Deep learning enables automatic quantitative assessment of puborectalis muscle and urogenital hiatus in plane of minimal hiatal dimensions
Open accessAbstract
OBJECTIVES: To measure the length, width and area of the urogenital hiatus (UH), and the length and mean echogenicity (MEP) of the puborectalis muscle (PRM), automatically and observer-independently, in the plane of minimal hiatal dimensions on transperineal ultrasound (TPUS) images, by automatic segmentation of the UH and the PRM using deep learning. METHODS: In 1318 three- and four-dimensional (3D/4D) TPUS volume datasets from 253 nulliparae at 12 and 36 weeks' gestation, two-dimensional (2D) images in the plane of minimal hiatal dimensions with the PRM at rest, on maximum contraction and on maximum Valsalva maneuver, were obtained manually and the UH and PRM were segmented manually. In total, 713 of the images were used to train a convolutional neural network (CNN) to segment automatically the UH and PRM in the plane of minimal hiatal dimensions. In the remainder of the dataset (test set 1 (TS1); 601 images, four having been excluded), the performance of the CNN was evaluated by comparing automatic and manual segmentations. The performance of the CNN was also tested on 117 images from an independent dataset (test set 2 (TS2); two images having been excluded) from 40 nulliparae at 12 weeks' gestation, which were acquired and segmented manually by a different observer. The success of automatic segmentation was assessed visually. Based on the CNN segmentations, the following clinically relevant parameters were measured: the length, width and area of the UH, the length of the PRM and MEP. The overlap (Dice similarity index (DSI)) and surface distance (mean absolute distance (MAD) and Hausdorff distance (HDD)) between manual and CNN segmentations were measured to investigate their similarity. For the measured clinically relevant parameters, the intraclass correlation coefficients (ICCs) between manual and CNN results were determined. RESULTS: Fully automatic CNN segmentation was successful in 99.0% and 93.2% of images in TS1 and TS2, respectively. DSI, MAD and HDD showed good overlap and distance between manual and CNN segmentations in both test sets. This was reflected in the respective ICC values in TS1 and TS2 for the length (0.96 and 0.95), width (0.77 and 0.87) and area (0.96 and 0.91) of the UH, the length of the PRM (0.87 and 0.73) and MEP (0.95 and 0.97), which showed good to very good agreement. CONCLUSION: Deep learning can be used to segment automatically and reliably the PRM and UH on 2D ultrasound images of the nulliparous pelvic floor in the plane of minimal hiatal dimensions. These segmentations can be used to measure reliably UH dimensions as well as PRM length and MEP. © 2018 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of the International Society of Ultrasound in Obstetrics and Gynecology.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The need for manual selection of ROI before AI image processing was a limiting aspect for AI in pelvic floor US.
“the need for manual selection of ROI before AI image processing [211,213,214].”
From Evolving the Era of 5D Ultrasound? A Systematic Literature Review on the Applications for Artificial Intelligence Ultrasound Imaging in Obstetrics and Gynecology (2023) · cites this paper as [214]
The Discussion (page unavailable) identifies manual selection of the plane of minimal hiatal dimensions as a limitation before the CNN method can be used clinically. The Methods > Data section (page unavailable) confirms that this plane was obtained manually before CNN processing. The paper does not describe this step as manual selection of a region of interest (ROI), so the claim's specific term is not established. (LLM, conf=0.84)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The Measurement of Observer Agreement for Categorical Data
Landis, J. R., & Koch, G. G. (1977) · Biometrics · doi:10.2307/2529310 · Cited by 81,148 · cited 1× · see citing works
“For these measurements, mean ± SD and intraclass correlation coefficients (ICCs) with 95% CI were calculated using Python and the ICCs were evaluated according to the subgroup definitions of Landis and Koch 20 .”
MethodGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · see citing works
STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT
Martin Bland, J., & Altman, D. (1986) · The Lancet · doi:10.1016/s0140-6736(86)90837-8 · Cited by 47,965 · see citing works
GAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,268 · see citing works
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332 · cited 1× · see citing works
“In the last 5 years, deep learning has had an increasing impact on automating the analysis of medical imaging data 1 .”
BackgroundFukushima, K. (1980) · Biological Cybernetics · doi:10.1007/bf00344251 · Cited by 5,759 · cited 2× · see citing works
“The TPUS images of 40 subjects were selected randomly (test set 2, TS2) and the PRM and UH were segmented manually at rest, on contraction and on Valsalva, following the same procedure as that used for the first data set.”
BackgroundMethodProceedings of the 26th International Conference on Neural Information Processing Systems
Burges, C. J. C., Bottou, L., Welling, M., Zoubin Ghahramani, A., & Weinberger, K. Q. (2013) · Cited by 1,323 · see citing works
Biometry of the pubovisceral muscle and levator hiatus by three‐dimensional pelvic floor ultrasound
Dietz, H. P., Shek, C., & CLARKE, B. (2005) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.1899 · Cited by 506 · cited 1× · see citing works
“UH dimensions 9,10 and mean echogenicity (MEP) 11–13 and global strain of the puborec-talis muscle (PRM) 14 provide information about PRM composition and function, and are therefore parameters of potential clinical relevance 15,16 .”
BackgroundMuscle ultrasound in neuromuscular disorders
Pillen, S., Arts, I. M. P., & Zwarts, M. J. (2008) · Muscle & Nerve · doi:10.1002/mus.21015 · Cited by 432 · cited 1× · see citing works
“UH dimensions 9,10 and mean echogenicity (MEP) 11–13 and global strain of the puborec-talis muscle (PRM) 14 provide information about PRM composition and function, and are therefore parameters of potential clinical relevance 15,16 .”
BackgroundHough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound
Milletarì, F., Ahmadi, S., Kroll, C., Plate, A., Rozanski, V. E., Maiostre, J., Levin, J., Dietrich, O., Ertl-Wagner, B. B., Bötzel, K., et al. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2017.04.002 · Cited by 394 · see citing works
Minimal criteria for the diagnosis of avulsion of the puborectalis muscle by tomographic ultrasound
Dietz, H. P., Bernardo, M. J., Kirby, A. C., & Shek, K. L. (2010) · International Urogynecology Journal · doi:10.1007/s00192-010-1329-4 · Cited by 343 · cited 1× · see citing works
“Avulsion of the PRM influences its appearance on TPUS and there is no complete agreement between experts on the appearance of avulsions 24–27 .”
BackgroundAlzheimer rsquo s disease diagnostics by a 3D deeply supervised adaptable convolutional network
Ghazal, M. (2018) · Frontiers in Bioscience · doi:10.2741/4606 · Cited by 204 · see citing works
Multi-resolution-Tract CNN with Hybrid Pretrained and Skin-Lesion Trained Layers
Kawahara, J., & Hamarneh, G. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-47157-0_20 · Cited by 174 · cited 1× · see citing works
“In medicine, CNNs are used for diagnosis, for example in discrimination between images of benign and malignant skin lesions 5 and the detection of Alzheimer’s disease on magnetic resonance imaging (MRI) 6 .”
MethodThe levator–urethra gap measurement: a more objective means of determining levator avulsion?
Dietz, H. P., Abbu, A., & Shek, K. L. (2008) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.6268 · Cited by 146 · see citing works
Left Ventricular Systolic Strain in Chronic Kidney Disease and Hemodialysis Patients
Liu, Y.-W., Su, C.-T., Huang, Y., Yang, C.-S., Huang, J., Yang, M.-T., Chen, J.-H., & Tsai, W. (2010) · American Journal of Nephrology · doi:10.1159/000322709 · Cited by 94 · see citing works
The reliability of puborectalis muscle measurements with 3-dimensional ultrasound imaging
Weinstein, M. M., Jung, S.-A., Pretorius, D. H., Nager, C. W., den Boer, D. J., & Mittal, R. K. (2007) · American Journal of Obstetrics and Gynecology · doi:10.1016/j.ajog.2007.02.041 · Cited by 86 · cited 4× · see citing works
“The reliability of the measured clinical parameters with respect to the UH and PRM can be compared to the results obtained manually by Weinstein et al. 10 , van Veelen et al. 18 and Grob et al. 19 .”
BackgroundResultInfluentialvan Veelen, G. A., Schweitzer, K. J., & van der Vaart, C. H. (2013) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.12523 · Cited by 38 · see citing works
van Delft, K. W. M., Sultan, A. H., Thakar, R., Shobeiri, S. A., & Kluivers, K. B. (2014) · International Urogynecology Journal · doi:10.1007/s00192-014-2426-6 · Cited by 34 · see citing works
Bonmati, E., Hu, Y., Sindhwani, N., Dietz, H., D'hooge, J., Barratt, D. C., Deprest, J. A., & Vercauteren, T. K. (2018) · Lirias (KU Leuven) · doi:10.1117/1.jmi · Cited by 32 · see citing works
Semi-automatic outlining of levator hiatus
Sindhwani, N., Barbosa, D., Alessandrini, M., Heyde, B., Dietz, H. P., D’hooge, J., & Deprest, J. A. (2015) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.15777 · Cited by 26 · cited 2× · see citing works
“Our results can be compared to the (semi) automatic segmentation results obtained for the UH, reported previously by Sindhwani et al. 22 and Bonmati et al. 8 .”
ResultBonmati, E., Hu, Y., Sindhwani, N., Dietz, H. P., D’hooge, J., Barratt, D. C., Deprest, J. A., & Vercauteren, T. K. (2018) · Journal of medical imaging · doi:10.1117/1.jmi.5.2.021206 · Cited by 26 · cited 3× · see citing works
“Segmentation can also be learned by CNN and was found to be successful in, for example, segmenting brain structures on MRI and ultrasound 7 and segmentation of the urogenital hiatus (UH) 8 .”
BackgroundMethodResultAutomatic segmentation of puborectalis muscle on three‐dimensional transperineal ultrasound
van den Noort, F., Grob, A. T. M., Slump, C. H., van der Vaart, C. H., & van Stralen, M. (2017) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.18927 · Cited by 20 · cited 3× · see citing works
“The DSI values were lower for the PRM than for the UH because DSI is sensitive to the shape of segmentations; round segmentations (such as the UH) are more likely to have high DSI values as compared with thin segmentations (such as the PRM) 17 .”
BackgroundMethodInfluentialMeasuring echogenicity and area of the puborectalis muscle: method and reliability
Grob, A. T. M., Veen, A., Schweitzer, K. J., Withagen, M. I. J., van Veelen, G. A., & van der Vaart, C. H. (2014) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.13409 · Cited by 18 · cited 3× · see citing works
“The reliability of the measured clinical parameters with respect to the UH and PRM can be compared to the results obtained manually by Weinstein et al. 10 , van Veelen et al. 18 and Grob et al. 19 .”
MethodResultSilva, A. S. D., Digesu, G. A., Dell’Utri, C., Fritsch, H., Pifarotti, P., & Khullar, V. (2015) · Neurourology and Urodynamics · doi:10.1002/nau.22781 · Cited by 17 · see citing works
van Veelen, G. A., Schweitzer, K. J., van Delft, K. W. M., Kluivers, K. B., Weemhoff, M., & van der Vaart, C. H. (2014) · International Urogynecology Journal · doi:10.1007/s00192-014-2414-x · Cited by 15 · see citing works
Changes in the mean echogenicity and area of the puborectalis muscle during pregnancy and postpartum
Grob, A. T. M., Withagen, M. I. J., van de Waarsenburg, M. K., Schweitzer, K. J., & van der Vaart, C. H. (2015) · International Urogynecology Journal · doi:10.1007/s00192-015-2905-4 · Cited by 13 · cited 8× · see citing works
“From these segmentations, we could measure reliably the width, length and area of the UH, MEP and length of the PRM.”
BackgroundMethodInfluentialStructural changes in puborectalis muscle after vaginal delivery
van de Waarsenburg, M. K., van der Vaart, C. H., & Withagen, M. I. J. (2018) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.19170 · Cited by 13 · cited 1× · see citing works
“UH dimensions 9,10 and mean echogenicity (MEP) 11–13 and global strain of the puborec-talis muscle (PRM) 14 provide information about PRM composition and function, and are therefore parameters of potential clinical relevance 15,16 .”
BackgroundChanges in global strain of puborectalis muscle during pregnancy and postpartum
Grob, A. T. M., Hitschrich, N., van de Waarsenburg, M. K., Withagen, M. I. J., Schweitzer, K. J., & van der Vaart, C. H. (2017) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.17488 · Cited by 10 · cited 1× · see citing works
“UH dimensions 9,10 and mean echogenicity (MEP) 11–13 and global strain of the puborec-talis muscle (PRM) 14 provide information about PRM composition and function, and are therefore parameters of potential clinical relevance 15,16 .”
BackgroundAssociation of First-Trimester Echogenicity of the Puborectalis Muscle With Mode of Delivery
Grob, A. T. M., Withagen, M. I. J., van de Waarsenburg, M. K., Schweitzer, K. J., & van der Vaart, C. H. (2016) · Obstetrics and Gynecology · doi:10.1097/aog.0000000000001443 · Cited by 6 · cited 2× · see citing works
“In a previous study 12 , ultrasound images from the 253 women had been segmented manually in the plane of minimal hiatal dimensions.”
Method
Flagged first, then by citations
Research works printed but not linked: 1
- [23]Goodfellow IJ, Pouget‐Abadie J, Mirza M, Xu B, Warde‐Farley D, Ozair S, Courville A, Bengio Y. Generative adversarial nets In Proceedings of the 27th International Conference on Neural Information Processing Systems, vol 2, Ghahramani Z, Welling M, Cortes C, Lawrence ND, Weinberger KQ (eds). MIT Press, Cambridge, MA, 2014; 2672– 2680.
Cited by
Sorted by citations
Application of Artificial Intelligence in Medicine: An Overview
Liu, P.-R., Lu, L., Zhang, J.-Y., Huo, T.-T., Liu, S.-X., & Ye, Z.-W. (2021) · Current Medical Science · doi:10.1007/s11596-021-2474-3 · Cited by 258 · see citing works
“Other scholars have also confirmed that the use of AI can promote the traditional ultrasonographic detection of tumors in the thyroid, breast, bronchia, puborectalis muscle, and urogenital hiatus as well as other obstetric and gynecological lesions, with a high efficiency and accuracy [39–44] .”
The Integration of Artificial Intelligence into Clinical Practice
Karalis, V. D. (2024) · Applied Biosciences · doi:10.3390/applbiosci3010002 · Cited by 255 · see citing works
“Deep learning algorithms have been utilized in various applications, including identifying muscle diseases [168], determining cone positioning, and segmentation of muscle imaging [169].”
MethodIntroduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology
Drukker, L., Noble, J. A., & Papageorghiou, A. T. (2020) · Ultrasound in Obstetrics & Gynecology · doi:10.1002/uog.22122 · Cited by 240 · see citing works
“…have used AI methodology to evaluate adnexal masses 21 , the risk of lymph node metastases in endometrial cancer 22 , pelvic organ function 23,24 and breast lesions 25–27 , assess aneuploidy risk 28 , predict fetal lung maturity 29 , perinatal outcome 30 , shoulder dystocia 31 and brain…”
MethodArtificial intelligence in ultrasound
Shen, Y., Chen, L., Yue, W., & Xu, H. (2021) · European Journal of Radiology · doi:10.1016/j.ejrad.2021.109717 · Cited by 220 · see citing works
Dhombres, F., Bonnard, J., Bailly, K., Maurice, P., Papageorghiou, A. T., & Jouannic, J.-M. (2022) · Journal of Medical Internet Research · doi:10.2196/35465 · Cited by 93 · see citing works
“The two main AI methods in the 66 selected papers were represented by ML methods [14-47,66-70] (59%, n=39) and by knowledge base methods [50-65,71-79] (38%, n=25).”
BackgroundMethodInfluentialMachine learning methods to support personalized neuromusculoskeletal modelling
Saxby, D. J., Killen, B. A., Pizzolato, C., Carty, C. P., Diamond, L. E., Modenese, L., Fernandez, J., Davico, G., Barzan, M., Lenton, G. K., et al. (2020) · Biomechanics and Modeling in Mechanobiology · doi:10.1007/s10237-020-01367-8 · Cited by 90 · see citing works
Artificial intelligence (AI) in the detection of rectosigmoid deep endometriosis
Guerriero, S., Pascual, M. A., AJOSSA, S., Neri, M., Musa, E., Graupera, B., Rodríguez, I., & Alcázar, J. L. (2021) · European Journal of Obstetrics & Gynecology and Reproductive Biology · doi:10.1016/j.ejogrb.2021.04.012 · Cited by 62 · see citing works
Jost, E., Kosian, P., Jimenez Cruz, J., Albarqouni, S., Gembruch, U., Strizek, B., & Recker, F. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12216833 · Cited by 44 · see citing works
Deep learning-based decision support system for weeds detection in wheat fields
Jabir, B., & Falih, N. (2021) · International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering · doi:10.11591/ijece.v12i1.pp816-825 · Cited by 44 · see citing works
van den Noort, F., Manzini, C., van der Vaart, C. H., van Limbeek, M. A. J., Slump, C. H., & Grob, A. T. M. (2022) · Ultrasound in Obstetrics & Gynecology · doi:10.1002/uog.24810 · Cited by 25 · see citing works
Boissady, E., Comble, A. D. L., Zhu, X., Abbott, J. A., & Hespel, A. (2021) · Frontiers in Veterinary Science · doi:10.3389/fvets.2021.764570 · Cited by 25 · see citing works
Sainz‐Bueno, J. A., Bonomi, M. J., Suárez-Serrano, C., Medrano-Sánchez, E. M., Sánchez, A. A., Fernández-Palacín, A., & García‐Mejido, J. A. (2022) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-21-877 · Cited by 24 · see citing works
Ke, J., Lv, Y., Ma, F., Du, Y., Xiong, S., Wang, J., & Wang, J. (2023) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-22-658 · Cited by 21 · see citing works
“Applying such deep learning-based approaches in medicine has resulted in major breakthroughs in various surgical fields (20-24).”
Automatic Extraction of Hiatal Dimensions in 3-D Transperineal Pelvic Ultrasound Recordings
Williams, H., Cattani, L., Van Schoubroeck, D., Yaqub, M., Sudre, C., Vercauteren, T., D'Hooge, J., & Deprest, J. (2021) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2021.08.009 · Cited by 19 · see citing works
Zhang, M., Lin, X., Zheng, Z., Chen, Y., Ren, Y., & Zhang, X. (2021) · International Urogynecology Journal · doi:10.1007/s00192-021-04859-y · Cited by 18 · see citing works
Current developments in artificial intelligence from obstetrics and gynecology to urogynecology
Seval, M. M., & Varlı, B. (2023) · Frontiers in Medicine · doi:10.3389/fmed.2023.1098205 · Cited by 18 · see citing works
Development and validation of a composite AI model for the diagnosis of levator ani muscle avulsion
Wu, S., Ren, Y., Lin, X., Huang, Z., Zheng, Z., & Zhang, X. (2022) · European Radiology · doi:10.1007/s00330-022-08754-y · Cited by 15 · see citing works
García‐Mejido, J. A., Solis‐Martín, D., Martín‐Morán, M., de Paz, C. F.-C., Palacín, F. F., & Sainz‐Bueno, J. A. (2024) · International Urogynecology Journal · doi:10.1007/s00192-024-05841-0 · Cited by 13 · see citing works
Type of levator ani muscle avulsion as predictor for the disappearance of avulsion
García‐Mejido, J. A., & Sainz‐Bueno, J. A. (2020) · Neurourology and Urodynamics · doi:10.1002/nau.24484 · Cited by 13 · see citing works
A Review of the Challenges in Deep Learning for Skeletal and Smooth Muscle Ultrasound Images
Ardhianto, P., Tsai, J.-Y., Lin, C., Liau, B.-Y., Jan, Y., Akbari, V. B. H., & Lung, C.-W. (2021) · Applied Sciences · doi:10.3390/app11094021 · Cited by 13 · see citing works
“produced measurements with 2D images with a CNN with the urogenital hiatus and puborectalis muscle [37] with 713 images and achieved the highest Dice coefficient without any scarce data solution.”
BackgroundMethodInfluentialDeep learning-based pelvic levator hiatus segmentation from ultrasound images
Huang, Z., Qu, E., Meng, Y.-S., Zhang, M., Wei, Q., Bai, X.-H., & Zhang, X. (2022) · European Journal of Radiology Open · doi:10.1016/j.ejro.2022.100412 · Cited by 12 · see citing works
Zhang, X., Xiang, Y., Yao, J., Hu, X., Wang, Y., Liu, L., Wang, Y., & Wu, Y. (2023) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-22-1198 · Cited by 11 · see citing works
Appearance of the levator ani muscle subdivisions on 3D transperineal ultrasound
Manzini, C., van den Noort, F., Grob, A. T. M., Withagen, M. I. J., Slump, C. H., & van der Vaart, C. H. (2021) · Insights into Imaging · doi:10.1186/s13244-021-01037-y · Cited by 7 · see citing works
Youssef, A., Idris, O., Dodaro, M. G., Badr, I., Donna, G. D., & Kamel, R. (2019) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.20863 · Cited by 7 · see citing works
Ultrasound Diagnosis of Pelvic Organ Prolapse Using Artificial Intelligence
García‐Mejido, J. A., Galán‐Paez, J., Solis‐Martín, D., Palacín, F. F., Fernández-Palacín, A., & Sainz‐Bueno, J. A. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14113634 · Cited by 8 · see citing works
Wei, N., Li, X., Lu, X., Liu, X., Sun, R., & Wang, Y. (2024) · Journal of Ultrasound in Medicine · doi:10.1002/jum.16392 · Cited by 8 · see citing works
“21 The advantages include: 1) Short measurement time and simple operation: Current mainstream automatic measurements require physicians to identify resting frames and maximal Valsalva frames, whereas this can be automatically identi fi ed and generated results after instructing the patients to…”
BackgroundShi, K., Packet, B., Florian, R., Samešová, A., Haenen, K., Deprest, J. A., & Williams, H. (2025) · International Urogynecology Journal · doi:10.1007/s00192-025-06385-7 · Cited by 5 · see citing works
Advancements in artificial intelligence for pelvic floor ultrasound analysis
Huang, X. (2024) · American Journal of Translational Research · doi:10.62347/jxqq5395 · Cited by 5 · see citing works
Automatic Tomographic Ultrasound Imaging Sequence Extraction of the Anal Sphincter
Williams, H., Cattani, L., Vercauteren, T. K., Deprest, J. A., & D’hooge, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87583-1_4 · Cited by 5 · see citing works
Unsupervised convolutional autoencoders for 4D transperineal ultrasound classification
van den Noort, F., Manzini, C., Hofsteenge, M. T., Sırmaçek, B., van der Vaart, C. H., & Slump, C. H. (2023) · Journal of medical imaging · doi:10.1117/1.jmi.10.1.014004 · Cited by 5 · see citing works
“16,20 Recently, there has been a successful method to measure LAM strain on TPUS data.”
BackgroundMethodWu, S., Wu, J., Xu, Y., Tan, J. V. K., Wang, R., & Zhang, X. (2025) · International Urogynecology Journal · doi:10.1007/s00192-025-06211-0 · Cited by 4 · see citing works
Practical Weed Detection Based On Data Fusion Techniques In Precision Agriculture
Alaoui, A. E., Mousannif, H., Ayad, H., & dahmad, H. A. (2022) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis57111.2022.00081 · Cited by 4 · see citing works
“The state of the art in object detection YOLO model has been used to perform weed detection tasks With some modifi-cation, we tried to decrease the number of detection scales to two, and our model had scale coefficients of 0.50 width and 0.33 depth [19].”
MethodInfluentialQu, E., Wu, S., Zhang, M., Huang, Z., Zheng, Z., & Zhang, X. (2023) · International Urogynecology Journal · doi:10.1007/s00192-023-05686-z · Cited by 4 · see citing works
Guo, Z., Lu, X., Yao, J., Zhou, Y., Chen, C., Chen, J., Yang, D., Cao, Y., Zheng, W., Yang, X., et al. (2024) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2024.05.005 · Cited by 4 · see citing works
Chen, Y., Lin, X., Zhang, M., Qu, E., Huang, D., Mao, Y., Huang, Z., & Zhang, X. (2023) · Neurourology and Urodynamics · doi:10.1002/nau.25231 · Cited by 4 · see citing works
Recurrent U-net for automatic pelvic floor muscle segmentation on 3D ultrasoundPreprint
van den Noort, F., Sırmaçek, B., & Slump, C. H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.13833 · Cited by 4 · see citing works
“Segmentation of the urogenital hiatus and the LAM on a specific clinically relevant slice (2D) was successfully achieved with CNNs in two studies [15, 7].”
BackgroundMethodBrain views that benefit from three-dimensional ultrasound
Youssef, A., & Pilu, G. (2021) · Current Opinion in Obstetrics & Gynecology · doi:10.1097/gco.0000000000000689 · Cited by 3 · see citing works
Deep learning for segmentation of colorectal carcinomas on endoscopic ultrasound
van den Noort, F., ter Borg, F., Guitink, A., Faber, J., & Wolterink, J. M. (2024) · Techniques in Coloproctology · doi:10.1007/s10151-024-03056-5 · Cited by 3 · see citing works
Artificial Intelligence to Determine Correct Midsagittal Plane in Dynamic Transperineal Ultrasound
García‐Mejido, J. A., Galán‐Paez, J., Solis‐Martín, D., Martín‐Morán, M., Borrero, C., Fernández‐Gomez, A., Palacín, F. F., & Sainz‐Bueno, J. A. (2025) · Journal of Clinical Ultrasound · doi:10.1002/jcu.24050 · Cited by 2 · see citing works
“The majority of studies on AI in pelvic floor ultrasound are based on CNNs, used to determine the area of the levator hi-atus via three-dimensional ultrasound with a dice similarity index (DSI) greater than 0.9 (van den Noort et al. 2019; Bonmati et al. 2018; Huang et al. 2022; Li et al. 2019).”
InfluentialModern methods of diagnosis of gynecological diseases
Mitrofanova, P. V., Ramazanova, K. S., Khodova, M. E., Gagloeva, K. I., Palchaeva, A. T., Zhukova, V. S., Merkulova, A. P., Beshkok, M. B., Goroeva, A. Z., & Sidorenko, P. O. (2024) · Cardiometry · doi:10.18137/cardiometry.2024.31.138144 · Cited by 1 · see citing works
Zhang, S., He, S., Wu, J., Wang, D., Zeng, P., & Lyu, G. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102582 · Cited by 1 · see citing works
van de Waarsenburg, M. K., Withagen, M. I. J., van den Noort, F., van Leeuwen, J. H. S., & van der Vaart, C. H. (2018) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.20178 · Cited by 1 · see citing works
Automatic analysis of transperineal ultrasound images
den Noort, F. V. L.-V. (2022) · doi:10.3990/1.9789464192292
Aktuelle Aspekte zur künstlichen Intelligenz in der gynäkologischen Diagnostik
Scharf, J. L., Dracopoulos, C., Gembicki, M., Welp, A., & Weichert, J. (2022) · Die Gynäkologie · doi:10.1007/s00129-022-04993-8
Qu, E., & Zhang, M. X. (2023) · Advanced ultrasound in diagnosis and therapy · doi:10.37015/audt.2023.230021
Chen, B., Yi, Y., Zhang, C., Yan, Y., Wang, X., Shui, W., Zhou, M., Yang, G., & Ying, T. (2024) · Technology and Health Care · doi:10.3233/thc-240569
“Van et al. [20] developed a convolutional neural network (CNN) for automatically and reliably segmenting puborectalis muscles and the urogenital hiatus in transperineal ultrasound images of the pelvic floor in the plane of minimal hiatal dimensions.”
Patient-Specific Studies of Pelvic Floor Biomechanics Using Imaging
Wei, Q., Chitnis, P. V., & Shobeiri, S. A. (2025) · Springer eBooks · doi:10.1007/978-3-031-92486-6_20
Automated Recognition and Measurement for Levator Hiatus in 3D Ultrasound
Xu, F., Lin, Q., Xue, W., Xu, J., & Zhang, Y. (2025) · Journal of Ultrasound in Medicine · doi:10.1002/jum.70139
From traditional to digital: Artificial intelligence, transforming ultrasound in rheumatology
Lozano, D. J. M., Medina, Y. F., Beltrán-Ostos, A., & Guillén-Astete, C. A. (2026) · Revista Colombiana de Reumatología · doi:10.1016/j.rcreu.2026.504872
From traditional to digital: Artificial intelligence, transforming ultrasound in rheumatology
Lozano, D. J. M., Medina, Y. F., Beltrán-Ostos, A., & Guillén-Astete, C. A. (2026) · Revista Colombiana de Reumatología (English Edition) · doi:10.1016/j.rcreue.2026.504872
Taşkıran, D., Aslan, S., Kolsuz, S., Alçı, M., & Yiğitbaş, E. Y. (2026) · Diagnostics · doi:10.3390/diagnostics16162576
“…and gynecology, AI has been investigated for several diagnostic and prognostic applications, including the characterization of adnexal lesions, assessment of pelvic floor disorders, prediction of lymphatic dissemination in endometrial malignancies, and evaluation of fetal lung maturation [7–9].”
Zhang, C., Wu, R., 楼海亚, Liang, S., Zhou, L., Hongfei, J., & Li, S. (2026) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2026.08.018
- Authors
- van den Noort, F., van der Vaart, C. H., Grob, A. T. M., van de Waarsenburg, M. K., Slump, C. H., & van Stralen, M.
- Affiliations
- Robotics and Mechatronics, Faculty of Electrical Engineering, Mathematics and Computer Science, Technical Medical Center University of Twente Enschede The Netherlands
- Department of Reproductive Medicine and Gynecology University Medical Center Utrecht The Netherlands
- University of Twente (NL)
- Imaging Division University Medical Center Utrecht Utrecht The Netherlands
- ORCID
- Venue
- Ultrasound in Obstetrics & Gynecology
- Publisher
- Wiley
- Published
- 2019-06-26
- Volume
- 54
- Issue
- 2
- Pages
- 270-275
- ISSN
- 0960-7692 (ISSN-L)
- 1469-0705
- PMC
- PMC6772057
- OpenAlex
- W2900871980
- Cited by
- 52
- References
- 28
- Citations by year
- 2026: 4 · 2025: 7 · 2024: 8 · 2023: 8 · 2022: 7 · 2021: 13 · 2020: 3 · 2019: 1 · 2018: 1
- FWCI
- 2.25
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Ultrasound in Obstetrics and Gynecology (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- University of Twente Research Information (submittedVersion, cc-by-nc)
- Utrecht University Repository (Utrecht University) (submittedVersion, other-oa)
- Funders
- Nederlandse Organisatie voor Wetenschappelijk Onderzoek (15301)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Health Sciences › Medicine › Rheumatology › Pelvic floor disorders treatments
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- puborectalis muscle, urogenital hiatus, transperineal ultrasound, automatic segmentation, convolutional neural networks, pelvic floor, Valsalva maneuver, nulliparous women, pregnancy, 3D/4D ultrasound
- MeSH terms
- Abdominal Muscles, Deep Learning, Evaluation Studies as Topic, Female, Gestational Age, Humans, Muscle Contraction, Nerve Net, Pregnancy, Ultrasonography, Urogenital System, Valsalva Maneuver, Pelvic Floor, Imaging, Three-Dimensional
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
