Three-Dimensional Measurement of the Uterus on Magnetic Resonance Images: Development and Performance Analysis of an Automated Deep-Learning Tool

Overview

Journal Diagnostics (Basel)

Specialty Radiology

Date 2023 Aug 26

PMID 37627920

Authors

Daphne Mulliez

Edouard Poncelet

Laurie Ferret

Christine Hoeffel

Blandine Hamet

Lan Anh Dang

Nicolas Laurent

Guillaume Ramette

Affiliations

Soon will be listed here.

Abstract

Uterus measurements are useful for assessing both the treatment and follow-ups of gynaecological patients. The aim of our study was to develop a deep learning (DL) tool for fully automated measurement of the three-dimensional size of the uterus on magnetic resonance imaging (MRI). In this single-centre retrospective study, 900 cases were included to train, validate, and test a VGG-16/VGG-11 convolutional neural network (CNN). The ground truth was manual measurement. The performance of the model was evaluated using the objective key point similarity (OKS), the mean difference in millimetres, and coefficient of determination R. The OKS of our model was 0.92 (validation) and 0.96 (test). The average deviation and R coefficient between the AI measurements and the manual ones were, respectively, 3.9 mm and 0.93 for two-point length, 3.7 mm and 0.94 for three-point length, 2.6 mm and 0.93 for width, 4.2 mm and 0.75 for thickness. The inter-radiologist variability was 1.4 mm. A three-dimensional automated measurement was obtained in 1.6 s. In conclusion, our model was able to locate the uterus on MRIs and place measurement points on it to obtain its three-dimensional measurement with a very good correlation compared to manual measurements.

References

Brouwer C, Steenbakkers R, van den Heuvel E, Duppen J, Navran A, Bijl H . 3D Variation in delineation of head and neck organs at risk. Radiat Oncol. 2012; 7:32. PMC: 3337234. DOI: 10.1186/1748-717X-7-32. View

Sforazzini F, Salome P, Moustafa M, Zhou C, Schwager C, Rein K . Deep Learning-based Automatic Lung Segmentation on Multiresolution CT Scans from Healthy and Fibrotic Lungs in Mice. Radiol Artif Intell. 2022; 4(2):e210095. PMC: 8980878. DOI: 10.1148/ryai.210095. View

Hosny A, Parmar C, Quackenbush J, Schwartz L, Aerts H . Artificial intelligence in radiology. Nat Rev Cancer. 2018; 18(8):500-510. PMC: 6268174. DOI: 10.1038/s41568-018-0016-5. View

Ludwin A, Martins W . Correct measurement of uterine fundal internal indentation depth and angle: an important but overlooked issue for precise diagnosis of uterine anomalies. Ultrasound Obstet Gynecol. 2020; 58(3):497-499. DOI: 10.1002/uog.22192. View

Ushinsky A, Bardis M, Glavis-Bloom J, Uchio E, Chantaduly C, Nguyentat M . A 3D-2D Hybrid U-Net Convolutional Neural Network Approach to Prostate Organ Segmentation of Multiparametric MRI. AJR Am J Roentgenol. 2020; 216(1):111-116. DOI: 10.2214/AJR.19.22168. View

Kurata Y, Nishio M, Kido A, Fujimoto K, Yakami M, Isoda H . Automatic segmentation of the uterus on MRI using a convolutional neural network. Comput Biol Med. 2019; 114:103438. DOI: 10.1016/j.compbiomed.2019.103438. View

Taylor S, Romero A, Kammerer-Doak D, Qualls C, Rogers R . Abdominal hysterectomy for the enlarged myomatous uterus compared with vaginal hysterectomy with morcellation. Am J Obstet Gynecol. 2004; 189(6):1579-82. DOI: 10.1016/s0002-9378(03)00942-6. View

Theis M, Tonguc T, Savchenko O, Nowak S, Block W, Recker F . Deep learning enables automated MRI-based estimation of uterine volume also in patients with uterine fibroids undergoing high-intensity focused ultrasound therapy. Insights Imaging. 2023; 14(1):1. PMC: 9813298. DOI: 10.1186/s13244-022-01342-0. View

Kalantar R, Lin G, Winfield J, Messiou C, Lalondrelle S, Blackledge M . Automatic Segmentation of Pelvic Cancers Using Deep Learning: State-of-the-Art Approaches and Challenges. Diagnostics (Basel). 2021; 11(11). PMC: 8625809. DOI: 10.3390/diagnostics11111964. View

10.

Cardenas C, Yang J, Anderson B, Court L, Brock K . Advances in Auto-Segmentation. Semin Radiat Oncol. 2019; 29(3):185-197. DOI: 10.1016/j.semradonc.2019.02.001. View

11.

Bhandary S, Kuhn D, Babaiee Z, Fechter T, Benndorf M, Zamboglou C . Investigation and benchmarking of U-Nets on prostate segmentation tasks. Comput Med Imaging Graph. 2023; 107:102241. DOI: 10.1016/j.compmedimag.2023.102241. View

12.

Egbase P, Al-Sharhan M, Grudzinskas J . Influence of position and length of uterus on implantation and clinical pregnancy rates in IVF and embryo transfer treatment cycles. Hum Reprod. 2000; 15(9):1943-6. DOI: 10.1093/humrep/15.9.1943. View

13.

Bridges N, Cooke A, Healy M, Hindmarsh P, Brook C . Growth of the uterus. Arch Dis Child. 1996; 75(4):330-1. PMC: 1511752. DOI: 10.1136/adc.75.4.330. View

14.

van Assen M, Muscogiuri G, Caruso D, Lee S, Laghi A, De Cecco C . Artificial intelligence in cardiac radiology. Radiol Med. 2020; 125(11):1186-1199. DOI: 10.1007/s11547-020-01277-w. View

15.

Weisberg E . Insertion of intrauterine devices. Med J Aust. 1980; 2(7):359-62. DOI: 10.5694/j.1326-5377.1980.tb131874.x. View

16.

Garfield R, Saade G, Buhimschi C, Buhimschi I, Shi L, Shi S . Control and assessment of the uterus and cervix during pregnancy and labour. Hum Reprod Update. 1999; 4(5):673-95. DOI: 10.1093/humupd/4.5.673. View

17.

Chi I, Champion C, Wilkens L . Cervical dilatation in interval insertion of an IUD. Who requires it and does it lead to a high expulsion rate?. Contraception. 1987; 36(4):403-15. DOI: 10.1016/0010-7824(87)90089-8. View

18.

Thimansson E, Bengtsson J, Baubeta E, Engman J, Flondell-Site D, Bjartell A . Deep learning algorithm performs similarly to radiologists in the assessment of prostate volume on MRI. Eur Radiol. 2022; 33(4):2519-2528. PMC: 10017633. DOI: 10.1007/s00330-022-09239-8. View

19.

Adamou H, Magagi I, Oumarou Garba S, Habou O . Acute intestinal obstruction due to extrinsic compression by previa myoma and ectopic pregnancy: a case report. J Med Case Rep. 2018; 12(1):10. PMC: 5769554. DOI: 10.1186/s13256-017-1540-8. View

20.

Acsinte O, Rabischong B, Bourdel N, Canis M, Botchorishvili R . Laparoscopic Promontofixation in 10 Steps. J Minim Invasive Gynecol. 2017; 25(5):767. DOI: 10.1016/j.jmig.2017.10.020. View