Purpose: This review examines the diagnostic value of transvaginal 3D ultrasound
image texture analysis for the diagnosis of uterine adhesions. Materials and
Methods: The total clinical data of 53 patients with uterine adhesions
diagnosed by hysteroscopy and the imaging data of transvaginal three-dimensional
ultrasound from the Second Affiliated Hospital of Chongqing Medical University from June 2022 to August 2023
were retrospectively analysed. Based on hysteroscopic surgical records,
patients were divided into two independent groups: normal endometrium and
uterine adhesion sites. The samples were divided into a training set and a test
set, and the transvaginal 3D ultrasound was used to outline the region of
interest (ROI) and extract texture features for normal endometrium and uterine
adhesions based on hysteroscopic surgical recordings, the training set data
were feature screened and modelled using lasso regression and cross-validation,
and the diagnostic efficacy of the model was
assessed by applying the subjects’ operating characteristic (ROC)
curves. Results: For each group, 290 texture feature parameters were
extracted and three higher values were screened out, and the area under the
curve of the constructed ultrasonographic scoring model was 0.658 and 0.720 in
the training and test sets, respectively. Conclusion Relative clinical value of
transvaginal three-dimensional ultrasound image texture analysis for the
diagnosis of uterine adhesions.
References
[1]
Chinese Society of Obstetrics and Gynaecology of the Chinese Medical Association (2015) Chinese Expert Consensus on Clinical Diagnosis and Treatment of Uterine Adhesion. Chinese Journal of Obstetrics and Gynaecology, 50, 881-887.
[2]
Shu, Y., Cai, Ti., Liu, M., et al. (2021) Application of Ultrasound Combined with Uterine Acoustic Imaging in Uterine Adhesions. Chinese General Medicine, 19, 1351-1353, 1366.
[3]
Xiang, X., Hu, B., Li, H., et al. (2021) Progress of Clinical Application of Ultrasound in Diagnosing Uterine Adhesions. China Interventional Imaging and Therapy, 18, 631-634.
[4]
Jimah, B.B., Gorleku, P. and Baffour Appiah, A. (2020) Hysterosalpingography Findings and Jimah Ratio of the Uterine Cavity in Women with Infertility in Central Region, Ghana. Radiology Research and Practice, 2020, Article ID: 6697653.
https://doi.org/10.1155/2020/6697653
[5]
SzczypińSki, P.M., Strzelecki, M., Materka, A. and Klepaczko, A. (2009) MaZda—A Software Package for Image Texture Analysis. Computer Methods and Programs in Biomedicine, 94, 66-76. https://doi.org/10.1016/j.cmpb.2008.08.005
[6]
Marino, M.A., Pinker, K., Leithner, D., et al. (2020) Contrast-Enhanced Mammography and Radiomics Analysis for Noninvasive Breast Cancer Characterization: Initial Results. Molecular Imaging and Biology, 22, 780-787.
https://doi.org/10.1007/s11307-019-01423-5
[7]
Hodgdon, T., Thornhill, R.E., James, N.D., Beaulé, P.E., Speirs, A.D. and Rakhra, K.S. (2020) CT Texture Analysis of Acetabular Subchondral Bone Can Discriminate between Normal and Cam-Positive Hips. European Radiology, 30, 4695-4704.
https://doi.org/10.1007/s00330-020-06781-1
[8]
Kociolek, M., Strzelecki, M. and Szymajda, S. (2018) Effect of Image Normalization Schemes on Texture Classification Accuracy. 2018 Signal Processing: Algorithms, Architectures, Arrangements and Applications (SPA), Poznan, 19-21 September 2018, 152-157. https://doi.org/10.23919/SPA.2018.8563397
[9]
Sun, D.-Q., Wang, L.-H., Li, G.-Z., et al. (2021) Feasibility Study of Texture Analysis and Functional Magnetic Resonance Imaging for Predicting KRAS Mutations in Rectal Cancer. Journal of Clinical Radiology, 40, 924-929.
[10]
Dercle, L., Ammari, S., Bateson, M., et al. (2017) Limits of Radiomic-Based Entropy as a Surrogate of Tumor Heterogeneity: ROI-Area, Acquisition Protocol and Tissue Site Exert Substantial Influence. Scientific Reports, 7, Article 7952.
https://doi.org/10.1038/s41598-017-08310-5
[11]
Shen, M., Duan, H., Chang, Y. and Lin, Q. (2022) Prevalence and Risk Factors of Intrauterine Adhesions in Women with a Septate Uterus: A Retrospective Cohort Study. Reproductive BioMedicine Online, 44, 881-887.
https://doi.org/10.1016/j.rbmo.2022.02.004
[12]
Li, M., Deng, Y., Zhong, S., et al. (2018) Changes in Endometrial Volume and Blood Flow in Patients with Uterine Adhesions Assessed by Transvaginal Three-Dimensional Ultrasound. China Maternal and Child Health Care, 33, 4786-4788.
[13]
Green, R.W., Valentin, L., Alcazar, J.L., et al. (2018) Endometrial Cancer Off-Line Staging Using Two-Dimensional Transvaginal Ultrasound and Three-Dimensional Volume Contrast Imaging: Intermethod Agreement, Interrater Reliability and Diagnostic Accuracy. Gynecologic Oncology, 150, 438-445.
https://doi.org/10.1016/j.ygyno.2018.06.027
[14]
Zhu, X. and Mao, L. (2013) Diagnostic Value and Misdiagnosis of Uterine Adhesion by Transvaginal Three-Dimensional Ultrasound. Chinese Journal of Clinical Medical Imaging, 24, 127-129.
[15]
Li, P., Wang, D., Li, L., et al. (2020) Analysis of the Diagnostic Value of Transvaginal Three-Dimensional Ultrasound for Uterine Cavity Lesions. Journal of Practical Hospital Clinics, 17, 60-63.
[16]
Fan, L.-Z. (2022) Diagnostic Value of Transvaginal Three-Dimensional Ultrasonography for Uterine Adhesions and Reasons for Missed Diagnosis. Modern Medical Imaging, 31, 1774-1777.
[17]
Yu, J., Wu, Y., Hu, T., et al. (2022) Diagnostic Value of Transvaginal Three-Dimensional Ultrasonography for Uterine Adhesions and Analysis of Reasons for Missed Diagnosis. Imaging Research and Medical Application, 6, 164-166+169.
