Objective To create a semi-automated outlining tool for the levator hiatus, to reduce interobserver variability and and speed up analysis. Methods The proposed automated hiatus segmentation (AHS) algorithm takes a C-plane image

Tom Vercauteren, "Automatic segmentation method of pelvic floor levator hiatus in ultrasound using a selfnormalizing neural network," J. Med. Imag. 5(2), 021206 (2018), doi: 10.1117/1.JMI.5.2.021206. Abstract. Segmentation of the levator hiatus in ultrasound allows the extraction of biometrics, which are of importance for pelvic floor disorder assessment. We present a fully automatic method using a convolutional neural network (CNN) to outline the levator hiatus in a two-dimensional image extracted from a three-dimensional ultrasound volume. In particular, our method uses a recently developed scaled exponential linear unit (SELU) as a nonlinear self-normalizing activation function, which for the first time has been applied in medical imaging with CNN. SELU has important advantages such as being parameter-free and mini-batch independent, which may help to overcome memory constraints during training. A dataset with 91 images from 35 patients during Valsalva, contraction, and rest, all labeled by three operators, is used for training and evaluation in a leave-one-patient-out cross validation. Results show a median Dice similarity coefficient of 0.90 with an interquartile range of 0.08, with equivalent performance to the three operators (with a Williams' index of 1.03), and outperforming a U-Net architecture without the need for batch normalization. We conclude that the proposed fully automatic method achieved equivalent accuracy in segmenting the pelvic floor levator hiatus compared to a previous semiautomatic approach.

Background: Pelvic organ prolapse affects half of vaginally parous women. Several animal models are used to study its pathophysiology and treatment. Sheep are interesting because they develop spontaneously prolapse with similar risk factors as women and can be used for vaginal surgery. This study describes ovine pelvis anatomy and compares it to women's pelvis to provide anatomical tools for translational researchers. Methods: MRI, pelvic dissections, and histology were used for detailed macro- and microscopic analysis of relevant anatomical structures in 6 nulliparous ewes. Results: Although sheep are quadrupeds, the gross and microscopic anatomies are similar to the female pelvis. Principal differences are the shape and its orientation, the absence of the sacrospinous ligament and the internal obturator. The levator ani (except for the puborectalis) and the coccygeus muscle are present, yet the latter is more developed - coinciding with the tail. The dimensions and morphology of the ovine vagina is comparable. The retropubic and the rectovaginal space are accessible transvaginally. There is a wide expression of estrogen receptors with low or absent immunoreactivity in the urethral epithelium, bladder, anus and internal anal sphincter. Conclusion: The ovine pelvic floor has many anatomical and ultrastructural similarities to the female pelvic floor.

With advancing population age, pelvic-floor dysfunction (PFD) will affect an increasing number of women. Many of these women wish to maintain active lifestyles, indicating an urgent need for effective strategies to treat or, preferably, prevent the occurrence of PFD. Childbirth and pregnancy have both long been recognized as crucial contributing factors in the pathophysiology of PFD. Vaginal delivery of a child is a serious traumatic event, causing anatomical and functional changes in the pelvic floor. Similar changes to those experienced during childbirth can be found in symptomatic women, often many years after delivery. Thus, women with such PFD symptoms might have incompletely recovered from the trauma caused by vaginal delivery. This hypothesis creates the possibility that preventive measures can be initiated around the time of delivery. Secondary prevention has been shown to be beneficial in patients with many other chronic conditions. The current general consensus is that clinicians should aim to minimize the extent of damage during delivery, and aim to optimize healing processes after delivery, therefore preventing later dysfunction. A substantial amount of research investigating the potential of stem-cell injections as a therapeutic strategy for achieving this purpose is currently ongoing. Data from small animal models have demonstrated positive effects of mesenchymal stem-cell injections on the healing process following simulated vaginal birth injury.