1
|
Vargas-Cardona HD, Rodriguez-Lopez M, Arrivillaga M, Vergara-Sanchez C, García-Cifuentes JP, Bermúdez PC, Jaramillo-Botero A. Artificial intelligence for cervical cancer screening: Scoping review, 2009-2022. Int J Gynaecol Obstet 2024; 165:566-578. [PMID: 37811597 DOI: 10.1002/ijgo.15179] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2023] [Revised: 09/04/2023] [Accepted: 09/20/2023] [Indexed: 10/10/2023]
Abstract
BACKGROUND The intersection of artificial intelligence (AI) with cancer research is increasing, and many of the advances have focused on the analysis of cancer images. OBJECTIVES To describe and synthesize the literature on the diagnostic accuracy of AI in early imaging diagnosis of cervical cancer following Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR). SEARCH STRATEGY Arksey and O'Malley methodology was used and PubMed, Scopus, and Google Scholar databases were searched using a combination of English and Spanish keywords. SELECTION CRITERIA Identified titles and abstracts were screened to select original reports and cross-checked for overlap of cases. DATA COLLECTION AND ANALYSIS A descriptive summary was organized by the AI algorithm used, total of images analyzed, data source, clinical comparison criteria, and diagnosis performance. MAIN RESULTS We identified 32 studies published between 2009 and 2022. The primary sources of images were digital colposcopy, cervicography, and mobile devices. The machine learning/deep learning (DL) algorithms applied in the articles included support vector machine (SVM), random forest classifier, k-nearest neighbors, multilayer perceptron, C4.5, Naïve Bayes, AdaBoost, XGboots, conditional random fields, Bayes classifier, convolutional neural network (CNN; and variations), ResNet (several versions), YOLO+EfficientNetB0, and visual geometry group (VGG; several versions). SVM and DL methods (CNN, ResNet, VGG) showed the best diagnostic performances, with an accuracy of over 97%. CONCLUSION We concluded that the use of AI for cervical cancer screening has increased over the years, and some results (mainly from DL) are very promising. However, further research is necessary to validate these findings.
Collapse
Affiliation(s)
| | - Mérida Rodriguez-Lopez
- Faculty of Health Sciences, Universidad Icesi, Cali, Colombia
- Fundación Valle del Lili, Centro de Investigaciones Clínicas, Cali, Colombia
| | | | | | | | | | - Andres Jaramillo-Botero
- OMICAS Research Institute (iOMICAS), Pontificia Universidad Javeriana Cali, Cali, Colombia
- Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, California, USA
| |
Collapse
|
2
|
Nurmaini S, Rachmatullah MN, Agustiansyah P, Partan RU, Tutuko B, Rini DP, Darmawahyuni A, Firdaus F, Sapitri AI, Arum AW. CervicoXNet: an automated cervicogram interpretation network. Med Biol Eng Comput 2023; 61:2405-2416. [PMID: 37185967 DOI: 10.1007/s11517-023-02835-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2022] [Accepted: 04/05/2023] [Indexed: 05/17/2023]
Abstract
Visual inspection with acetic acid (VIA) is a pre-cancerous screening program for low-middle-income countries (LMICs). Due to the limited number of oncology-gynecologist clinicians in LMICs, VIA examinations are performed mainly by medical workers. However, the inability of the medical workers to recognize a significant pattern based on cervicograms, VIA examination produces high inter-observer variance and high false-positive rate. This study proposed an automated cervicogram interpretation using explainable convolutional neural networks named "CervicoXNet" to support medical workers decision. The total number of 779 cervicograms was used for the learning process: 487 with VIA ( +) and 292 with VIA ( -). We performed data augmentation process under a geometric transformation scenario, such process produces 7325 cervicogram with VIA ( -) and 7242 cervicogram with VIA ( +). The proposed model outperformed other deep learning models, with 99.22% accuracy, 100% sensitivity, and 98.28% specificity. Moreover, to test the robustness of the proposed model, colposcope images used to validate the model's generalization ability. The results showed that the proposed architecture still produced satisfactory performance, with 98.11% accuracy, 98.33% sensitivity, and 98% specificity. It can be proven that the proposed model has been achieved satisfactory results. To make the prediction results visually interpretable, the results are localized with a heat map in fine-grained pixels using a combination of Grad-CAM and guided backpropagation. CervicoXNet can be used an alternative early screening tool with VIA alone.
Collapse
Affiliation(s)
- Siti Nurmaini
- Intelligent System Research Group, Universitas Sriwijaya, Palembang, Indonesia.
| | | | - Patiyus Agustiansyah
- Department of Obstetrics and Gynaecology, Division of Oncology-Gynaecology, Mohammad Hoesin General Hospital, Palembang, Indonesia
| | - Radiyati Umi Partan
- Department of Internal Medicine, Mohammad Hoesin General Hospital, Palembang, Indonesia
| | - Bambang Tutuko
- Intelligent System Research Group, Universitas Sriwijaya, Palembang, Indonesia
| | - Dian Palupi Rini
- Department of Informatic Engineering, Faculty of Computer Science, Universitas Sriwijaya, Palembang, Indonesia
| | - Annisa Darmawahyuni
- Intelligent System Research Group, Universitas Sriwijaya, Palembang, Indonesia
| | - Firdaus Firdaus
- Intelligent System Research Group, Universitas Sriwijaya, Palembang, Indonesia
| | - Ade Iriani Sapitri
- Intelligent System Research Group, Universitas Sriwijaya, Palembang, Indonesia
| | - Akhiar Wista Arum
- Intelligent System Research Group, Universitas Sriwijaya, Palembang, Indonesia
| |
Collapse
|
3
|
Chen X, Pu X, Chen Z, Li L, Zhao KN, Liu H, Zhu H. Application of EfficientNet-B0 and GRU-based deep learning on classifying the colposcopy diagnosis of precancerous cervical lesions. Cancer Med 2023; 12:8690-8699. [PMID: 36629131 PMCID: PMC10134359 DOI: 10.1002/cam4.5581] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2022] [Revised: 11/23/2022] [Accepted: 12/17/2022] [Indexed: 01/12/2023] Open
Abstract
BACKGROUND Colposcopy is indispensable for the diagnosis of cervical lesions. However, its diagnosis accuracy for high-grade squamous intraepithelial lesion (HSIL) is at about 50%, and the accuracy is largely dependent on the skill and experience of colposcopists. The advancement in computational power made it possible for the application of artificial intelligence (AI) to clinical problems. Here, we explored the feasibility and accuracy of the application of AI on precancerous and cancerous cervical colposcopic image recognition and classification. METHODS The images were collected from 6002 colposcopy examinations of normal control, low-grade squamous intraepithelial lesion (LSIL), and HSIL. For each patient, the original, Schiller test, and acetic-acid images were all collected. We built a new neural network classification model based on the hybrid algorithm. EfficientNet-b0 was used as the backbone network for the image feature extraction, and GRU(Gate Recurrent Unit)was applied for feature fusion of the three modes examinations (original, acetic acid, and Schiller test). RESULTS The connected network classifier achieved an accuracy of 90.61% in distinguishing HSIL from normal and LSIL. Furthermore, the model was applied to "Trichotomy", which reached an accuracy of 91.18% in distinguishing the HSIL, LSIL and normal control at the same time. CONCLUSION Our results revealed that as shown by the high accuracy of AI in the classification of colposcopic images, AI exhibited great potential to be an effective tool for the accurate diagnosis of cervical disease and for early therapeutic intervention in cervical precancer.
Collapse
Affiliation(s)
- Xiaoyue Chen
- Department of Gynecology, Shanghai First Maternity and Infant Hospital, Tongji University School of Medicine, Shanghai, China
| | - Xiaowen Pu
- Department of Gynecology, Shanghai First Maternity and Infant Hospital, Tongji University School of Medicine, Shanghai, China
| | - Zhirou Chen
- Department of Gynecology, Shanghai First Maternity and Infant Hospital, Tongji University School of Medicine, Shanghai, China
| | - Lanzhen Li
- Department of Automation, Shanghai Jiao Tong University, Shanghai, China.,Ningbo Artificial Intelligent Institute, Shanghai Jiao Tong University, Ningbo, China
| | - Kong-Nan Zhao
- School of Basic Medical Science, Wenzhou Medical University, Wenzhou, China.,Australian Institute for Bioengineering and Nanotechnology, The University of Queensland, St Lucia, Queensland, Australia
| | - Haichun Liu
- Department of Automation, Shanghai Jiao Tong University, Shanghai, China.,Ningbo Artificial Intelligent Institute, Shanghai Jiao Tong University, Ningbo, China
| | - Haiyan Zhu
- Department of Gynecology, Shanghai First Maternity and Infant Hospital, Tongji University School of Medicine, Shanghai, China
| |
Collapse
|
4
|
Dash S, Sethy PK, Behera SK. Cervical Transformation Zone Segmentation and Classification based on Improved Inception-ResNet-V2 Using Colposcopy Images. Cancer Inform 2023; 22:11769351231161477. [PMID: 37008072 PMCID: PMC10064461 DOI: 10.1177/11769351231161477] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2022] [Accepted: 02/16/2023] [Indexed: 03/31/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Srikanta Dash
- Department of Electronics, Sambalpur University, Sambalpur, Odisha, India
| | - Prabira Kumar Sethy
- Department of Electronics, Sambalpur University, Sambalpur, Odisha, India
- Prabira Kumar Sethy, Department of Electronics, Sambalpur University, Jyoti Vihar, Sambalpur, Odisha 768019, India.
| | | |
Collapse
|
5
|
Pleş L, Radosa JC, Sima RM, Chicea R, Olaru OG, Poenaru MO. The Accuracy of Cytology, Colposcopy and Pathology in Evaluating Precancerous Cervical Lesions. Diagnostics (Basel) 2022; 12:diagnostics12081947. [PMID: 36010299 PMCID: PMC9407050 DOI: 10.3390/diagnostics12081947] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/18/2022] [Revised: 08/07/2022] [Accepted: 08/10/2022] [Indexed: 11/16/2022] Open
Abstract
Introduction: Cervical cancer (CC) is the third most common cancer in the world, and Romania has the highest incidence of cervical cancer in Europe. The aim of this study was to evaluate the correlation between cytology, colposcopy, and pathology for the early detection of premalignant cervical lesions in a group of Romanian patients. Methods: This observational type 2 cohort study included 128 women from our unit, “Bucur” Maternity, who were referred for cervical cancer screening. Age, clinical diagnosis, cytology results, colposcopy impression, and biopsy results were considered. Colposcopy was performed by two experienced examiners. The pathological examination was performed by an experienced pathologist. Results: The cytology found high-grade squamous intraepithelial lesions in 60.9% of patients, low-grade squamous intraepithelial lesions in 28.1%, atypical squamous cells for which a high-grade lesion could not be excluded in 9.4%, and atypical squamous cells of undetermined significance, known as repeated LSIL, in 1.6%. The first evaluator identified low-grade lesions in 56.3%, high-grade lesions in 40.6%, and invasion in 3.1% of patients. The second evaluator identified low-grade lesions in 59.4%, high-grade lesions in 32.0%, and invasion in 8.6% of patients. The pathological exam identified low-grade lesions in 64.1%, high-grade lesions in 25%, and carcinoma in 14% of patients. The colposcopic accuracy was greater than the cytologic accuracy. Conclusions: Colposcopy remains an essential tool for the identification of cervical premalignant cancer cells. Standardization of the protocol provided an insignificant interobserver variability and can serve as support for further postgraduate teaching.
Collapse
Affiliation(s)
- Liana Pleş
- Department of Obstetrics and Gynecology, Carol Davila University of Medicine and Pharmacy, 050474 Bucharest, Romania
- Bucur Maternity, Saint John Hospital, 012361 Bucharest, Romania
| | - Julia-Carolina Radosa
- Department for Gynaecology, Obstetrics and Reproductive Medicine, Saarland University Hospital, Kirrberger Straße 100, Building 9, 66421 Homburg, Germany
| | - Romina-Marina Sima
- Department of Obstetrics and Gynecology, Carol Davila University of Medicine and Pharmacy, 050474 Bucharest, Romania
- Bucur Maternity, Saint John Hospital, 012361 Bucharest, Romania
- Correspondence:
| | - Radu Chicea
- Faculty of Medicine, Lucian Blaga University of Sibiu, 550024 Sibiu, Romania
| | - Octavian-Gabriel Olaru
- Department of Obstetrics and Gynecology, Carol Davila University of Medicine and Pharmacy, 050474 Bucharest, Romania
- Bucur Maternity, Saint John Hospital, 012361 Bucharest, Romania
| | - Mircea-Octavian Poenaru
- Department of Obstetrics and Gynecology, Carol Davila University of Medicine and Pharmacy, 050474 Bucharest, Romania
- Bucur Maternity, Saint John Hospital, 012361 Bucharest, Romania
| |
Collapse
|
6
|
Ma JH, You SF, Xue JS, Li XL, Chen YY, Hu Y, Feng Z. Computer-aided diagnosis of cervical dysplasia using colposcopic images. Front Oncol 2022; 12:905623. [PMID: 35992807 PMCID: PMC9389460 DOI: 10.3389/fonc.2022.905623] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2022] [Accepted: 07/11/2022] [Indexed: 11/13/2022] Open
Abstract
Backgroundcomputer-aided diagnosis of medical images is becoming more significant in intelligent medicine. Colposcopy-guided biopsy with pathological diagnosis is the gold standard in diagnosing CIN and invasive cervical cancer. However, it struggles with its low sensitivity in differentiating cancer/HSIL from LSIL/normal, particularly in areas with a lack of skilled colposcopists and access to adequate medical resources.Methodsthe model used the auto-segmented colposcopic images to extract color and texture features using the T-test method. It then augmented minority data using the SMOTE method to balance the skewed class distribution. Finally, it used an RBF-SVM to generate a preliminary output. The results, integrating the TCT, HPV tests, and age, were combined into a naïve Bayes classifier for cervical lesion diagnosis.Resultsthe multimodal machine learning model achieved physician-level performance (sensitivity: 51.2%, specificity: 86.9%, accuracy: 81.8%), and it could be interpreted by feature extraction and visualization. With the aid of the model, colposcopists improved the sensitivity from 53.7% to 70.7% with an acceptable specificity of 81.1% and accuracy of 79.6%.Conclusionusing a computer-aided diagnosis system, physicians could identify cancer/HSIL with greater sensitivity, which guided biopsy to take timely treatment.
Collapse
Affiliation(s)
| | | | | | | | | | - Yan Hu
- *Correspondence: Zhen Feng, ; Yan Hu,
| | - Zhen Feng
- *Correspondence: Zhen Feng, ; Yan Hu,
| |
Collapse
|
7
|
Park J, Yang H, Roh HJ, Jung W, Jang GJ. Encoder-Weighted W-Net for Unsupervised Segmentation of Cervix Region in Colposcopy Images. Cancers (Basel) 2022; 14:3400. [PMID: 35884460 PMCID: PMC9317688 DOI: 10.3390/cancers14143400] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/22/2022] [Revised: 07/05/2022] [Accepted: 07/11/2022] [Indexed: 11/26/2022] Open
Abstract
Cervical cancer can be prevented and treated better if it is diagnosed early. Colposcopy, a way of clinically looking at the cervix region, is an efficient method for cervical cancer screening and its early detection. The cervix region segmentation significantly affects the performance of computer-aided diagnostics using a colposcopy, particularly cervical intraepithelial neoplasia (CIN) classification. However, there are few studies of cervix segmentation in colposcopy, and no studies of fully unsupervised cervix region detection without image pre- and post-processing. In this study, we propose a deep learning-based unsupervised method to identify cervix regions without pre- and post-processing. A new loss function and a novel scheduling scheme for the baseline W-Net are proposed for fully unsupervised cervix region segmentation in colposcopy. The experimental results showed that the proposed method achieved the best performance in the cervix segmentation with a Dice coefficient of 0.71 with less computational cost. The proposed method produced cervix segmentation masks with more reduction in outliers and can be applied before CIN detection or other diagnoses to improve diagnostic performance. Our results demonstrate that the proposed method not only assists medical specialists in diagnosis in practical situations but also shows the potential of an unsupervised segmentation approach in colposcopy.
Collapse
Affiliation(s)
- Jinhee Park
- School of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Korea;
- Neopons, Daegu 41404, Korea
| | - Hyunmo Yang
- Department of Biomedical Engineering, Ulsan National Institute of Science and Technology, Ulsan 44919, Korea; (H.Y.); (W.J.)
| | - Hyun-Jin Roh
- Department of Obstetrics and Gynaecology, University of Ulsan College of Medicine, Ulsan University Hospital, Ulsan 44033, Korea;
| | - Woonggyu Jung
- Department of Biomedical Engineering, Ulsan National Institute of Science and Technology, Ulsan 44919, Korea; (H.Y.); (W.J.)
| | - Gil-Jin Jang
- School of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Korea;
- School of Electronics Engineering, Kyungpook National University, Daegu 41566, Korea
| |
Collapse
|
8
|
Fan Y, Ma H, Fu Y, Liang X, Yu H, Liu Y. Colposcopic multimodal fusion for the classification of cervical lesions. Phys Med Biol 2022; 67. [PMID: 35617940 DOI: 10.1088/1361-6560/ac73d4] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2022] [Accepted: 05/26/2022] [Indexed: 01/01/2023]
Abstract
Objective: Cervical cancer is one of the two biggest killers of women and early detection of cervical precancerous lesions can effectively improve the survival rate of patients. Manual diagnosis by combining colposcopic images and clinical examination results is the main clinical diagnosis method at present. Developing an intelligent diagnosis algorithm based on artificial intelligence is an inevitable trend to solve the objectification of diagnosis and improve the quality and efficiency of diagnosis.Approach: A colposcopic multimodal fusion convolutional neural network (CMF-CNN) was proposed for the classification of cervical lesions. Mask region convolutional neural network was used to detect the cervical region while the encoding network EfficientNet-B3 was introduced to extract the multimodal image features from the acetic image and iodine image. Finally, Squeeze-and-Excitation, Atrous Spatial Pyramid Pooling, and convolution block were also adopted to encode and fuse the patient's clinical text information.Main results: The experimental results showed that in 7106 cases of colposcopy, the accuracy, macro F1-score, macro-areas under the curve of the proposed model were 92.70%, 92.74%, 98.56%, respectively. They are superior to the mainstream unimodal image classification models.Significance: CMF-CNN proposed in this paper combines multimodal information, which has high performance in the classification of cervical lesions in colposcopy, so it can provide comprehensive diagnostic aid.
Collapse
Affiliation(s)
- Yinuo Fan
- The Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, People's Republic of China
| | - Huizhan Ma
- The School of Precision Instrument and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, People's Republic of China
| | - Yuanbin Fu
- The College of Intelligence and Computidng, Tianjin University, Tianjin 300072, People's Republic of China
| | - Xiaoyun Liang
- The School of Precision Instrument and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, People's Republic of China
| | - Hui Yu
- The Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, People's Republic of China.,The School of Precision Instrument and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, People's Republic of China
| | - Yuzhen Liu
- The Department of Obstetrics and Gynecology, Affiliated Hospital of Weifang Medical University, Weifang 261042, People's Republic of China
| |
Collapse
|
9
|
Subarna T, Sukumar P. Detection and classification of cervical cancer images using CEENET deep learning approach. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2022. [DOI: 10.3233/jifs-220173] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Earlier detection of cervical cancer in women can save their lives before a chronic development. The accurate detection in cancer tissues of cervix in the human body is very important. In this article, cervical images were classified into either affected or healthy images using deep learning architecture. The proposed approach was designed with the modules of Edge detector, complex wavelet transform, feature derivation and Convolutional Neural Networks (CNN) architecture with segmentation. The edge pixels in the source cervical image were detected using Kirsch’s edge detector, the Complex Wavelet Transform (CWT) was there used to decompose the edge detected cervical images into number of sub bands. Local Derivative Pattern (LDP) and statistical features were computed from the decomposed sub bands and feature map was constructed using the computed features. The featured map along with the source cervical image was fed into the Cervical Ensemble Network (CEENET) model for classifying of cervical images into the classes healthy or cancer (affected).
Collapse
Affiliation(s)
- T.G. Subarna
- Department of Electronics and Communication Engineering, Nanadha Engineering College, Erode, Tamilnadu, India
| | - P. Sukumar
- Department of Electronics and Communication Engineering, Nanadha Engineering College, Erode, Tamilnadu, India
| |
Collapse
|
10
|
Deep learning in image-based breast and cervical cancer detection: a systematic review and meta-analysis. NPJ Digit Med 2022; 5:19. [PMID: 35169217 PMCID: PMC8847584 DOI: 10.1038/s41746-022-00559-z] [Citation(s) in RCA: 32] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/24/2021] [Accepted: 12/22/2021] [Indexed: 12/15/2022] Open
Abstract
Accurate early detection of breast and cervical cancer is vital for treatment success. Here, we conduct a meta-analysis to assess the diagnostic performance of deep learning (DL) algorithms for early breast and cervical cancer identification. Four subgroups are also investigated: cancer type (breast or cervical), validation type (internal or external), imaging modalities (mammography, ultrasound, cytology, or colposcopy), and DL algorithms versus clinicians. Thirty-five studies are deemed eligible for systematic review, 20 of which are meta-analyzed, with a pooled sensitivity of 88% (95% CI 85–90%), specificity of 84% (79–87%), and AUC of 0.92 (0.90–0.94). Acceptable diagnostic performance with analogous DL algorithms was highlighted across all subgroups. Therefore, DL algorithms could be useful for detecting breast and cervical cancer using medical imaging, having equivalent performance to human clinicians. However, this tentative assertion is based on studies with relatively poor designs and reporting, which likely caused bias and overestimated algorithm performance. Evidence-based, standardized guidelines around study methods and reporting are required to improve the quality of DL research.
Collapse
|
11
|
Oh TI, Kang MJ, Jeong YJ, Zhang T, Yeo SG, Park DC. Tissue Characterization Using an Electrical Bioimpedance Spectroscopy-Based Multi-Electrode Probe to Screen for Cervical Intraepithelial Neoplasia. Diagnostics (Basel) 2021; 11:diagnostics11122354. [PMID: 34943591 PMCID: PMC8700646 DOI: 10.3390/diagnostics11122354] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2021] [Revised: 12/09/2021] [Accepted: 12/11/2021] [Indexed: 12/22/2022] Open
Abstract
The successful management of cervical intraepithelial neoplasia (CIN) with proper screening and treatment methods could prevent cervical cancer progression. We propose a bioimpedance spectroscopic measurement device and a multi-electrode probe as an independent screening tool for CIN. To evaluate the performance of this screening method, we enrolled 123 patients, including 69 patients with suspected CIN and 54 control patients without cervical dysplasia who underwent a hysterectomy for benign disease (non-CIN). Following conization, the electrical properties of the excised cervical tissue were characterized using an electrical bioimpedance spectroscopy-based multi-electrode probe. Twenty-eight multifrequency voltages were collected through the two concentric array electrodes via a sensitivity-optimized measurement protocol based on an electrical energy concentration method. The electrical properties of the CIN and non-CIN groups were compared with the results of the pathology reports. Reconstructed resistivity tended to decrease in the CIN and non-CIN groups as frequency increased. Reconstructed resistivity from 625 Hz to 50 kHz differed significantly between the CIN and non-CIN groups (p < 0.001). Using 100 kHz as the reference, the difference between the CIN and non-CIN groups was significant. Based on the difference in reconstructed resistivity between 100 kHz and the other frequencies, this method had a sensitivity of 94.3%, a specificity of 84%, and an accuracy of 90% in CIN screening. The feasibility of noninvasive CIN screening was confirmed through the difference in the frequency spectra evaluated in the excised tissue using the electrical bioimpedance spectroscopy-based multi-electrode screening probe.
Collapse
Affiliation(s)
- Tong In Oh
- Department of Biomedical Engineering, College of Medicine, Kyung Hee University, Seoul 02447, Korea; (T.I.O.); (Y.J.J.); (T.Z.)
- Medical Science Research Institute, Kyung Hee University Medical Center, Seoul 02447, Korea;
| | - Min Ji Kang
- Department of Obstetrics and Gynecology, College of Medicine, The Catholic University of Korea, Seoul 06591, Korea;
| | - You Jeong Jeong
- Department of Biomedical Engineering, College of Medicine, Kyung Hee University, Seoul 02447, Korea; (T.I.O.); (Y.J.J.); (T.Z.)
| | - Tingting Zhang
- Department of Biomedical Engineering, College of Medicine, Kyung Hee University, Seoul 02447, Korea; (T.I.O.); (Y.J.J.); (T.Z.)
| | - Seung Geun Yeo
- Medical Science Research Institute, Kyung Hee University Medical Center, Seoul 02447, Korea;
| | - Dong Choon Park
- Department of Obstetrics and Gynecology, College of Medicine, The Catholic University of Korea, Seoul 06591, Korea;
- Department of Obstetrics and Gynecology, Saint Vincent’s Hospital, The Catholic University of Korea, Suwon 16247, Korea
- Correspondence: ; Tel.: +82-31-881-8894
| |
Collapse
|