Preoperative CECT-Based Multitask Model Predicts Peritoneal Recurrence and Disease-Free Survival in Advanced Ovarian Cancer: A Multicenter Study.

RATIONALE AND OBJECTIVES: Peritoneal recurrence is the predominant pattern of recurrence in advanced ovarian cancer (AOC) and portends a dismal prognosis. Accurate prediction of peritoneal recurrence and disease-free survival (DFS) is crucial to identify patients who might benefit from intensive treatment. We aimed to develop a predictive model for peritoneal recurrence and prognosis in AOC. METHODS: In this retrospective multi-institution study of 515 patients, an end-to-end multi-task convolutional neural network (MCNN) comprising a segmentation convolutional neural network (CNN) and a classification CNN was developed and tested using preoperative CT images, and MCNN-score was generated to indicate the peritoneal recurrence and DFS status in patients with AOC. We evaluated the accuracy of the model for automatic segmentation and predict prognosis. RESULTS: The MCNN achieved promising segmentation performances with a mean Dice coefficient of 84.3% (range: 78.8%-87.0%). The MCNN was able to predict peritoneal recurrence in the training (AUC 0.87; 95% CI 0.82-0.90), internal test (0.88; 0.85-0.92), and external test set (0.82; 0.78-0.86). Similarly, MCNN demonstrated consistently high accuracy in predicting recurrence, with an AUC of 0.85; 95% CI 0.82-0.88, 0.83; 95% CI 0.80-0.86, and 0.85; 95% CI 0.83-0.88. For patients with a high MCNN-score of recurrence, it was associated with poorer DFS with P < 0.0001 and hazard ratios of 0.1964 (95% CI: 0.1439-0.2680), 0.3249 (95% CI: 0.1896-0.5565), and 0.3458 (95% CI: 0.2582-0.4632). CONCLUSION: The MCNN approach demonstrated high performance in predicting peritoneal recurrence and DFS in patients with AOC.

Predicting Neoadjuvant Chemotherapy Response and High-Grade Serous Ovarian Cancer From CT Images in Ovarian Cancer with Multitask Deep Learning: A Multicenter Study.

RATIONALE AND OBJECTIVES: Accurate prediction neoadjuvant chemotherapy (NACT) response in ovarian cancer (OC) is essential for personalized medicine. We aimed to develop and validate a deep learning (DL) model based on pretreatment contrast-enhanced CT (CECT) images for predicting NACT responses and classifying high-grade serous ovarian cancer (HGSOC) to identify patients who may benefit from NACT. MATERIALS AND METHODS: This multicenter study, which contained both retrospective and prospective studies, included consecutive OC patients (n = 757) from three hospitals. Using WHO RECIST 1.1 for the reference standard, a total of 587 women with 1761 images were included in the training and validation sets, 67 women with 201 images were included in the prospective sets, and 103 women with 309 images were included in the external sets. A multitask DL model based on the multiperiod CT image was developed to predict NACT response and HGSOC. RESULTS: Logistic regression analysis showed that peritoneal invasion, retinal invasion, and inguinal lymph node metastasis were independent predictors. The DL achieved promising segmentation performances with DICEmean= 0.83 (range: 0.78-0.87). For predicting NACT response, the DL model combined with clinical risk factors obtained area under the receiver operating characteristic curve (AUCs) of 0.87 (0.83-0.89), 0.88 (0.86-0.91), 0.86 (0.82-0.89), and 0.79 (0.75-0.82) in the training, validation, prospective, and external sets, respectively. The AUCs were 0.91 (0.87-0.94), 0.89 (0.86-0.91), 0.80 (0.76-0.84), and 0.80 (0.75-0.85) in four sets in HGSOC classification. CONCLUSION: The multitask DL model developed using multiperiod CT images exhibited a promising performance for predicting NACT response and HGSOC with OC, which could provide valuable information for individualized treatment.

Long Non-Coding RNA Differentiation Antagonizing Nonprotein Coding RNA (DANCR) Promotes Proliferation and Invasion of Pancreatic Cancer by Sponging miR-214-5p to Regulate E2F2 Expression.

BACKGROUND Long non-coding RNA differentiation antagonizing nonprotein coding RNA (lncRNA DANCR) has been reported to act as an oncogene in various human cancers. The role of DANCR in development of pancreatic cancer (PC) is unknown. The aim of our research was to investigate the biological role of DANCR in PC. MATERIAL AND METHODS Expressions of DANCR, miR-214-5p, and E2F2 mRNA in PC tissues and cell lines were examined by qRT-PCR. Western blotting was carried out for detection of E2F2 protein expression in PC cells. Transwell assays were used to examine the metastatic ability of PC cells, while CCK-8 and colony formation assay were applied to evaluate cell proliferation. The effects of DANCR on PC cells were assessed by knockdown in vitro and in vivo. The regulatory mechanism of competitive endogenous RNAs were obtained from bioinformatics prediction and luciferase reporter assay. RESULTS DANCR was markedly upregulated in clinical tissues and cell lines of PC. High DANCR expression exhibited a significant correlation with poor prognosis. DANCR knockdown inhibited growth and metastasis of PC cells. Furthermore, DANCR acted as sponge to regulate miR-214-5p, and miR-214-5p inhibitor reversed the effects of DANCR knockdown on PC cells. Moreover, DANCR positively modulated E2F2 expression through miR-214-5p in PC cells. CONCLUSIONS Collectively, our findings demonstrated that lncRNA DANCR/miR-214-5p/E2F2 axis acts as an oncogene in PC development, which might provide a potential target for PC therapy.

[Determination of major carbonyls in mainstream smoke by rapid column high performance liquid chromatography].

Abstract: The determination of major carbonyl compounds in mainstream cigarette smoke by rapid column high performance liquid chromatography was investigated. The cigarette smoke was collected using a Cambridge filter treated with acidic solution of 2, 4-dinitrophenyl-hydrazine. Formaldehyde, acetaldehyde, acetone, acrolein, propionaldehyde, crotonaldehyde, 2-butanone and butyraldehyde were extracted from the Cambridge filter with 50 mL of 2% pyridine acetonitrile solution. The carbonyl compounds in samples were separated on a ZORBAX Stable Bound rapid column (50 mm x 4. 6 mm, 1. 8 microm) in approximately seven minutes and then determined by high performance liquid chromatography with a diode array detector. The average recoveries were in the range of 89. 1% to 99. 2% and the relative standard deviations (RSDs) were generally below 6. 0%. The eight carbonyl compounds in the mainstream smoke of five brands of cigarettes were determined using this method. This method is faster, simpler and consumes less solvent. It is suitable for rapid analysis of carbonyl compounds in mainstream cigarette smoke.