Simplified Convolutional Neural Network Application for Cervix Type Classification via Colposcopic Images
The inner parts of the human body are usually inspected endoscopically using special equipment. For instance, each part of the female reproductive system can be examined endoscopically (laparoscopy, hysteroscopy, and colposcopy). The primary purpose of colposcopy is the early detection of malignant...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/9/6/240 |
| _version_ | 1797489950598365184 |
|---|---|
| author | Vitalii Pavlov Stanislav Fyodorov Sergey Zavjalov Tatiana Pervunina Igor Govorov Eduard Komlichenko Viktor Deynega Veronika Artemenko |
| author_facet | Vitalii Pavlov Stanislav Fyodorov Sergey Zavjalov Tatiana Pervunina Igor Govorov Eduard Komlichenko Viktor Deynega Veronika Artemenko |
| author_sort | Vitalii Pavlov |
| collection | DOAJ |
| description | The inner parts of the human body are usually inspected endoscopically using special equipment. For instance, each part of the female reproductive system can be examined endoscopically (laparoscopy, hysteroscopy, and colposcopy). The primary purpose of colposcopy is the early detection of malignant lesions of the cervix. Cervical cancer (CC) is one of the most common cancers in women worldwide, especially in middle- and low-income countries. Therefore, there is a growing demand for approaches that aim to detect precancerous lesions, ideally without quality loss. Despite its high efficiency, this method has some disadvantages, including subjectivity and pronounced dependence on the operator’s experience. The objective of the current work is to propose an alternative to overcoming these limitations by utilizing the neural network approach. The classifier is trained to recognize and classify lesions. The classifier has a high recognition accuracy and a low computational complexity. The classification accuracies for the classes normal, LSIL, HSIL, and suspicious for invasion were 95.46%, 79.78%, 94.16%, and 97.09%, respectively. We argue that the proposed architecture is simpler than those discussed in other articles due to the use of the global averaging level of the pool. Therefore, the classifier can be implemented on low-power computing platforms at a reasonable cost. |
| first_indexed | 2024-03-10T00:23:59Z |
| format | Article |
| id | doaj.art-a2a05951d44b4a63a65d112d74ca1861 |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-10T00:23:59Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-a2a05951d44b4a63a65d112d74ca18612023-11-23T15:37:52ZengMDPI AGBioengineering2306-53542022-05-019624010.3390/bioengineering9060240Simplified Convolutional Neural Network Application for Cervix Type Classification via Colposcopic ImagesVitalii Pavlov0Stanislav Fyodorov1Sergey Zavjalov2Tatiana Pervunina3Igor Govorov4Eduard Komlichenko5Viktor Deynega6Veronika Artemenko7Higher School of Applied Physics and Space Technologies, Peter the Great St. Petersburg Polytechnic University, 195251 St. Petersburg, RussiaHigher School of Applied Physics and Space Technologies, Peter the Great St. Petersburg Polytechnic University, 195251 St. Petersburg, RussiaHigher School of Applied Physics and Space Technologies, Peter the Great St. Petersburg Polytechnic University, 195251 St. Petersburg, RussiaPersonalised Medicine Centre, 197341 St. Petersburg, RussiaPersonalised Medicine Centre, 197341 St. Petersburg, RussiaPersonalised Medicine Centre, 197341 St. Petersburg, RussiaPersonalised Medicine Centre, 197341 St. Petersburg, RussiaPersonalised Medicine Centre, 197341 St. Petersburg, RussiaThe inner parts of the human body are usually inspected endoscopically using special equipment. For instance, each part of the female reproductive system can be examined endoscopically (laparoscopy, hysteroscopy, and colposcopy). The primary purpose of colposcopy is the early detection of malignant lesions of the cervix. Cervical cancer (CC) is one of the most common cancers in women worldwide, especially in middle- and low-income countries. Therefore, there is a growing demand for approaches that aim to detect precancerous lesions, ideally without quality loss. Despite its high efficiency, this method has some disadvantages, including subjectivity and pronounced dependence on the operator’s experience. The objective of the current work is to propose an alternative to overcoming these limitations by utilizing the neural network approach. The classifier is trained to recognize and classify lesions. The classifier has a high recognition accuracy and a low computational complexity. The classification accuracies for the classes normal, LSIL, HSIL, and suspicious for invasion were 95.46%, 79.78%, 94.16%, and 97.09%, respectively. We argue that the proposed architecture is simpler than those discussed in other articles due to the use of the global averaging level of the pool. Therefore, the classifier can be implemented on low-power computing platforms at a reasonable cost.https://www.mdpi.com/2306-5354/9/6/240convolutional neural networkscolposcopypathologiessuspicious for invasioncervical cancer |
| spellingShingle | Vitalii Pavlov Stanislav Fyodorov Sergey Zavjalov Tatiana Pervunina Igor Govorov Eduard Komlichenko Viktor Deynega Veronika Artemenko Simplified Convolutional Neural Network Application for Cervix Type Classification via Colposcopic Images Bioengineering convolutional neural networks colposcopy pathologies suspicious for invasion cervical cancer |
| title | Simplified Convolutional Neural Network Application for Cervix Type Classification via Colposcopic Images |
| title_full | Simplified Convolutional Neural Network Application for Cervix Type Classification via Colposcopic Images |
| title_fullStr | Simplified Convolutional Neural Network Application for Cervix Type Classification via Colposcopic Images |
| title_full_unstemmed | Simplified Convolutional Neural Network Application for Cervix Type Classification via Colposcopic Images |
| title_short | Simplified Convolutional Neural Network Application for Cervix Type Classification via Colposcopic Images |
| title_sort | simplified convolutional neural network application for cervix type classification via colposcopic images |
| topic | convolutional neural networks colposcopy pathologies suspicious for invasion cervical cancer |
| url | https://www.mdpi.com/2306-5354/9/6/240 |
| work_keys_str_mv | AT vitaliipavlov simplifiedconvolutionalneuralnetworkapplicationforcervixtypeclassificationviacolposcopicimages AT stanislavfyodorov simplifiedconvolutionalneuralnetworkapplicationforcervixtypeclassificationviacolposcopicimages AT sergeyzavjalov simplifiedconvolutionalneuralnetworkapplicationforcervixtypeclassificationviacolposcopicimages AT tatianapervunina simplifiedconvolutionalneuralnetworkapplicationforcervixtypeclassificationviacolposcopicimages AT igorgovorov simplifiedconvolutionalneuralnetworkapplicationforcervixtypeclassificationviacolposcopicimages AT eduardkomlichenko simplifiedconvolutionalneuralnetworkapplicationforcervixtypeclassificationviacolposcopicimages AT viktordeynega simplifiedconvolutionalneuralnetworkapplicationforcervixtypeclassificationviacolposcopicimages AT veronikaartemenko simplifiedconvolutionalneuralnetworkapplicationforcervixtypeclassificationviacolposcopicimages |