To explore the clinical value of a multimodal predictive model based on multiparametric magnetic resonance imaging(MRI) radiomics combined with deep learning(DL) features for the preoperative noninvasive assessment of mismatch repair-deficient(MMRd) status in endometrial cancer(EC).

Patients diagnosed with EC at Peking Union Medical College Hospital from January 2015 to December 2021 were retrospectively enrolled and randomly divided into a training set and a validation set at a ratio of 8∶2. Relevant clinical data were collected, and radiomics features and DL features were extracted from preoperative contrast-enhanced T1-weighted imaging(CE-T1WI), fat-suppressed T2-weighted imaging(fs-T2WI), and diffusion-weighted imaging(DWI) sequences. High-dimensional feature selection and dimensionality reduction were performed sequentially using the recursive feature elimination(RFE) algorithm to generate a radiomics score(Rad-score) and a deep learning score(DL-score), respectively. Multivariate logistic regression was utilized to construct a clinical model, a pure radiomics model, a clinical-radiomics model, and an integrated multimodal model incorporating clinical indicators, Rad-score, and DL-score. Model performance was assessed and compared using area under receiver operating characteristic curve(AUC) and DeLong test.

A total of 509 patients were enrolled in this study, comprising 413 in the training cohort and 96 in the validation cohort. Independent predictors: Multivariate analysis indicated that preoperative fasting blood glucose level, histological grade, lymph node metastasis status, Rad-score, and DL-score were all independent significant predictors of MMRd status in EC patients. The integrated multimodal model demonstrated optimal predictive performance with an AUC of 0.699(95% CI: 0.635-0.763) in the training set, which was superior to the clinical model(AUC=0.629, 95% CI: 0.561-0.697) and the pure radiomics model(AUC=0.641, 95% CI: 0.575-0.706). In the validation set, the integrated model maintained good generalizability, achieving an AUC of 0.655(95% CI: 0.535-0.775), and its diagnostic efficacy was higher than that of the clinical model(AUC=0.578, 95% CI: 0.450-0.705) and the pure radiomics model(AUC=0.611, 95% CI: 0.488-0.734). According to the DeLong test, the incorporation of DL features resulted in the clinicalradiomicsdeep learning model performing better than both the clinicalonly model(P=0.027) and the radiomicsonly model(P=0.044) in the training cohort.

The initially developed clinical-radiomics-deep learning model exhibits a certain predictive potential for the MMRd status in patients with EC. The inclusion of DL features may help complement the limitations of traditional evaluations, offering a preliminary radiological reference for preoperative non-invasive screening. However, given the current diagnostic performance, its overall accuracy and clinical generalizability warrant further validation in multi-center, large-sample external cohort studies.

Immune checkpoint inhibitors have shown remarkable benefits in the treatment of solid tumors,while the occurrence of atypical response patterns and immune-related adverse events during treatment challenges the accuracy of therapeutic evaluation.Medical imaging is crucial for the evaluation of immunotherapy.It enables the assessment of treatment efficacy via both morphological and functional ways and offers unique a predictive val-ue when being combined with artificial intelligence.Here we review the recent research progress in imaging-based evaluation of solid tumors treated with immune checkpoint inhibitors.

OBJECTIVETo evaluate the effectiveness of FTA Elute® Cartridge (GE healthcare, Kent, UK) in combination with hybrid capture 2 (HC2) testing for cervical cancer screening.

METHODSFrom May to June 2012, 412 women aged 25 to 65 years in Jiangxi Tonggu were enrolled in the study. We used pathological outcome as the gold standard, and the accuracy of the FTA card in combination with HC2 testing was investigated from both physician- and self-sampling, respectively.

RESULTSPhysician sampling using the FTA card in combination with HC2 testing showed a comparable sensitivity (12/13) with the liquid based medium, but a higher specificity 69.5% (266/383) vs (77.8%, 298/383) (P < 0.001).When self sampling method was used, the sensitivity and specificity of using the FTA card in combination with HC2 testing with liquid based medium was 10/13 vs 8/13(P = 0.625) and (62.3%, 238/382) vs (75.7%, 289/382) (P < 0.001). The agreement of detection results for HC2 between FTA and liquid-based sampling medium was 86.1% (340/395) and 79.5% (314/395). For physician-collected samples used for HC2 testing to detect CIN2+, the accuracy of the FTA card was superior to that of the liquid-based medium (area under the receiver operating characteristic curve (AUC) = 0.898, 95%CI:0.838-0.958).

CONCLUSIONFTA Elute® cartridge in combination with HC2 testing is a promising method of specimen transport for cervical cancer screening programs with a good precision.With further optimization, it could become an effective method for cervical cancer screening in various economic levels of areas.

Adult ; Early Detection of Cancer ; Female ; Humans ; Middle Aged ; Sensitivity and Specificity ; Specimen Handling ; Uterine Cervical Neoplasms

status.Conclusion HPV6 and HPV-16 were the most two popular HPV types in the whole population,while HPV-16 was the most common type in CIN2+ population.HPV-16 seroprevalence increased with severity of cervical intraepithelial neoplasia.

The infection rate of Oncomelania snails, emergence rate of Schistosoma japa-nicum cercariae, number of emerged cercariae and survival time of infected snails were observed experimentally by exposing single snails to different number of miracidia (i.e. 1, 5, 10, 20 and 40 respectively). The infection rate of snails was shown to be increased with the increasing number of miracidia. The frequency of cercaria emergence of infected snails varied significantly in different seasons and the highest was in spring and summer. No cercaria emergence was observed in winter. The average number of cercariae emerged from a single infected snail in each observation was 70.67, and through the whole lifetime in this experiment, 1,148.85?96.29. There was no significant difference in average number of emerged cercariae among the 5 groups of infected snails. The maximum number of cercariae emerged from one infected snail was 8,079. Calculated from the begining of cercaria emergence, the survival time of infected snails was in average 118.28?9.94 days, and the longest being 839 days. There was no significant difference in survival time among the 5 groups, and 94.8% infected snails died within one year.