*Result*: Development of a High-Performance Ultrasound Prediction Model for the Diagnosis of Endometrial Cancer: An Interpretable XGBoost Algorithm Utilizing SHAP Analysis.
Title:
Development of a High-Performance Ultrasound Prediction Model for the Diagnosis of Endometrial Cancer: An Interpretable XGBoost Algorithm Utilizing SHAP Analysis.
Authors:
Lai H; Department of Ultrasound, Fujian Provincial Maternity and Children's Hospital, Fuzhou, China., Wu Q; Department of Ultrasound, Fujian Provincial Maternity and Children's Hospital, Fuzhou, China., Weng Z; Department of Ultrasound, Fujian Provincial Maternity and Children's Hospital, Fuzhou, China., Lyu G; Department of Ultrasound, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, China., Yang W; Department of Ultrasound, Fujian Provincial Maternity and Children's Hospital, Fuzhou, China., Ye F; Department of Ultrasound, Fujian Provincial Maternity and Children's Hospital, Fuzhou, China.
Source:
Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine [J Ultrasound Med] 2026 Mar; Vol. 45 (3), pp. 511-528. Date of Electronic Publication: 2025 Sep 29.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: John Wiley and Sons Country of Publication: England NLM ID: 8211547 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1550-9613 (Electronic) Linking ISSN: 02784297 NLM ISO Abbreviation: J Ultrasound Med Subsets: MEDLINE
Imprint Name(s):
Publication: 2017- : Oxford, UK : John Wiley and Sons
Original Publication: [Philadelphia, Pa.] : W.B. Saunders, c1982-
Original Publication: [Philadelphia, Pa.] : W.B. Saunders, c1982-
MeSH Terms:
Endometrial Neoplasms*/diagnostic imaging , Machine Learning*, Ultrasonography/methods ; Endometrium/diagnostic imaging ; Humans ; Female ; Retrospective Studies ; Middle Aged ; Sensitivity and Specificity ; Adult ; Algorithms ; Aged ; Reproducibility of Results ; Predictive Value of Tests ; Boosting Machine Learning Algorithms
References:
Snijesh VP, Krishnamurthy S, Bhardwaj V, et al. SHH signaling as a key player in endometrial cancer: unveiling the correlation with good prognosis, low proliferation, and anti‐tumor immune milieu. Int J Mol Sci 2024; 25:10443. https://doi.org/10.3390/ijms251910443.
Oaknin A, Bosse TJ, Creutzberg CL, et al. Endometrial cancer: ESMO clinical practice guideline for diagnosis, treatment and follow‐up. Ann Oncol 2022; 33:860–877. https://doi.org/10.1016/j.annonc.2022.05.009.
Ding K, Yuan Y, Chong Q‐Y, et al. Autocrine prolactin stimulates endometrial carcinoma growth and metastasis and reduces sensitivity to chemotherapy. Endocrinology 2017; 158:1595–1611. https://doi.org/10.1210/en.2016-1903.
Huang G‐Q, Xi Y‐Y, Zhang C‐J, Jiang X. Serum human epididymis protein 4 combined with carbohydrate antigen 125 for endometrial carcinoma diagnosis: a meta‐analysis and systematic review. Genet Test Mol Biomarkers 2019; 23:580–588. https://doi.org/10.1089/gtmb.2019.0046.
Haldorsen IS, Salvesen HB. What is the best preoperative imaging for endometrial cancer? Curr Oncol Rep 2016; 18:25. https://doi.org/10.1007/s11912-016-0506-0.
Ascher SM, Reinhold C. Imaging of cancer of the endometrium. Radiol Clin North Am 2002; 40:563–576. https://doi.org/10.1016/s0033-8389(01)00013-6.
Zhang Y, Wang Z, Zhang J, et al. Deep learning model for classifying endometrial lesions. J Transl Med 2021; 19:10. https://doi.org/10.1186/s12967-020-02660-x.
Moro F, Albanese M, Boldrini L, et al. Developing and validating ultrasound‐based radiomics models for predicting high‐risk endometrial cancer. Ultrasound Obstet Gynecol 2022; 60:256–268. https://doi.org/10.1002/uog.24805.
Taddese AA, Tilahun BC, Awoke T, Atnafu A, Mamuye A, Mengiste SA. Deep‐learning models for image‐based gynecological cancer diagnosis: a systematic review and meta‐analysis. Front Oncol 2023; 13:1216326. https://doi.org/10.3389/fonc.2023.1216326.
Stanzione A, Cuocolo R, Del Grosso R, et al. Deep myometrial infiltration of endometrial cancer on MRI: a radiomics‐powered machine learning pilot study. Acad Radiol 2021; 28:737–744. https://doi.org/10.1016/j.acra.2020.02.028.
Yan S, Xiong F, Xin Y, Zhou Z, Liu W. Optimizing evaluation of endometrial receptivity in recurrent pregnancy loss: a preliminary investigation integrating radiomics from multimodal ultrasound via machine learning. Front Endocrinol (Lausanne) 2024; 15:1380829. https://doi.org/10.3389/fendo.2024.1380829.
Topol EJ. High‐performance medicine: the convergence of human and artificial intelligence. Nat Med 2019; 25:44–56. https://doi.org/10.1038/s41591-018-0300-7.
Zelli V, Manno A, Compagnoni C, et al. Classification of tumor types using XGBoost machine learning model: a vector space transformation of genomic alterations. J Transl Med 2023; 21:836. https://doi.org/10.1186/s12967-023-04720-4.
Bhardwaj V, Sharma A, Parambath SV, et al. Machine learning for endometrial cancer prediction and prognostication. Front Oncol 2022; 12:852746. https://doi.org/10.3389/fonc.2022.852746.
Yasar S, Yagin FH, Melekoglu R, Ardigò LP. Integrating proteomics and explainable artificial intelligence: a comprehensive analysis of protein biomarkers for endometrial cancer diagnosis and prognosis. Front Mol Biosci 2024; 11:1389325. https://doi.org/10.3389/fmolb.2024.1389325.
Leone FPG, Timmerman D, Bourne T, et al. Terms, definitions and measurements to describe the sonographic features of the endometrium and intrauterine lesions: a consensus opinion from the International Endometrial Tumor Analysis. Ultrasound Obstet Gynecol 2010; 35:103–112. https://doi.org/10.1002/uog.7487.
Dueholm M, Hjorth IMD, Dahl K, Pedersen LK, Ørtoft G. Identification of endometrial cancers and atypical hyperplasia: development and validation of a simplified system for ultrasound scoring of endometrial pattern. Maturitas 2019; 123:15–24. https://doi.org/10.1016/j.maturitas.2019.01.017.
Stachowicz N, Smoleń A, Ciebiera M, et al. Risk assessment of endometrial hyperplasia or endometrial cancer with simplified ultrasound‐based scoring systems. Diagnostics 2021; 11:442. https://doi.org/10.3390/diagnostics11030442.
Lin X‐L, Zhang D‐S, Ju Z‐Y, Li X‐M, Zhang Y‐Z. Diagnostic value of different color ultrasound diagnostic method in endometrial lesions. World J Clin Cases 2021; 9:5037–5045. https://doi.org/10.12998/wjcc.v9.i19.5037.
Van Holsbeke C, Ameye L, Testa AC, et al. Development and external validation of new ultrasound‐based mathematical models for preoperative prediction of high‐risk endometrial cancer. Ultrasound Obstet Gynecol 2014; 43:586–595. https://doi.org/10.1002/uog.13216.
Lin D, Wang H, Liu L, et al. IETA ultrasonic features combined with GI‐RADS classification system and tumor biomarkers for surveillance of endometrial carcinoma: an innovative study. Cancers (Basel) 2022; 14:5631. https://doi.org/10.3390/cancers14225631.
Park H, Lee HJ, Kim HG, et al. Endometrium segmentation on transvaginal ultrasound image using key‐point discriminator. Med Phys 2019; 46:3974–3984. https://doi.org/10.1002/mp.13677.
Liu X, Qin X, Luo Q, et al. A transvaginal ultrasound‐based deep learning model for the noninvasive diagnosis of myometrial invasion in patients with endometrial cancer: comparison with radiologists. Acad Radiol 2024; 31:2818–2826. https://doi.org/10.1016/j.acra.2023.12.035.
Satei J, Afrakhteh AN, Aldecoa KAT. Endometrial adenocarcinoma in young women: a case report and review of literature. Cureus 2023; 15:e45287. https://doi.org/10.7759/cureus.45287.
Bi Q, Li Q, Yang J, et al. Preliminary application of magnetization transfer imaging in the study of normal uterus and uterine lesions. Front Oncol 2022; 12:853815. https://doi.org/10.3389/fonc.2022.853815.
Thoprasert P, Phaliwong P, Smanchat B, Prommas S, Bhamarapravatana K, Suwannarurk K. Endometrial thickness measurement as predictor of endometrial hyperplasia and cancer in perimenopausal uterine bleeding: cross‐sectional study. Asian Pac J Cancer Prev 2023; 24:693–699. https://doi.org/10.31557/APJCP.2023.24.2.693.
Giannella L, Mfuta K, Setti T, Boselli F, Bergamini E, Cerami LB. Diagnostic accuracy of endometrial thickness for the detection of intra‐uterine pathologies and appropriateness of performed hysteroscopies among asymptomatic postmenopausal women. Eur J Obstet Gynecol Reprod Biol 2014; 177:29–33. https://doi.org/10.1016/j.ejogrb.2014.03.025.
Ghoubara A, Emovon E, Sundar S, Ewies A. Thickened endometrium in asymptomatic postmenopausal women – determining an optimum threshold for prediction of atypical hyperplasia and cancer. J Obstet Gynaecol 2018; 38:1146–1149. https://doi.org/10.1080/01443615.2018.1458081.
Sg V, G R, S H, et al. Risk of endometrial cancer in asymptomatic postmenopausal women in relation to ultrasonographic endometrial thickness: systematic review and diagnostic test accuracy meta‐analysis. Am J Obstet Gynecol 2023; 228:22–35.e2. https://doi.org/10.1016/j.ajog.2022.07.043.
Zhou Y, Mendonca SC, Abel GA, et al. Variation in “fast‐track” referrals for suspected cancer by patient characteristic and cancer diagnosis: evidence from 670 000 patients with cancers of 35 different sites. Br J Cancer 2018; 118:24–31. https://doi.org/10.1038/bjc.2017.381.
Dueholm M, Møller C, Rydbjerg S, Hansen ES, Ørtoft G. An ultrasound algorithm for identification of endometrial cancer. Ultrasound Obstet Gynecol 2014; 43:557–568. https://doi.org/10.1002/uog.13205.
Fischerova D, Frühauf F, Zikan M, et al. Factors affecting sonographic preoperative local staging of endometrial cancer. Ultrasound Obstet Gynecol 2014; 43:575–585. https://doi.org/10.1002/uog.13248.
Epstein E, Van Holsbeke C, Mascilini F, et al. Gray‐scale and color Doppler ultrasound characteristics of endometrial cancer in relation to stage, grade and tumor size. Ultrasound Obstet Gynecol 2011; 38:586–593. https://doi.org/10.1002/uog.9038.
Van Den Bosch T, Verbakel JY, Valentin L, et al. Typical ultrasound features of various endometrial pathologies described using International Endometrial Tumor Analysis (IETA) terminology in women with abnormal uterine bleeding. Ultrasound Obstet Gynecol 2021; 57:164–172. https://doi.org/10.1002/uog.22109.
Alcázar JL, Pascual MÁ, Ajossa S, et al. Reproducibility of the International Endometrial Analysis Group color score for assigning the amount of flow within the endometrium using stored 3‐dimensional volumes. J Ultrasound Med 2017; 36:1347–1354. https://doi.org/10.7863/ultra.16.06002.
Epstein E, Fischerova D, Valentin L, et al. Ultrasound characteristics of endometrial cancer as defined by International Endometrial Tumor Analysis (IETA) consensus nomenclature: prospective multicenter study. Ultrasound Obstet Gynecol 2018; 51:818–828. https://doi.org/10.1002/uog.18909.
Kabil Kucur S, Temizkan O, Atis A, et al. Role of endometrial power Doppler ultrasound using the International Endometrial Tumor Analysis group classification in predicting intrauterine pathology. Arch Gynecol Obstet 2013; 288:649–654. https://doi.org/10.1007/s00404-013-2813-0.
Epstein E, Valentin L. Managing women with post‐menopausal bleeding. Best Pract Res Clin Obstet Gynaecol 2004; 18:125–143. https://doi.org/10.1016/j.bpobgyn.2003.10.001.
Alcazar JL, Galvan R. Three‐dimensional power Doppler ultrasound scanning for the prediction of endometrial cancer in women with postmenopausal bleeding and thickened endometrium. Am J Obstet Gynecol 2009; 200:44.e1–44.e6. https://doi.org/10.1016/j.ajog.2008.08.027.
Chennazhi KP, Nayak NR. Regulation of angiogenesis in the primate endometrium: vascular endothelial growth factor. Semin Reprod Med 2009; 27:80–89. https://doi.org/10.1055/s-0028-1108012.
Ferrara N, Gerber H‐P, LeCouter J. The biology of VEGF and its receptors. Nat Med 2003; 9:669–676. https://doi.org/10.1038/nm0603-669.
Heremans R, Van Den Bosch T, Valentin L, et al. Ultrasound features of endometrial pathology in women without abnormal uterine bleeding: results from the International Endometrial Tumor Analysis study (IETA3). Ultrasound Obstet Gynecol 2022; 60:243–255. https://doi.org/10.1002/uog.24910.
Chen B, Wang P, He W, et al. Standardized IETA criteria enhance accuracy of junior and intermediate ultrasound radiologists in diagnosing malignant endometrial and intrauterine lesions. Ultrasound Obstet Gynecol 2024; 64:528–537. https://doi.org/10.1002/uog.29102.
Petrila O, Nistor I, Romedea NS, Negru D, Scripcariu V. Can the ADC value be used as an imaging “biopsy” in endometrial cancer? 2024; 14:325. https://doi.org/10.3390/diagnostics14030325.
Sarvi F, Alleyassin A, Aghahosseini M, Ghasemi M, Gity S. Hysteroscopy: A necessary method for detecting uterine pathologies in post‐menopausal women with abnormal uterine bleeding or increased endometrial thickness. Turk J Obstet Gynecol 2016; 13:183–188. https://doi.org/10.4274/tjod.66674.
Oaknin A, Bosse TJ, Creutzberg CL, et al. Endometrial cancer: ESMO clinical practice guideline for diagnosis, treatment and follow‐up. Ann Oncol 2022; 33:860–877. https://doi.org/10.1016/j.annonc.2022.05.009.
Ding K, Yuan Y, Chong Q‐Y, et al. Autocrine prolactin stimulates endometrial carcinoma growth and metastasis and reduces sensitivity to chemotherapy. Endocrinology 2017; 158:1595–1611. https://doi.org/10.1210/en.2016-1903.
Huang G‐Q, Xi Y‐Y, Zhang C‐J, Jiang X. Serum human epididymis protein 4 combined with carbohydrate antigen 125 for endometrial carcinoma diagnosis: a meta‐analysis and systematic review. Genet Test Mol Biomarkers 2019; 23:580–588. https://doi.org/10.1089/gtmb.2019.0046.
Haldorsen IS, Salvesen HB. What is the best preoperative imaging for endometrial cancer? Curr Oncol Rep 2016; 18:25. https://doi.org/10.1007/s11912-016-0506-0.
Ascher SM, Reinhold C. Imaging of cancer of the endometrium. Radiol Clin North Am 2002; 40:563–576. https://doi.org/10.1016/s0033-8389(01)00013-6.
Zhang Y, Wang Z, Zhang J, et al. Deep learning model for classifying endometrial lesions. J Transl Med 2021; 19:10. https://doi.org/10.1186/s12967-020-02660-x.
Moro F, Albanese M, Boldrini L, et al. Developing and validating ultrasound‐based radiomics models for predicting high‐risk endometrial cancer. Ultrasound Obstet Gynecol 2022; 60:256–268. https://doi.org/10.1002/uog.24805.
Taddese AA, Tilahun BC, Awoke T, Atnafu A, Mamuye A, Mengiste SA. Deep‐learning models for image‐based gynecological cancer diagnosis: a systematic review and meta‐analysis. Front Oncol 2023; 13:1216326. https://doi.org/10.3389/fonc.2023.1216326.
Stanzione A, Cuocolo R, Del Grosso R, et al. Deep myometrial infiltration of endometrial cancer on MRI: a radiomics‐powered machine learning pilot study. Acad Radiol 2021; 28:737–744. https://doi.org/10.1016/j.acra.2020.02.028.
Yan S, Xiong F, Xin Y, Zhou Z, Liu W. Optimizing evaluation of endometrial receptivity in recurrent pregnancy loss: a preliminary investigation integrating radiomics from multimodal ultrasound via machine learning. Front Endocrinol (Lausanne) 2024; 15:1380829. https://doi.org/10.3389/fendo.2024.1380829.
Topol EJ. High‐performance medicine: the convergence of human and artificial intelligence. Nat Med 2019; 25:44–56. https://doi.org/10.1038/s41591-018-0300-7.
Zelli V, Manno A, Compagnoni C, et al. Classification of tumor types using XGBoost machine learning model: a vector space transformation of genomic alterations. J Transl Med 2023; 21:836. https://doi.org/10.1186/s12967-023-04720-4.
Bhardwaj V, Sharma A, Parambath SV, et al. Machine learning for endometrial cancer prediction and prognostication. Front Oncol 2022; 12:852746. https://doi.org/10.3389/fonc.2022.852746.
Yasar S, Yagin FH, Melekoglu R, Ardigò LP. Integrating proteomics and explainable artificial intelligence: a comprehensive analysis of protein biomarkers for endometrial cancer diagnosis and prognosis. Front Mol Biosci 2024; 11:1389325. https://doi.org/10.3389/fmolb.2024.1389325.
Leone FPG, Timmerman D, Bourne T, et al. Terms, definitions and measurements to describe the sonographic features of the endometrium and intrauterine lesions: a consensus opinion from the International Endometrial Tumor Analysis. Ultrasound Obstet Gynecol 2010; 35:103–112. https://doi.org/10.1002/uog.7487.
Dueholm M, Hjorth IMD, Dahl K, Pedersen LK, Ørtoft G. Identification of endometrial cancers and atypical hyperplasia: development and validation of a simplified system for ultrasound scoring of endometrial pattern. Maturitas 2019; 123:15–24. https://doi.org/10.1016/j.maturitas.2019.01.017.
Stachowicz N, Smoleń A, Ciebiera M, et al. Risk assessment of endometrial hyperplasia or endometrial cancer with simplified ultrasound‐based scoring systems. Diagnostics 2021; 11:442. https://doi.org/10.3390/diagnostics11030442.
Lin X‐L, Zhang D‐S, Ju Z‐Y, Li X‐M, Zhang Y‐Z. Diagnostic value of different color ultrasound diagnostic method in endometrial lesions. World J Clin Cases 2021; 9:5037–5045. https://doi.org/10.12998/wjcc.v9.i19.5037.
Van Holsbeke C, Ameye L, Testa AC, et al. Development and external validation of new ultrasound‐based mathematical models for preoperative prediction of high‐risk endometrial cancer. Ultrasound Obstet Gynecol 2014; 43:586–595. https://doi.org/10.1002/uog.13216.
Lin D, Wang H, Liu L, et al. IETA ultrasonic features combined with GI‐RADS classification system and tumor biomarkers for surveillance of endometrial carcinoma: an innovative study. Cancers (Basel) 2022; 14:5631. https://doi.org/10.3390/cancers14225631.
Park H, Lee HJ, Kim HG, et al. Endometrium segmentation on transvaginal ultrasound image using key‐point discriminator. Med Phys 2019; 46:3974–3984. https://doi.org/10.1002/mp.13677.
Liu X, Qin X, Luo Q, et al. A transvaginal ultrasound‐based deep learning model for the noninvasive diagnosis of myometrial invasion in patients with endometrial cancer: comparison with radiologists. Acad Radiol 2024; 31:2818–2826. https://doi.org/10.1016/j.acra.2023.12.035.
Satei J, Afrakhteh AN, Aldecoa KAT. Endometrial adenocarcinoma in young women: a case report and review of literature. Cureus 2023; 15:e45287. https://doi.org/10.7759/cureus.45287.
Bi Q, Li Q, Yang J, et al. Preliminary application of magnetization transfer imaging in the study of normal uterus and uterine lesions. Front Oncol 2022; 12:853815. https://doi.org/10.3389/fonc.2022.853815.
Thoprasert P, Phaliwong P, Smanchat B, Prommas S, Bhamarapravatana K, Suwannarurk K. Endometrial thickness measurement as predictor of endometrial hyperplasia and cancer in perimenopausal uterine bleeding: cross‐sectional study. Asian Pac J Cancer Prev 2023; 24:693–699. https://doi.org/10.31557/APJCP.2023.24.2.693.
Giannella L, Mfuta K, Setti T, Boselli F, Bergamini E, Cerami LB. Diagnostic accuracy of endometrial thickness for the detection of intra‐uterine pathologies and appropriateness of performed hysteroscopies among asymptomatic postmenopausal women. Eur J Obstet Gynecol Reprod Biol 2014; 177:29–33. https://doi.org/10.1016/j.ejogrb.2014.03.025.
Ghoubara A, Emovon E, Sundar S, Ewies A. Thickened endometrium in asymptomatic postmenopausal women – determining an optimum threshold for prediction of atypical hyperplasia and cancer. J Obstet Gynaecol 2018; 38:1146–1149. https://doi.org/10.1080/01443615.2018.1458081.
Sg V, G R, S H, et al. Risk of endometrial cancer in asymptomatic postmenopausal women in relation to ultrasonographic endometrial thickness: systematic review and diagnostic test accuracy meta‐analysis. Am J Obstet Gynecol 2023; 228:22–35.e2. https://doi.org/10.1016/j.ajog.2022.07.043.
Zhou Y, Mendonca SC, Abel GA, et al. Variation in “fast‐track” referrals for suspected cancer by patient characteristic and cancer diagnosis: evidence from 670 000 patients with cancers of 35 different sites. Br J Cancer 2018; 118:24–31. https://doi.org/10.1038/bjc.2017.381.
Dueholm M, Møller C, Rydbjerg S, Hansen ES, Ørtoft G. An ultrasound algorithm for identification of endometrial cancer. Ultrasound Obstet Gynecol 2014; 43:557–568. https://doi.org/10.1002/uog.13205.
Fischerova D, Frühauf F, Zikan M, et al. Factors affecting sonographic preoperative local staging of endometrial cancer. Ultrasound Obstet Gynecol 2014; 43:575–585. https://doi.org/10.1002/uog.13248.
Epstein E, Van Holsbeke C, Mascilini F, et al. Gray‐scale and color Doppler ultrasound characteristics of endometrial cancer in relation to stage, grade and tumor size. Ultrasound Obstet Gynecol 2011; 38:586–593. https://doi.org/10.1002/uog.9038.
Van Den Bosch T, Verbakel JY, Valentin L, et al. Typical ultrasound features of various endometrial pathologies described using International Endometrial Tumor Analysis (IETA) terminology in women with abnormal uterine bleeding. Ultrasound Obstet Gynecol 2021; 57:164–172. https://doi.org/10.1002/uog.22109.
Alcázar JL, Pascual MÁ, Ajossa S, et al. Reproducibility of the International Endometrial Analysis Group color score for assigning the amount of flow within the endometrium using stored 3‐dimensional volumes. J Ultrasound Med 2017; 36:1347–1354. https://doi.org/10.7863/ultra.16.06002.
Epstein E, Fischerova D, Valentin L, et al. Ultrasound characteristics of endometrial cancer as defined by International Endometrial Tumor Analysis (IETA) consensus nomenclature: prospective multicenter study. Ultrasound Obstet Gynecol 2018; 51:818–828. https://doi.org/10.1002/uog.18909.
Kabil Kucur S, Temizkan O, Atis A, et al. Role of endometrial power Doppler ultrasound using the International Endometrial Tumor Analysis group classification in predicting intrauterine pathology. Arch Gynecol Obstet 2013; 288:649–654. https://doi.org/10.1007/s00404-013-2813-0.
Epstein E, Valentin L. Managing women with post‐menopausal bleeding. Best Pract Res Clin Obstet Gynaecol 2004; 18:125–143. https://doi.org/10.1016/j.bpobgyn.2003.10.001.
Alcazar JL, Galvan R. Three‐dimensional power Doppler ultrasound scanning for the prediction of endometrial cancer in women with postmenopausal bleeding and thickened endometrium. Am J Obstet Gynecol 2009; 200:44.e1–44.e6. https://doi.org/10.1016/j.ajog.2008.08.027.
Chennazhi KP, Nayak NR. Regulation of angiogenesis in the primate endometrium: vascular endothelial growth factor. Semin Reprod Med 2009; 27:80–89. https://doi.org/10.1055/s-0028-1108012.
Ferrara N, Gerber H‐P, LeCouter J. The biology of VEGF and its receptors. Nat Med 2003; 9:669–676. https://doi.org/10.1038/nm0603-669.
Heremans R, Van Den Bosch T, Valentin L, et al. Ultrasound features of endometrial pathology in women without abnormal uterine bleeding: results from the International Endometrial Tumor Analysis study (IETA3). Ultrasound Obstet Gynecol 2022; 60:243–255. https://doi.org/10.1002/uog.24910.
Chen B, Wang P, He W, et al. Standardized IETA criteria enhance accuracy of junior and intermediate ultrasound radiologists in diagnosing malignant endometrial and intrauterine lesions. Ultrasound Obstet Gynecol 2024; 64:528–537. https://doi.org/10.1002/uog.29102.
Petrila O, Nistor I, Romedea NS, Negru D, Scripcariu V. Can the ADC value be used as an imaging “biopsy” in endometrial cancer? 2024; 14:325. https://doi.org/10.3390/diagnostics14030325.
Sarvi F, Alleyassin A, Aghahosseini M, Ghasemi M, Gity S. Hysteroscopy: A necessary method for detecting uterine pathologies in post‐menopausal women with abnormal uterine bleeding or increased endometrial thickness. Turk J Obstet Gynecol 2016; 13:183–188. https://doi.org/10.4274/tjod.66674.
Contributed Indexing:
Keywords: International Endometrial Tumor Analysis; SHAP; XGBoost; endometrial cancer; machine learning; prediction model; ultrasonography
Entry Date(s):
Date Created: 20250930 Date Completed: 20260208 Latest Revision: 20260208
Update Code:
20260209
DOI:
10.1002/jum.70082
PMID:
41024607
Database:
MEDLINE
*Further Information*
*Objectives: To develop and validate an ultrasonography-based machine learning (ML) model for predicting malignant endometrial and cavitary lesions.
Methods: This retrospective study was conducted on patients with pathologically confirmed results following transvaginal or transrectal ultrasound from 2021 to 2023. Endometrial ultrasound features were characterized using the International Endometrial Tumor Analysis (IETA) terminology. The dataset was ranomly divided (7:3) into training and validation sets. LASSO (least absolute shrinkage and selection operator) regression was applied for feature selection, and an extreme gradient boosting (XGBoost) model was developed. Performance was assessed via receiver operating characteristic (ROC) analysis, calibration, decision curve analysis, sensitivity, specificity, and accuracy.
Results: Among 1080 patients, 6 had a non-measurable endometrium. Of the remaining 1074 cases, 641 were premenopausal and 433 postmenopausal. Performance of the XGBoost model on the test set: The area under the curve (AUC) for the premenopausal group was 0.845 (0.781-0.909), with a relatively low sensitivity (0.588, 0.442-0.722) and a relatively high specificity (0.923, 0.863-0.959); the AUC for the postmenopausal group was 0.968 (0.944-0.992), with both sensitivity (0.895, 0.778-0.956) and specificity (0.931, 0.839-0.974) being relatively high. SHapley Additive exPlanations (SHAP) analysis identified key predictors: endometrial-myometrial junction, endometrial thickness, endometrial echogenicity, color Doppler flow score, and vascular pattern in premenopausal women; endometrial thickness, endometrial-myometrial junction, endometrial echogenicity, and color Doppler flow score in postmenopausal women.
Conclusion: The XGBoost-based model exhibited excellent predictive performance, particularly in postmenopausal patients. SHAP analysis further enhances interpretability by identifying key ultrasonographic predictors of malignancy.
(© 2025 American Institute of Ultrasound in Medicine.)*