A custom deep learning architecture with image augmentation for intelligent gastrointestinal tract tissue classification

• Autorzy: Wieczorek Michał , Wojtas Natalia , Wituła Roman , Krawczyk Aleksandra , Rycerz Karol

Identyfikatory

DOI

10.61822/amcs-2024-0040

• Języki publikacji: EN

Abstrakty

EN

The origin of sampled tissue and characteristics of healthy organs is important for potential abnormality detection in veterinary medicine. Most often such information is given during the sampling process, but in some cases there is a possibility of mislabeling, especially in the education sector where some microscopic preparations might be made by students without proper knowledge or the inspected tissues are not of fully known origin. Occasionally, it is possible to determine the affiliation by searching characteristics of the organ in a sample; however, this is not always possible even for a skilled professional as some tissues vary too little between their counterparts in different species or even in different organs of the same species. Because of this, an automatic system able to perform such classification in a fraction of a second and with high accuracy can be helpful in such cases, especially considering the low cost of adding that solution to the current workflow. This paper presents a new dataset for healthy organ classification based on light microscope imagery containing 25 abstract classes of different organs of a few species. During the sampling process, 3680 images of healthy tissues were collected. Additionally, a custom deep learning architecture was created that is able to classify those samples between organs and species with a validation accuracy reaching 98.34%. Such performance is in some cases higher than that of a human specialist, especially when some examples have very small visual differences between one another or the classification is made on previously non-determining regions of the organ. Additionally, the collection of such a dataset provides a great opportunity for further work containing abnormality detection as it already provides information on the healthy organ description, which can be used for a deep learning model searching for illnesses or mutations. What is more, such a dataset and the corresponding artificial neural network constitute one of the first solutions of this kind in veterinary medicine, as most state-of-the-art papers focus on human medicine.

Słowa kluczowe

EN

deep learning; artificial intelligence; image augmentation; tissue classification; veterinary medicine

PL

uczenie głębokie; sztuczna inteligencja; augmentacja obrazu; klasyfikacja tkanek; medycyna weterynaryjna

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2024
• Tom: Vol. 34, no. 4
• Strony: 597--616
• Opis fizyczny: Bibliogr. 60 poz., rys., tab.

Twórcy

autor

Wieczorek Michał

• Faculty of Applied Mathematics, Silesian University of Technology, Kaszubska 23, 44-100 Gliwice, Poland

autor

Wojtas Natalia

• University of Life Sciences in Lublin, Akademicka 12, 20-950 Lublin, Poland

autor

Wituła Roman

• Faculty of Applied Mathematics, Silesian University of Technology, Kaszubska 23, 44-100 Gliwice, Poland

autor

Krawczyk Aleksandra

• Department of Animal Anatomy and Histology, University of Life Sciences in Lublin, Akademicka 12, 20-950 Lublin, Poland

autor

Rycerz Karol

• Department of Animal Anatomy and Histology, University of Life Sciences in Lublin, Akademicka 12, 20-950 Lublin, Poland

Bibliografia

• [1] Abayomi-Alli, O.O., Damaševičius, R., Wieczorek, M. and Woźniak, M. (2020). Data augmentation using principal component resampling for image recognition by deep learning, Artificial Intelligence and Soft Computing: 19th International Conference, ICAISC 2020, Zakopane, Poland, pp. 39-48.
• [2] Al-Juboory, R.W., Dauod, H.A. and Al-arajy, A.S. (2017). Comparative anatomical and histological study of the stomach in two IRAQI BIRDS (columba palumbus and tyto alba), IBN AL-Haitham Journal For Pure and Applied Science 29(2): 1-12.
• [3] Amorim, I., Taulescu,M.,Day,M., Catoi, C.,Reis, C.,Carneiro, F. and Gärtner, F. (2016). Canine gastric pathology: A review, Journal of Comparative Pathology 154(1): 9-37.
• [4] Angelou, V., Fiska, A., Tsingotjidou, A., Patsikas, M. and Papazoglou, L.G. (2023). Surgical anatomy of the gastrointestinal tract in cats, Animals 13(16): 2670.
• [5] Bacha Jr, W.J. and Bacha, L.M. (2012). Color Atlas of Veterinary Histology, Wiley, Hoboken.
• [6] Badawi, H., A Abd El-Rahman, Y., Salem, A. and Mohamed, A. (1998). Comparative morphological studies on the intestinal glands of the colon and rectum of some domestic animals, Assiut Veterinary Medical Journal 39(77): 36-53.
• [7] Banzato, T., Gelain, M. E., Aresu, L., Centelleghe, C., Benali, S.L. and Zotti, A. (2015). Quantitative analysis of ultrasonographic images and cytology in relation to histopathology of canine and feline liver: An ex-vivo study, Research in Veterinary Science 103: 164-169.
• [8] Basran, P. (2024 ). New horizons: Artificial intelligence in veterinary medicine, An interview, Cornell University, Ithaca, https://www.vet.cornell.edu/news/20230106/new-horizons-artificial-intelligence-veterinary-medicine.
• [9] Bazira, P.J. (2023). Anatomy of the oesophagus, Surgery (Oxford) 41(11): 691-697.
• [10] Bodes, F.J.S. and Martínez, F.J.P. (2023). Aughey and Frye’s Comparative Veterinary Histology with Clinical Correlates, CRC Press, Boca Raton.
• [11] Botlagunta, S. and Kedari, S. (2023). Histoarchitectural and histochemical studies on the oesophagus of local dog, The Pharma Innovation Journal 12(2): 1560-1565.
• [12] Carubbi, F., Alunno, A., Gerli, R. and Giacomelli, R. (2018). Histopathology of salivary glands, Reumatismo - The Italian Journal of Rheumatology 70(3): 146-154.
• [13] Catroxo, M., Lima, M. and Cappellaro, C. (1997). Histological aspects of the stomach (proventriculus and gizzard) of the red-capped cardinal (paroaria gularis gularis, linnaeus, 1766), Revista Chilena de Anatomía 15(1): 19-27.
• [14] Chivers, D.J. and Hladik, C.M. (1980). Morphology of the gastrointestinal tract in primates: Comparisons with other mammals in relation to diet, Journal of Morphology 166(3): 337-386.
• [15] Chungath, J.J. (1981). Anatomy and Histology of Ruminant Stomach of Goat, PhD thesis, College of Veterinary and Animal Sciences, Mannuthy.
• [16] Dawood, M.S., Abood, D.A. and Hameza, A.Y. (2022). The histological and histochemical features of the esophagus in local breed dogs (canis familiaris), Iraqi Journal of Veterinary Sciences 36(4): 1069-1074.
• [17] Doyama, H., Nakanishi, H. and Yao, K. (2021). Image-enhanced endoscopy and its corresponding histopathology in the stomach, Gut and Liver 15(3): 329.
• [18] Eberlova, L., Maleckova, A., Mik, P., Tonar, Z., Jirik, M., Mirka, H., Palek, R., Leupen, S. and Liska, V. (2020). Porcine liver anatomy applied to biomedicine, Journal of Surgical Research 250: 70-79.
• [19] Ezanno, P., Picault, S., Beaunée, G., Bailly, X., Muñoz, F., Duboz, R., Monod, H. and Guégan, J.-F. (2021). Research perspectives on animal health in the era of artificial intelligence, Veterinary Research 52: 1-15.
• [20] Fragoso-Garcia,M., Wilm, F., Bertram, C.A., Merz, S., Schmidt, A., Donovan, T., Fuchs-Baumgartinger, A., Bartel, A., Marzahl, C., Diehl, L., Puget, C., Maier, A., Aubreville, M., Breininger, K. and Klopfleisch, R. (2023). Automated diagnosis of 7 canine skin tumors using machine learning on H&E-stained whole slide images, Veterinary Pathology 60(6): 865-875.
• [21] Friedland, G.W., Kohatsu, S. and Lewin, K. (1971). Comparative anatomy of feline and canine gastric sling fibers: Analogy to human anatomy, American Journal of Digestive Diseases 16: 495-507.
• [22] Ghoshal, N. and Bal, H. (1989). Comparative morphology of the stomach of some laboratory mammals, Laboratory Animals 23(1): 21-29.
• [23] Hewetson, M. and Tallon, R. (2021). Equine squamous gastric disease: Prevalence, impact and management, Veterinary Medicine: Research and Reports 21(2021): 381-399.
• [24] Hogben, C.A.M., Kent, T.H., Woodward, P.A. and Sill, A. (1974). Quantitative histology of the gastric mucosa: Man, dog, cat, guinea pig, and frog, Gastroenterology 67(6): 1143-1154.
• [25] Hostetter, J.M. and Uzal, F.A. (2022). Gastrointestinal biopsy in the horse: Overview of collection, interpretation, and applications, Journal of Veterinary Diagnostic Investigation 34(3): 376-388.
• [26] Hristov, H. (2020). Avian stomach anatomy - A mini review, Bulgarian Journal of Veterinary Medicine 24(4): 461-468.
• [27] Jones, K.R., John, R.E. and Sundaram, V. (2022). Morpho-histological studies of the gastrointestinal tract of the orange-rumped agouti (dasyprocta leporina linnaeus, 1758), with special reference to morphometry and histometry, Animals 12(19): 2493.
• [28] Kararli, T.T. (1995). Comparison of the gastrointestinal anatomy, physiology, and biochemistry of humans and commonly used laboratory animals, Biopharmaceutics & Drug Disposition 16(5): 351-380.
• [29] Karlupia, N., Mahajan, P., Abrol, P. and Lehana, P.K. (2023). A genetic algorithm based optimized convolutional neural network for face recognition, International Journal of Applied Mathematics and Computer Science 33(1): 21-31, DOI: 10.34768/amcs-2023-0002.
• [30] Ker, J., Bai, Y., Lee, H.Y., Rao, J. and Wang, L. (2019). Automated brain histology classification using machine learning, Journal of Clinical Neuroscience 66: 239-245.
• [31] Khorshed, T., Moustafa, M.N. and Rafea, A. (2020). Deep learning for multi-tissue cancer classification of gene expressions (GeneXNet), IEEE Access 8: 90615-90629.
• [32] Kotzé, S.H., Van Der Merwe, E.L., Bennett, N.C. and O’Riain, M.J. (2010). The comparative anatomy of the abdominal gastrointestinal tract of six species of African mole-rats (rodentia, bathyergidae), Journal of Morphology 271(1): 50-60.
• [33] Kuryszko, J., Madej, J.P. and Kapuśniak, V. (2019). Guidebook to Animal History, Wroclaw University of Environmental and Life Science, Wroclaw, (in Polish).
• [34] Lechner-Doll, M., Von Engelhardt, W., Abbas, H., Mousa, L., Luciano, L. and Reale, E. (1995). Particularities in forestomach anatomy, physiology and biochemistry of camelids compared to ruminants, in J.-L. Tisserand (Ed.), Elevage et alimentation du dromadaire, CIHEAM, Zaragoza, pp. 19-32.
• [35] Lidbury, J., Rodrigues Hoffmann, A., Ivanek, R., Cullen, J., Porter, B., Oliveira, F., Van Winkle, T., Grinwis, G., Sucholdolski, J. and Steiner, J.M. (2017). Interobserver agreement using histological scoring of the canine liver, Journal of Veterinary Internal Medicine 31(3): 778-783.
• [36] Lingeman, C.H. and Garner, F. (1972). Comparative study of intestinal adenocarcinomas of animals and man, Journal of the National Cancer Institute 48(2): 325-346.
• [37] Longnecker, D.S. and Thompson, E.D. (2023). Anatomy, histology, and fine structure of the pancreas, in H.G. Beger et al. (Eds), The Pancreas: An Integrated Textbook of Basic Science, Medicine, and Surgery Wiley-Blackwell, Hoboken, pp. 9-22.
• [38] Mahadevan, V. (2020). Anatomy of the oesophagus, Surgery (Oxford) 38(11): 677-682.
• [39] Markovits, J.E., Betton, G.R., McMartin, D.N. and Turner, O.C. (2013). Gastrointestinal tract, in P.S. Sahota et al. (Eds), Toxicological Pathology Nonclinical Safety Assessment, CRC Press, Boca Raton, pp. 257-312.
• [40] McQuilken, S.A. (2021). The mouth, stomach and intestines, Anaesthesia & Intensive Care Medicine 22(5): 330-335.
• [41] Newman, S., Steiner, J., Woosley, K., Williams, D. and Barton, L. (2006). Histologic assessment and grading of the exocrine pancreas in the dog, Journal of Veterinary Diagnostic Investigation 18(1): 115-118.
• [42] Oza, P., Sharma, P., Patel, S., Adedoyin, F. and Bruno, A. (2022). Image augmentation techniques for mammogram analysis, Journal of Imaging 8(5): 141.
• [43] Porcheri, C. and Mitsiadis, T.A. (2019). Physiology, pathology and regeneration of salivary glands, Cells 8(9): 976.
• [44] Rak, E., Szczur, A., Bazan, J.G. and Bazan-Socha, S. (2023). Assessment measures of an ensemble classifier based on the distributivity equation to predict the presence of severe coronary artery disease, International Journal of Applied Mathematics and Computer Science 33(3): 361-377, DOI: 10.34768/amcs-2023-0026.
• [45] Rakha, E.A., Toss, M., Shiino, S., Gamble, P., Jaroensri, R., Mermel, C.H. and Chen, P.-H. C. (2021). Current and future applications of artificial intelligence in pathology: A clinical perspective, Journal of Clinical Pathology 74(7): 409-414.
• [46] Sellers, A. and Stevens, C. (1966). Motor functions of the ruminant forestomach, Physiological Reviews 46(4): 634-661.
• [47] Sheahan, D.G. and Jervis, H.R. (1976). Comparative histochemistry of gastrointestinal mucosubstances, American Journal of Anatomy 146(2): 103-131.
• [48] Shiina, T., Shimizu, Y., Izumi, N., Suzuki, Y., Asano, M., Atoji, Y., Nikami, H. and Takewaki, T. (2005). A comparative histological study on the distribution of striated and smooth muscles and glands in the esophagus of wild birds and mammals, Journal of Veterinary Medical Science 67(1): 115-117.
• [49] Stieger-Vanegas, S.M. and McKenzie, E. (2021). Abdominal imaging in small ruminants: Liver, spleen, gastrointestinal tract, and lymph nodes, Veterinary Clinics: Food Animal Practice 37(1): 55-74.
• [50] Suganuma, T., Katsuyama, T., Tsukahara, M., Tatematsu, M., Sakakura, Y. and Murata, F. (1981). Comparative histochemical study of alimentary tracts with special reference to the mucous neck cells of the stomach, American Journal of Anatomy 161(2): 219-238.
• [51] Taki-El-Deen, F. (2017). Comparative microscopic study on the tongue, oesophagus and stomach of two different birds in Egypt, The Egyptian Journal of Hospital Medicine 67(1): 359-365.
• [52] Tsuchitani, M., Sato, J. and Kokoshima, H. (2016). A comparison of the anatomical structure of the pancreas in experimental animals, Journal of Toxicologic Pathology 29(3): 147-154.
• [53] Vang, Y.S., Chen, Z. and Xie, X. (2018). Deep learning framework for multi-class breast cancer histology image classification, Image Analysis and Recognition: 15th International Conference, ICIAR 2018, Póvoa de Varzim, Portugal, pp. 914-922.
• [54] Voutsinou, A., Papazoglou, L.G., Antonopoulos, I. and Rallis, T.S. (2018). Clinical topographical anatomy of the gastro-oesophageal junction in the cat, Journal of Feline Medicine and Surgery 20(4): 308-311.
• [55] Watson, A.G. (1973). Structure of the canine oesophagus, New Zealand Veterinary Journal 21(9): 195-200.
• [56] Wojtas, N., Wieczorek, M. and Bełkot, Z. (2023). Malaria detection using custom semantic segmentation neural network architecture, Medycyna Weterynaryjna 79(8): 406-412.
• [57] Yang, L., Xie, T., Liu, M., Zhang, M., Qi, S. and Yang, J. (2023). Infrared small-target detection under a complex background based on a local gradient contrast method, International Journal of Applied Mathematics and Computer Science 33(1): 33-43, DOI: 10.34768/amcs-2023-0003.
• [58] Zahariev, P., Sapundzhiev, E., Pupaki, D., Rashev, P., Palov, A. and Todorov, T. (2010). Morphological characteristics of the canine and feline stomach mucosa, Anatomia, Histologia, Embryologia 39(6): 563-568.
• [59] Zahia, S., Sierra-Sosa, D., Garcia-Zapirain, B. and Elmaghraby, A. (2018). Tissue classification and segmentation of pressure injuries using convolutional neural networks, Computer Methods and Programs in Biomedicine 159: 51-58.
• [60] Zhang, F., Yang, J., Nezami, N., Laage-Gaupp, F., Chapiro, J., De Lin, M. and Duncan, J. (2018). Liver tissue classification using an auto-context-based deep neural network with a multi-phase training framework, Patch-Based Techniques in Medical Imaging: 4th International Workshop, Patch-MI 2018/MICCAI 2018, Granada, Spain, pp. 59-66.