Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing
Cervical intraepithelial neoplasia (CIN) and cervical cancer are major health problems faced by women worldwide. The conventional Papanicolaou (Pap) smear analysis is an effective method to diagnose cervical pre-malignant and malignant conditions by analyzing swab images. Various computer vision tec...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2021-02-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-348.pdf |
| _version_ | 1818925742757511168 |
|---|---|
| author | Anant R. Bhatt Amit Ganatra Ketan Kotecha |
| author_facet | Anant R. Bhatt Amit Ganatra Ketan Kotecha |
| author_sort | Anant R. Bhatt |
| collection | DOAJ |
| description | Cervical intraepithelial neoplasia (CIN) and cervical cancer are major health problems faced by women worldwide. The conventional Papanicolaou (Pap) smear analysis is an effective method to diagnose cervical pre-malignant and malignant conditions by analyzing swab images. Various computer vision techniques can be explored to identify potential precancerous and cancerous lesions by analyzing the Pap smear image. The majority of existing work cover binary classification approaches using various classifiers and Convolution Neural Networks. However, they suffer from inherent challenges for minute feature extraction and precise classification. We propose a novel methodology to carry out the multiclass classification of cervical cells from Whole Slide Images (WSI) with optimum feature extraction. The actualization of Conv Net with Transfer Learning technique substantiates meaningful Metamorphic Diagnosis of neoplastic and pre-neoplastic lesions. As the Progressive Resizing technique (an advanced method for training ConvNet) incorporates prior knowledge of the feature hierarchy and can reuse old computations while learning new ones, the model can carry forward the extracted morphological cell features to subsequent Neural Network layers iteratively for elusive learning. The Progressive Resizing technique superimposition in consultation with the Transfer Learning technique while training the Conv Net models has shown a substantial performance increase. The proposed binary and multiclass classification methodology succored in achieving benchmark scores on the Herlev Dataset. We achieved singular multiclass classification scores for WSI images of the SIPaKMed dataset, that is, accuracy (99.70%), precision (99.70%), recall (99.72%), F-Beta (99.63%), and Kappa scores (99.31%), which supersede the scores obtained through principal methodologies. GradCam based feature interpretation extends enhanced assimilation of the generated results, highlighting the pre-malignant and malignant lesions by visual localization in the images. |
| first_indexed | 2024-12-20T02:46:04Z |
| format | Article |
| id | doaj.art-ed7675937d9f4a4dbae11d836f04d26c |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-12-20T02:46:04Z |
| publishDate | 2021-02-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-ed7675937d9f4a4dbae11d836f04d26c2022-12-21T19:56:10ZengPeerJ Inc.PeerJ Computer Science2376-59922021-02-017e34810.7717/peerj-cs.348Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizingAnant R. Bhatt0Amit Ganatra1Ketan Kotecha2Centre of Excellence for Artificial Intelligence, Military College of Telecommunication Engineering, Mhow, Madhya Pradesh, IndiaDevang Patel Institute of Advance Technology and Research, Charotar University of Science and Technology, Changa, Gujarat, IndiaSymbiosis Centre for Applied Artificial Intelligence, Symbiosis International (Deemed University), Pune, Maharashtra, IndiaCervical intraepithelial neoplasia (CIN) and cervical cancer are major health problems faced by women worldwide. The conventional Papanicolaou (Pap) smear analysis is an effective method to diagnose cervical pre-malignant and malignant conditions by analyzing swab images. Various computer vision techniques can be explored to identify potential precancerous and cancerous lesions by analyzing the Pap smear image. The majority of existing work cover binary classification approaches using various classifiers and Convolution Neural Networks. However, they suffer from inherent challenges for minute feature extraction and precise classification. We propose a novel methodology to carry out the multiclass classification of cervical cells from Whole Slide Images (WSI) with optimum feature extraction. The actualization of Conv Net with Transfer Learning technique substantiates meaningful Metamorphic Diagnosis of neoplastic and pre-neoplastic lesions. As the Progressive Resizing technique (an advanced method for training ConvNet) incorporates prior knowledge of the feature hierarchy and can reuse old computations while learning new ones, the model can carry forward the extracted morphological cell features to subsequent Neural Network layers iteratively for elusive learning. The Progressive Resizing technique superimposition in consultation with the Transfer Learning technique while training the Conv Net models has shown a substantial performance increase. The proposed binary and multiclass classification methodology succored in achieving benchmark scores on the Herlev Dataset. We achieved singular multiclass classification scores for WSI images of the SIPaKMed dataset, that is, accuracy (99.70%), precision (99.70%), recall (99.72%), F-Beta (99.63%), and Kappa scores (99.31%), which supersede the scores obtained through principal methodologies. GradCam based feature interpretation extends enhanced assimilation of the generated results, highlighting the pre-malignant and malignant lesions by visual localization in the images.https://peerj.com/articles/cs-348.pdfCervical cytologyCervical cancerTransfer learningPapanicolaou smearProgressive resizingConvolution neural network |
| spellingShingle | Anant R. Bhatt Amit Ganatra Ketan Kotecha Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing PeerJ Computer Science Cervical cytology Cervical cancer Transfer learning Papanicolaou smear Progressive resizing Convolution neural network |
| title | Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing |
| title_full | Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing |
| title_fullStr | Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing |
| title_full_unstemmed | Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing |
| title_short | Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing |
| title_sort | cervical cancer detection in pap smear whole slide images using convnet with transfer learning and progressive resizing |
| topic | Cervical cytology Cervical cancer Transfer learning Papanicolaou smear Progressive resizing Convolution neural network |
| url | https://peerj.com/articles/cs-348.pdf |
| work_keys_str_mv | AT anantrbhatt cervicalcancerdetectioninpapsmearwholeslideimagesusingconvnetwithtransferlearningandprogressiveresizing AT amitganatra cervicalcancerdetectioninpapsmearwholeslideimagesusingconvnetwithtransferlearningandprogressiveresizing AT ketankotecha cervicalcancerdetectioninpapsmearwholeslideimagesusingconvnetwithtransferlearningandprogressiveresizing |