PetHIS: A New Histopathological Image Dataset for Detecting Breast Cancer in Domestic Canines

• Vinicius Barbosa da Silva IFMA
• Fabio Henrique Evangelista de Andrade UEMA
• Omar Andres Carmona Cortes IFMA

DOI: https://doi.org/10.5753/wvc.2023.27542

Resumo

Cancer is a severe disease that demands early discovery to increase the chances of survival and the probability of a cure. Its discovery is usually made through biopsy, a slow process subject to fatigue and psychological effects. Building intelligent computational visual tools to accelerate the diagnostic process is crucial in this context. The problem is that tools based on machine learning or deep learning, such as convolutional neural networks, depend on datasets to train the algorithm to create a proper model. Thus, this work proposes a dataset using histopathological images and augmentation of data from examinations of pets by the Laboratory of Veterinary Pathology. Tumor samples were obtained at the Veterinary Hospital School of the State University of Maranhão. Then, the dataset is used in a case study using VGG16 along with double transfer learning to demonstrate the applicability of the dataset. Results show that double transfer learning improves VGG16 efficiency, increasing metrics by around 5% using k-fold with k=5.

Palavras-chave: cancer detection, dataset, pets, convolutional neural networks, VGG16

Referências

Comissão de Animais de Companhia (COMAC), Coletiva de imprensa radar 2021 mercado de pet na pandemia. Brasil: Comac, 2021.

Comissão de Animais de Companhia (COMAC), Pesquisa Radar Pet: Brasil conta com a segunda maior população pet do mundo. Available at: [link]. Access date: Ago-17th-2023

Vessoni, A., Pesquisadores da Unesp participam de primeiro consenso mundial sobre hemangiossarcoma em cães. Available at: [link]. Access date: Ago-17th-2023

Cannon, C.M., Cats, Cancer and Comparative Oncology. Vet. Sci. 2015, 2, 111-–126.

Grüntzig, K.; Graf, R.; Hässig, M.; Welle, M.; Meier, D.; Lott, G.; Erni, D.; Schenker, N.; Guscetti, F.; Boo, G. et al. The swiss canine cancer registry: a retrospective study on the occurrence of tumours in dogs in switzerland from 1955 to 2008, J. Comp. Pathol., 152 (2–3), 2015, pp. 161–171.

Salas, Y.; Márquez, A.; Diaz, D.; Romero, L., Epidemiological study of mammary tumors in female dogs diagnosed during the period 2002–2012: a growing animal health problem, PLoS One, 10 (5) (2015), p. e0127381.

Egenvall, A.; Bonnett, B. N.; Öhagen, P.; Olson, P.; Hedhammar, V.; Euler, von H., Incidence of and survival after mammary tumors in a population of over 80,000 insured female dogs in sweden from 1995 to 2002, Prev. Vet. Med., 69 (1-2), 2005, pp. 109–127

Spanhol, F. A.; Oliveira, L. S.; Petitjean, C.; Heutte, L., A Dataset for Breast Cancer Histopathological Image Classification. Ieee Transactions On Biomedical Engineering, [S.L.], v. 63, n. 7, p. 1455-1462, Jul. 2016. Institute of Electrical and Electronics Engineers (IEEE). http://dx.doi.org/10.1109/tbme.2015.2496264.

Simonyan, K.; Zisserman, A., Very Deep Convolutional Networks for Large-Scale Image Recognition, arXiv, 2015.

Romeo, V,; Moy, L.; Pinker, K., AI-Enhanced PET and MR Imaging for Patients with Breast Cancer, PET Clinics, Volume 18, Issue 4, 2023, pp. 567–575.

Groheux, D., FDG-PET/CT for Primary Staging and Detection of Recurrence of Breast Cancer, Seminars in Nuclear Medicine, v. 52, Issue 5, 2022, pp. 508–519.

Michalski, K.; Stoykow, C.; Bronsert, P.; Juhasz-Böss, I.; Meyer, P. T.; Ruf, J.; Erbes, T.; Asberger, J., Association between gastrin-releasing peptide receptor expression as assessed with [68Ga]Ga-RM2 PET/CT and histopathological tumor regression after neoadjuvant chemotherapy in primary breast cancer, Nuclear Medicine and Biology, v. 86-87, 2020, pp. 37–43.

Gamba, C. O.; Dias, E. J.; Ribeiro, L. G. R.; Campos, L. G. R.; Estrela-Lima, A.; Ferreira, E.; Cassali, G. D., Histopathological and immunohistochemical assessment of invasive micropapillary mammary carcinoma in dogs: A retrospective study, The Veterinary Journal, v. 196, Issue 2, 2013, pp. 241–246.

Kumar, A.; Singh, S. K.; Saxena, S.; Lakshmanan, K.; Sangaiah, A. K.; Chauhan, H.; Shrivastava, S.; Singh, R. K., Deep feature learning for histopathological image classification of canine mammary tumors and human breast cancer, Information Sciences, v. 508, 2020, pp. 405–421, https://doi.org/10.1016/j.ins.2019.08.072.

Belsare, A. D., Histopathological Image Analysis Using Image Processing Techniques: an overview. Signal & Image Processing: An International Journal, [S.L.], v. 3, n. 4, 2012, pp. 23–36.

Hao, R.; Namdar, K.; Liu, L.; Haider, M. A.; Khalvati, F., A Comprehensive Study of Data Augmentation Strategies for Prostate Cancer Detection in Diffusion-Weighted MRI Using Convolutional Neural Networks. Journal Of Digital Imaging, [S.L.], v. 34, n. 4, 2021, pp. 862–876, http://dx.doi.org/10.1007/s10278-021-00478-7.

IMGAUG. Imgaug. Available at: [link]. Access date: Mar-4th-2023.

Krizhevsky, A.; , Alex; Sutskever, I.; Hinton, G. E., ImageNet classification with deep convolutional neural networks. Communications Of The Acm, [S.L.], v. 60, n. 6, p. 84–90, 24 maio 2017. Association for Computing Machinery (ACM), http://dx.doi.org2017/10.1145/3065386.

Iman, M.; Arabnia, H. R.; Rasheed, K., A Review of Deep Transfer Learning and Recent Advancements. Technologies, [S.L.], v. 11, n. 2, 2023, MDPI, http://dx.doi.org/10.3390/technologies11020040

Matos, J. de; Britto, A. de S.; Oliveira, L. E. S.; Koerich, A. L., Double Transfer Learning for Breast Cancer Histopathologic Image Classification, 2019 International Joint Conference On Neural Networks (Ijcnn), [S.L.], jul. 2019. IEEE. http://dx.doi.org/10.1109/ijcnn.2019.8852092.