Explore the vast range of titles available.

Background The World Health Organization (WHO) called for global action towards the elimination of cervical cancer. One of the main strategies is to screen 70% of women at the age between 35 and 45 years and 90% of women managed appropriately by 2030. So far, approximately 85% of cervical cancers occur in low- and middle-income countries (LMICs). The colposcopy-guided biopsy is crucial for detecting cervical intraepithelial neoplasia (CIN) and becomes the main bottleneck limiting screening performance. Unprecedented advances in artificial intelligence (AI) enable the synergy of deep learning and digital colposcopy, which offers opportunities for automatic image-based diagnosis. To this end, we discuss the main challenges of traditional colposcopy and the solutions applying AI-guided digital colposcopy as an auxiliary diagnostic tool in low- and middle- income countries (LMICs). Main body Existing challenges for the application of colposcopy in LMICs include strong dependence on the subjective experience of operators, substantial inter- and intra-operator variabilities, shortage of experienced colposcopists, consummate colposcopy training courses, and uniform diagnostic standard and strict quality control that are hard to be followed by colposcopists with limited diagnostic ability, resulting in discrepant reporting and documentation of colposcopy impressions. Organized colposcopy training courses should be viewed as an effective way to enhance the diagnostic ability of colposcopists, but implementing these courses in practice may not always be feasible to improve the overall diagnostic performance in a short period of time. Fortunately, AI has the potential to address colposcopic bottleneck, which could assist colposcopists in colposcopy imaging judgment, detection of underlying CINs, and guidance of biopsy sites. The automated workflow of colposcopy examination could create a novel cervical cancer screening model, reduce potentially false negatives and false positives, and improve the accuracy of colposcopy diagnosis and cervical biopsy. Conclusion We believe that a practical and accurate AI-guided digital colposcopy has the potential to strengthen the diagnostic ability in guiding cervical biopsy, thereby improves cervical cancer screening performance in LMICs and accelerates the process of global cervical cancer elimination eventually.

Background Colposcopy diagnosis and directed biopsy are the key components in cervical cancer screening programs. However, their performance is limited by the requirement for experienced colposcopists. This study aimed to develop and validate a Colposcopic Artificial Intelligence Auxiliary Diagnostic System (CAIADS) for grading colposcopic impressions and guiding biopsies. Methods Anonymized digital records of 19,435 patients were obtained from six hospitals across China. These records included colposcopic images, clinical information, and pathological results (gold standard). The data were randomly assigned (7:1:2) to a training and a tuning set for developing CAIADS and to a validation set for evaluating performance. Results The agreement between CAIADS-graded colposcopic impressions and pathology findings was higher than that of colposcopies interpreted by colposcopists (82.2% versus 65.9%, kappa 0.750 versus 0.516, p  < 0.001). For detecting pathological high-grade squamous intraepithelial lesion or worse (HSIL+), CAIADS showed higher sensitivity than the use of colposcopies interpreted by colposcopists at either biopsy threshold (low-grade or worse 90.5%, 95% CI 88.9–91.4% versus 83.5%, 81.5–85.3%; high-grade or worse 71.9%, 69.5–74.2% versus 60.4%, 57.9–62.9%; all p  < 0.001), whereas the specificities were similar (low-grade or worse 51.8%, 49.8–53.8% versus 52.0%, 50.0–54.1%; high-grade or worse 93.9%, 92.9–94.9% versus 94.9%, 93.9–95.7%; all p  > 0.05). The CAIADS also demonstrated a superior ability in predicting biopsy sites, with a median mean-intersection-over-union (mIoU) of 0.758. Conclusions The CAIADS has potential in assisting beginners and for improving the diagnostic quality of colposcopy and biopsy in the detection of cervical precancer/cancer.

In four randomised trials, human papillomavirus (HPV)-based screening for cervical cancer was compared with cytology-based cervical screening, and precursors of cancer were the endpoint in every trial. However, direct estimates are missing of the relative efficacy of HPV-based versus cytology-based screening for prevention of invasive cancer in women who undergo regular screening, of modifiers (eg, age) of this relative efficacy, and of the duration of protection. We did a follow-up study of the four randomised trials to investigate these outcomes. 176 464 women aged 20–64 years were randomly assigned to HPV-based (experimental arm) or cytology-based (control arm) screening in Sweden (Swedescreen), the Netherlands (POBASCAM), England (ARTISTIC), and Italy (NTCC). We followed up these women for a median of 6·5 years (1 214 415 person-years) and identified 107 invasive cervical carcinomas by linkage with screening, pathology, and cancer registries, by masked review of histological specimens, or from reports. Cumulative and study-adjusted rate ratios (experimental vs control) were calculated for incidence of invasive cervical carcinoma. The rate ratio for invasive cervical carcinoma among all women from recruitment to end of follow-up was 0·60 (95% CI 0·40–0·89), with no heterogeneity between studies (p=0·52). Detection of invasive cervical carcinoma was similar between screening methods during the first 2·5 years of follow-up (0·79, 0·46–1·36) but was significantly lower in the experimental arm thereafter (0·45, 0·25–0·81). In women with a negative screening test at entry, the rate ratio was 0·30 (0·15–0·60). The cumulative incidence of invasive cervical carcinoma in women with negative entry tests was 4·6 per 105 (1·1–12·1) and 8·7 per 105 (3·3–18·6) at 3·5 and 5·5 years, respectively, in the experimental arm, and 15·4 per 105 (7·9–27·0) and 36·0 per 105 (23·2–53·5), respectively, in the control arm. Rate ratios did not differ by cancer stage, but were lower for adenocarcinoma (0·31, 0·14–0·69) than for squamous-cell carcinoma (0·78, 0·49–1·25). The rate ratio was lowest in women aged 30–34 years (0·36, 0·14–0·94). HPV-based screening provides 60–70% greater protection against invasive cervical carcinomas compared with cytology. Data of large-scale randomised trials support initiation of HPV-based screening from age 30 years and extension of screening intervals to at least 5 years. European Union, Belgian Foundation Against Cancer, KCE-Centre d'Expertise, IARC, The Netherlands Organisation for Health Research and Development, the Italian Ministry of Health.

Cervical cancer (CC) is the leading cancer, which mainly affects women worldwide. It generally occurs from abnormal cell evolution in the cervix and a vital functional structure in the uterus. The importance of timely recognition cannot be overstated, which has led to various screening methods such as colposcopy, Human Papillomavirus (HPV) testing, and Pap smears to identify potential threats and enable early intervention. Early detection during the precancerous phase is crucial, as it provides an opportunity for effective treatment. The diagnosis and screening of CC depend on colposcopy and cytology models. Deep learning (DL) is an appropriate technique in computer vision, which has developed as a latent solution to increase the efficiency and accuracy of CC screening when equated to conventional clinical inspection models that are vulnerable to human error. This study presents a Leveraging Swin Transformer with an Ensemble of Deep Learning Model for Cervical Cancer Screening (LSTEDL-CCS) technique for colposcopy images. The presented LSTEDL-CCS technique aims to detect and classify CC on colposcopy images. Initially, the wiener filtering (WF) model is used for image pre-processing. Next, the swin transformer (ST) network is utilized for feature extraction. For the cancer detection process, the ensemble learning method is performed by employing three models, namely autoencoder (AE), bidirectional gated recurrent unit (BiGRU), and deep belief network (DBN). Finally, the hyperparameter tuning of the DL techniques is performed using the Pelican Optimization Algorithm (POA). A comprehensive experimental analysis is conducted, and the results are evaluated under diverse metrics. The performance validation of the LSTEDL-CCS methodology portrayed a superior accuracy value of 99.44% over existing models.

Tests for the DNA of high-risk types of human papillomavirus (HPV) have a higher sensitivity for cervical intraepithelial neoplasia grade 3 or worse (CIN3+) than does cytological testing, but the necessity of such testing in cervical screening has been debated. Our aim was to determine whether the effectiveness of cervical screening improves when HPV DNA testing is implemented. Women aged 29–56 years who were participating in the regular cervical screening programme in the Netherlands were randomly assigned to combined cytological and HPV DNA testing or to conventional cytological testing only. After 5 years, combined cytological and HPV DNA testing were done in both groups. The primary outcome measure was the number of CIN3+ lesions detected. Analyses were done by intention to treat. This trial is registered as an International Standard Randomised Controlled Trial, number ISRCTN20781131. 8575 women in the intervention group and 8580 in the control group were recruited, followed up for sufficient time (≥6·5 years), and met eligibility criteria for our analyses. More CIN3+ lesions were detected at baseline in the intervention group than in the control group (68/8575 vs 40/8580, 70% increase, 95% CI 15–151; p=0·007). The number of CIN3+ lesions detected in the subsequent round was lower in the intervention group than in the control group (24/8413 vs 54/8456, 55% decrease, 95% CI 28–72; p=0·001). The number of CIN3+ lesions over the two rounds did not differ between groups. The implementation of HPV DNA testing in cervical screening leads to earlier detection of CIN3+ lesions. Earlier detection of such lesions could permit an extension of the screening interval.

AbstractObjectiveTo evaluate the diagnostic accuracy of high-risk human papillomavirus (hrHPV) assays on self samples and the efficacy of self sampling strategies to reach underscreened women.DesignUpdated meta-analysis.Data sourcesMedline (PubMed), Embase, and CENTRAL from 1 January 2013 to 15 April 2018 (accuracy review), and 1 January 2014 to 15 April 2018 (participation review).Review methodsAccuracy review: hrHPV assay on a vaginal self sample and a clinician sample; and verification of the presence of cervical intraepithelial neoplasia grade 2 or worse (CIN2+) by colposcopy and biopsy in all enrolled women or in women with positive tests. Participation review: study population included women who were irregularly or never screened; women in the self sampling arm (intervention arm) were invited to collect a self sample for hrHPV testing; women in the control arm were invited or reminded to undergo a screening test on a clinician sample; participation in both arms was documented; and a population minimum of 400 women.Results56 accuracy studies and 25 participation trials were included. hrHPV assays based on polymerase chain reaction were as sensitive on self samples as on clinician samples to detect CIN2+ or CIN3+ (pooled ratio 0.99, 95% confidence interval 0.97 to 1.02). However, hrHPV assays based on signal amplification were less sensitive on self samples (pooled ratio 0.85, 95% confidence interval 0.80 to 0.89). The specificity to exclude CIN2+ was 2% or 4% lower on self samples than on clinician samples, for hrHPV assays based on polymerase chain reaction or signal amplification, respectively. Mailing self sample kits to the woman’s home address generated higher response rates to have a sample taken by a clinician than invitation or reminder letters (pooled relative participation in intention-to-treat-analysis of 2.33, 95% confidence interval 1.86 to 2.91). Opt-in strategies where women had to request a self sampling kit were generally not more effective than invitation letters (relative participation of 1.22, 95% confidence interval 0.93 to 1.61). Direct offer of self sampling devices to women in communities that were underscreened generated high participation rates (>75%). Substantial interstudy heterogeneity was noted (I2>95%).ConclusionsWhen used with hrHPV assays based on polymerase chain reaction, testing on self samples was similarly accurate as on clinician samples. Offering self sampling kits generally is more effective in reaching underscreened women than sending invitations. However, since response rates are highly variable among settings, pilots should be set up before regional or national roll out of self sampling strategies.

Cervical cancer, the second most prevalent cancer affecting women, arises from abnormal cell growth in the cervix, a crucial anatomical structure within the uterus. The significance of early detection cannot be overstated, prompting the use of various screening methods such as Pap smears, colposcopy, and Human Papillomavirus (HPV) testing to identify potential risks and initiate timely intervention. These screening procedures encompass visual inspections, Pap smears, colposcopies, biopsies, and HPV-DNA testing, each demanding the specialized knowledge and skills of experienced physicians and pathologists due to the inherently subjective nature of cancer diagnosis. In response to the imperative for efficient and intelligent screening, this article introduces a groundbreaking methodology that leverages pre-trained deep neural network models, including Alexnet, Resnet-101, Resnet-152, and InceptionV3, for feature extraction. The fine-tuning of these models is accompanied by the integration of diverse machine learning algorithms, with ResNet152 showcasing exceptional performance, achieving an impressive accuracy rate of 98.08%. It is noteworthy that the SIPaKMeD dataset, publicly accessible and utilized in this study, contributes to the transparency and reproducibility of our findings. The proposed hybrid methodology combines aspects of DL and ML for cervical cancer classification. Most intricate and complicated features from images can be extracted through DL. Further various ML algorithms can be implemented on extracted features. This innovative approach not only holds promise for significantly improving cervical cancer detection but also underscores the transformative potential of intelligent automation within the realm of medical diagnostics, paving the way for more accurate and timely interventions.

Objective To determine the association between depth of excision of cervical intraepithelial neoplasia and risk of preterm birth. Design Case-control study nested in record linkage cohort study. Setting 12 hospitals in England. Participants From a cohort of 11 471 women with at least one histological sample taken at colposcopy and a live singleton birth (before or after colposcopy), 1313 women with a preterm birth (20-36 weeks) were identified and frequency matched on maternal age at delivery, parity, and study site to 1313 women with term births (38-42 weeks). Main outcome measures Risk of preterm birth and very/extreme preterm birth by depth of excisional treatment of the cervical transformation zone. Results After exclusions, 768 preterm births (cases) and 830 term births after colposcopy remained. The risk of preterm birth was no greater in women with a previous small (<10 mm) excision (absolute risk 7.5%, 95% confidence interval 6.0% to 8.9%) than in women with a diagnostic punch biopsy (7.2%, 5.9% to 8.5%). Women with a medium (10-14 mm) (absolute risk 9.6%; relative risk 1.28, 0.98 to 1.68), large (15-19 mm) (15.3%; 2.04, 1.41 to 2.96), or very large (≥20 mm) excision (18.0%; 2.40, 1.53 to 3.75) had a higher risk of preterm delivery than those with small excision. The same pattern was seen in 161 women with very/extremely preterm births (20-31 weeks) and with increasing volume excised. Most births were conceived more than three years after colposcopy, and the risk of preterm delivery did not seem to depend on time from excision to conception. Conclusions The risk of preterm birth is at most minimally affected by a small excision. Larger excisions, particularly over 15 mm or 2.66 cm3, are associated with a doubling of the risk of both preterm and very preterm births. The risk does not decrease with increasing time from excision to conception. Efforts should be made to excise the entire lesion while preserving as much healthy cervical tissue as possible. Close obstetric monitoring is warranted for women who have large excisions of the cervical transformation zone.

Early detection of precancerous cervical lesions is critical for improving patient management and clinical outcomes. Hyperspectral imaging has emerged as a promising non-invasive, label-free imaging modality for rapid medical diagnosis. This work presents the development of a liquid-crystal-tunable-filter-based hyperspectral colposcopy system covering the visible and near-infrared spectral ranges. The proposed system integrates two tunable filters into an existing Optomic OP-C5 clinical colposcope, enabling hyperspectral acquisition from 460 to 1000 nm with 130 spectral bands at 5 nm resolution using a panchromatic camera. Two alternative acquisition strategies were investigated: (i) filtering the light received by the system, or (ii) filtering the light emitted toward the sample. In addition, wavelength-dependent exposure control was studied to compensate for reduced system sensitivity and improve the signal-to-noise ratio in low-efficiency spectral regions. The system was benchmarked against a previous custom hyperspectral implementation based on a commercial camera. The comparative analysis highlights the advantages and limitations of both approaches, demonstrating the proposed system’s suitability for integration into clinical workflows and its potential for early detection of precancerous cervical lesions during routine colposcopic examinations.