Weibull parametric model for survival analysis in women with endometrial cancer using clinical and T2-weighted MRI radiomic features.

BACKGROUND: Semiparametric survival analysis such as the Cox proportional hazards (CPH) regression model is commonly employed in endometrial cancer (EC) study. Although this method does not need to know the baseline hazard function, it cannot estimate event time ratio (ETR) which measures relative increase or decrease in survival time. To estimate ETR, the Weibull parametric model needs to be applied. The objective of this study is to develop and evaluate the Weibull parametric model for EC patients' survival analysis. METHODS: Training (n = 411) and testing (n = 80) datasets from EC patients were retrospectively collected to investigate this problem. To determine the optimal CPH model from the training dataset, a bi-level model selection with minimax concave penalty was applied to select clinical and radiomic features which were obtained from T2-weighted MRI images. After the CPH model was built, model diagnostic was carried out to evaluate the proportional hazard assumption with Schoenfeld test. Survival data were fitted into a Weibull model and hazard ratio (HR) and ETR were calculated from the model. Brier score and time-dependent area under the receiver operating characteristic curve (AUC) were compared between CPH and Weibull models. Goodness of the fit was measured with Kolmogorov-Smirnov (KS) statistic. RESULTS: Although the proportional hazard assumption holds for fitting EC survival data, the linearity of the model assumption is suspicious as there are trends in the age and cancer grade predictors. The result also showed that there was a significant relation between the EC survival data and the Weibull distribution. Finally, it showed that Weibull model has a larger AUC value than CPH model in general, and it also has smaller Brier score value for EC survival prediction using both training and testing datasets, suggesting that it is more accurate to use the Weibull model for EC survival analysis. CONCLUSIONS: The Weibull parametric model for EC survival analysis allows simultaneous characterization of the treatment effect in terms of the hazard ratio and the event time ratio (ETR), which is likely to be better understood. This method can be extended to study progression free survival and disease specific survival. TRIAL REGISTRATION: ClinicalTrials.gov NCT03543215, https://clinicaltrials.gov/ , date of registration: 30th June 2017.

Magnetic resonance imaging and clinical features of Mayer-Rokitansky-Küster-Hauser syndrome: A 10-year review from a dedicated specialist centre.

OBJECTIVE: To correlate the clinical history with imaging findings of women with Mayer-Rokitansky-Küster-Hauser (MRKH) syndrome. DESIGN: Retrospective cohort study. SETTING: A UK IOTA and ESGO-certified tertiary referral centre for disorders of reproductive development. POPULATION: All patients with a diagnosis of MRKH and who had undergone an MRI pelvis between 1 January 2011 and 31 April 2021 were included. METHODS: MRI images were analysed by specialist gynaecological radiologists. Clinical data was extracted from an electronic patient record system. Statistical analysis was computed in R (version 4.1.2), R base stats package and ggstatsplot (v0.5.0). MAIN OUTCOME MEASURES: Clinical history and predefined imaging features. RESULTS: One hundred and thirty-four patients were included. Median age at MRI was 18 years (10-64 years). Half (48.2%) of women presenting had a history of pain, most often abdominal (84.6%) or vaginal (9.2%). Remnants were identified in 91.8% of women (n = 123). 4.5% of women had imaging features of endometriosis (n = 6). Women with a functional remnants were significantly more likely to experience pain (p < 0.001). Pain history was not strongly associated with ectopic ovarian position. Common gynaecological pathology such as endometriosis, ovarian cysts and fibroids were also identified. CONCLUSIONS: We identify that majority of women with MRKH will have uterine remnants with a connecting fibrous band, and an ectopic ovarian position 44.0% of cases. Abdominal pain was significantly associated with functional remnants on MRI. Further work is required to identify how other gynaecological pathology impacts women with MRKH.

An Integrated Clinical-MR Radiomics Model to Estimate Survival Time in Patients With Endometrial Cancer.

BACKGROUND: Determination of survival time in women with endometrial cancer using clinical features remains imprecise. Features from MRI may improve the survival estimation allowing improved treatment planning. PURPOSE: To identify clinical features and imaging signatures on T2-weighted MRI that can be used in an integrated model to estimate survival time for endometrial cancer subjects. STUDY TYPE: Retrospective. POPULATION: Four hundred thirteen patients with endometrial cancer as training (N = 330, 66.41 ± 11.42 years) and validation (N = 83, 67.60 ± 11.89 years) data and an independent set of 82 subjects as testing data (63.26 ± 12.38 years). FIELD STRENGTH/SEQUENCE: 1.5-T and 3-T scanners with sagittal T2-weighted spin echo sequence. ASSESSMENT: Tumor regions were manually segmented on T2-weighted images. Features were extracted from segmented masks, and clinical variables including age, cancer histologic grade and risk score were included in a Cox proportional hazards (CPH) model. A group least absolute shrinkage and selection operator method was implemented to determine the model from the training and validation datasets. STATISTICAL TESTS: A likelihood-ratio test and decision curve analysis were applied to compare the models. Concordance index (CI) and area under the receiver operating characteristic curves (AUCs) were calculated to assess the model. RESULTS: Three radiomic features (two image intensity and volume features) and two clinical variables (age and cancer grade) were selected as predictors in the integrated model. The CI was 0.797 for the clinical model (includes clinical variables only) and 0.818 for the integrated model using training and validation datasets, the associated mean AUC value was 0.805 and 0.853. Using the testing dataset, the CI was 0.792 and 0.882, significantly different and the mean AUC was 0.624 and 0.727 for the clinical model and integrated model, respectively. DATA CONCLUSION: The proposed CPH model with radiomic signatures may serve as a tool to improve estimated survival time in women with endometrial cancer. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 2.

Optimal method for metabolic tumour volume assessment of cervical cancers with inter-observer agreement on [18F]-fluoro-deoxy-glucose positron emission tomography with computed tomography.

PURPOSE: Cervical cancer metabolic tumour volume (MTV) derived from [18F]-FDG PET/CT has a role in prognostication and therapy planning. There is no standard method of outlining MTV on [18F]-FDG PET/CT. The aim of this study was to assess the optimal method to outline primary cervical tumours on [18F]-FDG PET/CT using MRI-derived tumour volumes as the reference standard. METHODS: 81 consecutive cervical cancer patients with pre-treatment staging MRI and [18F]-FDG PET/CT imaging were included. MRI volumes were compared with different PET segmentation methods. Method 1 measured MTVs at different SUVmax thresholds ranging from 20 to 60% (MTV20-MTV60) with bladder masking and manual adjustment when required. Method 2 created an isocontour around the tumour prior to different SUVmax thresholds being applied. Method 3 used an automated gradient method. Inter-observer agreement of MTV, following manual adjustment when required, was recorded. RESULTS: For method 1, the MTV25 and MTV30 were closest to the MRI volumes for both readers (mean percentage change from MRI volume of 2.9% and 13.4% for MTV25 and - 13.1% and - 2.0% for MTV30 for readers 1 and 2). 70% of lesions required manual adjustment at MTV25 compared with 45% at MTV30. There was excellent inter-observer agreement between MTV30 to MTV60 (ICC ranged from 0.898-0.976 with narrow 95% confidence intervals (CIs)) and moderate agreement at lower thresholds (ICC estimates of 0.534 and 0.617, respectively for the MTV20 and MTV25 with wide 95% CIs). Bladder masking was performed in 86% of cases overall. For method 2, excellent correlation was demonstrated at MTV25 and MTV30 (mean % change from MRI volume of -3.9% and - 8.6% for MTV25 and - 16.9% and 19% for MTV30 for readers 1 and 2, respectively). This method also demonstrated excellent ICC across all thresholds with no manual adjustment. Method 3 demonstrated excellent ICC of 0.96 (95% CI 0.94-0.97) but had a mean percentage difference from the MRI volume of - 19.1 and - 18.2% for readers 1 and 2, respectively. 21% required manual adjustment for both readers. CONCLUSION: MTV30 provides the optimal correlation with MRI volume taking into consideration the excellent inter-reader agreement and less requirement for manual adjustment.

Staging, recurrence and follow-up of uterine cervical cancer using MRI: Updated Guidelines of the European Society of Urogenital Radiology after revised FIGO staging 2018.

OBJECTIVES: The recommendations cover indications for MRI examination including acquisition planes, patient preparation, imaging protocol including multi-parametric approaches such as diffusion-weighted imaging (DWI-MR),  dynamic contrast-enhanced imaging (DCE-MR) and standardised reporting. The document also underscores the value of whole-body 18-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography (FDG-PET/CT) and highlights potential future methods. METHODS: In 2019, the ESUR female pelvic imaging working group reviewed the revised 2018 FIGO staging system, the up-to-date clinical management guidelines, and the recent imaging literature. The RAND-UCLA Appropriateness Method (RAM) was followed to develop the current ESUR consensus guidelines following methodological steps: literature research, questionnaire developments, panel selection, survey, data extraction and analysis. RESULTS: The updated ESUR guidelines are recommendations based on ≥ 80% consensus among experts. If ≥ 80% agreement was not reached, the action was indicated as optional. CONCLUSIONS: The present ESUR guidelines focus on the main role of MRI in the initial staging, response monitoring and evaluation of disease recurrence. Whole-body FDG-PET plays an important role in the detection of lymph nodes (LNs) and distant metastases. KEY POINTS: • T2WI and DWI-MR are now recommended for initial staging, monitoring of response and evaluation of recurrence. • DCE-MR is optional; its primary role remains in the research setting. • T2WI, DWI-MRI and whole-body FDG-PET/CT enable comprehensive assessment of treatment response and recurrence.

Evaluating Fallopian Tube Patency: What the Radiologist Needs to Know.

Impaired tubal patency accounts for up to 35% of cases of subfertility and infertility. Hysterosalpingography (HSG) or hysterosalpingo-contrast sonography (HyCoSy) represents a first-line test in evaluating fallopian tube patency. Despite the association of HSG with ionizing radiation, HSG is a reference standard in assessing fallopian tube patency and tubal conditions such as tubal occlusion, salpingitis isthmica nodosa, and hydrosalpinx. HSG is widely available and utilizes either a water-soluble contrast medium (WSCM) or an oil-soluble contrast medium (OSCM). Compared with WSCM, HSG with OSCM results in a higher incidence of non-in vitro fertilization pregnancies and, therefore, may be preferred in women younger than 38 years with unexplained subfertility. HSG may also be helpful in assessment after sterilization or before fallopian tube recanalization. US-based tubal tests are free of ionizing radiation and include HyCoSy, with either air-saline or microbubble US contrast material, and hysterosalpingo-foam sonography (HyFoSy), a tubal patency test that utilizes a gel foam. A comprehensive US infertility evaluation of the pelvis and fallopian tubes can be achieved in one setting by adding coronal three-dimensional imaging of the uterus, saline infusion sonohysterography, and HyCoSy or HyFoSy to routine pelvic US. MR HSG and virtual CT HSG also depict tubal patency and uterine and adnexal pathologic conditions and may be considered in select patients. While laparoscopic chromopertubation remains the standard for tubal patency evaluation, its disadvantages are its invasiveness and cost. Knowledge of the different fallopian tube tests and radiologic appearance of normal and abnormal fallopian tubes results in fewer pitfalls, accurate interpretation, and optimal patient care. Online supplemental material is available for this article. ©RSNA, 2021.

Adnexal Torsion: Review of Radiologic Appearances.

Adnexal torsion is the twisting of the ovary, and often of the fallopian tube, on its ligamental supports, resulting in vascular compromise and ovarian infarction. The definitive management is surgical detorsion, and prompt diagnosis facilitates preservation of the ovary, which is particularly important because this condition predominantly affects premenopausal women. The majority of patients present with severe acute pain, vomiting, and a surgical abdomen, and the diagnosis is often made clinically with corroborative US. However, the symptoms of adnexal torsion can be variable and nonspecific, making an early diagnosis challenging unless this condition is clinically suspected. When adnexal torsion is not clinically suspected, CT or MRI may be performed. Imaging has an important role in identifying adnexal torsion and accelerating definitive treatment, particularly in cases in which the diagnosis is not an early consideration. Several imaging features are characteristic of adnexal torsion and can be seen to varying degrees across different modalities: a massive, edematous ovary migrated to the midline; peripherally displaced ovarian follicles resembling a string of pearls; a benign ovarian lesion acting as a lead mass; surrounding inflammatory change or free fluid; and the uterus pulled toward the side of the affected ovary. Hemorrhage and absence of internal flow or enhancement are suggestive of ovarian infarction. Pertinent conditions to consider in the differential diagnosis are a ruptured hemorrhagic ovarian cyst, massive ovarian edema, ovarian hyperstimulation, and a degenerating leiomyoma. Online supplemental material is available for this article. ©RSNA, 2021.

Society of Abdominal Radiology (SAR) and European Society of Urogenital Radiology (ESUR) joint consensus statement for MR imaging of placenta accreta spectrum disorders.

OBJECTIVES: This study was conducted in order to establish the joint Society of Abdominal Radiology (SAR) and European Society of Urogenital Radiology (ESUR) guidelines on placenta accreta spectrum (PAS) disorders and propose strategies to standardize image acquisition, interpretation, and reporting for this condition with MRI. METHODS: The published evidence-based data and the opinion of experts were combined using the RAND-UCLA Appropriateness Method and formed the basis for these consensus guidelines. The responses of the experts to questions regarding the details of patient preparation, MRI protocol, image interpretation, and reporting were collected, analyzed, and classified as "recommended" versus "not recommended" (if at least 80% consensus among experts) or uncertain (if less than 80% consensus among experts). RESULTS: Consensus regarding image acquisition, interpretation, and reporting was determined using the RAND-UCLA Appropriateness Method. The use of a tailored MRI protocol and standardized report was recommended. CONCLUSIONS: A standardized imaging protocol and reporting system ensures recognition of the salient features of PAS disorders. These consensus recommendations should be used as a guide for the evaluation of PAS disorders with MRI. KEY POINTS: • MRI is a powerful adjunct to ultrasound and provides valuable information on the topography and depth of placental invasion. • Consensus statement proposed a common lexicon to allow for uniformity in MRI acquisition, interpretation, and reporting of PAS disorders. • Seven MRI features, namely intraplacental dark T2 bands, uterine/placental bulge, loss of low T2 retroplacental line, myometrial thinning/disruption, bladder wall interruption, focal exophytic placental mass, and abnormal vasculature of the placental bed, reached consensus and are categorized as "recommended" for diagnosing PAS disorders.

MRI of female genital tract congenital anomalies: European Society of Urogenital Radiology (ESUR) guidelines.

OBJECTIVE: To develop imaging guidelines for the MR work-up of female genital tract congenital anomalies (FGTCA). METHODS: These guidelines were prepared based on a questionnaire sent to all members of the European Society of Urogenital Radiology (ESUR) Female Pelvic Imaging Working Group (FPI-WG), critical review of the literature and expert consensus decision. RESULTS: The returned questionnaires from 17 different institutions have shown reasonable homogeneity of practice. Recommendations with focus on patient preparation and MR protocol are proposed, as these are key to optimised examinations. Details on MR sequences and planning of uterus-orientated sequences are provided. CONCLUSIONS: The multiplanar capabilities and soft tissue resolution of MRI provide superb characterisation of the wide spectrum of findings in FGTCA. A standardised imaging protocol and method of reporting ensures that the salient features are recognised, contributing to a correct diagnosis and classification of FGTCA, associated anomalies and complications. These imaging guidelines are based on current practice among expert radiologists in the field and incorporate up to date information regarding MR protocols and essentials of recently published classification systems. KEY POINTS: • MRI allows comprehensive evaluation of female genital tract congenital anomalies, in a single examination. • A dedicated MRI protocol comprises uterus-orientated sequences and vaginal and renal evaluation. • Integration of classification systems and structured reporting helps in successful communication of the imaging findings.

2018 FIGO Staging Classification for Cervical Cancer: Added Benefits of Imaging.

Cervical cancer is the fourth most common cancer in women of all ages worldwide. The disease is staged using the International Federation of Gynecology and Obstetrics (FIGO) system, which was updated in 2018. The authors explain the key changes from the 2009 version and the rationale behind them. The changes have been made to reflect common clinical practice, differentiate prognostic outcomes, and guide treatment stratification. Treatment options are dependent on the stage of disease and include fertility-sparing and non-fertility-sparing surgical options as well as chemoradiotherapy for locally advanced disease. The updated FIGO staging gives added importance to MRI as a method of accurately measuring tumor size and depicting the presence of parametrial involvement. With the inclusion of lymph node involvement in the updated 2018 FIGO staging, cross-sectional imaging-and in particular, fluorodeoxyglucose PET/CT-has an increasing role in the depiction of nodal disease. Understanding the radiologic techniques used, the literature supporting them, and common imaging pitfalls ensures accurate staging of disease and optimization of treatment. ©RSNA, 2020 See discussion on this article by Javitt (pp 1823-1824).

Endometrial Cancer MRI staging: Updated Guidelines of the European Society of Urogenital Radiology.

OBJECTIVES: To update the 2009 ESUR endometrial cancer guidelines and propose strategies to standardize image acquisition, interpretation and reporting for endometrial cancer staging with MRI. METHODS: The published evidence-based data and the opinion of experts were combined using the RAND-UCLA Appropriateness Method and formed the basis for these consensus guidelines. The responses of the experts to 81 questions regarding the details of patient preparation, MR imaging protocol, image interpretation and reporting were collected, analysed and classified as "RECOMMENDED" versus "NOT RECOMMENDED" (if at least 80% consensus among experts) or uncertain (if less than 80% consensus among experts). RESULTS: Consensus regarding patient preparation, MR image acquisition, interpretation and reporting was determined using the RAND-UCLA Appropriateness Method. A tailored MR imaging protocol and a standardized report were recommended. CONCLUSIONS: These consensus recommendations should be used as a guide for endometrial cancer staging with MRI. KEY POINTS: • MRI is recommended for initial staging of endometrial cancer. • MR imaging protocol should be tailored based on the risk of lymph node metastases. • Myometrial invasion is best assessed using combined axial-oblique T2WI, DWI and contrast-enhanced imaging. • The mnemonic "Clinical and MRI Critical TEAM" summarizes key elements of the standardized report.

Anti-tumour activity of a first-in-class agent NUC-1031 in patients with advanced cancer: results of a phase I study.

BACKGROUND: Gemcitabine is used to treat a wide range of tumours, but its efficacy is limited by cancer cell resistance mechanisms. NUC-1031, a phosphoramidate modification of gemcitabine, is the first anti-cancer ProTide to enter the clinic and is designed to overcome these key resistance mechanisms. METHODS: Sixty-eight patients with advanced solid tumours who had relapsed after treatment with standard therapy were recruited to a dose escalation study to determine the recommended Phase II dose (RP2D) and assess the safety of NUC-1031. Pharmacokinetics and anti-tumour activity was also assessed. RESULTS: Sixty-eight patients received treatment, 50% of whom had prior exposure to gemcitabine. NUC-1031 was well tolerated with the most common Grade 3/4 adverse events of neutropaenia, lymphopaenia and fatigue occurring in 13 patients each (19%). In 49 response-evaluable patients, 5 (10%) achieved a partial response and 33 (67%) had stable disease, resulting in a 78% disease control rate. Cmax levels of the active intracellular metabolite, dFdCTP, were 217-times greater than those reported for equimolar doses of gemcitabine, with minimal toxic metabolite accumulation. The RP2D was determined as 825 mg/m2 on days 1, 8 and 15 of a 28-day cycle. CONCLUSIONS: NUC-1031 was well tolerated and demonstrated clinically significant anti-tumour activity, even in patients with prior gemcitabine exposure and in cancers not traditionally perceived as gemcitabine-responsive.

FDG PET/CT Pitfalls in Gynecologic and Genitourinary Oncologic Imaging.

The role of whole-body positron emission tomography (PET)/computed tomography (CT) with fluorodeoxyglucose ( FDG fluorodeoxyglucose ) is now established in the assessment of many gynecologic and genitourinary malignant tumors. FDG fluorodeoxyglucose PET/CT has been widely adopted for staging assessments in patients with suspected advanced disease, in cases of suspected disease recurrence, and for determining prognosis in a number of malignancies. A number of pitfalls are commonly encountered when reviewing FDG fluorodeoxyglucose PET/CT scans in gynecologic and genitourinary cases; these pitfalls can be classified into those that yield potential false-positive or false-negative results. Potential false positives include physiologic uptake of FDG fluorodeoxyglucose by the endometrium and ovaries in premenopausal patients, physiologic renal excretion of FDG fluorodeoxyglucose into the ureters and the urinary bladder, and increased FDG fluorodeoxyglucose activity in benign conditions such as uterine fibroids, pelvic inflammatory disease, and benign endometriotic cysts. Potential false negatives include low-level FDG fluorodeoxyglucose uptake by necrotic, mucinous, cystic, or low-grade tumors and the masking of serosal and peritoneal disease by adjacent physiologic bowel or bladder activity. In addition, there are inherent technical limitations-such as motion artifact (from respiratory motion and bowel peristalsis) and the limited spatial resolution of PET-that may limit the assessment of small-volume malignant disease. Knowledge of the key imaging features of physiologic and nonphysiologic FDG fluorodeoxyglucose uptake, in addition to understanding the principles of adequate patient preparation and PET scanning protocols, is important for accurate interpretation of gynecologic and genitourinary oncologic FDG fluorodeoxyglucose PET/CT studies. ©RSNA, 2017.

Subfertility: What the Radiologist Needs to Know.

The role of imaging in subfertility is well established but is changing. In addition to traditional fertility assessments, there is an emerging role for the radiologist. The role of imaging in fertility-restoring procedures in benign disease and congenital malformations is evolving, and there is a growing need for accurate identification of young candidates suitable for fertility-preserving surgery in the oncologic setting. To facilitate this developing role, knowledge of the key imaging modalities used and potential therapeutic applications is important for accurate diagnosis and interpretation by the radiologist. ©RSNA, 2017.

What's New in Imaging for Gynecologic Cancer?

Magnetic resonance imaging (MRI) is the optimal modality for local staging of gynecological tumors. Advances in functional MRI with diffusion-weighted and dynamic contrast-enhanced sequences provide more detailed information regarding tumor cellularity, vascularity, and viability. Fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) now has an established role in imaging for gynecological cancers, particularly staging of locally advanced cervical cancers and pre-salvage exenterative therapy in relapsed gynecologic tumors. Novel PET tracers, targeting other aspects of tumor biology, are being evaluated although none are currently in routine clinical use. New PET/MR scanners have the potential to combine the strengths of both modalities in one sitting. This review covers advances in gynecologic imaging concentrating on cervical, endometrial, and ovarian cancers.

Post-Radiation Therapy Imaging Appearances in Cervical Carcinoma.

Locally advanced and node-positive cervical cancers are usually treated with external beam radiation therapy and intracavitary brachytherapy with concomitant chemotherapy. In patients with locally advanced cervical cancer, imaging plays a vital role in pretreatment planning, assessment of primary tumor response to treatment, follow-up, and evaluation of treatment-related complications. Radiation therapy planning is crucial to successful local and regional control of disease. Patient selection criteria for radiation therapy with concomitant chemotherapy are described, as is assessment of treatment response of the primary cervical tumor at magnetic resonance (MR) imaging. Image interpretation can be challenging because of radiation therapy-related changes in the pelvic organs. Expected changes in the bladder, bowel, and bone marrow after radiation therapy are described, and multimodality imaging findings at computed tomography, MR imaging, and fluorine 18 fluorodeoxyglucose positron emission tomography are illustrated. Complications after radiation therapy have declined over recent years because of targeted radiation therapy. These complications can be divided into acute and chronic effects, where acute toxic effects occur within weeks of treatment. Chronic complications include cervical stenosis, small bowel stricture, fistula formation, and insufficiency fractures. Imaging is an essential tool in the care of patients with cervical cancer treated with chemotherapy and radiation therapy. The reporting radiologist should be familiar with the expected imaging appearances of the pelvic organs after radiation therapy, as well as potential complications, to avoid pitfalls in image interpretation.

Role of Imaging in Fertility-sparing Treatment of Gynecologic Malignancies.

Treatments for gynecologic cancer usually result in loss of fertility due to surgery or radical radiation therapy in the pelvis. In countries with an established screening program for cervical cancer, the majority of gynecologic malignancies occur in postmenopausal women. However, a substantial number of affected women are of childbearing age and have not completed their families. In these younger women, consideration of fertility preservation may be important. This article describes the fertility-sparing treatment options that are currently available and outlines the role of imaging in the selection of eligible patients on the basis of a review of the literature. In the setting of cervical cancer, magnetic resonance (MR) imaging is used to delineate the size, position, and stage of the tumor for selection of patients who are suitable for radical trachelectomy. In patients with solitary complex adnexal masses, diffusion- and perfusion-weighted MR imaging sequences are used to categorize the likelihood of invasive or borderline malignancy for consideration of unilateral ovarian resection, with fertility preservation when possible. In patients with endometrial cancer, MR imaging is used to rule out signs of invasive disease before hormone therapy is considered. Imaging is also used at patient follow-up to detect recurrent disease; however, evidence to support this application is limited. In conclusion, imaging is an essential tool in the care of patients with gynecologic malignancies who are considering fertility-preserving treatment options. ©RSNA, 2016.

Machine learning and radiomics for segmentation and classification of adnexal masses on ultrasound.

Ultrasound-based models exist to support the classification of adnexal masses but are subjective and rely upon ultrasound expertise. We aimed to develop an end-to-end machine learning (ML) model capable of automating the classification of adnexal masses. In this retrospective study, transvaginal ultrasound scan images with linked diagnoses (ultrasound subjective assessment or histology) were extracted and segmented from Imperial College Healthcare, UK (ICH development dataset; n = 577 masses; 1444 images) and Morgagni-Pierantoni Hospital, Italy (MPH external dataset; n = 184 masses; 476 images). A segmentation and classification model was developed using convolutional neural networks and traditional radiomics features. Dice surface coefficient (DICE) was used to measure segmentation performance and area under the ROC curve (AUC), F1-score and recall for classification performance. The ICH and MPH datasets had a median age of 45 (IQR 35-60) and 48 (IQR 38-57) years old and consisted of 23.1% and 31.5% malignant cases, respectively. The best segmentation model achieved a DICE score of 0.85 ± 0.01, 0.88 ± 0.01 and 0.85 ± 0.01 in the ICH training, ICH validation and MPH test sets. The best classification model achieved a recall of 1.00 and F1-score of 0.88 (AUC:0.93), 0.94 (AUC:0.89) and 0.83 (AUC:0.90) in the ICH training, ICH validation and MPH test sets, respectively. We have developed an end-to-end radiomics-based model capable of adnexal mass segmentation and classification, with a comparable predictive performance (AUC 0.90) to the published performance of expert subjective assessment (gold standard), and current risk models. Further prospective evaluation of the classification performance of this ML model against existing methods is required.