Interventional Radiology in Obstetrics and Gynecology: Updates in Women's Health

Multi-machine Learning Model Based on Habitat Subregions for Outcome Prediction in Adenomyosis Treated by Uterine Artery Embolization

RATIONALE AND OBJECTIVES

To establish and validate a predictive multi-machine learning model for the long-term efficacy of uterine artery embolization (UAE) in the treatment of adenomyosis based on habitat subregions.

MATERIALS AND METHODS

Patients who underwent UAE for adenomyosis at institution A between November 2015 and June 2018 were included in the training cohort and those at institution B between June 2017 and June 2019 were included in the test cohort. The regions of interest (ROI) were manually segmented on the T2-weighted images (T2WI). The ROIs were subsequently partitioned into habitat subregions using k-means clustering. Radiomic features were extracted from each subregion on T1WI, T2WI, apparent diffusion coefficient, and contrast-enhanced images. The least absolute shrinkage and selection operator (LASSO) was used to select the subregion radiomics features. With the improvement in patients' symptoms at 36 months post-UAE, the habitat subregion features were trained using six machine-learning classifiers. The most suitable classifier was chosen based on model performance to establish the habitat radiomics model (HRM). The efficacy of the model was validated using both the training and test cohorts. Finally, a whole-region radiomics model (WRM) and clinical model (CM) were established. The Delong test was used to compare the predictive performance of the habitat subregion model and the two other models.

RESULTS

The study included 258 patients, 191 in the training cohort and 67 in the test cohort. The ROIs were divided into four habitat subregions. Radiomics features were extracted from different sequence images of the subregions. After LASSO regression, 24 habitat subregion features were included in the model. Based on the receiver operating characteristic curve analysis, the area under the curve (AUC) of the HRM was 0.921 (95% CI, 0.857-0.985, training) and 0.890 (95% CI, 0.736-1.000, test). The AUCs for the WRM were 0.805 (95% CI, 0.737-0.872, training) and 0.693 (95% CI, 0.497-0.889, test). Compared to the HRM, the difference in predictive performance was statistically significant (p = 0.008, training; p = 0.007, test). The AUCs for the CM were 0.788 (95% CI, 0.711-0.866, training) and 0.735 (95% CI, 0.566-0.903, test). Compared to the HRM, there was a statistically significant difference in the training cohort (p = 0.014) but not in the test cohort (p = 0.186).

CONCLUSION

The HRM can predict the long-term efficacy of UAE in the treatment of adenomyosis. The predictive performance was superior to that of both the WRM and CM, serving as an effective tool to assist interventional physicians in clinical decision-making.

Interventional Therapy of Pelvic Venous Disorders (PeVD)

BACKGROUND

Pelvic venous disorders (PeVD) are an underdiagnosed cause of chronic pelvic pain in women. They are caused by venous insufficiency of the pelvic or ovarian veins, leading to the development of mainly periuterine and periovarian varices. It is a progressive disease if left untreated and can cause swelling, dyspareunia, dysmenorrhea, and other symptoms, some non-specific, that affect the patient's quality of life. Interventional therapies are a central component of the treatment of PeVD, with a variety of techniques available for both diagnosis and treatment.

METHOD

This review provides an overview of the pathophysiologic background, diagnosis, and, most importantly, interventional treatment options for PeVD.

RESULTS

There is a lack of standardized nomenclature and internationally accepted diagnostic criteria for PeVD as well as randomized controlled trials demonstrating clinical success. However, in clinical trials, endovascular therapy for PeVD has been shown to be safe and effective. This review presents the various interventional techniques for the treatment of PeVD, including embolization, stenting, and sclerotherapy.

CONCLUSION

The importance of PeVD is receiving growing recognition. Recent advances, such as the development of the Symptoms-Varices-Pathophysiology (SVP) classification, provide an impetus to standardize nomenclature and are the first step toward systematizing disease management. Interventional therapies provide a safe and tailored minimally invasive treatment option for patients with PeVD.

KEY POINTS

· Pelvic venous disorders are an underdiagnosed condition with frequently delayed diagnosis and debilitating symptoms.. · Until now, the PeVD nomenclature has been imprecise, with terms like May-Thurner syndrome/Nutcracker syndrome.. · Interventional approaches are effective and play a central role in PeVD treatment..

CITATION FORMAT

· Dewald CL, Becker LS, Meyer BC. Interventional Therapy of Pelvic Venous Disorders (PeVD). Fortschr Röntgenstr 2024; 196: 921 - 927.

Alternative treatments of adenomyosis - an update in procedural management and clinical outcomes

PURPOSE OF REVIEW

Adenomyosis is a common cause of abnormal uterine bleeding (AUB), dysmenorrhea, and pelvic pain. Definitive diagnosis and treatment have historically been by uterine histopathology at time of hysterectomy; however, advances in imaging have supported earlier diagnosis and subsequent conservative treatment. This review aims to update the evidence supporting the uterine-sparing, procedural management options with a focus on clinical outcomes.

RECENT FINDINGS

Uterine artery embolization (UAE), radiofrequency ablation (RFA), high-intensity focused ultrasound (HIFU), percutaneous microwave ablation (PMWA), and adenomyomectomy are minimally invasive interventions proven to be effective in reducing AUB and dysmenorrhea due to adenomyosis. Symptom improvement is associated with a decrease in uterine volume. Studies support the use of alternative treatment options given the overall low rates of symptom recurrence and reintervention. Combination therapy may be more effective than monotherapy.

SUMMARY

This review provides the current evidence for use of alternative treatment options for adenomyosis. Access to ablative therapies in the USA is limited and primarily off label, given lack of FDA approval. High-quality prospective and randomized controlled trials are needed in order to further delineate treatment comparisons, efficacy, safety, and ideal patient selection for these treatments. More data are needed to assess safety and utility in those desiring future fertility.

Treatment of adenomyosis, abdominal wall endometriosis and uterine leiomyoma with interventional radiology: A review of current evidences

Interventional radiology shows promises in the field of women's health, particularly in pelvic interventions. This review article discusses the latest advancements in interventional radiology techniques for pelvic conditions affecting women including adenomyosis, abdominal wall endometriosis and uterine leiomyoma. Extraperitoneal endometriosis involving the abdominal wall may be treated by percutaneous thermal ablation, such as cryoablation, whereas uterine leiomyoma and adenomyosis can be managed either using percutaneous thermal ablation or using uterine artery embolization. Continued research and development in interventional radiology will further enhance the minimally-invasive interventions available for women's health, improving outcomes and quality of life for this large patient population of women.

Construction and validation of a personalized prediction model for postpartum anxiety in pregnant women with preeclampsia

BACKGROUND

Preeclampsia is a pregnancy-specific multi-system disease with multi-factor and multi-mechanism characteristics. The cure for preeclampsia is to terminate the pregnancy and deliver the placenta. However, it will reduce the perinatal survival rate, prolong the pregnancy cycle, and increase the incidence of maternal complications. With relaxation of the birth policy, the number of elderly pregnant women has increased significantly, and the prevalence rate of preeclampsia has increased. Inappropriate treatment can seriously affect the normal postpartum life of pregnant women. Studies have shown that postpartum anxiety in women with preeclampsia can affect physical and mental health, as well as infant growth and development.

AIM

To analyze the factors influencing preeclampsia in pregnant women complicated with postpartum anxiety, and to construct a personalized predictive model.

METHODS

We retrospectively studied 528 pregnant women with preeclampsia who delivered in Wenzhou Hospital of Integrated Traditional Chinese and Western Medicine between January 2018 and December 2021. Their basic data were collected, and various physiological and biochemical indicators were obtained by laboratory examination. The self-rating anxiety scale was used to determine whether the women had postpartum anxiety 42 d after delivery. The independent factors influencing postpartum anxiety in early pregnant women with eclampsia were analyzed with multifactor logistic regression and a predictive model was constructed. The Hosmer-Lemeshow test and receiver operating characteristic (ROC) curve were used to evaluate the calibration and discrimination of the predictive model. Eighty pregnant women with preeclampsia admitted to our hospital from January 2022 to May 2022 were retrospectively selected to verify the prediction model.

RESULTS

We excluded 46 of the 528 pregnant women with preeclampsia because of loss to follow-up and adverse outcomes. A total of 482 cases completed the assessment of postpartum anxiety 42 d after delivery, and 126 (26.14%) had postpartum anxiety. Bad marital relationship, gender discrimination in family members, hematocrit (Hct), estradiol (E2) hormone and interleukin (IL)-6 were independent risk factors for postpartum anxiety in pregnant women with preeclampsia (P < 0.05). Prediction model: Logit (P) = 0.880 × marital relationship + 0.870 × gender discrimination of family members + 0.130 × Hct - 0.044 × E2 + 0.286 × IL-6 - 21.420. The area under the ROC curve of the model was 0.943 (95% confidence interval: 0.919-0.966). The threshold of the model was -1.507 according to the maximum Youden index (0.757), the corresponding sensitivity was 84.90%, and the specificity was 90.70%. Hosmer-Lemeshow χ2 = 5.900, P = 0.658. The sensitivity, specificity and accuracy of the model were 81.82%, 84.48% and 83.75%, respectively.

CONCLUSION

Poor marital relationship, family gender discrimination, Hct, IL-6 and E2 are the influencing factors of postpartum anxiety in preeclampsia women. The constructed prediction model has high sensitivity and specificity.