Search Results (696)

Background: Human papillomavirus (HPV)-related diseases remain a major global health problem, with cervical intraepithelial neoplasia (CIN) representing a key precursor to cervical cancer. Identification of high-risk HPV genotypes is essential for early diagnosis and appropriate management. This study aimed to evaluate the usefulness of in situ hybridization (ISH) for detecting HPV DNA in formalin-fixed, paraffin-embedded (FFPE) cervical tissue and to compare automated signal detection with manual histopathological assessment. Methods: This prospective, non-randomized study included 83 women undergoing diagnostic procedures for abnormal cytology or confirmed CIN between 2022 and 2023. Tissue specimens obtained during a loop electrosurgical excision procedure (LEEP) were examined using two ISH probes: ISH II for low-risk HPV types 6 and 11, and ISH III for high-risk HPV genotypes. Staining patterns and distributions were evaluated and correlated with molecular HPV testing and histopathological outcomes. Results: ISH II distribution was significantly associated with the presence of HPV type 6 or 11 (p < 0.001), although stain structure itself was not. ISH III stain structure was significantly associated with high-risk HPV genotypes (p = 0.020). A positive ISH II result predicted low-risk HPV infection with a sensitivity of 62.5% and specificity of 64.0%, while ISH III predicted high-risk HPV infection with a sensitivity of 86.36% but lower specificity (23.53%). Overall diagnostic accuracy was 63.86% for ISH II and 73.49% for ISH III. Conclusions: ISH proved to be a reproducible method for detecting HPV in archived cervical tissue, enabling assessment even years after specimen collection. Although PCR-based methods remain more widely used due to higher sensitivity and less invasive sampling, ISH provides valuable morphological context and may serve as a complementary diagnostic tool, particularly when only archival tissue is available. Full article

Cervical cancer, primarily caused by human papillomavirus (HPV) infection, remains a major cause of cancer-related mortality among women worldwide, making early detection through cytological screening essential. However, manual analysis of cytology images is time-consuming and subject to variability, while recent deep learning approaches, particularly transformer-based architectures, often require high computational resources, limiting their use in resource-constrained settings. In this study, we propose ECAViTNet, a lightweight hybrid CNN–Transformer architecture for cervical cytology image classification that balances accuracy and efficiency. The model integrates Efficient Channel Attention modules for adaptive feature recalibration, residual connections for stable optimization, MobileViT blocks to capture local and global dependencies, and gated multi-scale fusion mechanisms to enhance feature representation, along with progressive downsampling and skip connections to preserve fine-grained details. The proposed approach was evaluated on the SIPaKMeD dataset, achieving a test accuracy of 96.42% with only 982,491 parameters and a macro-average F1-score of 0.96 and a weighted-average F1-score of 0.96, while maintaining balanced class-wise performance and reduced computational cost compared to recent methods. These results demonstrate that ECAViTNet is an effective and efficient solution for automated cervical cytology classification, with strong potential for deployment in mobile health systems and low-resource clinical environments. Full article

Cervical cancer screening with high-risk human papillomavirus (HR-HPV) testing requires effective triage of HPV-positive women. Koilocytosis is a classic cytopathic effect of HPV infection, but its clinical significance in low-grade squamous intraepithelial lesions (LSILs) remains unclear. We retrospectively evaluated 157 HPV-positive women with LSIL cytology and follow-up data, including 140 women with concurrent biopsy results. Koilocytes were identified in 93/157 cases (59.2%) and were less frequent in HPV16/18-positive cases. Cervical intraepithelial neoplasia ≥ grade 2 (CIN2+) was detected in 9/84 koilocyte-positive cases (10.7%) and 16/56 koilocyte-negative cases (28.6%), whereas non-CIN findings were more common in koilocyte-positive cases. Koilocyte-positive cases also showed a longer time to regression from LSIL to negative for intraepithelial lesions or malignancy. These findings suggest that koilocytosis mainly reflects productive HPV infection and has limited utility for predicting CIN2+ in HPV-based screening triage. Excluding koilocytosis-driven low-grade cytological changes from triage positivity criteria may improve specificity and positive predictive value, supporting higher triage thresholds. Full article

Background: Human papillomavirus (HPV) is a serious infection which is primarily transmitted through sexual intercourse. Almost 100% of cervical cancers are caused by HPV. Limited awareness of HPV leads to delayed cancer diagnoses, significantly increasing mortality and morbidity rates. Aim: The purpose of this study was to develop strategies to increase awareness of human papillomavirus screening and vaccination among women in Limpopo Province, South Africa. Setting: This study was carried out in the Vhembe District of the Thulamela Municipality of Limpopo Province. Methods: The E-Delphi method was used, and the researcher used a quantitative approach. A total population of 15 nursing managers was part of the study. Questionnaires were used to collect data. Data were analysed using the statistical package for the social sciences version 26. Results: In Round 1, 8 (53.3%) of the 15 participants strongly supported the strategy of updating women with the most recently revised HPV screening guidelines. In Round 2, consensus was achieved, with 14 (93.3%) of the participants strongly agreeing that the development of teaching programmes in healthcare facilities is necessary. This indicates a strong convergence of expert opinion on the importance of structured educational interventions to support the implementation of the strategy. The consensus in this study was defined as ≥70% agreement between participants on each item. Conclusions: The lack of awareness of HPV is concerning because early detection and treatment can prevent serious health problems. The study used the E-Delphi method to assess the effectiveness of strategies to increase awareness of HPV screening and vaccination in women. Contribution: Health policy initiatives may improve public awareness of HPV and vaccination, especially by focusing on educating nurses, which could improve women’s awareness and encourage HPV screening and vaccination. Full article

Background: HPV16 is the most prevalent high-risk genotype associated with cervical cancer, yet the genetic variability and immune potential of the replication protein E1 are less characterized in asymptomatic infections. We assessed HPV16 E1 diversity and predicted conserved T-cell epitopes. Methods: We conducted a descriptive cross-sectional study of cervical samples from women undergoing HPV screening. HPV was detected with universal primers and then HPV16-specific PCR. Thirty HPV16-positive samples underwent full-length E1 amplification and nanopore amplicon sequencing. Variability and phylogeny were analyzed with Clustal Omega and MEGA (maximum likelihood). MHC class I and II epitopes were predicted with the IEDB using HLA alleles representative of South American populations and evaluated for conservation, toxicity, allergenicity, and population coverage. Results: Mutations were detected in 14/30 samples, while 16 sequences matched the reference (GenBank: NC_001526.3). European lineages (A1–A3) predominated, with one sequence in the Asian-American lineage D. Seven highly conserved MHC I epitopes and 37 conserved MHC II epitopes were identified. Epitopes mapped to multiple regions across the E1 sequence. Predicted global coverage was 94.38% for MHC I, 83.75% for MHC II, and 99.09% combined. Conclusions: HPV16 E1 is highly conserved and contains candidate T-cell targets with broad predicted coverage, supporting evaluation for future vaccine or immunotherapy strategies. Full article

The qualitative detection of circulating tumor human papillomavirus DNA (ctHPV) has shown promise in HPV-associated cancers. We performed a systematic review and meta-analysis to evaluate the association of pretreatment ctHPV levels with survival outcomes and quantitative tumor burden metrics. Databases were searched through 5 January 2026. Studies were eligible if they included patients with HPV-associated cancers and reported quantitative pretreatment ctHPV levels in relation to survival outcomes or tumor burden. Twenty-three studies were included in the quantitative synthesis. Higher pretreatment ctHPV levels were associated with poorer progression-free survival (PFS) (8 studies, n = 883; HR = 1.86, 95% CI 1.19–2.90; p = 0.013). This association was primarily driven by studies in oropharyngeal cancer (OPC; HR = 2.47, 95% CI 1.59–3.84; p = 0.007), whereas no significant association was observed in cervical cancer. In multivariable analyses, elevated ctHPV remained associated with shorter PFS (HR = 1.87, 95% CI 1.66–2.10; p = 0.002). No significant association was observed for overall survival. Pretreatment ctHPV correlated with nodal volume in OPC (r = 0.45), nodal and tumor volume in OPC/anal cancer (r = 0.39), primary tumor volume in OPC (r = 0.22), and tumor diameter in cervical cancer (r = 0.44). Higher pretreatment ctHPV levels are associated with greater tumor burden and poorer PFS in HPV-associated OPC. CtHPV shows potential as a prognostic biomarker, although further prospective studies and assay standardization are needed. Full article

Background: Artificial intelligence (AI) is reshaping oncology at every stage of the cancer care pathway, from population-level screening through molecular diagnosis, treatment planning, and post-treatment surveillance. Despite an exponential growth in AI oncology publications exceeding 5000 peer-reviewed studies annually, a critical and persistent gap separates demonstrated algorithmic performance from genuine patient benefit. Most published evidence derives from retrospective, single-institution studies conducted in curated dataset environments that systematically differ from real-world clinical deployment conditions. This comprehensive review examines the translational maturity of AI applications across 18 major malignancies, providing an evidence-stratified, cross-cancer assessment of where AI has fulfilled, approaches, or remains far from fulfilling its transformative potential in oncological care. Methods: A structured narrative review was conducted across PubMed/MEDLINE, Embase, IEEE Xplore, and the Cochrane Library, supplemented by regulatory grey literature including FDA 510(k) decision summaries, CE Technical Files, and ClinicalTrials.gov. Search terms combined cancer site-specific terminology with AI methodology terms and translational outcome descriptors. Studies were only included if they applied an AI or machine learning methodology to a defined clinical oncological task, reported a clearly specified performance evaluation, and involved human subjects or human-derived clinical data. Evidence quality was assessed using QUADAS-2, PROBAST, and Cochrane RoB 2. A five-tier translational readiness framework, grounded in the NIH T0–T4 translational spectrum and CONSORT-AI/SPIRIT-AI guidelines, was applied a priori to enable cross-cancer comparison. A rigorous distinction was maintained between diagnostic accuracy and clinical utility, defined as demonstrated impact on clinical decision-making or patient-centered outcomes. Results: Across all 18 malignancies, AI development varied profoundly by cancer type. Breast cancer and prostate cancer (Tier 1) represent the most mature AI ecosystems, with multiple FDA-cleared tools for mammographic screening and digital pathology achieving prospective multi-institutional validation; however, randomized evidence demonstrating reduced cancer-specific mortality remains absent. Lung, hepatocellular, and melanoma AI (Tier 2) have achieved regulatory milestones but face documented performance disparities across demographic subgroups, including DermaSensor’s 20.7% specificity in primary care settings and HCC model failures in non-viral disease etiologies. Colorectal, glioma, pancreatic, and ovarian cancers (Tier 3) exhibit technical maturity without clinical clarity: colorectal CADe systems increase adenoma detection but meta-analyses of 18,232 patients across 21 RCTs fail to demonstrate improvement in advanced neoplasia detection or cancer incidence reduction. A full study-level presentation of pooled estimates, confidence intervals, and heterogeneity statistics for each cited randomized evidence base across all cancer types would extend beyond the intended scope and format of this cross-cancer narrative review. Gastric, esophageal, cervical, bladder, head and neck, and endometrial cancers (Tier 4) demonstrate promising single-institutional or geographically restricted results without multi-institutional external validation, particularly notable for cervical cancer AI’s transformative potential in low- and middle-income countries constrained by absent regulatory frameworks. Hematologic malignancies, sarcoma, and pediatric solid tumors (Tier 5) face structural barriers, workflow incompatibility in hematopathology, extreme rarity in sarcoma (>70 subtypes, <15,000 US cases annually), and irreducible ethical constraints in pediatric data governance, that cannot be resolved through algorithmic refinement alone. Conclusions: Oncological AI has not yet fulfilled its clinical promise. Across all five translational tiers, a single finding is consistent: diagnostic accuracy is not a surrogate for patient benefit. AI tools with high sensitivity and specificity have repeatedly failed to demonstrate equivalent reductions in cancer-specific mortality, overdiagnosis, or procedural harm under real-world outcome scrutiny. Simultaneously, documented performance disparities across races, ethnicity, disease etiology, and geographic setting reveal that current AI systems risk amplifying the very health inequities they are positioned to resolve. Bridging this translational gap requires three coordinated systemic shifts: regulatory frameworks mandating post-market outcome surveillance as a condition of clinical clearance; prospective trial designs measuring patient-centered endpoints rather than diagnostic concordance alone; and sustained infrastructure investment in federated data governance, demographically inclusive training datasets, and LMIC-accessible regulatory pathways. AI holds genuine potential to reduce cancer mortality on a global scale—but only if held to the evidentiary and equity standards that the stakes of oncological care demand. Full article

Background: Breast cancer and gynecological malignancies, including cervical, ovarian, and endometrial cancers, remain leading causes of cancer incidence and mortality among women worldwide. This study investigated hereditary predisposition rates in women diagnosed with breast or gynecological cancer, focusing on the effect of age on germline pathogenic/likely pathogenic (P/LP) variant detection. We sought to determine whether younger age at diagnosis should be used as a criterion for patient selection for genetic testing. Methods: A total of 9084 consecutive females with breast cancer or gynecological tumors underwent germline NGS-based genetic testing (52 cancer-relevant genes) at Genekor laboratory from 2020–2026. Multivariable logistic regression evaluated factors associated with P/LP variant detection, adjusting for tumor type and family history. Results: Overall P/LP prevalence was approximately 20% (one in five patients), with tumor-specific rates of 19.24% in breast cancer, 27.59% in ovarian cancer, and 26.67% in endometrial cancer. P/LP prevalence declined significantly with age from 24.37% in patients <40 years to 15.90% in those ≥70 years, while Variants of Uncertain Significance (VUS) remained stable (40–43%). P/LP patients had earlier diagnosis (median 45 vs. 46 years, p < 0.001), driven predominantly by high-risk genes (13.87% in <40 y vs. 7.11% in ≥70 y). BRCA1 showed stronger age enrichment than BRCA2 (8.14% vs. 3.16% in <40 y; median diagnosis 43 vs. 45 years). Age remained independently associated with P/LP detection in multivariable analysis, with an 18% reduction in odds per 10-year increase for any P/LP (OR 0.82, 95% CI 0.78–0.86) and a stronger 28% reduction for high-risk variants (OR 0.72, 95% CI 0.67–0.78). Family history also independently predicted P/LP detection (OR 1.40, 95% CI 1.19–1.66). Conclusions: Although derived from a referral-based (and thus selected) population, these findings show that while younger patients have a higher prevalence of high-risk P/LP variants, clinically actionable findings are present across all age groups, including those ≥70 years. These results suggest that reliance on age alone to determine eligibility for genetic testing may be insufficient. Broadening access to testing beyond strict age-based criteria could improve the identification of hereditary cancer risk and inform patient management, although further evaluation in less selected populations is warranted. Full article

Persistent high-risk human papillomavirus (hr-HPV) infection drives cervical carcinogenesis, yet improved molecular biomarkers are needed to define high-risk groups. Circulating microRNAs (miRNAs), stable in blood and involved in carcinogenic pathways, represent promising liquid biopsy biomarkers. This study assessed five miRNAs for distinguishing high-grade squamous cell intraepithelial lesions (HSILs) and cervical cancer from healthy controls and for HPV stratification. Circulating miRNAs were quantified in blood samples from 80 women (38 HSIL, 10 cervical cancer, and 32 controls). Relative expression by disease and HPV status was measured by RT-qPCR and normalized to miRNA-23a. Diagnostic performance of single and combined miRNAs was evaluated by logistic regression and ROC curve analysis. Three circulating miRNAs (miR-21, miR-205, and miR-218) were found to be significantly differentially dysregulated in the patient cohorts. A combination of the three markers showed the best diagnostic value for HSIL (AUC of 0.81, sensitivity of 79%, and specificity of 71%) and cancer (AUC of 0.81, sensitivity of 90%, and specificity of 65%). Whereas miR-205 was significantly associated with HPV16/18 in HSIL patients, the combined model had the highest diagnostic performance for multiple HPV infections. Circulating miRNA signatures show promise as liquid biopsy biomarkers for detecting cervical dysplasia and stratifying for HPV status in HSIL, warranting validation in larger prospective studies. Full article

The Papanicolaou (Pap) smear, a cornerstone of cervical cancer prevention, has emerged as a compelling, though unconventional, biospecimen for the detection of ovarian cancer (OC). This structured narrative review synthesizes the evolving evidence on the utility of cervicovaginal cytology and molecular analysis of Pap test material for OC detection. While conventional cytology provides a proof of concept, its sensitivity is low, ranging from incidental detection of OC in 0.004% of routine screens to 19.3% in patients with known OC. Specific cytologic findings, however, carry significant predictive value: atypical glandular cells (AGC) confer a two-fold increased OC risk, and psammoma bodies (PB) are strongly associated with serous malignancies. Driven by the sensitivity limitations of morphology, the field has undergone a paradigm shift towards molecular detection. Foundational studies confirmed tumor-derived DNA, including hallmark TP53 mutations, is detectable in Pap samples years before diagnosis, though sensitivity is constrained by low DNA abundance and confounded by background clonal mutations. To overcome this, strategies have expanded to target broader genomic signatures, such as somatic copy number alterations (EVA test: 75% sensitivity, 96% specificity), and multi-gene mutation panels (PapSEEK: 33–45% sensitivity). The most promising advances lie in multi-omic approaches, particularly DNA methylation biomarkers, which have demonstrated sensitivities up to 81% with high specificity. Collectively, this evidence argues against repurposing the Pap test as a standalone OC screen but supports its strategic integration into a risk-stratified clinical algorithm. We propose a “reflex-to-molecular” model where high-risk cytology (e.g., AGC, PB) automatically triggers advanced molecular testing on the same sample. This model efficiently leverages existing infrastructure to triage high-risk women for definitive diagnostics. Prospective validation of this integrated approach is the essential next step toward transforming this test into a sentinel for malignancies of the upper female reproductive tract. Full article

Automated cellular detection using deep learning is a key strategy for optimising cervical cancer screening by reducing the healthcare workload and inter-observer variability. However, analysing Whole Slide Image (WSI) patches presents challenges such as annotation scarcity, morphological complexity, and class imbalance. This study systematically evaluates YOLO11-n, YOLO11-s, and YOLO11-m to assess the impact of target variable granularity and training paradigms on performance. Four strategies were analysed: independent and multi-class models, each evaluated at both the specific cell label and diagnostic macro-group levels. To ensure clinical robustness, patient-level data partitioning was implemented to prevent data leakage. Performance was measured using precision, recall, and mAP (0.5 and 0.5:0.95). The results reveal critical trade-offs between fine-grained discrimination and model generalisation when varying the architectural complexity and labelling strategies. The findings indicate that diagnostic aggregation improves stability, whereas single-class training optimises specialised detection. These results provide methodological guidelines for designing AI-assisted screening systems and may inform future extensions of WSI-level diagnostic pipelines. Full article

Cervical cancer is associated with persistent human papillomavirus (HPV) infections. The early detection of HPV is one of the key strategies for the effective treatment of cervical cancer. Current HPV molecular detection methods use enzyme-based nucleic acid amplification strategies that, although specific and sensitive, involve extensive workflows. Enzyme-free isothermal amplification detection strategies with the potential to adapt to low-resource settings for HPV oncogenic transcripts remain limited. This study aimed to validate a fluorescence-based branched hybridization chain reaction (bHCR) assay for the targeted detection of HPV 16/35 E6 oncogenic transcripts. Analytical performance was evaluated using a synthetic target and a negative clinical matrix, whereas the diagnostic performance of the bHCR assay was evaluated using clinically characterized samples (n = 67). The study demonstrated assay linearity over an analyte concentration range of 0.625–40 µM, with a statistically significant correlation between the fluorescence signal and target concentration (r² = 0.928, p < 0.0001). Analytical accuracy was assessed by pre-extraction spike recovery; achieved recoveries ranged from 70% to 86%, indicating potential RNA loss during the assay workflow. Analytical sensitivity determined the background signal threshold limit of blank (LoB) as 16,251.6 RFU, with detection and quantification at concentrations of 0.0625 µM (≈2.6 × 10¹¹ copies per reaction, limit of detection (LoD) and 0.125 µM (≈5.3 × 10¹¹ copies per reaction, limit of quantification (LoQ). The assay exhibited high diagnostic performance, with a diagnostic cut-off of 16,481 RFU and an area under the curve (AUC) of 0.9194. Specificity and sensitivity of the assay were 94% and 86%, respectively, with a Negative Predictive Value (NPV) of 85% and a Positive Predictive Value (PPV) of 94%. These findings demonstrate a reliable analytical assay with excellent diagnostic discrimination and warrant further optimization and expanded clinical validation. Full article

Background: Fine-needle aspiration thyroglobulin (FNA-Tg) is widely used to detect lymph node metastases in differentiated thyroid cancer (DTC), but optimal cut-off values remain controversial. Anti-thyroglobulin antibodies (anti-Tg), present in 25–40% of DTC patients, may interfere with FNA-Tg measurements. This study aimed to evaluate whether anti-Tg status necessitates different FNA-Tg diagnostic thresholds in the preoperative setting. Methods: We retrospectively analyzed 605 cervical lymph nodes from 393 preoperative DTC patients who underwent ultrasound-guided fine-needle aspiration (FNA) with concurrent FNA-Tg measurement (February 2019–April 2025). All lymph nodes had histopathological or cytological confirmation. Patients were stratified by anti-Tg status (>4.5 IU/mL). Receiver operating characteristic curve analysis determined optimal FNA-Tg cut-offs, and areas under the curve (AUCs) were compared using the DeLong test. Results: FNA-Tg demonstrated excellent overall diagnostic accuracy (AUC 0.963, 95% CI 0.946–0.980) with an optimal cut-off of 84.0 ng/mL (sensitivity 91.6%, specificity 95.3%). Anti-Tg-positive patients had significantly lower FNA-Tg levels in malignant lymph nodes compared to anti-Tg-negative patients (median 9872 vs. 22,327 ng/mL, p = 0.001). Subgroup analysis revealed superior performance in anti-Tg-negative patients (AUC 0.983, cut-off 84.4 ng/mL) compared to anti-Tg-positive patients (AUC 0.923, cut-off 65.7 ng/mL; p = 0.008). No significant correlation was observed between anti-Tg levels and FNA-Tg (ρ = −0.03, p = 0.501). Conclusions: Anti-Tg status influenced measured FNA-Tg levels and receiver operating characteristic (ROC) derived optimal thresholds in the preoperative setting. However, because malignant lymph nodes generally showed FNA-Tg values well above the benign range, the clinical impact of this difference appears limited in most clearly positive cases. These findings may still help refine interpretation in selected borderline cases. Full article

The detection and retrieval of specific single cells within a cell population is useful for elucidating cellular function as well as early-stage cancer diagnosis by detecting circulating tumor cells. Microcapillaries are used to retrieve specific single cells from cell populations; however, quick single-cell retrieval that firmly adheres to the substrate without damaging the cell is difficult. In this study, we propose a single-cell selective retrieval method using a cone-shaped light-responsive gas-generating polymer (LGP) microscaffold array chip. An LGP microscaffold array chip with cone-shaped LGP microscaffolds was fabricated without any special equipment. When human cervical cancer cells were spread on the LGP microscaffold array chip, adhesion was achieved, and single cells were arranged on up to 73.3% of the cone-shaped LGP microscaffolds. When low-toxicity ultraviolet A light was irradiated from the back of the LGP microscaffold array chip, only a single cell adhering to the cone-shaped LGP microscaffold was released by the generated N₂ gas bubbles. More than 90% of the retrieved cells adhered, spread, and could be cultured for over 24 h. In conclusion, the proposed method is a simple and quick single-cell retrieval method that requires only a conventional inverted fluorescence microscope. Full article

Background/Objectives: We developed a telehealth-enabled fiber-bundle endomicroscopy platform and evaluated its preclinical feasibility for targeted fluorescence imaging in cervical cancer models. Methods: The platform integrates a portable fiber-bundle endomicroscopy (FBE) system, fluorescein isothiocyanate (FITC)-labeled candidate peptides, and a secure web-based telehealth platform for remote consultation. The FBE probe achieved a field of view of 1,700 µm and a lateral resolution of 4 µm, enabling cellular-level fluorescence imaging in a compact, portable format. Four FITC-labeled peptides (SHS1*, SHS2*, FPP*, and CRL*) were evaluated in A549, SiHa, and CaSki cell lines. Ex vivo testing was performed on commercial cervical tissue-array samples. The telehealth platform was assessed for secure medical-image/video transmission and end-to-end latency in a simulated remote-consultation setting. Results: Among the tested probes, FPP*-FITC and CRL*-FITC showed higher fluorescence-positive fractions in the p16-overexpressing cervical cancer cell lines than in the A549 comparator line, with the strongest signals observed in CaSki cells. In ex vivo testing, CRL*-FITC generated higher fluorescence intensity in malignant cervical tissue-array samples than in non-malignant comparator tissues, with a reported 4.6- to 7.4-fold difference in mean signal intensity (p < 0.001). The telehealth platform supported the secure transmission of medical images and video and demonstrated an end-to-end latency of <500 ms in a simulated remote consultation setting. Conclusions: These results support the technical and preclinical feasibility of integrating targeted fluorescence imaging, portable fiber-bundle endomicroscopy, and telehealth into a single platform. This study should therefore be interpreted as a preclinical feasibility study evaluating optical, molecular, and telehealth integration, rather than as a clinically validated cervical cancer screening test. Full article