Mask region-based CNNs for cervical cancer progression diagnosis on pap smear examinations
This research presents a novel approach for cervical cancer detection and segmentation using tissue images with multiple cells. The study employs a novel deep learning architecture based on Mask Region-Based Convolutional Neural Network (RCNN) and statistical analysis. This new architecture enables...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023085961 |
| _version_ | 1797429921947058176 |
|---|---|
| author | Carolina Rutili de Lima Said G. Khan Syed H. Shah Luthiari Ferri |
| author_facet | Carolina Rutili de Lima Said G. Khan Syed H. Shah Luthiari Ferri |
| author_sort | Carolina Rutili de Lima |
| collection | DOAJ |
| description | This research presents a novel approach for cervical cancer detection and segmentation using tissue images with multiple cells. The study employs a novel deep learning architecture based on Mask Region-Based Convolutional Neural Network (RCNN) and statistical analysis. This new architecture enables us to achieve a high percentage of detection and pix-to-pix area segmentation. A mean Average Precision (mAP) higher than 60% for 3-class and 5-class was achieved. In addition, higher F1-scores of 70% for 3-class and 5-class were obtained. This investigation is a collaborative work, where a medical consultant collected the samples from the Papanicolaou (Pap) Smear examination and labeled the cells presented to the liquid-based cytology (LBC). Furthermore, the online available benchmark data set, SIPaKMeD, was also utilized. Additionally, sample images from the Mendeley data set were also labeled by the trained medical consultant for comparison. The proposed scheme automatically generates a full report for a medical consultant to identify the location of the malicious cells in the given images and expedite the diagnosis and treatment process. |
| first_indexed | 2024-03-09T09:19:54Z |
| format | Article |
| id | doaj.art-9121155abfd2490b9d26d23d0b4d6f13 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-09T09:19:54Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-9121155abfd2490b9d26d23d0b4d6f132023-12-02T07:02:04ZengElsevierHeliyon2405-84402023-11-01911e21388Mask region-based CNNs for cervical cancer progression diagnosis on pap smear examinationsCarolina Rutili de Lima0Said G. Khan1Syed H. Shah2Luthiari Ferri3Department of Electrical Engineering, National Taiwan Normal University, Taipei, Taiwan; Corresponding author.Department of Mechanical Engineering, College of Engineering, University of Bahrain Isa Town, BahrainCollege of Electrical and Communication Engineering, Yuan Ze University, Taoyuan, TaiwanInstituto de Patologia de Passo Fundo, Ijuí, BrazilThis research presents a novel approach for cervical cancer detection and segmentation using tissue images with multiple cells. The study employs a novel deep learning architecture based on Mask Region-Based Convolutional Neural Network (RCNN) and statistical analysis. This new architecture enables us to achieve a high percentage of detection and pix-to-pix area segmentation. A mean Average Precision (mAP) higher than 60% for 3-class and 5-class was achieved. In addition, higher F1-scores of 70% for 3-class and 5-class were obtained. This investigation is a collaborative work, where a medical consultant collected the samples from the Papanicolaou (Pap) Smear examination and labeled the cells presented to the liquid-based cytology (LBC). Furthermore, the online available benchmark data set, SIPaKMeD, was also utilized. Additionally, sample images from the Mendeley data set were also labeled by the trained medical consultant for comparison. The proposed scheme automatically generates a full report for a medical consultant to identify the location of the malicious cells in the given images and expedite the diagnosis and treatment process.http://www.sciencedirect.com/science/article/pii/S2405844023085961Cervical cancerMask RCNNDeep learningCells segmentation and classificationWhole tissue classificationHealth and technology |
| spellingShingle | Carolina Rutili de Lima Said G. Khan Syed H. Shah Luthiari Ferri Mask region-based CNNs for cervical cancer progression diagnosis on pap smear examinations Heliyon Cervical cancer Mask RCNN Deep learning Cells segmentation and classification Whole tissue classification Health and technology |
| title | Mask region-based CNNs for cervical cancer progression diagnosis on pap smear examinations |
| title_full | Mask region-based CNNs for cervical cancer progression diagnosis on pap smear examinations |
| title_fullStr | Mask region-based CNNs for cervical cancer progression diagnosis on pap smear examinations |
| title_full_unstemmed | Mask region-based CNNs for cervical cancer progression diagnosis on pap smear examinations |
| title_short | Mask region-based CNNs for cervical cancer progression diagnosis on pap smear examinations |
| title_sort | mask region based cnns for cervical cancer progression diagnosis on pap smear examinations |
| topic | Cervical cancer Mask RCNN Deep learning Cells segmentation and classification Whole tissue classification Health and technology |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023085961 |
| work_keys_str_mv | AT carolinarutilidelima maskregionbasedcnnsforcervicalcancerprogressiondiagnosisonpapsmearexaminations AT saidgkhan maskregionbasedcnnsforcervicalcancerprogressiondiagnosisonpapsmearexaminations AT syedhshah maskregionbasedcnnsforcervicalcancerprogressiondiagnosisonpapsmearexaminations AT luthiariferri maskregionbasedcnnsforcervicalcancerprogressiondiagnosisonpapsmearexaminations |