Deep learning based uterine fibroid detection in ultrasound images.

Uterine fibroids are common benign tumors originating from the uterus's smooth muscle layer, often leading to symptoms such as pelvic pain, and reproductive issues. Early detection is crucial to prevent complications such as infertility or the need for invasive treatments like hysterectomy. One of the main challenges in diagnosing uterine fibroids is the lack of specific symptoms, which can mimic other gynecological conditions. This often leads to under-diagnosis or misdiagnosis, delaying appropriate management. In this research, an attention based fine-tuned EfficientNetB0 model is proposed for the classification of uterine fibroids from ultrasound images. Attention mechanisms, permit the model to focus on particular parts of an image and move forward the model's execution by empowering it to specifically go to imperative highlights whereas overlooking irrelevant ones. The proposed approach has used a total of 1990 images divided into two classes: Non-uterine fibroid and uterine fibroid. The data augmentation methods have been connected to improve generalization and strength by exposing it to a wider range of varieties within the training data. The proposed model has obtained the value of accuracy as 0.99. Future research should focus on improving the accuracy and efficiency of diagnostic techniques, as well as evaluating their effectiveness in diverse populations with higher sensitivity and specificity for the detection of uterine fibroids, as well as biomarkers to aid in diagnosis.

A novel scoring system based on magnetic resonance imaging for the prediction of the difficulty of ultrasound-guided high-intensity focused ultrasound ablation for uterine fibroids.

OBJECTIVE: To develop a novel scoring system based on magnetic resonance imaging (MRI) for predicting the difficulty of ultrasound-guided high-intensity focused ultrasound (USgHIFU) ablation for uterine fibroids. MATERIALS AND METHODS: A total of 637 patients with uterine fibroids were enrolled. Sonication time, non-perfused volume ratio (NPVR), and ultrasound energy delivered for ablating 1 mm3 of fibroid tissue volume (E/V) were each classified as three levels and assigned scores from 0 to 2, respectively. Treatment difficulty level was then assessed by adding up the scores of sonication time, NPVR and E/V for each patient. The patients with score lower than 3 were categorized into low difficulty group, with score equal to or greater than 3 were categorized into high difficulty group. The potential predictors for treatment difficulty were compared between the two groups. Multifactorial logistic regression analysis model was created by analyzing the variables. The difficulty score system was developed using the beta coefficients of the logistic model. RESULTS: Signal intensity on T2WI, fibroid location index, largest diameter of fibroids, abdominal wall thickness, homogeneity of the signal of fibroids, and uterine position were independent influencing factors for the difficulty of USgHIFU for uterine fibroids. A prediction equation was obtained: difficulty score = 17 × uterine position (anteverted =0, retroverted =1)+71 × signal intensity (hypointense = 0, isointense/hyperintense = 1) +8 × enhancement (homogenous = 0, heterogeneous = 1)+25×(largest diameter of fibroids-20) +35 × (fibroid location index -0.2) +1×(abdominal wall thickness -5). CONCLUSIONS: This scoring system established based on MRI findings can be used to reliably predict the difficulty level of USgHIFU treatment of uterine fibroids.

The value of susceptibility weighted imaging for immediate assessing the hyperacute outcome of MRgFUS ablation for uterine fibroids: a preliminary study.

PURPOSE: To investigate the value of susceptibility weighted imaging (SWI) for assessing the hyperacute outcome of ablation of uterine fibroids immediately after magnetic resonance-guided focused ultrasound (MRgFUS) treatment. METHODS: This retrospective imaging study included patients who underwent SWI and contrast-enhanced (CE) MR within 15 min of MRgFUS ablation for uterine fibroids. Two readers independently assessed the SWI features of ablative lesions and their association with the non-perfused volume (NPV) ratio. The intraclass correlation coefficient (ICC) and diagnostic value of SWI findings were calculated. RESULTS: A total of 27 uterine fibroids from 21 participants (mean age 40.1 ± 7.2 years) were analyzed. 51.9% (14/27) leiomyomas had NPV ratio ≥90%. In post-ablation SWI images, the interobserver ICC for the relative signal intensity and hypointense peripheral rim were 0.613 and 0.843, respectively (both p < .001). There was a significant difference in the prevalence of hypointense peripheral rim in leiomyomas with NPV ratio ≥90% and < 90% (p < .01), while the prevalence of relative signal intensity showed no significant difference (p > .05). When using the complete hypointense peripheral rim as a diagnostic criterion to identify NPV ratio ≥ 90%, readers 1 and 2 showed diagnostic sensitivity, specificity, and accuracy of 85.7%, 76.9%, 81.5%, and 78.6%, 76.9%, 77.8%, respectively. CONCLUSION: Identifying a complete hypointense peripheral rim on SWI may be a potential imaging marker for assessing the hyperacute outcome of uterine fibroids ablation by MRgFUS, specifically in determining whether the NPV ratio is ≥90%.

Development and validation of a deep learning-based method for automatic measurement of uterus, fibroid, and ablated volume in MRI after MR-HIFU treatment of uterine fibroids.

INTRODUCTION: The non-perfused volume divided by total fibroid load (NPV/TFL) is a predictive outcome parameter for MRI-guided high-intensity focused ultrasound (MR-HIFU) treatments of uterine fibroids, which is related to long-term symptom relief. In current clinical practice, the MR-HIFU outcome parameters are typically determined by visual inspection, so an automated computer-aided method could facilitate objective outcome quantification. The objective of this study was to develop and evaluate a deep learning-based segmentation algorithm for volume measurements of the uterus, uterine fibroids, and NPVs in MRI in order to automatically quantify the NPV/TFL. MATERIALS AND METHODS: A segmentation pipeline was developed and evaluated using expert manual segmentations of MRI scans of 115 uterine fibroid patients, screened for and/or undergoing MR-HIFU treatment. The pipeline contained three separate neural networks, one per target structure. The first step in the pipeline was uterus segmentation from contrast-enhanced (CE)-T1w scans. This segmentation was subsequently used to remove non-uterus background tissue for NPV and fibroid segmentation. In the following step, NPVs were segmented from uterus-only CE-T1w scans. Finally, fibroids were segmented from uterus-only T2w scans. The segmentations were used to calculate the volume for each structure. Reliability and agreement between manual and automatic segmentations, volumes, and NPV/TFLs were assessed. RESULTS: For treatment scans, the Dice similarity coefficients (DSC) between the manually and automatically obtained segmentations were 0.90 (uterus), 0.84 (NPV) and 0.74 (fibroid). Intraclass correlation coefficients (ICC) were 1.00 [0.99, 1.00] (uterus), 0.99 [0.98, 1.00] (NPV) and 0.98 [0.95, 0.99] (fibroid) between manually and automatically derived volumes. For manually and automatically derived NPV/TFLs, the mean difference was 5% [-41%, 51%] (ICC: 0.66 [0.32, 0.85]). CONCLUSION: The algorithm presented in this study automatically calculates uterus volume, fibroid load, and NPVs, which could lead to more objective outcome quantification after MR-HIFU treatments of uterine fibroids in comparison to visual inspection. When robustness has been ascertained in a future study, this tool may eventually be employed in clinical practice to automatically measure the NPV/TFL after MR-HIFU procedures of uterine fibroids.

ACR Appropriateness Criteria® Management of Uterine Fibroids: 2023 Update.

Uterine fibroids are the most common benign tumor in women of reproductive age and can present with symptoms including bleeding, bulk related symptoms, and infertility. Several treatment options are available for the management of uterine fibroids, including medical management, minimally invasive therapies such as uterine artery embolization and MR-guided focused ultrasound ablation, and surgical interventions ranging from laparoscopic myomectomy to open hysterectomy. Given this wide range of therapeutic interventions, it is important to understand the data supporting these interventions and to be able to apply it in different clinical settings. This document provides a summary of recent trials supporting various therapies for uterine fibroids, including recent evidence for MR-guided focused ultrasound ablation and a detailed discussion of fertility outcomes in myomectomy and uterine fibroid embolization. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

Risk factors affecting long-term efficacy of ultrasound-guided high-intensity focused ultrasound treatment for multiple uterine fibroids.

OBJECTIVES: To investigate the long-term efficacy of ultrasound-guided high-intensity focused ultrasound (USgHIFU) for multiple uterine fibroids and the factors associated with recurrence. MATERIALS AND METHODS: Five hundred and forty-nine patients with multiple uterine fibroids treated with USgHIFU from June 2017 to June 2019 were retrospectively analyzed. The Pictorial Blood Loss Assessment Chart (PBAC) was used to assess menstrual blood loss. The patients were asked to undergo pre- and post-USgHIFU magnetic resonance imaging (MRI) and complete routine follow-up after USgHIFU. Cox regression analysis was used to investigate the risk factors associated with recurrence. RESULTS: The median number of fibroids per patient was 3 (interquartile range: 3-4), and a total of 1371 fibroids were treated. Among them, 446 patients completed 3 years follow-up. Recurrence, defined as PBAC score above or equal to 100 and/or the residual fibroid volume increased by 10%, was detected in 90 patients within 3 years after USgHIFU, with a cumulative recurrence rate of 20.2% (90/446). The multi-factor Cox analysis showed that age was a protective factor for recurrence. Younger patients have a greater chance of recurrence than older patients. Mixed hyperintensity of fibroids on T2WI and treatment intensity were risk factors for recurrence. Patients with hyperintense uterine fibroids and treated with lower treatment intensity were more likely to experience recurrence than other patients after USgHIFU. No major adverse effects occurred. CONCLUSIONS: USgHIFU can be used to treat multiple uterine fibroids safely and effectively. The age, T2WI signal intensity and treatment intensity are factors related to recurrence.

Heterotopic pregnancy: a case report of intrauterine hydatidiform mole with tubal pregnancy.

We herein report a rare case of simultaneous intrauterine molar pregnancy and tubal pregnancy. A woman of childbearing age who had never been pregnant underwent an ultrasound examination 70 days after the onset of menopause. She had a history of ovulation induction. The ultrasound findings suggested a partial hydatidiform mole. She was then pathologically confirmed to have a complete hydatidiform mole after uterine suction dilation and curettage. On postoperative day 4, an ultrasound examination before discharge showed an inhomogeneous mass in the left adnexal region with mild lower abdominal pain. On postoperative day 17, the blood human chorionic gonadotropin level did not drop as expected, and a follow-up examination still indicated a mass in the left adnexal region. We were unable to rule out an ectopic hydatidiform mole. Hysteroscopy with laparoscopic exploration of the left adnexal mass and salpingotomy suggested a diagnosis of intrauterine hydatidiform mole combined with left tubal pregnancy.

Retroperitoneal dermoid cyst complicated with uterine adenomyoma: a case report and literature review.

Pelvic masses frequently originate from the pelvic cavity and are often associated with uterine, ovarian, or intestinal disorders. This report describes the case of a patient with a pelvic mass diagnosed as a retroperitoneal dermoid cyst at our hospital. We analyzed this case and conducted a literature review, to mitigate the risk of misdiagnosis and enhance the treatment of retroperitoneal masses.

Eclampsia, HELLP and PRES in a 16-week partial molar pregnancy.

Eclampsia spectrum disorders are a set of serious complications of pregnancy that commonly present after 20 weeks of gestation. There is an association between molar pregnancy, a gestational trophoblastic disease resulting from abnormal fertilisation and gametogenesis, and eclampsia spectrum disorders which can result in manifestation of pre-eclamptic symptomatology earlier than 20 weeks of gestation. We report a case of a gravida 1 para 0 in her mid 20s at 16-weeks gestation presenting with partial hydatidiform mole who developed eclampsia, haemolysis, elevated liver enzymes and low platelets syndrome and posterior reversible encephalopathy syndrome. Ultrasound findings were consistent with molar pregnancy and pathology confirmed partial molar pregnancy with triploid 69, XYY karyotype. This case highlights the early onset potential of eclampsia spectrum disorders in molar pregnancies while suggesting screening such patients for hypertensive disorders.

A Case Report of Uterine Torsion in a Postmenopausal Female with a Large Leiomyoma.

This case report discusses a diagnosis of uterine torsion in an 84-year-old woman who presented with five days of right lower quadrant abdominal pain, nausea, vomiting, constipation, and poor intake. Computed tomography (CT) imaging demonstrated a whorled configuration at the junction of the cervix and lower uterine segment, with the left gonadal vein crossing midline, and two previously known right leiomyomas now appearing on the left. These findings were consistent with the diagnosis of uterine torsion. She then underwent an urgent exploratory laparotomy, and the uterus was found to be dextroverted 270 degrees, with dark mottled purple tissue and engorged vessels. A supracervical hysterectomy and bilateral salpingo-oopherectomy were performed. Final pathology demonstrated extensive necrosis. This case reviews the classic presentation and imaging findings for the rare diagnosis of uterine torsion and options for management of both non-gravid and gravid patients.

Massive Hepatocellular Carcinoma Combined With Giant Uterine Fibroid on 18 F-FDG PET/CT.

ABSTRACT: A 50-year-old woman was admitted due to a liver mass discovered by ultrasound in routine physical examination. MRI demonstrated a large hepatocellular carcinoma. It also discovered an abdominal mass simultaneously. 18 F-FDG PET/CT was performed for staging. PET/CT showed mixed and mild metabolism of the hepatic lesion and giant abdominopelvic mass, respectively. Hepatocellular carcinoma combined with a benign mass in abdominopelvic cavity from uterine was considered and finally proved pathologically. We present a rare case of woman with large liver cancer accompanied by giant uterine fibroid where 18 F-FDG PET/CT helped in making the right diagnosis.

The Predictive Effect of Quantitative Analysis of Signal Intensity Heterogeneity on T2-Weighted MR Images for High-intensity Focused Ultrasound Treatment of Uterine Fibroids.

RATIONALE AND OBJECTIVES: To investigate whether the quantitative index of signal intensity (SI) heterogeneity on T2-weighted (T2W) magnetic resonance images can predict the difficulty and efficacy of high-intensity focused ultrasound (HIFU) ablation for uterine fibroids. MATERIALS AND METHODS: The standard deviation (SD) of T2W image (T2WI) SI was used to quantify SI heterogeneity. The correlation between SD and the non-perfused volume ratio (NPVR) in 575 patients undergoing HIFU treatment was retrospectively analyzed, and the efficacy of SD in predicting NPVR was discussed. Three classifications were made based on the SD, and the ablation difficulty and ablation effect of different grades were compared. A total of 65 cases from another center were used as an external validation set to verify the classification performance of SD. RESULTS: The SD of SI was negatively correlated with NPVR (r = -0.460, p < 0.001). The predictive efficiency of SD for the ablation effect was higher than that of the scaled signal intensity (0.767 vs. 0.701, p = 0.006). Univariate and multivariate logistic regression analyses showed that SD was an independent predictor of ablation effect. Based on SD, the three classifications were divided into SD I: SD < 101.0, SD II: 101.0 ≤ SD < 138.7, and SD III: SD≥ 138.7. The treatment time, sonication time, treatment intensity, and total energy of SD I were lower than those of SD II and III (p < 0.05). CONCLUSION: The heterogeneity of T2WI SI of uterine fibroids is negatively correlated with NPVR. The SD of SI can be used to predict the ablation difficulty and ablation effect of HIFU.

Giant uterine tumor and miscarriage: how to proceed?

Expanding uterine masses can be the cause of pregnancy loss and add technical difficulties to uterus evacuation due to the intense anatomical distortion of the endocervical canal and uterine cavity. The literature is scarce in the peculiarities of the management of missed abortions in uterus with important distorted anatomies. We report a case of a primigravida patient who presented a rapid and expressive increase of abdominal volume due to a giant uterine mass, evolving to miscarriage. Ultrasound can be a useful tool, allowing visualization of the endocervical path and uterine cavity, helping to perform uterine evacuation in the presence of anatomical distortion without compromising the reproductive future. To the best of our knowledge, no such case has been previously reported.

Use of natural language processing to uncover racial bias in obstetrical documentation.

Natural Language Processing (NLP), a form of Artificial Intelligence, allows free-text based clinical documentation to be integrated in ways that facilitate data analysis, data interpretation and formation of individualized medical and obstetrical care. In this cross-sectional study, we identified all births during the study period carrying the radiology-confirmed diagnosis of fibroid uterus in pregnancy (defined as size of largest diameter of >5 cm) by using an NLP platform and compared it to non-NLP derived data using ICD10 codes of the same diagnosis. We then compared the two sets of data and stratified documentation gaps by race. Using fibroid uterus in pregnancy as a marker, we found that Black patients were more likely to have the diagnosis entered late into the patient's chart or had missing documentation of the diagnosis. With appropriate algorithm definitions, cross referencing and thorough validation steps, NLP can contribute to identifying areas of documentation gaps and improve quality of care.

Pilot Study on Boiling Histotripsy Treatment of Human Leiomyoma Ex Vivo.

OBJECTIVE: As an alternative to surgical excision and magnetic resonance-guided thermal high-intensity focused ultrasound ablation of uterine leiomyoma, this work was aimed at pilot feasibility demonstration of use of ultrasound-guided boiling histotripsy for non-invasive non-thermal fractionation of human uterine leiomyoma ex vivo. METHODS: A custom-made sector ultrasound transducer of 1.5-MHz operating frequency and nominal f-number F# = 0.75 was used to produce a volumetric lesion (two layers of 5 × 5 foci with a 1 mm step) in surgically resected human leiomyoma ex vivo. A sequence of 10 ms pulses (P+/P-/As = 157/-25/170 MPa in situ) with 1% duty cycle was delivered N = 30 times per focus under B-mode guidance. The treatment outcome was evaluated via B-mode imaging and histologically with hematoxylin and eosin and Masson's trichrome staining. RESULTS: The treatment was successfully performed in less than 30 min and resulted in formation of a rectangular lesion visualized on B-mode images during the sonication as an echogenic region, which sustained for about 10 min post-treatment. Histology revealed loss of cellular structure, necrotic debris and globules of degenerated collagen in the target volume surrounded by injured smooth muscle cells. CONCLUSION: The pilot experiment described here indicates that boiling histotripsy is feasible for non-invasive mechanical disintegration of human uterine leiomyoma ex vivo under B-mode guidance, encouraging further investigation and optimization of this potential clinical application of boiling histotripsy.

Clinical signs and diagnosis of fibroids from adolescence to menopause.

The aim of this review was to provide an updated assessment of the present diagnostic tools and clinical symptoms and signs to evaluate uterine fibroids (UFs) on the basis of current guidelines, recent scientific evidence, and a PubMed and Google Scholar search for peer-reviewed original and review articles related to clinical signs and diagnosis of UFs. Approximately 50%-75% of UFs are considered nonclinically relevant. When present, the most common symptoms are abnormal uterine bleeding, pelvic pain and/or bulk symptoms, and reproductive failure. Transvaginal ultrasound is recommended as the initial diagnostic modality because of its accessibility and high sensitivity, although magnetic resonance imaging appears to be the most accurate diagnostic tool to date in certain cases. Other emerging techniques, such as saline infusion sonohysterography, elastography, and contrast-enhanced ultrasonography, may contribute to improving diagnostic accuracy in selected cases. Moreover, artificial intelligence has begun to demonstrate its ability as a complementary tool to improve the efficiency of UF diagnosis. Therefore, it is critical to standardize descriptions of transvaginal ultrasound images according to updated classifications and to individualize the use of the different complementary diagnostic tools available to achieve precise uterine mapping that can lead to targeted therapeutic approaches according to the clinical context of each patient.

Successful treatment of a rare giant accessory cavitated uterine mass: a case report.

An accessory cavitated uterine mass (ACUM) is a very rare obstructive genital malformation characterized by pelvic pain and severe dysmenorrhea. It is easily mistaken for other obstructive genital malformations in women, such as cystic uterine adenomyosis or cystic degeneration of uterine fibroids. This case report describes a 30-year-old patient with a huge uterine cornual mass. Successful resection was performed by surgical excision, and the lesion was diagnosed as an ACUM. Given the rarity of a giant ACUM, this report also includes a brief review of the relevant literature.

Large-scale uterine myoma MRI dataset covering all FIGO types with pixel-level annotations.

Uterine myomas are the most common pelvic tumors in women, which can lead to abnormal uterine bleeding, abdominal pain, pelvic compression symptoms, infertility, or adverse pregnancy. In this article, we provide a dataset named uterine myoma MRI dataset (UMD), which can be used for clinical research on uterine myoma imaging. The UMD is the largest publicly available uterine MRI dataset to date including 300 cases of uterine myoma T2-weighted imaging (T2WI) sagittal patient images and their corresponding annotation files. The UMD covers 9 types of uterine myomas classified by the International Federation of Obstetrics and Gynecology (FIGO), which were annotated and reviewed by 11 experienced doctors to ensure the authority of the annotated data. The UMD is helpful for uterine myomas classification and uterine 3D reconstruction tasks, which has important implications for clinical research on uterine myomas.

Diffusion-weighted imaging as a potential non-gadolinium alternative for immediate assessing the hyperacute outcome of MRgFUS ablation for uterine fibroids.

The aim of this study was to investigate the value of diffusion-weighted imaging (DWI) as a potential non-gadolinium alternative for promptly assessing the hyperacute outcome of magnetic resonance-guided focused ultrasound (MRgFUS) treatment for uterine fibroids. In this retrospective study we included 65 uterine fibroids from 44 women, who underwent axial DWI (b-value: 800 s/mm2) and contrast-enhanced (CE) MR within 15 min post-ablation. Two blinded observers independently reviewed the DWI findings of ablated necrotic lesions and measured their volumes on DWI and CE images. The post-ablation DWI images revealed clear depiction of ablative necrotic lesions in all fibroids, which were classified into two types: the bull's eye sign (type 1) and the bright patch sign (type 2). The inter-observer intraclass correlation coefficient for classifying DWI signal types was 0.804 (p < 0.001). Volumetric analysis of ablated necrosis using DWI and CE T1-weighted imaging showed no significant variance, nor did the non-perfused volume ratios (all p > 0.05). Bland-Altman analysis revealed a mean difference of 2.38% and 1.71% in non-perfused volume ratios between DWI and CE, with 95% limits of agreement from - 19.06 to 23.82% and - 18.40 to 21.82%, respectively. The findings of this study support the potential of DWI as a viable non-gadolinium alternative for evaluating the hyperacute outcomes of MRgFUS ablation in uterine fibroids.