Segmentation of ovarian cyst in ultrasound images using AdaResU-net with optimization algorithm and deep learning model.

Ovarian cysts pose significant health risks including torsion, infertility, and cancer, necessitating rapid and accurate diagnosis. Ultrasonography is commonly employed for screening, yet its effectiveness is hindered by challenges like weak contrast, speckle noise, and hazy boundaries in images. This study proposes an adaptive deep learning-based segmentation technique using a database of ovarian ultrasound cyst images. A Guided Trilateral Filter (GTF) is applied for noise reduction in pre-processing. Segmentation utilizes an Adaptive Convolutional Neural Network (AdaResU-net) for precise cyst size identification and benign/malignant classification, optimized via the Wild Horse Optimization (WHO) algorithm. Objective functions Dice Loss Coefficient and Weighted Cross-Entropy are optimized to enhance segmentation accuracy. Classification of cyst types is performed using a Pyramidal Dilated Convolutional (PDC) network. The method achieves a segmentation accuracy of 98.87%, surpassing existing techniques, thereby promising improved diagnostic accuracy and patient care outcomes.

Retrospective Review of Management of Antenatally Diagnosed Ovarian Cysts at the Hospital for Sick Children.

INTRODUCTION: Postnatal management of antenatally diagnosed ovarian cysts is not well-defined. The clinical course, management, and outcomes of patients with antenatally diagnosed ovarian cysts were reviewed. METHODS: Infants <1 year of age with antenatally diagnosed ovarian cyst managed at The Hospital for Sick Children between January 2017 and December 2021 were included. Patient charts were reviewed for postnatal ultrasound (US) images, management, clinical course and complications. Mixed linear regression analysis was used to model the change in cyst size over time. RESULTS: In total, 52 patients were included and 10 patients had no cyst identified at their first postnatal US. Of the remaining cases, 36% were simple/physiologic and 64% had complex features. Two underwent percutaneous aspiration while 40 patients were managed expectantly with most cysts (62%) resolving. The rate of resolution was significantly higher and faster for simple compared to complex cysts (84% versus 52%, p < 0.05). Cysts that persisted at the end of the study period (n = 14) had all decreased in size, with a rate of resolution similar to resolved cysts. Only one patient managed expectantly required urgent laparoscopy for salpingoophorectomy. CONCLUSION: Antenatally diagnosed ovarian cysts exhibit high rates of resolution with expectant management, supporting the safety and efficacy for expectant management for these patients. LEVEL OF EVIDENCE: III.

Endometrioma surgery: Hit with your best shot (But know when to stop).

Ovarian endometriomas (OEs) are commonly detected by ultrasound in individuals affected by endometriosis. Although surgery was widely regarded in the past as the gold standard for treating OEs, especially in the case of large cysts, the surgical management of OEs remains debated. Firstly, OEs often represent the "tip of the iceberg" of underlying deep endometriosis, and this should be considered when treating OEs to ameliorate patients' pain for focusing on the surgical objectives and providing better patient counseling. In the context of fertility care, OEs may have a detrimental effect on ovarian reserve through structural alterations, inflammatory responses, and oocyte reserve depletion. Conversely, the surgical approach may exacerbate the decline within the same ovarian reserve. While evidence suggests no improvement in in-vitro fertilization (IVF) outcomes following OE surgery, further studies are needed to understand the impact of OE surgery on spontaneous fertility. Therefore, optimal management of OEs is based on individual patient and fertility characteristics such as the woman's age, length of infertility, results of ovarian reserve tests, and surgical background. Among the available surgical approaches, cystectomy appears advantageous in terms of reduced recurrence rates, and traditionally, bipolar coagulation has been used to achieve hemostasis following this approach. Driven by concerns about the negative impact on ovarian reserve, alternative methods to obtain hemostasis include suturing the cyst bed, and novel methodologies such as CO2 laser and plasma energy have emerged as viable surgical options for OEs. In instances where sonographic OE features are non-reassuring, surgery should be contemplated to obtain tissue for histological diagnosis and rule out eventual ovarian malignancy.

Discriminative diagnosis of ovarian endometriosis cysts and benign mucinous cystadenomas based on the ConvNeXt algorithm.

PURPOSE: The objective of this study was to develop a deep learning model, using the ConvNeXt algorithm, that can effectively differentiate between ovarian endometriosis cysts (OEC) and benign mucinous cystadenomas (MC) by analyzing ultrasound images. The performance of the model in the diagnostic differentiation of these two conditions was also evaluated. METHODS: A retrospective analysis was conducted on OEC and MC patients who had sought medical attention at the Fourth Affiliated Hospital of Harbin Medical University between August 2018 and May 2023. The diagnosis was established based on postoperative pathology or the characteristics of aspirated fluid guided by ultrasound, serving as the gold standard. Ultrasound images were collected and subjected to screening and preprocessing procedures. The data set was randomly divided into training, validation, and testing sets in a ratio of 5:3:2. Transfer learning was utilized to determine the initial weights of the ConvNeXt deep learning algorithm, which were further adjusted by retraining the algorithm using the training and validation ultrasound images to establish a new deep learning model. The weights that yielded the highest accuracy were selected to evaluate the diagnostic performance of the model using the validation set. Receiver operating characteristic (ROC) curves were generated, and the area under the curve (AUC) was calculated. Additionally, sensitivity, specificity, positive predictive value, negative predictive value, positive likelihood ratio, negative likelihood ratio, and odds ratio were calculated. Decision curve analysis (DCA) curves were plotted. RESULTS: The study included 786 ultrasound images from 184 patients diagnosed with either OEC or MC. The deep learning model achieved an AUC of 0.90 (95 % CI: 0.85-0.95) in accurately distinguishing between the two conditions, with a sensitivity of 90 % (95 % CI: 84 %-95 %), specificity of 90 % (95 % CI: 77 %-97 %), a positive predictive value of 96 % (95 % CI: 91 %-99 %), a negative predictive value of 77 % (95 % CI: 63 %-88 %), a positive likelihood ratio of 9.27 (95 % CI: 3.65-23.56), and a negative likelihood ratio of 0.11 (95 % CI: 0.06-0.19). The DCA curve demonstrated the practical clinical utility of the model. CONCLUSIONS: The deep learning model developed using the ConvNeXt algorithm exhibits high accuracy (90 %) in distinguishing between OEC and MC. This model demonstrates excellent diagnostic performance and clinical utility, providing a novel approach for the clinical differentiation of these two conditions.

Opting for conservative management over surgery for neonatal ovarian cysts.

OBJECTIVE: To explore the suitability of conservative management for neonatal ovarian cysts in newborns. METHODS: A retrospective cohort study was conducted, involving infants diagnosed with neonatal abdominal/pelvic cysts at two separate medical institutions from January 2015 through July 2021. Data collection included clinical characteristics, imaging results, pathological findings, and postnatal outcomes. Statistical analyses were performed using the Student's t-test, Mann-Whitney U-test, and receiver operating characteristic (ROC) curve. RESULTS: In total, 34 cases of neonatal abdominal/pelvic cystic masses were detected, with mean birth weight of 3401 ± 515 g. Of these, 22 patients underwent postnatal cystectomy/oophorectomy. Pathological assessments revealed 16 uncomplicated cysts, 5 complex cysts, and 1 ovarian cyst with torsion complications. Notably, the cysts' dimensions at the time of surgical intervention had significantly decreased from the initial measurements (p = 0.015). The ROC curve analysis presented an area under the curve of 0.642, indicating moderate accuracy in employing cyst size as a discriminative feature to differentiate complex from simple ovarian cysts. Additionally, a short-term follow-up of nonsurgical cases indicated a 100% resolution rate by 24 months of age (n = 9). CONCLUSION: Given their predominantly benign nature, the majority of neonatal ovarian cysts seem to be amenable to conservative management. This approach remains justified for larger cysts with minimal torsion risk, as well as considering the observed reduction in cyst size at birth, which further supports the case against surgical intervention.

A giant ovarian cyst torsion: Case report.

INTRODUCTION: Adnexal torsion (AT) is one of a gynecological condition characterized by an acute abdomen. Clinically, a giant ovarian cyst torsion with a diameter of 30 cm is rare. Therefore, an accurate and timely diagnosis and treatment are important. PATIENT CONCERNS: A 25-year-old unmarried female, presented to the emergency department with intermittent abdominal cramps after a sudden change in position. Considering her symptoms and examination, ultrasound, and magnetic resonance imaging (MRI) results, ovarian cyst torsion was suspected. DIAGNOSIS: Giant ovarian cyst torsion. INTERVENTIONS: Surgical intervention with exploratory laparotomy was performed immediately. OUTCOMES: Intraoperatively, we found a 30-cm left ovarian cyst with a clear root. The left fallopian tube, infundibulopelvic ligament, and ovarian ligament were twisted 900 degrees. Finally, the pathological report revealed mucinous cystadenoma. CONCLUSION: Giant ovarian cyst torsion with a diameter of 30 cm is rare. Considering her symptoms and examination, ultrasound, and MRI results, ovarian cyst torsion was suspected. The patient was successfully treated using emergency surgery.

Splenic torsion mistaken for an ovarian cyst: a case report.

BACKGROUND: Wandering spleen (or ectopic spleen) refers to a hyper-mobile spleen resulting in its displacement from the normal anatomical position to usually in the lower abdominal or pelvic cavity. While ultrasound is often the first radiological modality used, Computed Tomography (CT) shows a clear picture and aides to reach a diagnosis. In circumstances where appropriate imaging modalities are not available, or the operator is inexperienced, diagnosis of wandering spleen can be missed. CASE PRESENTATION: A 22-nulligravida unmarried Sindhi female had presented to the Emergency Room (ER) with a 5-day history of intermittent severe lower abdominal pain. An ultrasound at a local practitioner had suggested an ovarian cyst. Ultrasound-pelvis and later CT scan at our facility reported an enlarged wandering spleen with torsion of its pedicle and infarction. Exploratory laparotomy with splenectomy was done. An enlarged wandering spleen was found with torsion of the splenic vein and thrombosed arterial supply from omentum wrapped over the mass. The patient developed thrombocytosis post-surgery but otherwise did well and was discharged after 2 days. CONCLUSION: Splenic torsion secondary to a wandering spleen can be challenging to diagnose, especially in resource limited settings where ultrasound might be the only modality available. Timely diagnosis and proper intervention are key to saving the life and the spleen.

Ultrasound study of natural progression of ovarian endometrioma.

OBJECTIVE: To determine the natural progression of ovarian endometrioma in women who are managed expectantly. METHODS: This was a retrospective cohort study of 83 women with evidence of ovarian endometrioma who were managed expectantly between April 2007 and May 2022. The study was conducted in the Department of Women's Health, University College London Hospitals and The Gynecology Ultrasound Centre, London, UK. We searched our ultrasound clinic databases to identify women aged 18 years or older with evidence of ovarian endometrioma who were managed expectantly for ≥ 6 months. All women attended for a minimum of two ultrasound scans performed by a single expert ultrasound operator. In addition to patient demographics, we recorded the number, mean diameter and location of each cyst. The cyst growth rate was expressed as annual change in the mean diameter. RESULTS: A total of 1922 women who attended our gynecology clinic during the study period were found to have evidence of moderate or severe endometriosis on pelvic ultrasound examination. Of those, 83 women had evidence of ovarian endometrioma and were managed expectantly. The median age of women was 39 (range, 26-51) years at the initial visit. Each woman had at least two ultrasound scans performed by a single expert operator at a minimum interval of ≥ 6 months. Of 83 women diagnosed with endometrioma, 50 (60% (95% CI, 49-71%)) had a single cyst and the remainder had multiple cysts. The median number of endometriomas per patient was 1 (range, 1-5) and the median follow-up time was 634 (range, 187-2984) days. A total of 39/83 (47% (95% CI, 36-58%)) women experienced an overall reduction in size of cysts, in 18/83 (22% (95% CI, 13-32%)) the cysts increased in size and in 26/83 (31% (95% CI, 22-42%)) women, no meaningful change in size was observed. The median change in mean cyst diameter per woman during the study period was -2.7 (range, -57.7 to 39.3) mm, with a median annual regression rate of -1.7 (range, -24.6 to 42.0) mm/year/woman. Overall, when compared with the initial visit, cysts were significantly smaller at follow-up (median diameter, 22.3 (range, 6.7-77.0) mm vs 18.5 (range, 5.0-72.0) mm; P = 0.009). We did not identify any clinical characteristics that could reliably predict the chance of endometrioma progression. CONCLUSIONS: In the majority of women with an ultrasound diagnosis of ovarian endometrioma, the cysts do not increase in size significantly over time and they could be managed expectantly. This evidence may help clinicians when counseling asymptomatic or minimally symptomatic women about management of ovarian endometrioma. © 2024 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

MRI combined with clinical features to differentiate ovarian thecoma-fibroma with cystic degeneration from ovary adenofibroma.

OBJECTIVE: To explore the value of magnetic resonance imaging (MRI) and clinical features in identifying ovarian thecoma-fibroma (OTF) with cystic degeneration and ovary adenofibroma (OAF). METHODS: A total of 40 patients with OTF (OTF group) and 28 patients with OAF (OAF group) were included in this retrospective study. Univariable and multivariable analyses were performed on clinical features and MRI between the two groups, and the receiver operating characteristic (ROC) curve was plotted to estimate the optimal threshold and predictive performance. RESULTS: The OTF group had smaller cyst degeneration degree (P < .001), fewer black sponge sign (20% vs. 53.6%, P = .004), lower minimum apparent diffusion coefficient value (ADCmin) (0.986 (0.152) vs. 1.255 (0.370), P < .001), higher age (57.4 ± 14.2 vs. 44.1 ± 15.9, P = .001) and more postmenopausal women (72.5% vs. 28.6%, P < .001) than OAF. The area under the curve of MRI, clinical features and MRI combined with clinical features was 0.870, 0.841, and 0.954, respectively, and MRI combined with clinical features was significantly higher than the other two (P < .05). CONCLUSION: The cyst degeneration degree, black sponge sign, ADCmin, age and menopause were independent factors in identifying OTF with cystic degeneration and OAF. The combination of MRI and clinical features has a good effect on the identification of the two. ADVANCES IN KNOWLEDGE: This is the first time to distinguish OTF with cystic degeneration from OAF by combining MRI and clinical features. It shows the diagnostic performance of MRI, clinical features, and combination of the two. This will facilitate the discriminability and awareness of these two diseases among radiologists and gynaecologists.

Risk Factors in Fetal Ovarian Cysts for Postnatal Adverse Outcomes.

AIM: To investigate the natural history of fetal ovarian cysts and elucidate the risk factors for postnatal adverse outcomes in fetal ovarian cysts. METHODS: The study subjects were 18 cases with ovarian cysts prenatally diagnosed using ultrasonography at our hospital between 2007 and 2020. The subjects were classified by cyst characteristics according to echogenic patterns [simple cyst (S) and complex cyst (C)], changes in echogenic patterns (S-to-S, S-to-C, and C-to-C), and diameters (<40 and ≥ 40 mm). Clinical parameters and outcomes were compared between S and C patterns, S-to-S and S-to-C patterns, and <40 and ≥ 40 mm diameters. RESULTS: Cases with S and C patterns (15 and 3, respectively) had median gestational ages of 35 and 36 weeks, respectively, and maximum cyst diameters of 36 and 57mm, respectively. The number of cases with S-to-S, S-to-C and C-to-C patterns were 11, 4 and 3, respectively. The maximum cyst diameter in cases with S-to-C patterns (58 mm) was larger than that in cases with S-to-S patterns (34 mm) (P<0.05). Placental weight in cases with cysts >40 mm and/or cyst expansion was greater than that in cases with neither or both conditions (P<0.05). Spontaneous resolution (before and after birth) occurred in 8 of 9 and 3 of 9 cases with maximum cyst diameters <40 and ≥ 40 mm, respectively. Ovarian function was lost in 2 cases with S-to-C patterns and in 2 cases with C-to-C patterns. CONCLUSION: Cases with cyst diameters ≥ 40 mm and/or cyst expansion during the late third trimester had greater placental weight and more postnatal adverse outcomes.

Laparoscopic Management of Auto-Amputated Ovarian Cyst in an Infant.

ABSTRACT: The routine schedule of antenatal ultrasound scans has led to an increased frequency of detection of foetal ovarian cysts. Although most of them regress spontaneously, some may grow into large cysts and undergo torsion followed by auto-amputation. However, pre- and post-natal scans may fail to identify this event. We report a case of a prenatally diagnosed ovarian cyst that failed to resolve conservatively and was increasing in size in post-natal ultrasounds. Pre-operative ultrasound and magnetic resonance imaging failed to detect the auto-amputation. The diagnosis was confirmed on laparoscopy which offers a safe and effective method for the removal of ovarian cysts in neonates and infants.

[Ovarian masses in infants and children]. / Raumforderungen des Ovars im Kindesalter.

BACKGROUND: Abnormalities of the ovary are frequently seen on ultrasound examination, sometimes symptomatic, but are more commonly asymptomatic. PURPOSE: Presentation of the most important entities of ovarian masses and their imaging features in infants and children. Discussion of criteria for differentiation between benign and potentially malignant masses. MATERIALS AND METHODS: Review of current literature and presentation of image examples. RESULTS: The most common lesions are ovarian cysts in infants, which usually do not require therapy. Because of the risk of torsion, surgery should be discussed for lesions with a size of 5 cm or more. Benign teratomas represent three-quarters of all solid tumors of the infantile ovary. Malignant masses are rare. The task of imaging is to assess the potential risk of malignancy, also using imaging scores. CONCLUSIONS: Imaging plays a crucial role for therapeutic considerations. Depending on the potential risk, ovarian-sparing surgery is preferred to preserve fertility, as long as the oncologic risk is reasonable.

Laparoscopic Ovarian-Sparing Surgery for the Management of Benign Ovarian Lesions in Pediatric Patients: A Retrospective Analysis.

INTRODUCTION: Laparoscopic ovarian-sparing surgery (OSS) is safe and effective management approach for benign ovarian lesions in pediatric patients. This study evaluates the outcomes of females younger than 18 years who underwent the OSS procedure between December 2013 and November 2022 at a single institution. MATERIAL AND METHODS: We conducted a retrospective analysis of records from 82 females who underwent OSS for ovarian lesions. OSS was performed based on diagnostic imaging that suggested the benign nature of the lesion. RESULTS: Of the 82 patients studied, 78 had unilateral lesions and 4 had bilateral synchronous lesions. The mean age was 14 years. The majority (62 cases) of the surgeries were laparoscopic, with 20 requiring conversion to open surgery due to factors such as indistinguishable edges and large size of the lesion. We identified 8 cases of ovarian torsion. The surgical specimens revealed that 46 were ovarian teratomas, 2 were granulosa cell tumors, 15 were cystadenomas, and 23 were functional cysts. There were no intraoperative complications. Two recurrences were observed in patients who were initially treated for bilateral ovarian teratomas. One patient developed a pelvic abscess. Additionally, three patients had metachronous ovarian tumors during the follow-up period. In patients followed with ultrasound imaging, the viable ovary was visualized in 83.6% of the cases (61 out of 73). CONCLUSION: Our findings demonstrate the effectiveness of laparoscopic OSS in preserving ovarian function and providing clinical benefits in patients with benign ovarian lesions. We recommend regular follow-up with ultrasound to exclude metachronous lesions or recurrence. LEVEL OF EVIDENCE: III.