ABSTRACT
Cervical cancer is the third neoplasm in frequency worldwide between women. Screening techniques in general population have demonstrated clear effectiveness as its implementation has decreased cervical cancer incidence and mortality more than 70% in several countries. This benefit is related with detection of early pre-malignant asymptomatic lesions, that can be treated to avoid their progression to invasive cancer. Papanicolau cervical smear is the most common cancer screening technique worldwide used since described by Giorgios Papanicolau on 1928. Sampling techniques have been improved in last years, based on simplifying and automatizing procedures. However, after preparing the samples, an expert review of the microscopic images is needed. There are few automatic diagnostic methods published, but their results are not as good as an expert examination. In this paper, we develop a microscopic cervical cells database using Papanicolau cervical smears from our patients, sampled few minutes before performing a cone biopsy on them. With this procedure, we have both the cervical smear and the biopsy diagnostics, tagged as Gold Standard. Then, a deep-learning methodology is performed for the automatic categorization of pre-malignant and benign cervical cells. We use the the Caffe deep-learning framework to leverage NVIDIA GPU computing architectures to deal with this real patient database in a reduced time-frame. Our results reveal the deep learning methodology is robust in this biomedical classification, reaching up to 78% Accuracy.
- Charles V Biscotti, Andrea E Dawson, Bruce Dziura, Luis Galup, Teresa Darragh, Amir Rahemtulla, and Lisa Wills-Frank. 2005. Assisted primary screening using the automated ThinPrep Imaging System. American journal of clinical pathology 123, 2 (2005), 281--287.Google Scholar
- Paolo Bulgaresi, Maria Paola Cariaggi, Grazia Maria Troni, and Stefano Ciatto. 2006. Quality control of the autopap screening system employed as a primary screening device: rapid review of smears coded as no further review. Tumori 92, 4 (2006), 276--278.Google ScholarCross Ref
- Deborah J Chute, Harumi Lim, and Christina S Kong. 2010. BD focalpoint slide profiler performance with atypical glandular cells on SurePath Papanicolaou smears. Cancer cytopathology 118, 2 (2010), 68--74.Google Scholar
- Massimo Confortini, Lucia Bonardi, Paolo Bulgaresi, Maria Paola Cariaggi, Silvia Cecchini, Stefano Ciatto, Ida Cipparrone, Laura Galanti, Cristina Maddau, Marzia Matucci, et al. 2003. A feasibility study of the use of the AutoPap screening system as a primary screening and location-guided rescreening device. Cancer Cytopathology 99, 3 (2003), 129--134.Google ScholarCross Ref
- Andre Esteva, Brett Kuprel, Roberto A Novoa, Justin Ko, Susan M Swetter, Helen M Blau, and Sebastian Thrun. 2017. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 7639 (2017), 115.Google Scholar
- Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio. 2016. Deep learning. Vol. 1. MIT press Cambridge. Google ScholarDigital Library
- JA Halford, T Batty, T Boost, J Duhig, J Hall, C Lee, and K Walker. 2010. Comparison of the sensitivity of conventional cytology and the ThinPrep Imaging System for 1,083 biopsy confirmed high-grade squamous lesions. Diagnostic cytopathology 38, 5 (2010), 318--326.Google Scholar
- Henry C Kitchener, R Blanks, H Cubie, M Desai, G Dunn, R Legood, A Gray, Z Sadique, and S Moss. 2011. MAVARIC--a comparison of automation-assisted and manual cervical screening: a randomised controlled trial. Clinical Governance: An International Journal 16, 3 (2011).Google ScholarCross Ref
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105. Google ScholarDigital Library
- Jinsa Kuruvilla and K Gunavathi. 2014. Lung cancer classification using neural networks for CT images. Computer methods and programs in biomedicine 113, 1 (2014), 202--209. Google ScholarDigital Library
- Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature 521, 7553 (2015), 436.Google Scholar
- Sergey Levine, Chelsea Finn, Trevor Darrell, and Pieter Abbeel. 2016. End-to-end training of deep visuomotor policies. The Journal of Machine Learning Research 17, 1 (2016), 1334--1373. Google ScholarDigital Library
- Fei-Fei Li and Andrej Karpathy. 2015. Convolutional Neural Networks for Visual Recognition.Google Scholar
- Pim Moeskops, Max A Viergever, Adriënne M Mendrik, Linda S de Vries, Manon JNL Benders, and Ivana Išgum. 2016. Automatic segmentation of MR brain images with a convolutional neural network. IEEE transactions on medical imaging 35, 5 (2016), 1252--1261.Google Scholar
- Nima Habibzadeh Motlagh, Mahboobeh Jannesary, HamidReza Aboulkheyr, Pegah Khosravi, Olivier Elemento, Mehdi Totonchi, and Iman Hajirasouliha. 2018. Breast Cancer Histopathological Image Classification: A Deep Learning Approach. bioRxiv (2018), 242818.Google Scholar
- TJ Palmer, SM Nicoll, ME McKean, AJ Park, D Bishop, L Baker, and JEA Imrie. 2013. Prospective parallel randomized trial of the MultiCyteâĎć ThinPrep® imaging system: the Scottish experience. Cytopathology 24, 4 (2013), 235--245.Google ScholarCross Ref
- George N Papanicolaou and Herbert F Traut. 1941. The diagnostic value of vaginal smears in carcinoma of the uterus. American Journal of Obstetrics and Gynecology 42, 2 (1941), 193--206.Google ScholarCross Ref
- Tara N Sainath, Abdel-rahman Mohamed, Brian Kingsbury, and Bhuvana Ramabhadran. 2013. Deep convolutional neural networks for LVCSR. In Acoustics, speech and signal processing (ICASSP), 2013 IEEE international conference on. IEEE, 8614--8618.Google Scholar
- Korsuk Sirinukunwattana, Shan E Ahmed Raza, Yee-Wah Tsang, David RJ Snead, Ian A Cree, and Nasir M Rajpoot. 2016. Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images. IEEE transactions on medical imaging 35, 5 (2016), 1196--1206.Google Scholar
- Vivienne Sze, Yu-Hsin Chen, Tien-Ju Yang, and Joel S Emer. 2017. Efficient processing of deep neural networks: A tutorial and survey. Proc. IEEE 105, 12 (2017), 2295--2329.Google ScholarCross Ref
- Rebecca Wong, Angelique W Levi, Malini Harigopal, Kevin Schofield, and David C Chhieng. 2012. The positive impact of simultaneous implementation of the BD FocalPoint GS Imaging System and lean principles on the operation of gynecologic cytology. Archives of pathology & laboratory medicine 136, 2 (2012), 183--189.Google Scholar
Index Terms
- Deep Learning Approach for Classifying Papanicolau Cervical Smears
Recommendations
Review on Deep Learning Methods Used for Computer-aided Lung Cancer Detection and Diagnosis
ACAI '19: Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial IntelligenceCancer is one of the diseases with high mortality rates in the 21st century, with lung cancer being the first in all cancer morbidity and mortality rates. In recent years, with the large rise of data and artificial intelligence researches, the auxiliary ...
Single and Clustered Cervical Cell Classification with Ensemble and Deep Learning Methods
AbstractCervical cancer if detected early has an upward of 89% survival rate. The leading tool in identifying cervical cancer in its infancy is the Papanicolaou (Pap smear) test, which since its introduction dropped cervical cancer related deaths by 60%. ...
Classification of cervical cancer using machine learning techniques: a review
One of the most prevalent and deadliest malignancies in women is cervical malignancy. It is the fourth major cause of death among women worldwide. Women's lives can be saved if this malignancy is identified at a precancerous stage because it is fully ...
Comments