Colposcopic Images Research Articles

Early Cervical Cancer Diagnosis with SWIN-Transformer and Convolutional Neural Networks.

Introduction: Early diagnosis of cervical cancer at the precancerous stage is critical for effective treatment and improved patient outcomes. Objective: This study aims to explore the use of SWIN Transformer and Convolutional Neural Network (CNN) hybrid models combined with transfer learning to classify precancerous colposcopy images. Methods: Out of 913 images from 200 cases obtained from the Colposcopy Image Bank of the International Agency for Research on Cancer, 898 met quality standards and were classified as normal, precancerous, or cancerous based on colposcopy and histopathological findings. The cases corresponding to the 360 precancerous images, along with an equal number of normal cases, were divided into a 70/30 train-test split. The SWIN Transformer and CNN hybrid model combines the advantages of local feature extraction by CNNs with the global context modeling by SWIN Transformers, resulting in superior classification performance and a more automated process. The hybrid model approach involves enhancing image quality through preprocessing, extracting local features with CNNs, capturing the global context with the SWIN Transformer, integrating these features for classification, and refining the training process by tuning hyperparameters. Results: The trained model achieved the following classification performances on fivefold cross-validation data: a 94% Area Under the Curve (AUC), an 88% F1 score, and 87% accuracy. On two completely independent test sets, which were never seen by the model during training, the model achieved an 80% AUC, a 75% F1 score, and 75% accuracy on the first test set (precancerous vs. normal) and an 82% AUC, a 78% F1 score, and 75% accuracy on the second test set (cancer vs. normal). Conclusions: These high-performance metrics demonstrate the models' effectiveness in distinguishing precancerous from normal colposcopy images, even with modest datasets, limited data augmentation, and the smaller effect size of precancerous images compared to malignant lesions. The findings suggest that these techniques can significantly aid in the early detection of cervical cancer at the precancerous stage.

Effect of a multi-ingredient coriolus-versicolor-based vaginal gel in women with HPV-dependent cervical lesions: the PAPILOBS real-life prospective study

Human papillomavirus (HPV) is responsible for virtually all cervical cancers in women. HPV infection and persistency may lead to different-grade squamous intraepithelial lesions that can result in high-grade lesions and cancer. The objective was to prospectively evaluate the results of using a Coriolus-versicolor-based vaginal gel (Papilocare®) on HPV-dependent low-grade cervical lesion repair in a real-life scenario. HPV-positive women _ 25 years with ASCUS/LSIL cervical cytology results and concordant colposcopy images were included, receiving the vaginal gel one cannula/day for 21 days (first month) + one cannula/alternate days (five months). A 6-month second treatment cycle was prescribed when needed. Repair of the cervical low-grade lesions through cytology and colposcopy, HPV clearance, and level of satisfaction, and tolerability were evaluated. In total, 192 and 201 patients accounted for the total and safety analyses, respectively, and 77.1% repaired cervical lesions at 6 or 12 months (76.0% for high-risk HPV). Additionally, 71.6% achieved HPV clearance throughout the study’s duration (70.6% for high-risk HPV). Satisfaction level was rated 7.9 and 7.5 out of 10 at 6 and 12 months, respectively. Only three mild–moderate product-related adverse events were reported, and all of them were resolved by the end of the study. In our study, we observed higher regression rates of low-grade cervical lesions in women treated with Papilocare® vaginal gel than spontaneous regression rates reported in the literature.

Automated image clarity detection for the improvement of colposcopy imaging with multiple devices

The proportion of women dying from cervical cancer in middle- and low-income countries is over 60%, twice that of their high-income counterparts. A primary screening strategy to eliminate this burden is cervix visualization and application of 3–5% acetic acid, inducing contrast in potential lesions. Recently, machine learning tools have emerged to aid visual diagnosis. As low-cost visualization tools expand, it is important to maximize image quality at the time of the exam or of images used in algorithms. Objective: We present the use of an object detection algorithm, the YOLOv5 model, to localize the cervix and describe blur within a multi-device image database. Methods: We took advantage of the Fourier domain to provide pseudo-labeling of training and testing images. A YOLOv5 model was trained using Pocket Colposcope, Mobile ODT EVA, and standard of care digital colposcope images. Results: When tested on all devices, this model achieved a mean average precision score, sensitivity, and specificity of 0.9, 0.89, and 0.89, respectively. Mobile ODT EVA and Pocket Colposcope hold out sets yielded mAP scores of 0.81 and 0.83, respectively, reflecting the generalizability of the algorithm. Compared to physician annotation, it yielded an accuracy of 0.72. Conclusion: This method provides an informed quantitative, generalizable analysis of captured images that is highly concordant with expert annotation. Significance: This quality control framework can assist in the standardization of colposcopy workflow, data acquisition, and image analysis and in doing so increase the availability of usable positive images for the development of deep learning algorithms.

Usability of a smartphone-compatible, confocal micro-endoscope for cervical cancer screening in resource-limited settings

BackgroundMore efficient methods to detect and treat precancerous lesions of the cervix at a single visit, such as low-cost confocal microscopy, could improve early diagnosis and hence outcomes. We piloted a prototype smartphone-compatible confocal micro-endoscope (SCME) among women presenting to a public cervical cancer screening clinic in Kampala, Uganda. We describe the piloting of the SCME device at an urban clinic used by lower cadre staff.MethodsWe screened women aged 18 and 60 years, who presented for cervical cancer screening at the Kawempe National Referral Hospital Kampala, and evaluated the experience of their providers (nurses). Nurses received a 2-day training by the study doctors on how to use the SCME, which was added to the standard Visual Inspection with Acetic acid (VIA)-based cervical cancer screening. The SCME was used to take colposcopy images before and after VIA at positions 12 and 6 O’clock if VIA negative, and on precancer-suspicious lesions if VIA positive. We used questionnaires to assess the women’s experiences after screening, and the experience of the nurses who operated the SCME.ResultsBetween November 2021 and July 2022, we screened 291 women with a median age of 36 years and 65.7% were HIV positive. Of the women screened, 146 were eligible for VIA, 123 were screened with the SCME, and we obtained confocal images from 103 women. Of those screened with the SCME, 60% found it comfortable and 81% were willing to screen again with it. Confocal images from 79% of the women showed distinguishable cellular features, while images from the remaining 21% were challenging to analyze. Nurses reported a mean score of 85% regarding the SCME’s usefulness to their work, 71% regarding their satisfaction and willingness to use it again, 63% in terms of ease of use, and 57% concerning the ease of learning how to operate the SCME.ConclusionOur findings demonstrate the feasibility of using the SCME by lower cadre staff in low-resource settings to aid diagnosis of precancerous lesions. However, more work is needed to make it easier for providers to learn how to operate the SCME and capture high-quality confocal images.

Multiscale Optical Imaging Fusion for Cervical Precancer Diagnosis: Integrating Widefield Colposcopy and High-Resolution Endomicroscopy.

Early detection and treatment of cervical precancers can prevent disease progression. However, in low-resource communities with a high incidence of cervical cancer, high equipment costs and a shortage of specialists hinder preventative strategies. This manuscript presents a low-cost multiscale in vivo optical imaging system coupled with a computer-aided diagnostic system that could enable accurate, real-time diagnosis of high-grade cervical precancers. The system combines portable colposcopy and high-resolution endomicroscopy (HRME) to acquire spatially registered widefield and microscopy videos. A multiscale imaging fusion network (MSFN) was developed to identify cervical intraepithelial neoplasia grade 2 or more severe (CIN 2+). The MSFN automatically identifies and segments the ectocervix and lesions from colposcopy images, extracts nuclear morphology features from HRME videos, and integrates the colposcopy and HRME information. With a threshold value set to achieve sensitivity equal to clinical impression (0.98 [p = 1.0]), the MSFN achieved a significantly higher specificity than clinical impression (0.75 vs. 0.43, p = 0.000006). Our findings show that multiscale optical imaging of the cervix allows the highly sensitive and specific detection of high-grade precancers. The multiscale imaging system and MSFN could facilitate the accurate, real-time diagnosis of cervical precancers in low-resource settings.

Artificial Intelligence in Early Detection of Cervical Intraepithelial Neoplasia

Artificial Intelligence (AI) is a quickly evolving field of technology used to develop intelligent machines capable of performing tasks such as problem solving, decision making , perception, language processing, and learning. This paper explores the application of AI in the field of gynecological oncology, specifically in the diagnosis of cervical cancer. The paper proposes a hybrid AI model that uses a Gaussian mixture model and a deep learning model to segment and classifies colposcope images. The model performed with satisfactory segmentation metrics of sensitivity, specificity, dice index, and Jaccard index of 0.976, 0.989, 0.954, and 0.856, respectively. This model aims to accurately classify cancer and non-cancer cases from a colposcope image. The results showed that this method could effectively segment the colposcopy images and extract the cervix region. This can be a valuable tool for automated cancer diagnosis and can help improve the diagnosis's accuracy.

Zipime-Weka-Schista study protocol: a longitudinal cohort study and economic evaluation of an integrated home-based approach for genital multipathogen screening in women, including female genital schistosomiasis, human papillomavirus, Trichomonas and HIV in Zambia

IntroductionMultiplathogen home-based self-sampling offers an opportunity to increase access to screening and treatment in endemic settings with high coinfection prevalence of sexually transmitted (HIV, Trichomonas vaginalis (Tv), human papillomavirus (HPV))...

Classification of cervical lesions based on multimodal features fusion

Cervical cancer is a severe threat to women's health worldwide with a long cancerous cycle and a clear etiology, making early screening vital for the prevention and treatment. Based on the dataset provided by the Obstetrics and Gynecology Hospital of Fudan University, a four-category classification model for cervical lesions including Normal, low-grade squamous intraepithelial lesion (LSIL), high-grade squamous intraepithelial lesion (HSIL) and cancer (Ca) is developed. Considering the dataset characteristics, to fully utilize the research data and ensure the dataset size, the model inputs include original and acetic colposcopy images, lesion segmentation masks, human papillomavirus (HPV), thinprep cytologic test (TCT) and age, but exclude iodine images that have a significant overlap with lesions under acetic images. Firstly, the change information between original and acetic images is introduced by calculating the acetowhite opacity to mine the correlation between the acetowhite thickness and lesion grades. Secondly, the lesion segmentation masks are utilized to introduce prior knowledge of lesion location and shape into the classification model. Lastly, a cross-modal feature fusion module based on the self-attention mechanism is utilized to fuse image information with clinical text information, revealing the features correlation. Based on the dataset used in this study, the proposed model is comprehensively compared with five excellent models over the past three years, demonstrating that the proposed model has superior classification performance and a better balance between performance and complexity. The modules ablation experiments further prove that each proposed improved module can independently improve the model performance.

Deep Learning Diagnostic Classification of Cervical Images to Augment Colposcopic Impression.

A deep learning classifier that improves the accuracy of colposcopic impression. Colposcopy images taken 56 seconds after acetic acid application were processed by a cervix detection algorithm to identify the cervical region. We optimized models based on the SegFormer architecture to classify each cervix as high-grade or negative/low-grade. The data were split into histologically stratified, random training, validation, and test subsets (80%-10%-10%). We replicated a 10-fold experiment to align with a prior study utilizing expert reviewer analysis of the same images. To evaluate the model's robustness across different cameras, we retrained it after dividing the dataset by camera type. Subsequently, we retrained the model on a new, histologically stratified random data split and integrated the results with patients' age and referral data to train a Gradient Boosted Tree model for final classification. Model accuracy was assessed by the receiver operating characteristic area under the curve (AUC), Youden's index (YI), sensitivity, and specificity compared to the histology. Out of 5,485 colposcopy images, 4,946 with histology and a visible cervix were used. The model's average performance in the 10-fold experiment was AUC = 0.75, YI = 0.37 (sensitivity = 63%, specificity = 74%), outperforming the experts' average YI of 0.16. Transferability across camera types was effective, with AUC = 0.70, YI = 0.33. Integrating image-based predictions with referral data improved outcomes to AUC = 0.81 and YI = 0.46. The use of model predictions alongside the original colposcopic impression boosted overall performance. Deep learning cervical image classification demonstrated robustness and outperformed experts. Further improved by including additional patient information, it shows potential for clinical utility complementing colposcopy.

Deep learning-based cervical lesion segmentation in colposcopic images

Artificial intelligence assisted cancer detection has changed the ream of diagnosis precision. This study aims to propose a segmentation network using artificial intelligence for accurately segmenting the cervix region and acetowhite lesions in cervigram images, addressing the shortage of skilled colposcopists and streamlining the training process. A computational approach is employed to develop and train a deep learning model specifically tailored for cervix region and acetowhite lesion segmentation in cervigram images. A dataset acquired in collaboration with KIDWAI memorial cancer research institute is used for building the model. Cervigram images are collected for training and validation, and a deep learning architecture is constructed and trained using annotated datasets. The segmentation network based on efficientnet architecture and atrous spatial pyramid pooling is designed to accurately identify and delineate the target regions, with performance evaluation conducted using precision, accuracy, recall, dice score, and specificity metrics. The proposed segmentation network achieves a precision of 0.7387±0.1541, accuracy of 0.9291, recall of 0.7912±0.1439, dice score of 0.7431±0.1506, and specificity of 0.9589±0.0131, indicating its reliability and robustness in segmenting cervix regions and acetowhite lesions in cervigram images. This research demonstrates the feasibility and effectiveness of using artificial intelligence-based computational models for cervix region and acetowhite lesion segmentation in cervigram images. It provides a foundation for further investigations into classifying cervix malignancy using AI techniques, potentially enhancing early detection and treatment of cervical cancer while addressing the shortage of skilled professionals in the field

FMA-Net: Fusion of Multi-Scale Attention for Grading Cervical Precancerous Lesions

Cervical cancer, as the fourth most common cancer in women, poses a significant threat to women’s health. Vaginal colposcopy examination, as the most cost-effective step in cervical cancer screening, can effectively detect precancerous lesions and prevent their progression into cancer. The size of the lesion areas in the colposcopic images varies, and the characteristics of the lesions are complex and difficult to discern, thus heavily relying on the expertise of the medical professionals. To address these issues, this paper constructs a vaginal colposcopy image dataset, ACIN-3, and proposes a Fusion Multi-scale Attention Network for the detection of cervical precancerous lesions. First, we propose a heterogeneous receptive field convolution module to construct the backbone network, which utilizes combinations of convolutions with different structures to extract multi-scale features from multiple receptive fields and capture features from different-sized regions of the cervix at different levels. Second, we propose an attention fusion module to construct a branch network, which integrates multi-scale features and establishes connections in both the spatial and channel dimensions. Finally, we design a dual-threshold loss function and introduce positive and negative thresholds to improve sample weights and address the issue of data imbalance in the dataset. Multiple experiments are conducted on the ACIN-3 dataset to demonstrate the superior performance of our approach compared to some classical and recent advanced methods. Our method achieves an accuracy of 92.2% in grading and 94.7% in detection, with average AUCs of 0.9862 and 0.9878. Our heatmap illustrates the accuracy of our approach in focusing on the locations of lesions.

Improving cervical cancer classification in PAP smear images with enhanced segmentation and deep progressive learning-based techniques.

Cervical cancer, a prevalent and deadly disease among women, comes second only to breast cancer, with over 700 daily deaths. The Pap smear test is a widely utilized screening method for detecting cervical cancer in its early stages. However, this manual screening process is prone to a high rate of false-positive outcomes because of human errors. Researchers are using machine learning and deep learning in computer-aided diagnostic tools to address this issue. These tools automatically analyze and sort cervical cytology and colposcopy images, improving the precision of identifying various stages of cervical cancer. This article uses state-of-the-art deep learning methods, such as ResNet-50 for categorizing cervical cancer cells to assist medical professionals. The method includes three key steps: preprocessing, segmentation using k-means clustering, and classifying cancer cells. The model is assessed based on performance metrics viz; precision, accuracy, kappa score, precision, sensitivity, and specificity. In the end, the high success rate shows that the ResNet50 model is a valuable tool for timely detection of cervical cancer. In conclusion, the infected cervical region is pinpointed using spatial K-means clustering and preprocessing operations. This sequence of actions is followed by a progressive learning technique. The Progressive Learning technique then proceeded through several stages: Stage 1 with 64 × 64 images, Stage 2 with 224 × 224 images, Stage 3 with 512 × 512 images, and the final Stage 4 with 1024 × 1024 images. The outcomes show that the suggested model is effective for analyzing Pap smear tests, achieving 97.4% accuracy and approx. 98% kappa score.

Knowledge of cytology results affects the performance of colposcopy: a crossover study

ObjectiveTo determine whether knowledge of cytology affects the colposcopist’s diagnostic accuracy in the identification of cervical intraepithelial neoplasia grade 2 and worse (≥ CIN2).MethodIn this cross-over study, healthcare professionals interpreted colposcopy images from 80 patient cases with known histological diagnoses. For each case, 2 images taken with a colposcope were provided (native and after acetic acid application). Inclusion criteria consisted of women with a transformation zone type 1 or 2, who had both a cytological and histological diagnosis. Cases were distributed across two online surveys, one including and one omitting the cytology. A wash-out period of six weeks between surveys was implemented. Colposcopists were asked to give their diagnosis for each case as < CIN2 or ≥ CIN2 on both assessments. Statistical analysis was conducted to compare the two interpretations.ResultsKnowledge of cytology significantly improved the sensitivity when interpreting colposcopic images, from 51.1% [95%CI: 39.3 to 62.8] to 63.7% [95%CI: 52.1 to 73.9] and improved the specificity from 63.5% [95%CI: 52.3 to 73.5] to 76.6% [95%CI: 67.2 to 84.0]. Sensitivity was higher by 38.6% when a high-grade cytology (ASC-H, HSIL, AGC) was communicated compared to a low-grade cytology (inflammation, ASC-US, LSIL). Specificity was higher by 31% when a low-grade cytology was communicated compared to a high-grade.ConclusionsOur data suggests that knowledge of cytology increases sensitivity and specificity for diagnosis of ≥ CIN2 lesions at colposcopy. Association between cytology and histology may have contributed to the findings.

Clinical experience of using the technique of uterine artery embolization in the treatment of submucous uterine fibroids in the Vidar Medical Center, Vinnytsia (2008–2022)

Myoma of the uterus is a benign neoplasm. The technique of uterine artery embolization (UAE) is used to treat uterine fibroids and is highly effective. The principle of embolization is based on the fact that all blood vessels that supply the uterus end in the endometrium.During UAE small parts are injected – emboli, which are spread along these vessels with the blood flow. In the vessels of the myoma the emboli cannot pass through the capsule of the myoma, so they block the vessels that supply it with blood. This leads to the cessation of blood supply to myomatous nodes, and subsequently there is a decrease in the size of these nodes, on average by 50–60% during the year, with a gradual decrease during the following years of life.This minimally invasive procedure is performed under local anesthesia – after femoral artery puncture, with X-ray control of angiography and intraoperative assessment of blood flow in fibroid nodes using ultrasound (US).Over 15 years of work, 1,400 UAE operations of uterine fibroids have been performed, of which more than 70 cases are UAE of submucosal myomas. Later, when the clinical picture of expulsion of these submucosal nodes appeared, transvaginal myomectomy was performed. Such a combined technique demonstrated high efficiency.The article describes clinical cases of patients who received treatment of large submucosal myoma by the UAE method followed by transvaginal myomectomy of the nascent node. In total, 5 clinical cases are described, the results of ultrasound, macropreparations, and colposcopic images are presented. A clinical case of a uterine myoma, the size of which corresponded to 21 weeks of pregnancy and a volume of 1500 cm3, is presented: after the above complex treatment method the volume of the uterus decreased according to ultrasound examination to 122 cm3. Also, a clinical case of a patient with uterine myoma, massive bleeding, whose hemoglobin level was 67 g/l is described. The patient was performed by UAE followed by transvaginal myomectomy for expulsion of the submucosal node.So, the described complex method of treatment of submucous uterine fibroids demonstrated high efficiency of clinical results.

A customized ConvNeXt‐XL network with fusion of deep and handcrafted features for colposcopy image classification

AbstractCervical cancer is the second most frequent cancer among women of all age groups worldwide. It occurs due to human papillomavirus. In the premature stages, the symptoms will not be predominant until they reach the final stage of cancer. Detection and classification of cervical cancer always demand gynecologists with the necessary skills and experience. The goal of the proposed work is to develop a deep learning framework to facilitate the automated classification of cervical cancer using colposcopy images. The following Deep Convolutional Neural Network (DCNN) models are proposed to detect cervical cancer and classify cervix‐type images. (i) the pre‐trained DCNNs, namely VGG16, ResNet50, InceptionV3, InceptionResNetV2, and ConvNeXtXLarge (ConvNeXt‐XL) using Softmax classifier based on deep features; (ii) the ConvNeXt‐XL model with classification using Support Vector Machine (SVM), K Nearest Neighbor (KNN) and Decision Tree (DT) based on deep features; (iii) a customized ConvNeXt‐XL network to enhance the classification accuracy using serially concatenated handcrafted and deep features. The research experiment was carried out separately using two datasets: the Cervix‐Type dataset (Type 1, Type 2, and Type 3) and the Real Time Cervical dataset (Normal and Abnormal). The simulation outcome confirms that the customized ConvNeXt‐XL helped to improve the classification accuracy with the Cervix‐Type dataset (&gt;97%) and Real Time Cervical dataset (&gt;98%).

A Corresponding Region Fusion Framework for Multi-Modal Cervical Lesion Detection.

Cervical lesion detection (CLD) using colposcopic images of multi-modality (acetic and iodine) is critical to computer-aided diagnosis (CAD) systems for accurate, objective, and comprehensive cervical cancer screening. To robustly capture lesion features and conform with clinical diagnosis practice, we propose a novel corresponding region fusion network (CRFNet) for multi-modal CLD. CRFNet first extracts feature maps and generates proposals for each modality, then performs proposal shifting to obtain corresponding regions under large position shifts between modalities, and finally fuses those region features with a new corresponding channel attention to detect lesion regions on both modalities. To evaluate CRFNet, we build a large multi-modal colposcopic image dataset collected from our collaborative hospital. We show that our proposed CRFNet surpasses known single-modal and multi-modal CLD methods and achieves state-of-the-art performance, especially in terms of Average Precision.

Colposcopic Image Segmentation Based on Feature Refinement and Attention

Colposcopic Image Segmentation Based on Feature Refinement and Attention

MFEM-CIN: A Lightweight Architecture Combining CNN and Transformer for the Classification of Pre-Cancerous Lesions of the Cervix.

Goal: Cervical cancer is one of the most common cancers in women worldwide, ranking among the top four. Unfortunately, it is also the fourth leading cause of cancer-related deaths among women, particularly in developing countries where incidence and mortality rates are higher compared to developed nations. Colposcopy can aid in the early detection of cervical lesions, but its effectiveness is limited in areas with limited medical resources and a lack of specialized physicians. Consequently, many cases are diagnosed at later stages, putting patients at significant risk. Methods: This paper proposes an automated colposcopic image analysis framework to address these challenges. The framework aims to reduce the labor costs associated with cervical precancer screening in undeserved regions and assist doctors in diagnosing patients. The core of the framework is the MFEM-CIN hybrid model, which combines Convolutional Neural Networks (CNN) and Transformer to aggregate the correlation between local and global features. This combined analysis of local and global information is scientifically useful in clinical diagnosis. In the model, MSFE and MSFF are utilized to extract and fuse multi-scale semantics. This preserves important shallow feature information and allows it to interact with the deep feature, enriching the semantics to some extent. Conclusions: The experimental results demonstrate an accuracy rate of 89.2% in identifying cervical intraepithelial neoplasia while maintaining a lightweight model. This performance exceeds the average accuracy achieved by professional physicians, indicating promising potential for practical application. Utilizing automated colposcopic image analysis and the MFEM-CIN model, this research offers a practical solution to reduce the burden on healthcare providers and improve the efficiency and accuracy of cervical cancer diagnosis in resource-constrained areas.

Deep feature extraction and fine κ-nearest neighbour for enhanced human papillomavirus detection in cervical cancer - a comprehensive analysis of colposcopy images.

This study introduces a novel methodology for classifying human papillomavirus (HPV) using colposcopy images, focusing on its potential in diagnosing cervical cancer, the second most prevalent malignancy among women globally. Addressing a crucial gap in the literature, this study highlights the unexplored territory of HPV-based colposcopy image diagnosis for cervical cancer. Emphasising the suitability of colposcopy screening in underdeveloped and low-income regions owing to its small, cost-effective setup that eliminates the need for biopsy specimens, the methodological framework includes robust dataset augmentation and feature extraction using EfficientNetB0 architecture. The optimal convolutional neural network model was selected through experimentation with 19 architectures, and fine-tuning with the fine κ-nearest neighbour algorithm enhanced the classification precision, enabling detailed distinctions with a single neighbour. The proposed methodology achieved outstanding results, with a validation accuracy of 99.9% and an area under the curve (AUC) of 99.86%, with robust performance on test data, 91.4% accuracy, and an AUC of 91.76%. These remarkable findings underscore the effectiveness of the integrated approach, which offers a highly accurate and reliable system for HPV classification.Conclusions: This research sets the stage for advancements in medical imaging applications, prompting future refinement and validation in diverse clinical settings.

Agreement on Lesion Presence and Location at Colposcopy.

The reproducibility and sensitivity of image-based colposcopy is low, but agreement on lesion presence and location remains to be explored. Here, we investigate the interobserver agreement on lesions on colposcopic images by evaluating and comparing marked lesions on digitized colposcopic images between colposcopists. Five colposcopists reviewed images from 268 colposcopic examinations. Cases were selected based on histologic diagnosis, i.e., normal/cervical intraepithelial neoplasia (CIN)1 ( n = 50), CIN2 ( n = 50), CIN3 ( n = 100), adenocarcinoma in situ ( n = 53), and cancer ( n = 15). We obtained digitized time-series images every 7-10 seconds from before acetic acid application to 2 minutes after application. Colposcopists were instructed to digitally annotate all areas with acetowhitening or suspect of lesions. To estimate the agreement on lesion presence and location, we assessed the proportion of images with annotations and the proportion of images with overlapping annotated area by at least 4 (4+) colposcopists, respectively. We included images from 241 examinations (1 image from each) with adequate annotations. The proportion with a least 1 lesion annotated by 4+ colposcopists increased by severity of histologic diagnosis. Among the CIN3 cases, 84% had at least 1 lesion annotated by 4+ colposcopists, whereas 54% of normal/CIN1 cases had a lesion annotated. Notably, the proportion was 70% for adenocarcinoma in situ and 71% for cancer. Regarding lesion location, there was no linear association with severity of histologic diagnosis. Despite that 80% of the CIN2 and CIN3 cases were annotated by 4+ colposcopists, we did not find increasing agreement on lesion location with histology severity. This underlines the subjective nature of colposcopy.