Dataset Information

Germline BRCA 1-2 status prediction through ovarian ultrasound images radiogenomics: a hypothesis generating study (PROBE study).

ABSTRACT: Radiogenomics is a specific application of radiomics where imaging features are linked to genomic profiles. We aim to develop a radiogenomics model based on ovarian US images for predicting germline BRCA1/2 gene status in women with healthy ovaries. From January 2013 to December 2017 a total of 255 patients addressed to germline BRCA1/2 testing and pelvic US documenting normal ovaries, were retrospectively included. Feature selection for univariate analysis was carried out via correlation analysis. Multivariable analysis for classification of germline BRCA1/2 status was then carried out via logistic regression, support vector machine, ensemble of decision trees and automated machine learning pipelines. Data were split into a training (75%) and a testing (25%) set. The four strategies obtained a similar performance in terms of accuracy on the testing set (from 0.54 of logistic regression to 0.64 of the auto-machine learning pipeline). Data coming from one of the tested US machine showed generally higher performances, particularly with the auto-machine learning pipeline (testing set specificity 0.87, negative predictive value 0.73, accuracy value 0.72 and 0.79 on training set). The study shows that a radiogenomics model on machine learning techniques is feasible and potentially useful for predicting gBRCA1/2 status in women with healthy ovaries.

SUBMITTER: Nero C

PROVIDER: S-EPMC7536234 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Germline BRCA 1-2 status prediction through ovarian ultrasound images radiogenomics: a hypothesis generating study (PROBE study).

Nero Camilla C Ciccarone Francesca F Boldrini Luca L Lenkowicz Jacopo J Paris Ida I Capoluongo Ettore Domenico ED Testa Antonia Carla AC Fagotti Anna A Valentini Vincenzo V Scambia Giovanni G

Scientific reports 20201005 1

Radiogenomics is a specific application of radiomics where imaging features are linked to genomic profiles. We aim to develop a radiogenomics model based on ovarian US images for predicting germline BRCA1/2 gene status in women with healthy ovaries. From January 2013 to December 2017 a total of 255 patients addressed to germline BRCA1/2 testing and pelvic US documenting normal ovaries, were retrospectively included. Feature selection for univariate analysis was carried out via correlation analys ...[more]

PMID: 33020566

Similar Datasets

Project description:ObjectiveTo describe the testing rate, patient characteristics, temporal trends, timing, and results of germline and somatic BRCA testing in patients with ovarian cancer using real-world data.MethodsWe included a cross-sectional subset of adult patients diagnosed with ovarian cancer between January 1, 2011, and November 30, 2018, who received frontline treatment and were followed for at least 1 year in a real-world database. The primary outcome was receipt of BRCA testing, classified by biosample source as germline (blood or saliva) or somatic (tissue). Lines of therapy (frontline, second line, third line) were derived based on dates of surgery and chemotherapy. Descriptive statistics were analyzed.ResultsAmong 2,557 patients, 72.2% (n=1,846) had at least one documented BRCA test. Among tested patients, 62.5% (n=1,154) had only germline testing, 10.6% (n=197) had only somatic testing, and 19.9% (n=368) had both. Most patients had testing before (9.7%, n=276) or during (48.6%, n=1,521) frontline therapy, with 17.6% (n=273) tested during second-line and 12.7% (n=129) tested during third-line therapy. Patients who received BRCA testing, compared with patients without testing, were younger (mean age 63 years vs 66 years, P <.001) and were more likely to be treated at an academic practice (10.4% vs 7.0%, P =.01), with differences by Eastern Cooperative Oncology Group performance score ( P <.001), stage of disease ( P <.001), histology ( P <.001), geography ( P <.001), and type of frontline therapy ( P <.001), but no differences based on race or ethnicity. The proportion of patients who received BRCA testing within 1 year of diagnosis increased from 24.6% of patients in 2011 to 75.6% of patients in 2018.ConclusionIn a large cohort of patients with ovarian cancer, significant practice disparities existed in testing for actionable BRCA mutations. Despite increased testing over time, many patients did not receive testing, suggesting missed opportunities to identify patients appropriate for targeted therapy and genetic counseling.

Project description:IntroductionUp to 75% of women with ovarian cancer experience psychosexual morbidity and approximately 15-20% of women with ovarian cancer have a germline BRCA1/2 mutation (gBRCAm). However, psychosexual morbidity remains unexplored in women with gBRCAm ovarian cancer.AimGiven their younger age, genetic diagnosis, breast cancer risk, and increased prevalence of surgically-induced menopause, we aim to assess whether women with gBRCAm ovarian cancer experience distinct psychosexual morbidity.MethodsPsychosexual morbidity was investigated in 2 cohorts of women with ovarian cancer: women with gBRCAm ovarian cancer vs women with gBRCA wildtype (gBRCAwt) ovarian cancer. Between August 2019 and March 2020, women with high-grade serous carcinoma of the ovary, Fallopian tube or primary peritoneum were approached in clinic or telephoned and invited to take part. Exclusion criteria included: women with alternative histology; women admitted from clinic; and women who lacked capacity to independently complete the questionnaire. The Female Sexual Function Index (FSFI) and background information were collected at a single time-point per patient. Scores below 26.55 were interpreted to suggest psychosexual dysfunction.Main outcome measureResponses including total and domain FSFI scores, self-reported psychosexual problems and interest in psychosexual support were compared.ResultsOf 103 women approached, 53% returned questionnaires. In this exploratory analysis, women with gBRCAm ovarian cancer were significantly younger (51-60 years vs 61-70 years, gBRCAwt, P = .010). There was a trend towards increased prevalence of surgical menopause (57% vs 27%, P = .097) and breast surgery (53% vs 22%, P = .132, gBRCAm vs gBRCAwt, respectively). Women with gBRCAm ovarian cancer scored higher in the FSFI questionnaire, particularly women under 60 years (15.1 vs 2.7, P = .070), approaching significance. Women with gBRCAm ovarian cancer expressed more interest for face-to-face services (P = .018), especially psychosexual therapy (65% vs 30%) and more often felt the service was insufficient, approaching significance (71% vs 44%, gBRCAm vs gBRCAwt, respectively, P = .076).ConclusionWomen with gBRCAm ovarian cancer are younger, express more interest for specialist psychosexual support and potentially different psychosexual problems, warranting further exploration. Logue C, Pugh J, Foden P, et al., Psychosexual Morbidity in Women With Ovarian Cancer: Evaluation by Germline BRCA Gene Mutational Status. Sex Med 2022;10:100465.

Dataset Information

Germline BRCA 1-2 status prediction through ovarian ultrasound images radiogenomics: a hypothesis generating study (PROBE study).

Publications

Germline BRCA 1-2 status prediction through ovarian ultrasound images radiogenomics: a hypothesis generating study (PROBE study).

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets