AI-based automated segmentation for ovarian/adnexal masses and their internal components on ultrasound imaging.

Purpose: Segmentation of ovarian/adnexal masses from surrounding tissue on ultrasound images is a challenging task. The separation of masses into different components may also be important for radiomic feature extraction. Our study aimed to develop an artificial intelligence-based automatic segmentation method for transvaginal ultrasound images that (1) outlines the exterior boundary of adnexal masses and (2) separates internal components. Approach: A retrospective ultrasound imaging database of adnexal masses was reviewed for exclusion criteria at the patient, mass, and image levels, with one image per mass. The resulting 54 adnexal masses (36 benign/18 malignant) from 53 patients were separated by patient into training (26 benign/12 malignant) and independent test (10 benign/6 malignant) sets. U-net segmentation performance on test images compared to expert detailed outlines was measured using the Dice similarity coefficient (DSC) and the ratio of the Hausdorff distance to the effective diameter of the outline ( R HD - D ) for each mass. Subsequently, in discovery mode, a two-level fuzzy c-means (FCM) unsupervised clustering approach was used to separate the pixels within masses belonging to hypoechoic or hyperechoic components. Results: The DSC (median [95% confidence interval]) was 0.91 [0.78, 0.96], and R HD - D was 0.04 [0.01, 0.12], indicating strong agreement with expert outlines. Clinical review of the internal separation of masses into echogenic components demonstrated a strong association with mass characteristics. Conclusion: A combined U-net and FCM algorithm for automatic segmentation of adnexal masses and their internal components achieved excellent results compared with expert outlines and review, supporting future radiomic feature-based classification of the masses by components.

Diagnostic Performance of Ultrasonography-Based Risk Models in Differentiating Between Benign and Malignant Ovarian Tumors in a US Cohort.

Importance: Ultrasonography-based risk models can help nonexpert clinicians evaluate adnexal lesions and reduce surgical interventions for benign tumors. Yet, these models have limited uptake in the US, and studies comparing their diagnostic accuracy are lacking. Objective: To evaluate, in a US cohort, the diagnostic performance of 3 ultrasonography-based risk models for differentiating between benign and malignant adnexal lesions: International Ovarian Tumor Analysis (IOTA) Simple Rules with inconclusive cases reclassified as malignant or reevaluated by an expert, IOTA Assessment of Different Neoplasias in the Adnexa (ADNEX), and Ovarian-Adnexal Reporting and Data System (O-RADS). Design, Setting, and Participants: This retrospective diagnostic study was conducted at a single US academic medical center and included consecutive patients aged 18 to 89 years with adnexal masses that were managed surgically or conservatively between January 2017 and October 2022. Exposure: Evaluation of adnexal lesions using the Simple Rules, ADNEX, and O-RADS. Main Outcomes and Measures: The main outcome was diagnostic performance, including area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, specificity, positive and negative predictive values, and positive and negative likelihood ratios. Surgery or follow-up were reference standards. Secondary analyses evaluated the models' performances stratified by menopause status and race. Results: The cohort included 511 female patients with a 15.9% malignant tumor prevalence (81 patients). Mean (SD) ages of patients with benign and malignant adnexal lesions were 44.1 (14.4) and 52.5 (15.2) years, respectively, and 200 (39.1%) were postmenopausal. In the ROC analysis, the AUCs for discriminative performance of the ADNEX and O-RADS models were 0.96 (95% CI, 0.93-0.98) and 0.92 (95% CI, 0.90-0.95), respectively. After converting the ADNEX continuous individualized risk into the discrete ordinal categories of O-RADS, the ADNEX performance was reduced to an AUC of 0.93 (95% CI, 0.90-0.96), which was similar to that for O-RADS. The Simple Rules combined with expert reevaluation had 93.8% sensitivity (95% CI, 86.2%-98.0%) and 91.9% specificity (95% CI, 88.9%-94.3%), and the Simple Rules combined with malignant classification had 93.8% sensitivity (95% CI, 86.2%-98.0%) and 88.1% specificity (95% CI, 84.7%-91.0%). At a 10% risk threshold, ADNEX had 91.4% sensitivity (95% CI, 83.0%-96.5%) and 86.3% specificity (95% CI, 82.7%-89.4%) and O-RADS had 98.8% sensitivity (95% CI, 93.3%-100%) and 74.4% specificity (95% CI, 70.0%-78.5%). The specificities of all models were significantly lower in the postmenopausal group. Subgroup analysis revealed high performances independent of race. Conclusions and Relevance: In this diagnostic study of a US cohort, the Simple Rules, ADNEX, and O-RADS models performed well in differentiating between benign and malignant adnexal lesions; this outcome has been previously reported primarily in European populations. Risk stratification models can lead to more accurate and consistent evaluations of adnexal masses, especially when used by nonexpert clinicians, and may reduce unnecessary surgeries.

Glucose-Regulated Protein 78 Is a Potential Serum and Imaging Marker for Early Detection of Ovarian Cancer.

BACKGROUND: Understanding malignant transformation associated with ovarian cancer (OVCA) is important to establish early detection tests. This study examined whether expression of glucose-regulated protein 78 (GRP78, marker of cellular stress) increases during OVCA development, and whether GRP78 can be detected by targeted-transvaginal ultrasound (TVUS) imaging. METHODS: Normal ovaries (n = 10), benign (n = 10) and malignant ovarian tumors at early (n = 8) and late stages (n = 16), hens with and without ovarian tumors at early and late stages (n = 10, each) were examined for GRP78 expression during OVCA development by immunohistochemistry, immunoblotting, gene expression and immunoassay. Feasibility of GRP78-targeted TVUS imaging in detecting early OVCA was examined. RESULTS: Compared with normal ovaries and benign tumors, intensity of GRP78 expression was higher (p < 0.0001) in OVCA patients. Compared with normal (9007.76 ± 816.54 pg/mL), serum GRP78 levels were significantly higher (p < 0.05) in patients with early (12,730.59 ± 817.35 pg/mL) and late-stage OVCA (13,930.12 ± 202.35) (p < 0.01). Compared with normal (222.62 ± 181.69 pg/mL), serum GRP78 levels increased (p < 0.05) in hens with early (590.19 ± 198.18 pg/mL) and late-stage OVCA (1261.38 ± 372.85) (p < 0.01). Compared with non-targeted, GRP78-targeted imaging enhanced signal intensity of TVUS (p < 0.0001). CONCLUSIONS: Tissue and serum levels of GRP78 increase in association with OVCA. GRP78 offers a potential serum and imaging marker for early OVCA detection.

Ovarian Masses: The Value of Acoustic Shadowing on Ultrasound Examination.

Adnexal lesions are a common finding in women and pose a clinical challenge since ovarian cancer is a highly lethal disease. However, most adnexal masses are benign, benefiting from a more conservative approach. In preoperative assessment, transvaginal ultrasound plays a key role in evaluating morphologic features that correlate with the risk of malignancy. The acoustic shadow is the loss of echo behind sound-absorbing components, such as calcifications or fibrous tissues, which are predominantly found in benign lesions. However, recognizing the acoustic shadow is a difficult skill to master, and its usefulness may be underappreciated.

World Federation for Ultrasound in Medicine Review Paper: Incidental Findings during Obstetrical Ultrasound.

Although the prevalence of incidental findings revealed during an obstetric ultrasound examination is low, the findings may include adnexal and cervical masses, uterine or urinary congenital malformations, free fluid in the pouch of Douglas or tortuous vessels (varices). Adnexal masses are the most common finding and vary in imaging characteristics. They are mainly unilateral, cystic masses with a low risk of malignancy that are treated conservatively. The International Ovarian Tumor Analysis scoring models may be helpful in differentiating benign from malignant masses. For those masses >5 cm, follow-up is recommended, and resection could be considered to avoid risk of torsion, rupture and hemorrhage, which may compromise pregnancy outcome. Uterine masses such as fibroids are commonly diagnosed early in the first trimester and should be followed up during pregnancy to evaluate any changes. Transabdominal and transvaginal ultrasound is the first-line test for the diagnosis of such incidentalomas; however, magnetic resonance ultrasound may have a useful role in excluding malignancy potential. As a result of their low frequency and the lack of good evidence, there are no specific guidelines on the management of incidentalomas detected at obstetric scans. Their management should follow the related general guidelines for ovarian, cervical and uterine masses, with individualized management depending on the pregnancy status.

Ocular Ultrasound: Review of Bioeffects and Safety, Including Fetal and Point of Care Perspective: Review of Bioeffects and Safety, Including Fetal and Point-of-Care Perspective.

Ocular ultrasound is an invaluable tool for the evaluation of the eye and orbit. However, the eye and orbit are potentially sensitive to the thermal and mechanical effects of ultrasound. When performing B-mode imaging, dedicated ocular settings should be used. If these settings are not available, limiting the acoustic output to Food and Drug Administration (FDA) recommended maximum levels is strongly advised. Especially important is the acoustic output in spectral (pulsed) and color Doppler modes, which can exceed the FDA's maximum recommended levels for the eye. Adjusting settings to decrease acoustic output and limiting the time of the examination should be done when performing a Doppler examination. The acoustic output of shear wave elastography is significantly higher than FDA guidelines for the eye and should be considered experimental.

Ultrasound for Aesthetic Applications: A Review of Biophysical Mechanisms and Safety.

Aesthetic ultrasound is used for fat reduction and to improve skin appearance. In this review, the fundamental mechanisms by which ultrasound can alter tissue are outlined. The technologies that are commercially available or under development are discussed. Finally, recommendations are made for safe and effective use of aesthetic ultrasound.

Managing Incidental Findings Reported by Medical, Sonography and Other Students Performing Educational Ultrasound Examinations.

The evolution of ultrasound imaging into a key technology for diagnostic practice has resulted in its incorporation into the education of medical students worldwide. Although the introduction of ultrasound into medical schools' curricula is relatively recent, training of sonographers and other ultrasound users is mature. Ultrasound is being used in a variety of learning environments and clinical settings, from courses in anatomy and physiology to clinical rotations where medical and other students may scan healthy volunteers or patients, sometimes with little to no supervision. Educators may be apprehensive about a perceived high likelihood that students will encounter unexpected findings during these sessions, which could distress the patient or ultrasound model as well as the student, and result in problems that would be more pronounced if such incidental findings are complex. Policies are needed to address how to manage incidental ultrasound findings that are identified during educational activities. This article summarizes the background and provides a framework for establishing and implementing a well-designed and thoughtful approach for dealing with incidental findings observed in volunteer subjects by medical students during training courses in ultrasound diagnostic scanning. Subject confidentiality should be respected, and review of incidental findings should be transparent without provoking unnecessary anxiety. It is the responsibility of the instructor or supervisor to ensure adequate clinical follow-up if indicated.

Safety Aspects of Perinatal Ultrasound.

Ultrasound safety is of particular importance in fetal and neonatal scanning. Fetal tissues are vulnerable and often still developing, the scanning depth may be low, and potential biological effects have been insufficiently investigated. On the other hand, the clinical benefit may be considerable. The perinatal period is probably less vulnerable than the first and second trimesters of pregnancy, and ultrasound is often a safer alternative to other diagnostic imaging modalities. Here we present step-by-step procedures for obtaining clinically relevant images while maintaining ultrasound safety. We briefly discuss the current status of the field of ultrasound safety, with special attention to the safety of novel modalities, safety considerations when ultrasound is employed for research and education, and ultrasound of particularly vulnerable tissues, such as the neonatal lung. This CME is prepared by ECMUS, the safety committee of EFSUMB, with contributions from OB/GYN clinicians with a special interest in ultrasound safety.

Incidence of malignant transformation in the oviductal fimbria in laying hens, a preclinical model of spontaneous ovarian cancer.

Ovarian high grade serous carcinoma (HGSC) is a lethal form of ovarian cancer (OVCA). In most cases it is detected at late stages as the symptoms are non-specific during early stages. Emerging information suggests that the oviductal fimbria is a site of origin of ovarian HGSC. Currently available tests cannot detect ovarian HGSC at early stage. The lack of a preclinical model with oviductal fimbria that develops spontaneous ovarian HGSC is a significant barrier to developing an early detection test for this disease. The goal of this study was to examine if the oviductal fimbria in hens is a site of origin of HGSC and whether it expresses several putative markers expressed in ovarian HGSC in patients. A total of 135 laying hens (4 years old) were selected from a flock using transvaginal ultrasound (TVUS) imaging, followed by euthanasia and gross examination for the presence of solid masses and ascites. Histological types of carcinomas were determined by hematoxylin and eosin staining. Expression of WT-1, mutant p53, CA-125, PAX2 and Ki67 in normal or malignant fimbriae or ovaries were examined using immunohistochemistry, immunoblotting and gene expression assays. This study detected tumors in oviductal fimbriae in hens and routine staining revealed ovarian HGSC-like microscopic features in these tumors. These tumors showed similarities to ovarian HGSC in patients in expressing several markers. Compared with normal fimbriae, intensities of expression of WT-1, mutant p53, CA-125, and Ki67 were significantly (P<0.05) higher in fimbrial tumors. In contrast, expression of PAX2 decreased gradually as the tumor progressed to late stages. The patterns of expression of these markers were similar to those in ovarian HGSC patients. Thus, tumors of the oviductal fimbria in hens may offer a preclinical model to study different aspects of spontaneous ovarian HGSC in women including its early detection.

Use of the angiogenic biomarker profile to risk stratify patients with fetal growth restriction.

BACKGROUND: Novel angiogenic biomarker profiles have demonstrated emerging evidence for predicting preeclampsia onset, severity, and adverse outcomes. Limited data exist in screening patients with fetal growth restriction for preeclampsia development using angiogenic biomarkers. OBJECTIVE: The objective of this study was to risk stratify patients with fetal growth restriction using a soluble fms-like tyrosine kinase-1 to placental growth factor ratio. Previously published cutoff of 38 was used to predict preeclampsia development and severity as well as adverse maternal or neonatal outcomes within a 2-week time period. STUDY DESIGN: This was a prospective observational cohort study performed in a single tertiary hospital. Patients with a singleton fetal growth restriction pregnancy between 24 and 37 weeks' gestation were evaluated using serial 2-week encounters from the time of enrollment to delivery. Pregnancies with proven genetic or infectious etiology of fetal growth restriction or congenital anomalies were excluded. Ultrasound growth and Doppler measurements were obtained at the start of every encounter with routine preeclampsia laboratory tests and blood pressure checks when clinically indicated. Maternal serum was collected for all serial encounters and measured for soluble fms-like tyrosine kinase-1 and placental growth factor after delivery in a double-blinded fashion. Maternal charts were reviewed for baseline demographic characteristics, pregnancy diagnoses and outcomes, and neonatal outcomes. RESULTS: A total of 45 patients were enrolled for a total of 77 encounters, with the median (quartile 1, quartile 3) gestational age of the study enrolled at 31.43 (28.14-33.57) weeks. Patients were divided into low-risk (ratio of <38) and high-risk (ratio of ≥38) groups. Baseline characteristics of patients did not show any marked differences, including preeclampsia labs or ultrasound parameters, between the 2 groups. Systolic and diastolic blood pressures upon enrollment were statistically elevated when soluble fms-like tyrosine kinase-1 to placental growth factor ratio was ≥38 (P=.02 and P=.01, respectively). Compared to patients with a low ratio, patients with a high ratio had a greater proportion of preeclampsia diagnosis, higher rates of preterm delivery under 34 and 37 weeks gestation, smaller neonatal birthweight, and a shorter time to delivery from testing to delivery. CONCLUSION: Among patients with fetal growth restriction, the soluble fms-like tyrosine kinase-1 to placental growth factor ratio may serve as a potential biomarker for identifying at risk patients for developing preeclampsia and subsequently preterm delivery.

Obstetric ultrasound: where are we and where are we going?

Diagnostic ultrasound (DUS) is, arguably, the most common technique used in obstetrical practice. From A mode, first described by Ian Donald for gynecology in the late 1950s, to B mode in the 1970s, real-time and gray-scale in the early 1980s, Doppler a little later, sophisticated color Doppler in the 1990s and three dimensional/four-dimensional ultrasound in the 2000s, DUS has not ceased to be closely associated with the practice of obstetrics. The latest innovation is the use of artificial intelligence which will, undoubtedly, take an increasing role in all aspects of our lives, including medicine and, specifically, obstetric ultrasound. In addition, in the future, new visualization methods may be developed, training methods expanded, and workflow and ergonomics improved.

Diagnostic Ultrasound Safety Review for Point-of-Care Ultrasound Practitioners.

Potential ultrasound exposure safety issues are reviewed, with guidance for prudent use of point-of-care ultrasound (POCUS). Safety assurance begins with the training of POCUS practitioners in the generation and interpretation of diagnostically valid and clinically relevant images. Sonographers themselves should minimize patient exposure in accordance with the as-low-as-reasonably-achievable principle, particularly for the safety of the eye, lung, and fetus. This practice entails the reduction of output indices or the exposure duration, consistent with the acquisition of diagnostically definitive images. Informed adoption of POCUS worldwide promises a reduction of ionizing radiation risks, enhanced cost-effectiveness, and prompt diagnoses for optimal patient care.

Medical Ultrasound Disinfection and Hygiene Practices: WFUMB Global Survey Results.

As ultrasound technology rapidly evolves and is used more frequently in every area of medical diagnosis and treatment, it may be overlooked as a potential vector in the transmission of a health care-associated infection. A survey on disinfection and hygiene practice in medical ultrasound was disseminated via the World Federation for Ultrasound in Medicine and Biology (WFUMB) to its six member federations and associated ultrasound societies globally. One thousand twenty-nine responses were obtained across a broad range of ultrasound practitioners. A total of 76% of respondents used transducer covers every time to scan open wounds and 71% when blood and bodily fluids were present or for an interventional procedure. Approved high-level disinfectants are not always used, even when blood comes into contact with the transducer or after endocavity scans. Alcohol-based wipes were used by many respondents to clean both external transducers and endocavity transducers. Open-ended responses indicated that a large caseload hindered the time required for cleaning and that access to clear guidelines would be beneficial. Global survey results indicate that some users do not comply with disinfection practice, and there is a gap in knowledge on basic infection prevention and control education within the ultrasound unit. As the infectious status of a patient is not often disclosed prior to an ultrasound examination, training in suitable protocols for the cleaning and disinfection of ultrasound equipment is imperative to mitigate the risk of potential infection.

Early 2D/3D ultrasound diagnosis of pleural effusion in fetuses with Turner syndrome.

Most guidelines on ultrasound examinations during pregnancy do not recommend routine early pregnancy scan in uncomplicated and asymptomatic pregnancies (ie, before 10 weeks based on last menstrual period). There is, however, a growing patient's expectation to have an early scan to confirm dating and verify the pregnancy is intrauterine and viable. We present three well-documented cases of patients who had an early (7-8 weeks) dating transvaginal scan revealing pleural effusion in the embryo. In all cases cytogenetic analysis confirmed monosomy for the X chromosome, consistent with a clinical diagnosis of Turner syndrome.