BACKGROUND Cervical cytology screening is usually laborious with a heavy workload and poor diagnostic consistency. The authors have developed an artificial intelligence (AI) microscope that can provide onsite diagnostic assistance for cervical cytology screening in real time. METHODS A total of 2167 cervical cytology slides were selected from a cohort of 10,601 cases from Shenzhen Maternity and Child Healthcare Hospital, and the training data set consisted of 42,073 abnormal cervical epithelial cells. The recognition results of an AI technique were presented in a microscope eyepiece by an augmented reality technique. Potentially abnormal cells were highlighted with binary classification results in a 10× field of view (FOV) and with multiclassification results according to the Bethesda system in 20× and 40× FOVs. In addition, 486 slides were selected for the reader study to evaluate the performance of the AI microscope. RESULTS In the reader study, which compared manual reading with AI assistance, the sensitivities for the detection of low‐grade squamous intraepithelial lesions and high‐grade squamous intraepithelial lesions were significantly improved from 0.837 to 0.923 (P < .001) and from 0.830 to 0.917 (P < .01), respectively; the κ score for atypical squamous cells of undetermined significance (ASCUS) was improved from 0.581 to 0.637; the averaged pairwise κ of consistency for multiclassification was improved from 0.649 to 0.706; the averaged pairwise κ of consistency for binary classification was improved from 0.720 to 0.798; and the averaged pairwise κ of ASCUS was improved from 0.557 to 0.639. CONCLUSIONS The results of this study show that an AI microscope can provide real‐time assistance for cervical cytology screening and improve the efficiency and accuracy of cervical cytology diagnosis.
Background Comprehensive metabolic panel tests (CMP) are routinely performed in extremely premature infants within the first days of life. The association between the parameters of first postnatal CMP and the risk of bronchopulmonary dysplasia (BPD) remains elusive. Methods A retrospective analysis was performed to evaluate the correlation between the parameters of first postnatal CMP and the risk of BPD in a cohort of extremely premature infants (born with a gestational age less than 28 weeks or a birth weight less than 1000 grams) at the neonatal intensive care unit, Shenzhen Maternity and Child Healthcare Hospital, from January 2016 to October 2018. A multivariant regression model was built to assess the association of the first postnatal CMP with the development of BPD. Results A total of 256 extremely premature infants were included in this study. BPD developed in 76 (29.7%) infants. The first CMP in these infants was performed at 5 to 8 days after birth. The levels of blood urea nitrogen (BUN) and magnesium were significantly higher in infants with BPD compared to infants with no BPD (10.2 versus 7.5 mmol/L, P < 0.001 and 0.9 versus 0.8 U/L, P = 0.001, respectively) whereas the level of alkaline phosphatase (ALP) and total protein was significantly lower in infants with BPD (215.5 versus 310.0 U/L, P = 0.002 and 41.2 versus 42.9 g/L, P = 0.037, respectively). Multiple analysis showed that a higher level of BUN (>8.18 mmol/L) was independently associated with BPD (OR 3.261, 95% CI 1.779-5.978). Conclusion Our findings indicate that a higher postnatal BUN level (>8.18 mmol/L) may be a predictor for the development of BPD in extremely premature infants.
Objective: Partial patients diagnosed with CIN2 on biopsy include CIN3 .To compare the histopathological results before and after conization of CIN2 for exploring stratified management for CIN2 in women aged ≥25 years. Design: A observational retrospective study. Setting: China. Population: 307 women aged 19~40 years diagnosed as CIN2 on biopsy with cervical squamocolumnar junction visible. Methods: Compared immediate conization specimen histopathology with the biopsy histopathology,and explored the risk factors to predict CIN3 in cone histopathology. Main outcome measures: Cone-histopathology-grading rate of CIN2. Risk factors predicting cone histopathology upgrading. Constructing an individualized algorithm for CIN2 stratified management using risk factors. Results: the cone-histopathology-upgrading rate of CIN2 was 22.5%(including one case of cervical microinvasive squamous cell carcinoma).In univariable analysis: age, HPV16/18, HSIL cytology were high-risk factors of cone histopathology upgrading(CIN3 )(P<0.05). In multivariable analysis: HPV16/18(OR 2.399,[95%CI 1.326-4.338]) and HSIL cytology(OR 3.295,[95%CI 1.622-6.692]) were independently risk factors. Conclusion: CIN2 patients aged ≥25 years were with a higher proportion of CIN3 and stratified treatment should be considered.Patients with HPV16/18 infection and HSIL cytology owned the highest rate of CIN3 in the rest cervix,surgical treatment should be taken. For those with HPV16/18 infecton and ASCUS/LSIL cytology, or other high-risk HPV infection and HSIL cytology were with a relatively higher proportion of CIN3 , treatment should be individualized. However, for patients with HPV16/18 infection and NILM cytology or other high-risk HPV infection and ASCUS/LSIL cytology, the risk of CIN3 was relatively low,conservative treatment should be taken.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.