Conectar
To evaluate the cost-effectiveness of the levonorgestrel intrauterine system (LNG-IUS) compared with hysteroscopic niche resection (HNR) for women with niche-related postmenstrual spotting.
Economic evaluation from a healthcare perspective, conducted alongside a randomised controlled trial with 12 months of follow-up.
A single-centre study at a university hospital in Shanghai was carried out between October 2019 and January 2021.
A total of 208 women aged 18–48 years with niche-related spotting who were suitable for a HNR, defined as a residual myometrium of at least 2.2 mm confirmed by MRI.
Participants were randomly assigned to LNG-IUS insertion (n=104) or HNR (n=104).
The primary outcome was reduction in postmenstrual spotting at 6 months, defined as ≥50% decrease in spotting days compared with baseline. Cost-effectiveness was expressed as incremental cost-effectiveness ratios (ICERs), calculated by dividing cost differences in effective rate and spotting days.
Mean costs (diagnostic, examination, surgical) were compared between groups using Student’s t-test, standardised to 2019 price levels. Uncertainty around cost-effectiveness was assessed with non-parametric bootstrapping and cost-effectiveness acceptability curves.
At 6 months, 78.4% (80/102) of women in the LNG-IUS group and 73.1% (76/104) in the HNR group reported improvement in spotting symptoms (RR 1.07, 95% CI 0.92 to 1.25). Spotting reduction was greater with LNG-IUS (0.0 days, IQR 0.0 to 2.8) compared with HNR (2.0 days, IQR 0.8 to 4.3; p
LNG-IUS is highly cost-effective compared with HNR for the treatment of niche-related postmenstrual spotting at 6 months. These findings support LNG-IUS as first-line therapy for niche-related spotting in women with a residual myometrium ≥2.2 mm.
ChiCTR1900025677.
by Dilara Tank, Bianca G. S. Schor, Lisa M. Trommelen, Judith A. F. Huirne, Iacer Calixto, Robert A. de Leeuw
PurposeTransvaginal ultrasound (TVUS) is pivotal for diagnosing reproductive pathologies in individuals assigned female at birth, often serving as the primary imaging method for gynecologic evaluation. Despite recent advancements in AI-driven segmentation, its application to gynecological ultrasound still needs further attention. Our study aims to bridge this gap by training and evaluating two state-of-the-art deep learning (DL) segmentation models on TVUS data.
Materials and methodsAn experienced gynecological expert manually segmented the uterus in our TVUS dataset of 124 patients with adenomyosis, comprising still images (n = 122), video screenshots (n = 472), and 3D volume screenshots (n = 452). Two popular DL segmentation models, U-Net and nnU-Net, were trained on the entire dataset, and each imaging type was trained separately. Optimization for U-Net included varying batch size, image resolution, pre-processing, and augmentation. Model performance was measured using the Dice score (DSC).
ResultsU-Net and nnU-Net had good mean segmentation performances on the TVUS uterus segmentation dataset (0.75 to 0.97 DSC). We observed that training on specific imaging types (still images, video screenshots, 3D volume screenshots) tended to yield better segmentation performance than training on the complete dataset for both models. Furthermore, nnU-Net outperformed the U-Net across all imaging types. Lastly, we report the best results using the U-Net model with limited pre-processing and augmentations.
ConclusionsTVUS datasets are well-suited for DL-based segmentation. nnU-Net training was faster and yielded higher segmentation performance; thus, it is recommended over manual U-Net tuning. We also recommend creating TVUS datasets that include only one imaging type and are as clutter-free as possible. The nnU-Net strongly benefited from being trained on 3D volume screenshots in our dataset, likely due to their lack of clutter. Further validation is needed to confirm the robustness of these models on TVUS datasets. Our code is available on https://github.com/dilaratank/UtiSeg.
FreshRSS 