Internet of health things-driven deep learning system for detection and classification of cervical cells using transfer
- PDF / 1,992,754 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 76 Downloads / 208 Views
Internet of health things‑driven deep learning system for detection and classification of cervical cells using transfer learning Aditya Khamparia1 · Deepak Gupta2 · Victor Hugo C. de Albuquerque3 · Arun Kumar Sangaiah4 · Rutvij H. Jhaveri5
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Cervical cancer is one of the fastest growing global health problems and leading cause of mortality among women of developing countries. Automated Pap smear cell recognition and classification in early stage of cell development is crucial for effective disease diagnosis and immediate treatment. Thus, in this article, we proposed a novel internet of health things (IoHT)-driven deep learning framework for detection and classification of cervical cancer in Pap smear images using concept of transfer learning. Following transfer learning, convolutional neural network (CNN) was combined with different conventional machine learning techniques like K nearest neighbor, naïve Bayes, logistic regression, random forest and support vector machines. In the proposed framework, feature extraction from cervical images is performed using pre-trained CNN models like InceptionV3, VGG19, SqueezeNet and ResNet50, which are fed into dense and flattened layer for normal and abnormal cervical cells classification. The performance of the proposed IoHT frameworks is evaluated using standard Pap smear Herlev dataset. The proposed approach was validated by analyzing precision, recall, F1-score, training–testing time and support parameters. The obtained results concluded that CNN pre-trained model ResNet50 achieved the higher classification rate of 97.89% with the involvement of random forest classifier for effective and reliable disease detection and classification. The minimum training time and testing time required to train model were 0.032 s and 0.006 s, respectively. Keywords Transfer · IoHT · Classification · Regression · Pre-trained
* Arun Kumar Sangaiah [email protected]; [email protected] Extended author information available on the last page of the article
13
Vol.:(0123456789)
A. Khamparia et al.
1 Introduction Cervical cancer is one of the fastest evolving and dangerous cancers which affect the life of several women worldwide. According to the reports of World Health Organization, cervical cancer is growing rapidly among Indian women which occurs approximately 1 in 53 women as compared to 1 in 100 women suffering from such ailment worldwide. The most common and frequent symptom observed in most of the suffered patients was unusual discharge or bleeding from vagina. For medical treatment and diagnosis, Pap smear test is adopted for the identification of abnormalities present in cervical cells like cell disruption, change in cell size, cell color, mucus, etc. The accurate and manual segmentation of Pap smear cells is challenging among cytologists due to overlapping of Pap cells; thus, it become very difficult and time-consuming to delineate the inflammatory cell and mucus presence in cell image. A b
Data Loading...
