G.F., Bevilacqua, V.: Computer vision and deep learning techniques for pedestrian detection and tracking: a survey. Neurocomputing (2018). https://doi.org/10.1016/j.neucom.2018.01.092
Acknowledgment
This study has been partially funded from the INNONETWORK program of the Apulia Region, project SOS – Smart Operating Shelter (project n. 9757YR7).
The authors would like to thank Federica Albanese, Davide Mallardi and Dr Michele Rossini for the medical domain support and the manual annotation of the glomeruli whole slide images for the input dataset creation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Cascarano, G.D. et al. (2019). An Innovative Neural Network Framework for Glomerulus Classification Based on Morphological and Texture Features Evaluated in Histological Images of Kidney Biopsy. In: Huang, DS., Huang, ZK., Hussain, A. (eds) Intelligent Computing Methodologies. ICIC 2019. Lecture Notes in Computer Science(), vol 11645. Springer, Cham. https://doi.org/10.1007/978-3-030-26766-7_66
Download citation
DOI: https://doi.org/10.1007/978-3-030-26766-7_66
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-26765-0
Online ISBN: 978-3-030-26766-7
eBook Packages: Computer ScienceComputer Science (R0)