Improving Mobile-Based Cervical Cytology Screening: A Deep Learning Nucleus-Based Approach for Lesion Detection
Liquid-based cytology (LBC) plays a crucial role in the effective early detection of cervical cancer, contributing to substantially decreasing mortality rates. However, the visual examination of microscopic slides is a challenging, time-consuming, and ambiguous task. Shortages of specialized staff a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/17/9850 |
| _version_ | 1797582805613412352 |
|---|---|
| author | Vladyslav Mosiichuk Ana Sampaio Paula Viana Tiago Oliveira Luís Rosado |
| author_facet | Vladyslav Mosiichuk Ana Sampaio Paula Viana Tiago Oliveira Luís Rosado |
| author_sort | Vladyslav Mosiichuk |
| collection | DOAJ |
| description | Liquid-based cytology (LBC) plays a crucial role in the effective early detection of cervical cancer, contributing to substantially decreasing mortality rates. However, the visual examination of microscopic slides is a challenging, time-consuming, and ambiguous task. Shortages of specialized staff and equipment are increasing the interest in developing artificial intelligence (AI)-powered portable solutions to support screening programs. This paper presents a novel approach based on a RetinaNet model with a ResNet50 backbone to detect the nuclei of cervical lesions on mobile-acquired microscopic images of cytology samples, stratifying the lesions according to The Bethesda System (TBS) guidelines. This work was supported by a new dataset of images from LBC samples digitalized with a portable smartphone-based microscope, encompassing nucleus annotations of 31,698 normal squamous cells and 1395 lesions. Several experiments were conducted to optimize the model’s detection performance, namely hyperparameter tuning, transfer learning, detected class adjustments, and per-class score threshold optimization. The proposed nucleus-based methodology improved the best baseline reported in the literature for detecting cervical lesions on microscopic images exclusively acquired with mobile devices coupled to the µSmartScope prototype, with per-class average precision, recall, and F1 scores up to 17.6%, 22.9%, and 16.0%, respectively. Performance improvements were obtained by transferring knowledge from networks pre-trained on a smaller dataset closer to the target application domain, as well as including normal squamous nuclei as a class detected by the model. Per-class tuning of the score threshold also allowed us to obtain a model more suitable to support screening procedures, achieving F1 score improvements in most TBS classes. While further improvements are still required to use the proposed approach in a clinical context, this work reinforces the potential of using AI-powered mobile-based solutions to support cervical cancer screening. Such solutions can significantly impact screening programs worldwide, particularly in areas with limited access and restricted healthcare resources. |
| first_indexed | 2024-03-10T23:27:45Z |
| format | Article |
| id | doaj.art-7f76efae9d224c21ab795c1382cdec8b |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T23:27:45Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-7f76efae9d224c21ab795c1382cdec8b2023-11-19T07:52:39ZengMDPI AGApplied Sciences2076-34172023-08-011317985010.3390/app13179850Improving Mobile-Based Cervical Cytology Screening: A Deep Learning Nucleus-Based Approach for Lesion DetectionVladyslav Mosiichuk0Ana Sampaio1Paula Viana2Tiago Oliveira3Luís Rosado4Fraunhofer Portugal AICOS, Rua Alfredo Allen 455/461, 4200-135 Porto, PortugalFraunhofer Portugal AICOS, Rua Alfredo Allen 455/461, 4200-135 Porto, PortugalISEP, Polytechnic of Porto, School of Engineering, Rua Dr. António Bernardino de Almeida, 431, 4249-015 Porto, PortugalFirst Solutions—Sistemas de Informação S.A., Rua Conselheiro Costa Braga, 502F, 4450-102 Matosinhos, PortugalFraunhofer Portugal AICOS, Rua Alfredo Allen 455/461, 4200-135 Porto, PortugalLiquid-based cytology (LBC) plays a crucial role in the effective early detection of cervical cancer, contributing to substantially decreasing mortality rates. However, the visual examination of microscopic slides is a challenging, time-consuming, and ambiguous task. Shortages of specialized staff and equipment are increasing the interest in developing artificial intelligence (AI)-powered portable solutions to support screening programs. This paper presents a novel approach based on a RetinaNet model with a ResNet50 backbone to detect the nuclei of cervical lesions on mobile-acquired microscopic images of cytology samples, stratifying the lesions according to The Bethesda System (TBS) guidelines. This work was supported by a new dataset of images from LBC samples digitalized with a portable smartphone-based microscope, encompassing nucleus annotations of 31,698 normal squamous cells and 1395 lesions. Several experiments were conducted to optimize the model’s detection performance, namely hyperparameter tuning, transfer learning, detected class adjustments, and per-class score threshold optimization. The proposed nucleus-based methodology improved the best baseline reported in the literature for detecting cervical lesions on microscopic images exclusively acquired with mobile devices coupled to the µSmartScope prototype, with per-class average precision, recall, and F1 scores up to 17.6%, 22.9%, and 16.0%, respectively. Performance improvements were obtained by transferring knowledge from networks pre-trained on a smaller dataset closer to the target application domain, as well as including normal squamous nuclei as a class detected by the model. Per-class tuning of the score threshold also allowed us to obtain a model more suitable to support screening procedures, achieving F1 score improvements in most TBS classes. While further improvements are still required to use the proposed approach in a clinical context, this work reinforces the potential of using AI-powered mobile-based solutions to support cervical cancer screening. Such solutions can significantly impact screening programs worldwide, particularly in areas with limited access and restricted healthcare resources.https://www.mdpi.com/2076-3417/13/17/9850artificial intelligencemachine learningdeep learningcervical cancercervical cytologynucleus detection |
| spellingShingle | Vladyslav Mosiichuk Ana Sampaio Paula Viana Tiago Oliveira Luís Rosado Improving Mobile-Based Cervical Cytology Screening: A Deep Learning Nucleus-Based Approach for Lesion Detection Applied Sciences artificial intelligence machine learning deep learning cervical cancer cervical cytology nucleus detection |
| title | Improving Mobile-Based Cervical Cytology Screening: A Deep Learning Nucleus-Based Approach for Lesion Detection |
| title_full | Improving Mobile-Based Cervical Cytology Screening: A Deep Learning Nucleus-Based Approach for Lesion Detection |
| title_fullStr | Improving Mobile-Based Cervical Cytology Screening: A Deep Learning Nucleus-Based Approach for Lesion Detection |
| title_full_unstemmed | Improving Mobile-Based Cervical Cytology Screening: A Deep Learning Nucleus-Based Approach for Lesion Detection |
| title_short | Improving Mobile-Based Cervical Cytology Screening: A Deep Learning Nucleus-Based Approach for Lesion Detection |
| title_sort | improving mobile based cervical cytology screening a deep learning nucleus based approach for lesion detection |
| topic | artificial intelligence machine learning deep learning cervical cancer cervical cytology nucleus detection |
| url | https://www.mdpi.com/2076-3417/13/17/9850 |
| work_keys_str_mv | AT vladyslavmosiichuk improvingmobilebasedcervicalcytologyscreeningadeeplearningnucleusbasedapproachforlesiondetection AT anasampaio improvingmobilebasedcervicalcytologyscreeningadeeplearningnucleusbasedapproachforlesiondetection AT paulaviana improvingmobilebasedcervicalcytologyscreeningadeeplearningnucleusbasedapproachforlesiondetection AT tiagooliveira improvingmobilebasedcervicalcytologyscreeningadeeplearningnucleusbasedapproachforlesiondetection AT luisrosado improvingmobilebasedcervicalcytologyscreeningadeeplearningnucleusbasedapproachforlesiondetection |