Dynamic magnetic resonance imaging; reliability of assessment and correlation with clinical findings of pelvic organ prolapse

Squeeze-and-excitation-attention-based mobile vision transformer for grading recognition of bladder prolapse in pelvic MRI images

BACKGROUND

Bladder prolapse is a common clinical disorder of pelvic floor dysfunction in women, and early diagnosis and treatment can help them recover. Pelvic magnetic resonance imaging (MRI) is one of the most important methods used by physicians to diagnose bladder prolapse; however, it is highly subjective and largely dependent on the clinical experience of physicians. The application of computer-aided diagnostic techniques to achieve a graded diagnosis of bladder prolapse can help improve its accuracy and shorten the learning curve.

PURPOSE

The purpose of this study is to combine convolutional neural network (CNN) and vision transformer (ViT) for grading bladder prolapse in place of traditional neural networks, and to incorporate attention mechanisms into mobile vision transformer (MobileViT) for assisting in the grading of bladder prolapse.

METHODS

This study focuses on the grading of bladder prolapse in pelvic organs using a combination of a CNN and a ViT. First, this study used MobileNetV2 to extract the local features of the images. Next, a ViT was used to extract the global features by modeling the non-local dependencies at a distance. Finally, a channel attention module (i.e., squeeze-and-excitation network) was used to improve the feature extraction network and enhance its feature representation capability. The final grading of the degree of bladder prolapse was thus achieved.

RESULTS

Using pelvic MRI images provided by a Huzhou Maternal and Child Health Care Hospital, this study used the proposed method to grade patients with bladder prolapse. The accuracy, Kappa value, sensitivity, specificity, precision, and area under the curve of our method were 86.34%, 78.27%, 83.75%, 95.43%, 85.70%, and 95.05%, respectively. In comparison with other CNN models, the proposed method performed better.

CONCLUSIONS

Thus, the model based on attention mechanisms exhibits better classification performance than existing methods for grading bladder prolapse in pelvic organs, and it can effectively assist physicians in achieving a more accurate bladder prolapse diagnosis.

Clinical applications of pelvic floor imaging: opinion statement endorsed by the society of abdominal radiology (SAR), American Urological Association (AUA), and American Urogynecologic Society (AUGS)

Pelvic floor dysfunction is prevalent, with multifactorial causes and variable clinical presentations. Accurate diagnosis and assessment of the involved structures commonly requires a multidisciplinary approach. Imaging is often complementary to clinical assessment, and the most commonly used modalities for pelvic floor imaging include fluoroscopic defecography, magnetic resonance defecography, and pelvic floor ultrasound. This collaboration opinion paper was developed by representatives from multiple specialties involved in care of patients with pelvic floor dysfunction (radiologists, urogynecologists, urologists, and colorectal surgeons). Here, we discuss the utility of imaging techniques in various clinical scenarios, highlighting the perspectives of referring physicians. The final draft was endorsed by the Society of Abdominal Radiology (SAR), American Urogynecologic Society (AUGS), and the American Urological Association (AUA).

MR defecography in ano-rectal dysfunction: a clinical-radiological correlation study

Background

The aim of this work is to assess the diagnostic accuracy of MR defecography in ano-rectal dysfunction [ARD] for proper treatment planning.

Results

MR defecography was done to 30 patients with ARD for detection of its functional and structural causes. Increased perineal descent was detected in 70% of cases, rectocele in 46.7%, rectal intussusception in 40%, cystocele in 26.7%, uterine prolapse in 27.7%, enterocele in 13.3%, and paradoxical puborectalis contraction in 30%.

Conclusion

MR defecography is an essential diagnostic tool for optimum management of ano-rectal dysfunction patients.

Dynamic Pelvic Magnetic Resonance Imaging Evaluation of Pelvic Organ Prolapse Compared to Physical Examination Findings

OBJECTIVE

To compare dynamic magnetic resonance imaging (dMRI) defecography phase findings with physical examination (PE) grading in the evaluation of pelvic organ prolapse (POP).

METHODS

We retrospectively reviewed 274 consecutive patients who underwent dMRI with defecography. Baden-Walker grading of POP, absolute dMRI values, and grading by dMRI were collected for anterior, apical, and posterior compartments. Anatomically significant POP on PE was defined as Baden-Walker Grade ≥3 and on dMRI by dMRI Grade ≥2. A Spearman's Rank correlation was performed between absolute dMRI values and respective POP grades.

RESULTS

A total of 178 female patients were included. Anatomically insignificant and significant cystoceles had a 26.4% (19/72) and 84.6% (66/78) agreement respectively. Anatomically insignificant and significant apical prolapse had a 2.0% (2/100) and 62.9% (17/27) agreement respectively. Anatomically insignificant and significant posterior prolapse had a 49.5% (51/103) and 78.7% (59/75) agreement respectively. PE detected only 30% (9/30) of total dMRI detected enteroceles and misdiagnosed 10% (3/30) of these patients with a rectocele.

CONCLUSION

The dMRI defecography phase correlated well for anatomically significant prolapse in anterior and posterior compartments. dMRI was superior to PE for enterocele detection and was better able to distinguish an enterocele from a rectocele. Thus, dMRI may have the greatest diagnostic value in cases where the presence of an enterocele is unclear in apical and/or posterior compartments.

Magnetic resonance defecography versus clinical examination and fluoroscopy: a systematic review and meta-analysis

BACKGROUND

Magnetic resonance defecography (MRD) allows for dynamic visualisation of the pelvic floor compartments when assessing for pelvic floor dysfunction. Additional benefits over traditional techniques are largely unknown. The aim of this study was to compare detection and miss rates of pelvic floor abnormalities with MRD versus clinical examination and traditional fluoroscopic techniques.

METHODS

A systematic review and meta-analysis was conducted in accordance with recommendations from the Preferred Reporting Items for Systematic Reviews and Meta-Analyses. MEDLINE, Embase and the Cochrane Central Register of Controlled Trials were accessed. Studies were included if they reported detection rates of at least one outcome of interest with MRD versus EITHER clinical examination AND/OR fluoroscopic techniques within the same cohort of patients.

RESULTS

Twenty-eight studies were included: 14 studies compared clinical examination to MRD, and 16 compared fluoroscopic techniques to MRD. Detection and miss rates with MRD were not significantly different from clinical examination findings for any outcome except enterocele, where MRD had a higher detection rate (37.16% with MRD vs 25.08%; OR 2.23, 95% CI 1.21-4.11, p = 0.010) and lower miss rates (1.20 vs 37.35%; OR 0.05, 95% CI 0.01-0.20, p = 0.0001) compared to clinical examination. However, compared to fluoroscopy, MRD had a lower detection rate for rectoceles (61.84 vs 73.68%; OR 0.48 95% CI 0.30-0.76, p = 0.002) rectoanal intussusception (37.91 vs 57.14%; OR 0.32, 95% CI 0.16-0.66, p = 0.002) and perineal descent (52.29 vs 74.51%; OR 0.36, 95% CI 0.17-0.74, p = 0.006). Miss rates of MRD were also higher compared to fluoroscopy for rectoceles (15.96 vs 0%; OR 15.74, 95% CI 5.34-46.40, p < 0.00001), intussusception (36.11 vs 3.70%; OR 10.52, 95% CI 3.25-34.03, p = 0.0001) and perineal descent (32.11 vs 0.92%; OR 12.30, 95% CI 3.38-44.76, p = 0.0001).

CONCLUSIONS

MRD has a role in the assessment of pelvic floor dysfunction. However, clinicians need to be mindful of the risk of underdiagnosis and consider the use of additional imaging.