Accelerated and accurate cervical cancer diagnosis using a novel stacking ensemble method with explainable AI
Cervical cancer is a preventable yet life-threatening disease that claims hundreds of thousands of lives each year, particularly in low-resource settings where timely screening is scarce. Current Deep Learning (DL) approaches for automated cervical cytology classification encounter challenges such a...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352914825000450 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849725973113602048 |
|---|---|
| author | Md Ismail Hossain Siddiqui Shakil Khan Zishad Hossain Limon Hamdadur Rahman Mahbub Alam Khan Abdullah Al Sakib S M Masfequier Rahman Swapno Rezaul Haque Ahmed Wasif Reza Abhishek Appaji |
| author_facet | Md Ismail Hossain Siddiqui Shakil Khan Zishad Hossain Limon Hamdadur Rahman Mahbub Alam Khan Abdullah Al Sakib S M Masfequier Rahman Swapno Rezaul Haque Ahmed Wasif Reza Abhishek Appaji |
| author_sort | Md Ismail Hossain Siddiqui |
| collection | DOAJ |
| description | Cervical cancer is a preventable yet life-threatening disease that claims hundreds of thousands of lives each year, particularly in low-resource settings where timely screening is scarce. Current Deep Learning (DL) approaches for automated cervical cytology classification encounter challenges such as class imbalance, computational inefficiency, and inadequate generalizability. This study proposes a novel CerviXEnsemble model that integrates multiple pre-trained DL architectures (Inception-ResNetV2, EfficientNet-B6, ResNet152, Inception-ResNetV2, EfficientNet-B6, DenseNet201, and NASNetMobile) as base learners, along with a dense-layer meta-learner that refines and consolidates predictions for improved robustness. Unlike traditional single-CNN models, our stacking ensemble approach utilizes diverse feature representations to enhance classification stability and generalization across multiple cytology datasets. To validate the model, we experimented with the Herlev and SIPaKMeD benchmark datasets in this study. Techniques like contrast enhancement and data augmentation were employed to optimize feature extraction. The model achieved state-of-the-art performance, attaining an accuracy of 99.38 % and an F1-score of 98.49 % on the Herlev dataset and an accuracy of 98.71 % and an F1-score of 97.53 % on SIPaKMeD. These performances are superior to previous studies in controlling class imbalance and providing stable predictions over different samples. Additionally, Explainable AI (XAI) techniques were incorporated to ensure transparent and interpretable predictions, aiding clinicians in their decision-making processes. An interpratable web application was developed for real-time Pap smear analysis to reduce the diagnostic workload for pathologists by identifying high-risk samples. This solution shows great promise for use in various healthcare settings, maintaining high diagnostic accuracy while requiring minimal computational resources, making it suitable for both urban hospitals and rural clinics. |
| format | Article |
| id | doaj-art-4ad0713dfbc3470a96b4b80cd3e49da2 |
| institution | DOAJ |
| issn | 2352-9148 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj-art-4ad0713dfbc3470a96b4b80cd3e49da22025-08-20T03:10:20ZengElsevierInformatics in Medicine Unlocked2352-91482025-01-015610165710.1016/j.imu.2025.101657Accelerated and accurate cervical cancer diagnosis using a novel stacking ensemble method with explainable AIMd Ismail Hossain Siddiqui0Shakil Khan1Zishad Hossain Limon2Hamdadur Rahman3Mahbub Alam Khan4Abdullah Al Sakib5S M Masfequier Rahman Swapno6Rezaul Haque7Ahmed Wasif Reza8Abhishek Appaji9Department of Engineering/Industrial Management, Westcliff University, Irvine, CA, 92614, USADepartment of Business Analytics, International American University, 3440 Wilshire Blvd STE 1000, Los Angeles, CA, 90010, USADepartment of Computer Science, Westcliff University, Irvine, CA, 92614, USADepartment of Management Information System, International American University, 3440 Wilshire Blvd STE 1000, Los Angeles, CA, 90010, USADepartment of Management Information System, Pacific State University, 3424 Wilshire Blvd., 12th Floor Los Angeles, CA, 90010, USADepartment of Information Technology, Westcliff University, Irvine, CA, 92614, USADepartment of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, 1216, BangladeshDepartment of Computer Science and Engineering, East West University, Dhaka, 1212, BangladeshDepartment of Computer Science and Engineering, East West University, Dhaka, 1212, BangladeshDepartment of Medical Electronics Engineering, B.M.S. College of Engineering, Bull Temple Rd, Basavanagudi, Bangalore, Karnataka, 560019, India; Maastricht University, University Eye Clinic Maastricht, Minderbroedersberg 4-6, Maastricht, Netherlands; Corresponding author. Department of Medical Electronics Engineering, B.M.S. College of Engineering, Bull Temple Rd, Basavanagudi, Bangalore, Karnataka, 560019, India.Cervical cancer is a preventable yet life-threatening disease that claims hundreds of thousands of lives each year, particularly in low-resource settings where timely screening is scarce. Current Deep Learning (DL) approaches for automated cervical cytology classification encounter challenges such as class imbalance, computational inefficiency, and inadequate generalizability. This study proposes a novel CerviXEnsemble model that integrates multiple pre-trained DL architectures (Inception-ResNetV2, EfficientNet-B6, ResNet152, Inception-ResNetV2, EfficientNet-B6, DenseNet201, and NASNetMobile) as base learners, along with a dense-layer meta-learner that refines and consolidates predictions for improved robustness. Unlike traditional single-CNN models, our stacking ensemble approach utilizes diverse feature representations to enhance classification stability and generalization across multiple cytology datasets. To validate the model, we experimented with the Herlev and SIPaKMeD benchmark datasets in this study. Techniques like contrast enhancement and data augmentation were employed to optimize feature extraction. The model achieved state-of-the-art performance, attaining an accuracy of 99.38 % and an F1-score of 98.49 % on the Herlev dataset and an accuracy of 98.71 % and an F1-score of 97.53 % on SIPaKMeD. These performances are superior to previous studies in controlling class imbalance and providing stable predictions over different samples. Additionally, Explainable AI (XAI) techniques were incorporated to ensure transparent and interpretable predictions, aiding clinicians in their decision-making processes. An interpratable web application was developed for real-time Pap smear analysis to reduce the diagnostic workload for pathologists by identifying high-risk samples. This solution shows great promise for use in various healthcare settings, maintaining high diagnostic accuracy while requiring minimal computational resources, making it suitable for both urban hospitals and rural clinics.http://www.sciencedirect.com/science/article/pii/S2352914825000450Cervical cancerExplainable AIPap smear image analysisDiagnostic toolEnsemble learning |
| spellingShingle | Md Ismail Hossain Siddiqui Shakil Khan Zishad Hossain Limon Hamdadur Rahman Mahbub Alam Khan Abdullah Al Sakib S M Masfequier Rahman Swapno Rezaul Haque Ahmed Wasif Reza Abhishek Appaji Accelerated and accurate cervical cancer diagnosis using a novel stacking ensemble method with explainable AI Informatics in Medicine Unlocked Cervical cancer Explainable AI Pap smear image analysis Diagnostic tool Ensemble learning |
| title | Accelerated and accurate cervical cancer diagnosis using a novel stacking ensemble method with explainable AI |
| title_full | Accelerated and accurate cervical cancer diagnosis using a novel stacking ensemble method with explainable AI |
| title_fullStr | Accelerated and accurate cervical cancer diagnosis using a novel stacking ensemble method with explainable AI |
| title_full_unstemmed | Accelerated and accurate cervical cancer diagnosis using a novel stacking ensemble method with explainable AI |
| title_short | Accelerated and accurate cervical cancer diagnosis using a novel stacking ensemble method with explainable AI |
| title_sort | accelerated and accurate cervical cancer diagnosis using a novel stacking ensemble method with explainable ai |
| topic | Cervical cancer Explainable AI Pap smear image analysis Diagnostic tool Ensemble learning |
| url | http://www.sciencedirect.com/science/article/pii/S2352914825000450 |
| work_keys_str_mv | AT mdismailhossainsiddiqui acceleratedandaccuratecervicalcancerdiagnosisusinganovelstackingensemblemethodwithexplainableai AT shakilkhan acceleratedandaccuratecervicalcancerdiagnosisusinganovelstackingensemblemethodwithexplainableai AT zishadhossainlimon acceleratedandaccuratecervicalcancerdiagnosisusinganovelstackingensemblemethodwithexplainableai AT hamdadurrahman acceleratedandaccuratecervicalcancerdiagnosisusinganovelstackingensemblemethodwithexplainableai AT mahbubalamkhan acceleratedandaccuratecervicalcancerdiagnosisusinganovelstackingensemblemethodwithexplainableai AT abdullahalsakib acceleratedandaccuratecervicalcancerdiagnosisusinganovelstackingensemblemethodwithexplainableai AT smmasfequierrahmanswapno acceleratedandaccuratecervicalcancerdiagnosisusinganovelstackingensemblemethodwithexplainableai AT rezaulhaque acceleratedandaccuratecervicalcancerdiagnosisusinganovelstackingensemblemethodwithexplainableai AT ahmedwasifreza acceleratedandaccuratecervicalcancerdiagnosisusinganovelstackingensemblemethodwithexplainableai AT abhishekappaji acceleratedandaccuratecervicalcancerdiagnosisusinganovelstackingensemblemethodwithexplainableai |