Cervical Transformation Zone Segmentation and Classification based on Improved Inception-ResNet-V2 Using Colposcopy Images
The second most frequent malignancy in women worldwide is cervical cancer. In the transformation(transitional) zone, which is a region of the cervix, columnar cells are continuously converting into squamous cells. The most typical location on the cervix for the development of aberrant cells is the t...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2023-03-01
|
| Series: | Cancer Informatics |
| Online Access: | https://doi.org/10.1177/11769351231161477 |
| _version_ | 1797857521342349312 |
|---|---|
| author | Srikanta Dash Prabira Kumar Sethy Santi Kumari Behera |
| author_facet | Srikanta Dash Prabira Kumar Sethy Santi Kumari Behera |
| author_sort | Srikanta Dash |
| collection | DOAJ |
| description | The second most frequent malignancy in women worldwide is cervical cancer. In the transformation(transitional) zone, which is a region of the cervix, columnar cells are continuously converting into squamous cells. The most typical location on the cervix for the development of aberrant cells is the transformation zone, a region of transforming cells. This article suggests a 2-phase method that includes segmenting and classifying the transformation zone to identify the type of cervical cancer. In the initial stage, the transformation zone is segmented from the colposcopy images. The segmented images are then subjected to the augmentation process and identified with the improved inception-resnet-v2. Here, multi-scale feature fusion framework that utilizes 3 × 3 convolution kernels from Reduction-A and Reduction-B of inception-resnet-v2 is introduced. The feature extracted from Reduction-A and Reduction -B is concatenated and fed to SVM for classification. This way, the model combines the benefits of residual networks and Inception convolution, increasing network width and resolving the deep network’s training issue. The network can extract several scales of contextual information due to the multi-scale feature fusion, which increases accuracy. The experimental results reveal 81.24% accuracy, 81.24% sensitivity, 90.62% specificity, 87.52% precision, 9.38% FPR, and 81.68% F1 score, 75.27% MCC, and 57.79% Kappa coefficient. |
| first_indexed | 2024-04-09T20:59:10Z |
| format | Article |
| id | doaj.art-eb70a68719914db0ac2a1d873936b19f |
| institution | Directory Open Access Journal |
| issn | 1176-9351 |
| language | English |
| last_indexed | 2024-04-09T20:59:10Z |
| publishDate | 2023-03-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Cancer Informatics |
| spelling | doaj.art-eb70a68719914db0ac2a1d873936b19f2023-03-29T14:05:04ZengSAGE PublishingCancer Informatics1176-93512023-03-012210.1177/11769351231161477Cervical Transformation Zone Segmentation and Classification based on Improved Inception-ResNet-V2 Using Colposcopy ImagesSrikanta Dash0Prabira Kumar Sethy1Santi Kumari Behera2Department of Electronics, Sambalpur University, Sambalpur, Odisha, IndiaDepartment of Electronics, Sambalpur University, Sambalpur, Odisha, IndiaDepartment of CSE, VSSUT Burla, Sambalpur, Odisha, IndiaThe second most frequent malignancy in women worldwide is cervical cancer. In the transformation(transitional) zone, which is a region of the cervix, columnar cells are continuously converting into squamous cells. The most typical location on the cervix for the development of aberrant cells is the transformation zone, a region of transforming cells. This article suggests a 2-phase method that includes segmenting and classifying the transformation zone to identify the type of cervical cancer. In the initial stage, the transformation zone is segmented from the colposcopy images. The segmented images are then subjected to the augmentation process and identified with the improved inception-resnet-v2. Here, multi-scale feature fusion framework that utilizes 3 × 3 convolution kernels from Reduction-A and Reduction-B of inception-resnet-v2 is introduced. The feature extracted from Reduction-A and Reduction -B is concatenated and fed to SVM for classification. This way, the model combines the benefits of residual networks and Inception convolution, increasing network width and resolving the deep network’s training issue. The network can extract several scales of contextual information due to the multi-scale feature fusion, which increases accuracy. The experimental results reveal 81.24% accuracy, 81.24% sensitivity, 90.62% specificity, 87.52% precision, 9.38% FPR, and 81.68% F1 score, 75.27% MCC, and 57.79% Kappa coefficient.https://doi.org/10.1177/11769351231161477 |
| spellingShingle | Srikanta Dash Prabira Kumar Sethy Santi Kumari Behera Cervical Transformation Zone Segmentation and Classification based on Improved Inception-ResNet-V2 Using Colposcopy Images Cancer Informatics |
| title | Cervical Transformation Zone Segmentation and Classification based on Improved Inception-ResNet-V2 Using Colposcopy Images |
| title_full | Cervical Transformation Zone Segmentation and Classification based on Improved Inception-ResNet-V2 Using Colposcopy Images |
| title_fullStr | Cervical Transformation Zone Segmentation and Classification based on Improved Inception-ResNet-V2 Using Colposcopy Images |
| title_full_unstemmed | Cervical Transformation Zone Segmentation and Classification based on Improved Inception-ResNet-V2 Using Colposcopy Images |
| title_short | Cervical Transformation Zone Segmentation and Classification based on Improved Inception-ResNet-V2 Using Colposcopy Images |
| title_sort | cervical transformation zone segmentation and classification based on improved inception resnet v2 using colposcopy images |
| url | https://doi.org/10.1177/11769351231161477 |
| work_keys_str_mv | AT srikantadash cervicaltransformationzonesegmentationandclassificationbasedonimprovedinceptionresnetv2usingcolposcopyimages AT prabirakumarsethy cervicaltransformationzonesegmentationandclassificationbasedonimprovedinceptionresnetv2usingcolposcopyimages AT santikumaribehera cervicaltransformationzonesegmentationandclassificationbasedonimprovedinceptionresnetv2usingcolposcopyimages |