Artificial intelligence as a teaching tool for gynaecological ultrasound: A systematic search and scoping review.

Purpose: The aim of this study was to investigate the current application of artificial intelligence (AI) tools in the teaching of ultrasound skills as they pertain to gynaecological ultrasound. Methods: A scoping review was performed. Eight databases (MEDLINE, EMBASE, EMCARE, CINAHL, Scopus, Web of Science, IEEE Xplore and ACM digital library) were searched in December 2022 using predefined keywords. All types of publications were eligible for inclusion so long as they reported the use of an AI tool, included reference to or discussion of teaching or the improvement of ultrasound skills and pertained to gynaecological ultrasound. Conference abstracts and non-English language papers which could not be adequately translated into English were excluded. Results: The initial database search returned 481 articles. After screening against our inclusion and exclusion criteria, two were deemed to meet the inclusion criteria. Neither of the articles included reported original research (one systematic review and one review article). Neither of the included articles explicitly provided details of specific tools developed for the teaching of ultrasound skills for gynaecological imaging but highlighted similar applications within the field of obstetrics which could potentially be expanded. Conclusion: Artificial intelligence can potentially assist in the training of sonographers and other ultrasound operators, including in the field of gynaecological ultrasound. This scoping review revealed however that to date, no original research has been published reporting the use or development of such a tool specifically for gynaecological ultrasound.

Noninvasive diagnostic imaging for endometriosis part 1: a systematic review of recent developments in ultrasound, combination imaging, and artificial intelligence.

Endometriosis affects 1 in 9 women and those assigned female at birth. However, it takes 6.4 years to diagnose using the conventional standard of laparoscopy. Noninvasive imaging enables a timelier diagnosis, reducing diagnostic delay as well as the risk and expense of surgery. This review updates the exponentially increasing literature exploring the diagnostic value of endometriosis specialist transvaginal ultrasound (eTVUS), combinations of eTVUS and specialist magnetic resonance imaging, and artificial intelligence. Concentrating on literature that emerged after the publication of the IDEA consensus in 2016, we identified 6192 publications and reviewed 49 studies focused on diagnosing endometriosis using emerging imaging techniques. The diagnostic performance of eTVUS continues to improve but there are still limitations. eTVUS reliably detects ovarian endometriomas, shows high specificity for deep endometriosis and should be considered diagnostic. However, a negative scan cannot preclude endometriosis as eTVUS shows moderate sensitivity scores for deep endometriosis, with the sonographic evaluation of superficial endometriosis still in its infancy. The fast-growing area of artificial intelligence in endometriosis detection is still evolving, but shows great promise, particularly in the area of combined multimodal techniques. We finalize our commentary by exploring the implications of practice change for surgeons, sonographers, radiologists, and fertility specialists. Direct benefits for endometriosis patients include reduced diagnostic delay, better access to targeted therapeutics, higher quality operative procedures, and improved fertility treatment plans.

Noninvasive diagnostic imaging for endometriosis part 2: a systematic review of recent developments in magnetic resonance imaging, nuclear medicine and computed tomography.

Endometriosis affects 1 in 9 women, taking 6.4 years to diagnose using conventional laparoscopy. Non-invasive imaging enables timelier diagnosis, reducing diagnostic delay, risk and expense of surgery. This review updates literature exploring the diagnostic value of specialist endometriosis magnetic resonance imaging (eMRI), nuclear medicine (NM) and computed tomography (CT). Searching after the 2016 IDEA consensus, 6192 publications were identified, with 27 studies focused on imaging for endometriosis. eMRI was the subject of 14 papers, NM and CT, 11, and artificial intelligence (AI) utilizing eMRI, 2. eMRI papers describe diagnostic accuracy for endometriosis, methodologies, and innovations. Advantages of eMRI include its: ability to diagnose endometriosis in those unable to tolerate transvaginal endometriosis ultrasound (eTVUS); a panoramic pelvic view, easy translation to surgical fields; identification of hyperintense iron in endometriotic lesions; and ability to identify super-pelvic lesions. Sequence standardization means eMRI is less operator-dependent than eTVUS, but higher costs limit its role to a secondary diagnostic modality. eMRI for deep and ovarian endometriosis has sensitivities of 91-93.5% and specificities of 86-87.5% making it reliable for surgical mapping and diagnosis. Superficial lesions too small for detection in larger capture sequences, means a negative eMRI doesn't exclude endometriosis. Combined with thin sequence capture and improved reader expertise, eMRI is poised for rapid adoption into clinical practice. NM labeling is diagnostically limited in absence of suitable unique marker for endometrial-like tissue. CT studies expose the reproductively aged to radiation. AI diagnostic tools, combining independent eMRI and eTVUS endometriosis markers, may result in powerful capability. Broader eMRI use, will optimize standards and protocols. Reporting systems correlating to surgical anatomy will facilitate interdisciplinary preoperative dialogues. eMRI endometriosis diagnosis should reduce repeat surgeries with mental and physical health benefits for patients. There is potential for early eMRI diagnoses to prevent chronic pain syndromes and protect fertility outcomes.

Australasian sonographers' knowledge, awareness, and attitudes towards the international evidence-based guidelines for the diagnosis of polycystic ovarian syndrome.

Introduction/Purpose: Many guidelines have been utilised to diagnose polycystic ovarian syndrome (PCOS). The most recent are the International Evidence Based Guideline for the Assessment and Management of Polycystic Ovary Syndrome 2018 (2018 IEBG). This study aimed to assess the awareness, knowledge, and attitudes of Australasian sonographers' regarding these guidelines. Methods: An online cross-sectional survey was disseminated to sonographers. Qualitative and quantitative questions were asked around awareness, knowledge, and attitudes towards the 2018 IEBG. Statistical and thematic analyses of the results were performed. Results: Ninety responses were included in the final analysis. Fifty-two percent (52.2%) of participants were aware of the 2018 IEBG but only 31.1% used it in their workplaces. Fifty-eight percent (57.9%) of participants correctly identified the sonographic features that suggest PCOS, and 3.5% correctly identified all minimum recommended inclusions for reporting a gynaecological ultrasound for PCOS. Prior to being supplied the 2018 IEBG, 15.8% of participants correctly answered clinical scenario-based knowledge questions, which increased to 29.4% correctly after being supplied the guideline; however, this difference was not statistically significant. There were no statistically significant associations between demographics and knowledge of the 2018 IEBG. Discussion: Several areas of confusion surrounding wording and interpretation of the 2018 IEBG were highlighted. Consideration should be given to barriers of implementation and strategies to overcome these. Conclusion: More education surrounding the sonographic diagnosis of PCOS and the 2018 IEBG is needed. Scanning protocols used amongst sonographers varied, suggesting that inconsistency in sonographic diagnosis may exist. Future reviews of the 2018 IEBG should focus on reducing ambiguity in wording, which may be responsible for some of the varied interpretation of these guidelines.

What is the accuracy of transvaginal ultrasound for endometriosis mapping prior to surgery when performed by a sonographer within an outpatient women's imaging centre?

INTRODUCTION: This study aimed to assess the accuracy of transvaginal ultrasound (TVUS) for the mapping of endometriosis before surgery when performed by sonographers in an outpatient women's imaging centre. METHODS: A prospective longitudinal cohort study was performed. The study group comprised of 201 women who underwent a comprehensive TVUS assessment, performed by a sonographer. Laparoscopy was performed as the reference standard. Complete TVUS and surgical data were available for 53 women who were included in the final analysis. RESULTS: Endometriosis was confirmed at a surgery in 50/53 (94.3%) participants, with 25/53 (47.2%) having deep endometriosis (DE) nodules and/or endometriomas present. TVUS for mapping of DE had an overall sensitivity of 84.0%, specificity of 89.3%, PPV of 87.5%, NPV of 86.2%, LR+ of 7.85, LR- of 0.18, and accuracy of 86.8% (P < 0.001). Ovarian immobility had poor sensitivity for detecting localised superficial endometriosis, DE, adhesions, and/or endometriomas (Left = 61.9% and right = 13.3%) but high specificities (left = 87.5% and right = 94.7%). Site-specific tenderness had low sensitivities and moderate specificities for the same. All soft markers of endometriosis failed to reach statistical significance except for left ovarian immobility (P = <0.001). CONCLUSION: Sonographers well experienced in obstetric and gynaecological imaging, working in an outpatient women's imaging setting can accurately map DE; however, the performance of soft markers for detection of SE was poor.

How long does a transvaginal ultrasound examination for endometriosis take in comparison to a routine transvaginal ultrasound examination?

INTRODUCTION: This study aimed to determine the additional time needed to perform an endometriosis transvaginal ultrasound (eTVUS) compared to routine transvaginal ultrasound (rTVUS). METHODS: A retrospective case-control study was performed. The study group included 199 eTVUS performed between September 2019 and September 2020. The control group comprised 105 consecutive rTVUS studies performed in the same time period. The time stamps on the ultrasound images of all cases in both groups were reviewed to determine the time taken to perform each study. Mean, median, minimum and maximum scan times for both groups were calculated as was percentage difference between scan times. A two-tailed, unpaired t-test of the normalised data and a Mann-Whitney U test assessing time difference of scans between two groups were performed with P value <0.05 considered statistically significant. RESULTS: Performing eTVUS took significantly longer than rTVUS with increases in the mean (8.4 vs 13.8 min, 64%), median (7 vs 12 min, 71%), minimum (4 vs 7 min, 75%) and maximum (19 vs 42 min, 121%) scan times. The Mann-Whitney U test indicated a statistically significant difference in the median scan times (5.0, CI 4.0-6.0), P < 0.001. An independent t-test of the normalised data revealed a significantly larger mean scan time for eTVUS than rTVUS, Mean = 9.05 95%CI [13.17-4.94], t(302) = 4.327, P < 0.001. R 2 = 0.583. CONCLUSION: Endometriosis transvaginal ultrasound added an average 5.4 min to rTVUS, which is statistically significant. For ultrasound departments wanting to offer this technique, doubling the scan time allocated to perform a transvaginal ultrasound (TVUS) is suggested.

Current Status of Transvaginal Ultrasound Accuracy in the Diagnosis of Deep Infiltrating Endometriosis Before Surgery: A Systematic Review of the Literature.

Endometriosis is a common gynecologic condition affecting as many as 1 per 10 women. Transvaginal ultrasound (TVUS) has become a frontline tool in the diagnosis of deep infiltrating endometriosis (DIE) before surgery. The primary aim of this review was to determine the accuracy of TVUS for DIE. The secondary aim was to determine accuracy specifically when a sonographer performed the TVUS examination. A systematic review was performed, searching literature by following a population, intervention, comparator, and outcome outline. MEDLINE, Embase, Emcare, and Google Scholar were searched in July 2018 and in November 2019. Including "sonographer" in the search terms yielded no results, so our terms were expanded. Two hundred and four articles were returned from the searches, and 35 were ultimately included in the final review. Analysis of the returned articles revealed the TVUS is a valuable diagnostic tool for DIE before surgery. Sensitivities ranged from 78.5% to 85.3%, specificities from 46.1% to 92.5%, and accuracies from 75.7% to 97%. Most authors reported site-specific sensitivities and specificities, which varied greatly between locations. Site-specific sensitivities ranged from 10% to 88.9% (uterosacral ligaments), 20% to 100% (bladder), 33.3% to 98.1% (rectosigmoid colon), and 31% to 98.7% (pouch of Douglas). Site-specific specificities ranged from 75% to 99.6% (uterosacral ligaments), 96.4% to 100% (bladder), 86% to 100% (rectosigmoid colon), and 90% to 100% (pouch of Douglas). Transvaginal ultrasound is an accurate tool in the diagnosis of DIE; however, limited data exist as to whether this technique is accurate when performed by sonographers. More evidence surrounding the reliability between operators is also needed.

How to perform a gynaecological ultrasound in the paediatric or adolescent patient.

Ultrasound is the first-line imaging modality in the assessment of the female reproductive system in all age groups. However, the paediatric and adolescent subset of patients present a particular set of challenges. These include technical challenges that come from largely being limited by transabdominal imaging as well as dealing with the often-complex social issues around the sexual health of adolescents. In addition, this group of patients has a unique set of pathologies that are not seen in the adult population and conversely, common gynaecological conditions affecting adults such as endometriosis and polycystic ovarian syndrome are difficult to diagnose in adolescents. Therefore, we propose that paediatric and adolescent gynaecological ultrasound requires a different approach. This paper summarises the differences in technique, common pathologies and touches on some of the relevant social issues that are unique to this population of patients.

Sonographic demonstration of stomach pathology: Reviewing the cases.

Introduction: The stomach can be the source of complaints for many patients attending for upper abdominal ultrasound. It is not routinely imaged as part of most upper abdominal ultrasound protocols, with sonographers and sonologists alike commonly muttering the line; "I can't see the stomach on ultrasound". However, this is incorrect, as the gastric antrum can almost always be visualised sonographically. Discussion: It is possible to detect a range of pathologies affecting the stomach sonographically, from common, largely tolerable conditions such as hiatus hernias through to life-threatening neoplasms. Conclusion: The stomach can easily be assessed during routine abdominal ultrasound providing the sonographer has knowledge of stomach anatomy, normal ultrasound appearances and limitations to its visualisation. While endoscopy is the gold standard for investigation of the stomach and upper gastrointestinal tract, many patients will initially present for abdominal ultrasound due to its easy, non-invasive nature, ready availability and low cost. For patients with mild abdominal symptoms, a normal abdominal ultrasound may be the extent of their imaging investigations meaning stomach pathologies may go undiagnosed.