ABSTRACT
OBJECTIVE: Investigate the association between p16/Ki-67 dual stain cytology test (DST) results, obtained prior to- and 6 months after LLETZ surgery for treatment of CIN, and the follow-up regimen three years after treatment. METHODS: Secondary analysis of a prospective cohort study. Cervical cytology samples were obtained just prior to- and 6 months after LLETZ and underwent conventional liquid-based cytology (LBC) and p16/Ki-67 dual staining, as well as high-risk HPV genotyping. Clinical management after the LLETZ was according to Belgian national guidelines, with clinicians being blinded to DST results at both time points. Case records were reviewed in 01/2023 to document the follow-up regimen on average three years afterwards: women had either been advised to return to routine screening (i.e., three-annual LBC testing according to the Belgian guideline at that time), or were still subject to more frequent posttreatment surveillance (i.e., more frequent visits because of persistent hrHPV infection or absence of cytological regression). RESULTS: The follow-up regimen was recorded in 79/110 women originally recruited (72%). The need for continued intense posttreatment surveillance was associated with hrHPV infection 6 months after treatment (79.3% vs. 18.0%, p < 0.001), a positive DST result at baseline and follow-up (41.4% vs. 84.0%, p < 0.001-55.2% vs. 16.0%, p < 0.001), and persistent cytological anomalies at 6 months (at an ASCUS or worse threshold, 37.9% vs. 16.0%, p = 0.028). In multivariable logistic regression analysis, a positive DST at baseline (aOR 20.1, 95%CI 2.03-199.1) was independently associated with the need for intense post-treatment surveillance multiple years after treatment. CONCLUSION: This exploratory study suggests a possible role of dual-stain cytology in predicting treatment outcome multiple years after LLETZ surgery.
ABSTRACT
INTRODUCTION: ultrasonography in the first trimester of pregnancy offers an early screening tool to identify high risk pregnancies. Artificial intelligence (AI) algorithms have the potential to improve the accuracy of diagnosis and assist the clinician in early risk stratification. OBJECTIVE: to conduct a systematic review of the use of AI in ultrasonography in the first trimester of pregnancy. METHODS: We conducted a systematic literature review by searching in computerised databases Pubmed, Embase and Google Scholar from inception to January 2024. Full text peer reviewed journal publications written in English on the evaluation of AI in first trimester pregnancy imaging were included. Review papers, conference abstracts, posters, animal studies, non-English and non-peer-reviewed articles were excluded. Risk of bias was assessed by using PROBAST. RESULTS: Of the 1595 non-duplicated records screened, 27 studies were included. Twelve studies focussed on segmentation, eight on plane detection, six on image classification and one on both segmentation and classification. Five studies included fetuses with a gestational age of less than ten weeks. The size of the datasets was relatively small, as sixteen studies included less than 1000 cases. The models were evaluated by different metrics. Duration to run the algorithm was reported in twelve publications and ranged between less than one second and fourteen minutes. Only one study was externally validated. CONCLUSION: Even though the included algorithms reported a good performance in a research setting on testing datasets, further research and collaboration between AI experts and clinicians is needed before implementation in clinical practice.
ABSTRACT
OBJECTIVE: Recent studies suggest that mucinous borderline ovarian tumors (MBOTs) belong to a high-risk group that is more likely to develop an invasive recurrence. The objective is to determine these risk factors. METHODS: A monocentric retrospective review of all consecutive patients with intestinal-type MBOT diagnosed between 1993 and 2013. All tumors were evaluated by one pathologist without knowledge of clinical outcome. Extensive surgical staging and pathological tumor sampling (1 block/cm diameter in tumors <10 cm and 2 blocks/cm diameter in tumors >10 cm) were performed in all cases. RESULTS: A total of 81 patients were included. Patients with micro-invasion were also included. None of the patients recurred. No bilateral tumors, nor tumors with International Federation of Gynecology and Obstetrics stage II or higher, were diagnosed. Median follow-up was 87 months. CONCLUSIONS: In our series of pure intestinal-type MBOT, including micro-invasion, no recurrences were observed. Given the heterogeneity of these tumors staging with at least unilateral salpingo-oophorectomy, extensive pathological sampling, and expert pathological review are of paramount importance to be able to diagnose a pure intestinal-type MBOT and excluding gastrointestinal mucinous tumors and more important, excluding an invasive focus, defining a mucinous ovarian carcinoma. When these conditions are fulfilled, the prognosis of pure intestinal-type MBOT is excellent.
