Objective: To systematically evaluate the diagnostic performance of an artificial intelligence (AI)-assisted diagnostic system in identifying squamous intraepithelial lesions of different grades, glandular cell lesions, and common pathogenic microorganisms in ThinPrep cytologic test of cervical samples, and to explore its potential value in improving the diagnostic capabilities of pathologists. Methods: A total of 1 096 cervical specimens were collected from patients undergoing ThinPrep cytologic test at Beijing Anzhen Hospital, Capital Medical University from October to December 2025. The "AI-assisted senior pathologist diagnosis" served as an initial gold standard. For uncertain cases, a consensus diagnosis reached by two senior cytopathologists after joint review was used as the final gold standard. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and concordance rate of the AI system for each diagnostic category were calculated. Cases of misdiagnosis and missed diagnosis were further reviewed, and the underlying morphological factors contributing to diagnostic errors were analyzed. Additionally, the application effect of AI as a continuous diagnostic quality improvement tool was evaluated. Results: The AI system showed significant variation in recognition performance across different diagnostic categories. For lesion diagnosis, the sensitivities were as follows: high-grade squamous intraepithelial lesion (HSIL), 100% (6/6);atypical squamous cells of undetermined significance (ASCUS), 90.5% (19/21);low-grade squamous intraepithelial lesion (LSIL), 76.5% (26/34), and atypical glandular cells (AGC), 75.0% (9/12). ASCUS had the lowest PPV (9.7%, 19/196) and the highest false-positive rate (16.1%, 177/1 096). For microorganism identification, clue cells showed the best performance [sensitivity 93.9% (46/49); PPV 95.8% (46/48)], followed by Candida [sensitivity 88.0% (44/50); PPV 72.1% (44/61)]. The sensitivities for Trichomonas and Actinomyces were both 100% (2/2; 2/2), but the PPVs were relatively low [11.1% (2/18); 22.2% (2/9), respectively]. Due to the small size of positive samples, these sensitivity estimates should be interpreted with caution. The system overall demonstrated high NPV (all >99%) and high specificity (all >98%). The main causes of misdiagnosis included the misinterpretion histiocytes in an atrophic background as AGC; the misclassification of pseudokoilocytes or reactive changes as LSIL; and the misidentification of multinucleated cells, inflammatory debris, or clusters of Lactobacillus for Herpes Simplex Virus (HSV), Trichomonas, or Actinomyces, respectively. Missed Candida diagnosis primarily occurred in cases with scant hyphae hidden within cell layers. Furthermore, the study found that by frequently presenting AI-flagged positive cases (e.g., ASCUS, AGC, and microorganisms), the system provided diagnostic pathologists with continuous, high-quality opportunities for case review and learning. Conclusions: In cervical cytology screening, the AI-assisted diagnostic system demonstrates high sensitivity and specificity for high-grade lesions and certain microorganisms (e.g., Candida and clue cells), along with an extremely high negative predictive value. It can effectively assist in primary screening and reduce the risk of missed diagnoses. Functioning as an intelligent pathology training adjunct, this system facilitates pathologists in reinforcing and refining their proficiency in lesion identification and differential diagnosis, thereby fostering iterative clinical advancement underpinned by human-AI synergism.

The objectives of this clinical case report were to highlight the value of late transrectal ultrasound examination for assessing fetal presentation, position and posture and to describe the management of a case of malposture associated with musculoskeletal and cerebellar abnormalities, including its in utero ultrasound diagnosis and outcome. A 7-year-old Gypsy Vanner mare, 339 days pregnant, was diagnosed with the presence of a bony fetal structure cranial to the cervix, without palpable head or limbs and minimal fetal movement. Transrectal ultrasound examination was instrumental in diagnosing a cranial presentation along with an abnormal posture (right-sided deviation of the fetus's neck, and a head in flexion). Transabdominal ultrasound examination confirmed the cranial presentation, with the fetus positioned high in the mare's pelvis. As soon as the parturition started at 349 days gestation, the mare underwent a cesarean section. The foal was stillborn, covered with meconium. Pathological examination revealed cerebellar lesions (hypoplastic granular cell layer, reduced number of Purkinje cells, and gliosis) as well as musculoskeletal abnormalities including arthrogryposis, scoliosis, angulation of the occipital condyles and sternum deformity. Genetic analysis showed underlying genetic abnormalities that may have contributed to abnormal fetal development and potentially to the observed malposition/posture. The mare recovered uneventfully from the cesarean section and went home seven days postoperatively. This case underscores the diagnostic value of a pre-foaling ultrasound examination to assess fetal presentation, position and posture, which was critical in preparing for a planned cesarean section and ultimately saving the mare.

We report a deceptive presentation of Squamous Cell Carcinoma of the Cervix in a 54-year-old postmenopausal woman who presented with postmenopausal bleeding associated with lower abdominal pain for a 3-month duration, with a normal-looking ectocervix. She was diagnosed with squamous cell carcinoma on a pap smear and cervical biopsy. Magnetic resonance imaging revealed an irregular endometrial cavity contour, and a T2 hyperintense lesion was seen (2.3 × 0.8 cm) involving the posterior lip of the cervix at the junction of stroma and endocervix with a mural spread along the uterine myometrium. Histopathology after Wertheim's hysterectomy revealed a squamous cell carcinoma of the endocervix, Stage pT1b3, that had spread superficially to the endometrium, myometrium, and left salpinx. The detection of immunohistochemical expression of p16, p63, and negative for ER and PR in the lesions of the cervix and the endometrium suggests that these two lesions are etiologically related, favoring the possibility of endometrial SCC secondary to cervical SCC.

Cervical cancer from persistent HPV infection is the leading cause of cancer death among Sub-Saharan African women. We here addressed the existing knowledge gap concerning the prevalence of HPV infection and cervical lesions in asymptomatic women living with HIV (WLWH) in Addis Ababa, Ethiopia. Adult WLWH (N = 334) were recruited at the HIV clinic of the Tikur Anbessa Specialized Hospital, Addis Ababa. Real-time PCR targeting 12 high-risk (HR) and 2 low-risk HPV types on cervical samples and Pap smear testing were performed. Logistic regression was used in IBM SPSS Statistics to identify factors associated with HPV infection and abnormal cytology. HR-HPV infections occurred in 20.6% of participants and the most prevalent HR-HPV genotypes were HPV35 (16.8%) and HPV16 (14.7%). Abnormal cytology was more common among HR-HPV-positive women than HR-HPV-negative women (36.1% vs. 12.6%, p < 0.0001). LSIL and HSIL were detected in 9.9% and 6.6% of HR-HPV-positive women, respectively. Condom use was associated with reduced odds of HPV infection and abnormal cytology. HR-HPV infections dominated by non-HPV16/18 types and abnormal cytology were common among asymptomatic WLWH in Ethiopia underscoring the need for strengthened cervical cancer screening, HPV vaccinations and safe-sex education for this high-risk population.

Cervical oedema during labour is relatively common, but severe circumferential oedema persisting at advanced dilation is rare, particularly in multiparous women. In such cases, the swollen cervix may mimic an obstructive mass and raise concern for labour obstruction, cervical laceration or avulsion if pushing is initiated.

HPV DNA-positive women with ASC-US/LSIL cytology constitute a heterogeneous triage group. We evaluated genotype-specific HPV E6/E7 mRNA testing with PreTect HPV-Proofer'7 in a population-based cohort from Tromsø and compared the findings descriptively with a previously published cohort from Bodø. This retrospective quality-assurance study included 1006 HPV DNA-positive women with ASC-US/LSIL cytology screened between 2019 and 2024, with linkage to regional pathology records through 31 December 2025. The assay detects E6/E7 mRNA from HPV16, 18, 31, 33, 45, 52, and 58. ASC-US/LSIL accounted for 42.5% of linked HPV DNA-positive women in Tromsø compared with 22.3% in Bodø. Among the mRNA-tested ASC-US/LSIL cohorts, mRNA positivity was similar (40.8% vs. 44.6%). In Tromsø, CIN2+ was recorded in 26.1% of mRNA-positive and 7.9% of mRNA-negative women (RR 3.31, 95% CI 2.41-4.55), whereas CIN3+ was recorded in 3.9% and 1.0%, respectively (RR 3.88, 95% CI 1.53-9.82). For CIN2+, sensitivity was 69.5%, specificity 64.4%, PPV 26.1%, and NPV 92.1%. Among HPV16/18 DNA-positive women, CIN2+ risk was 42.7% in mRNA-positive and 13.4% in mRNA-negative women. Simulated mRNA-guided referral reduced immediate colposcopy referrals by 59.2%. Genotype-specific mRNA testing provided clinically relevant risk stratification, with directionally similar patterns being observed in the Tromsø and Bodø cohorts; however, mRNA-negative women require structured surveillance.

Background: Endometriosis of the cervix is a rare, non-cancerous disease that can look or behave like cancerous cervical tissue, causing challenges regarding diagnosis and management. Discrimination between benign and malignant lesions can be difficult when utilizing cytological, colposcopic, and histopathological data if the findings do not agree with each other. Case Presentation: We report the case of an asymptomatic 45-year-old woman who was initially diagnosed with FIGO stage IA1 microinvasive cervical carcinoma based on cytological, colposcopic, and conization findings. Further evaluation yielded persistent uncertainty in diagnostic imaging and, in addition, a concern for invasive cervical disease. Therefore, the patient underwent a total hysterectomy with bilateral salpingo-oophorectomy, and the result of the postoperative evaluation was cervical endometriosis without evidence of invasive malignancy. This example demonstrates the diagnostic challenges associated with rare benign cervical lesions, which may resemble cervical carcinoma, and emphasizes the high-risk for overtreatment due to the vagueness of these types of cases. Conclusions: When there is a discrepancy among clinical findings, cytology, and histopathology in suspicious cervical lesions, cervical endometriosis must be considered in the differential diagnosis. To increase accuracy in diagnosis and minimize the possibility of unnecessary radical treatment, careful histopathologic reevaluation and multidisciplinary assessment are necessary.