RL-Cervix.Net: A Hybrid Lightweight Model Integrating Reinforcement Learning for Cervical Cell Classification

Overview

Journal Diagnostics (Basel)

Specialty Radiology

Date 2025 Feb 13

PMID 39941293

Authors

Shakhnoza Muksimova

Sabina Umirzakova

Jushkin Baltayev

Young-Im Cho

Affiliations

Soon will be listed here.

Abstract

Reinforcement learning (RL) represents a significant advancement in artificial intelligence (AI), particularly for complex sequential decision-making challenges. Its capability to iteratively refine decisions makes it ideal for applications in medicine, such as the detection of cervical cancer; a major cause of mortality among women globally. The Pap smear test, a crucial diagnostic tool for cervical cancer, benefits from enhancements in AI, facilitating the development of automated diagnostic systems that improve screening effectiveness. This research introduces RL-Cervix.Net, a hybrid model integrating RL with convolutional neural network (CNN) technologies, aimed at elevating the precision and efficiency of cervical cancer screenings. RL-Cervix.Net combines the robust ResNet-50 architecture with a reinforcement learning module tailored for the unique challenges of cytological image analysis. The model was trained and validated using three extensive public datasets to ensure its effectiveness under realistic conditions. A novel application of RL for dynamic feature refinement and adjustment based on reward functions was employed to optimize the detection capabilities of the model. The innovative integration of RL into the CNN framework allowed RL-Cervix.Net to achieve an unprecedented classification accuracy of 99.98% in identifying atypical cells indicative of cervical lesions. The model demonstrated superior accuracy and interpretability compared to existing methods, addressing variability and complexities inherent in cytological images. The RL-Cervix.Net model marks a significant breakthrough in the application of AI for medical diagnostics, particularly in the early detection of cervical cancer. By significantly improving diagnostic accuracy and efficiency, RL-Cervix.Net has the potential to enhance patient outcomes through earlier and more precise identification of the disease, ultimately contributing to reduced mortality rates and improved healthcare delivery.

References

Della Fera A, Warburton A, Coursey T, Khurana S, McBride A . Persistent Human Papillomavirus Infection. Viruses. 2021; 13(2). PMC: 7923415. DOI: 10.3390/v13020321. View

Cao L, Yang J, Rong Z, Li L, Xia B, You C . A novel attention-guided convolutional network for the detection of abnormal cervical cells in cervical cancer screening. Med Image Anal. 2021; 73:102197. DOI: 10.1016/j.media.2021.102197. View

Alsubai S, Alqahtani A, Sha M, Almadhor A, Abbas S, Mughal H . Privacy Preserved Cervical Cancer Detection Using Convolutional Neural Networks Applied to Pap Smear Images. Comput Math Methods Med. 2023; 2023:9676206. PMC: 10349677. DOI: 10.1155/2023/9676206. View

Fekri-Ershad S, Ramakrishnan S . Cervical cancer diagnosis based on modified uniform local ternary patterns and feed forward multilayer network optimized by genetic algorithm. Comput Biol Med. 2022; 144:105392. DOI: 10.1016/j.compbiomed.2022.105392. View

Zhao C, Shuai R, Ma L, Liu W, Wu M . Improving cervical cancer classification with imbalanced datasets combining taming transformers with T2T-ViT. Multimed Tools Appl. 2022; 81(17):24265-24300. PMC: 8933771. DOI: 10.1007/s11042-022-12670-0. View

Braila A, Poalelungi C, Albu C, Damian C, Dra L, Banateanu A . The Relationship Between Cervicovaginal Infection, Human Papillomavirus Infection and Cervical Intraepithelial Neoplasia in Romanian Women. Diseases. 2025; 13(1). PMC: 11764336. DOI: 10.3390/diseases13010018. View

Xu L, Cai F, Fu Y, Liu Q . Cervical cell classification with deep-learning algorithms. Med Biol Eng Comput. 2023; 61(3):821-833. DOI: 10.1007/s11517-022-02745-3. View

Chandran V, Sumithra M, Karthick A, George T, Deivakani M, Elakkiya B . Diagnosis of Cervical Cancer based on Ensemble Deep Learning Network using Colposcopy Images. Biomed Res Int. 2021; 2021:5584004. PMC: 8112909. DOI: 10.1155/2021/5584004. View

Fang S, Yang J, Wang M, Liu C, Liu S . An Improved Image Classification Method for Cervical Precancerous Lesions Based on ShuffleNet. Comput Intell Neurosci. 2022; 2022:9675628. PMC: 9489397. DOI: 10.1155/2022/9675628. View

10.

Habtemariam L, Zewde E, Simegn G . Cervix Type and Cervical Cancer Classification System Using Deep Learning Techniques. Med Devices (Auckl). 2022; 15:163-176. PMC: 9208738. DOI: 10.2147/MDER.S366303. View

11.

Huang J, Wang T, Zheng D, He Y . Nucleus segmentation of cervical cytology images based on multi-scale fuzzy clustering algorithm. Bioengineered. 2020; 11(1):484-501. PMC: 7161549. DOI: 10.1080/21655979.2020.1747834. View

12.

Huang P, Tan X, Chen C, Lv X, Li Y . AF-SENet: Classification of Cancer in Cervical Tissue Pathological Images Based on Fusing Deep Convolution Features. Sensors (Basel). 2020; 21(1). PMC: 7795214. DOI: 10.3390/s21010122. View

13.

K K, S K, K J A, B C . Enhancing Skin Cancer Classification using Efficient Net B0-B7 through Convolutional Neural Networks and Transfer Learning with Patient-Specific Data. Asian Pac J Cancer Prev. 2024; 25(5):1795-1802. PMC: 11318802. DOI: 10.31557/APJCP.2024.25.5.1795. View

14.

Klein S, Wuerdemann N, Demers I, Kopp C, Quantius J, Charpentier A . Predicting HPV association using deep learning and regular H&E stains allows granular stratification of oropharyngeal cancer patients. NPJ Digit Med. 2023; 6(1):152. PMC: 10439941. DOI: 10.1038/s41746-023-00901-z. View

15.

Maier A, Syben C, Lasser T, Riess C . A gentle introduction to deep learning in medical image processing. Z Med Phys. 2019; 29(2):86-101. DOI: 10.1016/j.zemedi.2018.12.003. View

16.

Muksimova S, Umirzakova S, Kang S, Cho Y . CerviLearnNet: Advancing cervical cancer diagnosis with reinforcement learning-enhanced convolutional networks. Heliyon. 2024; 10(9):e29913. PMC: 11061669. DOI: 10.1016/j.heliyon.2024.e29913. View