Radiomics-based ultrasOund Model for differentiating Uterine Sarcomas from leiomyomas (ROMUS) : a retrospective pilot Multicenter Italian Trials in Ovarian Cancer (MITO) study
(2026) In Ultrasound in Obstetrics and Gynecology 67(4). p.530-541- Abstract
Objective: To develop machine-learning models that incorporate clinical information and radiomics features extracted from ultrasound images to distinguish uterine sarcomas from leiomyomas. Methods: This retrospective, multicenter, pilot case–control study included 200 patients (100 with a uterine sarcoma and 100 with a usual-type leiomyoma, i.e. including no benign leiomyoma variants) who underwent preoperative ultrasound examination between January 2010 and June 2022. The patient cohort was split (70:30) into training and validation sets, with the same proportion of leiomyomas and sarcomas in each subset. We extracted radiomics features belonging to different families: intensity-based statistical features and textural features. The... (More)
Objective: To develop machine-learning models that incorporate clinical information and radiomics features extracted from ultrasound images to distinguish uterine sarcomas from leiomyomas. Methods: This retrospective, multicenter, pilot case–control study included 200 patients (100 with a uterine sarcoma and 100 with a usual-type leiomyoma, i.e. including no benign leiomyoma variants) who underwent preoperative ultrasound examination between January 2010 and June 2022. The patient cohort was split (70:30) into training and validation sets, with the same proportion of leiomyomas and sarcomas in each subset. We extracted radiomics features belonging to different families: intensity-based statistical features and textural features. The variables used in model building were patient age and the radiomics features that differed statistically significantly between sarcomas and leiomyomas and that were not redundant based on Spearman's correlation coefficient. Logistic regression, random forest, extreme gradient boosting (XGBoost) and support vector machine models were tested in the model development process. We evaluated the performance of the models in differentiating between sarcomas and leiomyomas using the area under the receiver-operating-characteristics curve (AUC), accuracy, sensitivity and specificity. We compared these results to those of subjective assessment by the original ultrasound examiner and to those of two independent expert ultrasound examiners who, blinded to clinical history, reviewed the same grayscale ultrasound images as those used for the radiomics analysis. Results: Sixty-three radiomics features were extracted. Of these, eight differed statistically significantly between sarcomas and leiomyomas and were not correlated, so were selected for inclusion in model building. In the validation set, the model that performed best in differentiating between sarcomas and leiomyomas was an XGBoost model integrating patient age and radiomics features. In the validation set, this model had an AUC of 0.93, sensitivity of 0.93 and specificity of 0.83, at a risk-of-malignancy cut-off of 47% (the cut-off that yielded the highest number of correct classifications based on Youden's index in the training set). The corresponding results for the model integrating only the radiomics features were: AUC of 0.87, sensitivity of 0.87 and specificity of 0.83. Subjective assessment by the original ultrasound examiner had a sensitivity of 0.87 and specificity of 1 in the validation set, while retrospective review of grayscale ultrasound images by ultrasound experts had a sensitivity of 0.87 and specificity of 0.80 (same results for both reviewers). Conclusion: A model including eight radiomics features and patient age demonstrated reasonably good discriminative and classification performance for distinguishing uterine sarcomas from leiomyomas. Its classification ability was similar to that of subjective assessment by the original ultrasound examiner, being more sensitive but less specific. To confirm the role of radiomics for discriminating between uterine sarcomas and leiomyomas, large prospective studies including benign leiomyoma variants are needed. If good performance of radiomics models can be confirmed, integrating automated radiomics analysis into ultrasound machine software may help ultrasound examiners to discriminate between sarcomas and benign leiomyomas.
(Less)
- author
- Ciccarone, F.
; Rizzi, A.
; Biscione, A.
; Baldassari, G.
; Tran, E. H.
; Pasciuto, T.
; Moro, F.
; Zinicola, G.
; Buonomo, F.
; Colombin, M.
; Ghezzi, F.
; Casarin, J.
; Mancari, R.
; Borella, F.
; Kardhashi, A.
; Roccio, M.
; Savelli, L.
; Cioffi, R.
; Fanfani, F.
; Ferrandina, G.
; Scambia, G.
; Valentin, L.
LU
; Lorusso, D.
and Testa, A. C.
(Less) - organization
- publishing date
- 2026-04
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- artificial intelligence, leiomyoma, radiomics, sarcomas, ultrasonography, uterine neoplasms
- in
- Ultrasound in Obstetrics and Gynecology
- volume
- 67
- issue
- 4
- pages
- 12 pages
- publisher
- John Wiley & Sons Inc.
- external identifiers
-
- scopus:105032149850
- pmid:41791853
- ISSN
- 0960-7692
- DOI
- 10.1002/uog.70187
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2026 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.
- id
- 41ade7ef-295c-49ec-a889-7e2974df22f6
- date added to LUP
- 2026-05-07 15:24:56
- date last changed
- 2026-06-18 18:40:39
@article{41ade7ef-295c-49ec-a889-7e2974df22f6,
abstract = {{<p>Objective: To develop machine-learning models that incorporate clinical information and radiomics features extracted from ultrasound images to distinguish uterine sarcomas from leiomyomas. Methods: This retrospective, multicenter, pilot case–control study included 200 patients (100 with a uterine sarcoma and 100 with a usual-type leiomyoma, i.e. including no benign leiomyoma variants) who underwent preoperative ultrasound examination between January 2010 and June 2022. The patient cohort was split (70:30) into training and validation sets, with the same proportion of leiomyomas and sarcomas in each subset. We extracted radiomics features belonging to different families: intensity-based statistical features and textural features. The variables used in model building were patient age and the radiomics features that differed statistically significantly between sarcomas and leiomyomas and that were not redundant based on Spearman's correlation coefficient. Logistic regression, random forest, extreme gradient boosting (XGBoost) and support vector machine models were tested in the model development process. We evaluated the performance of the models in differentiating between sarcomas and leiomyomas using the area under the receiver-operating-characteristics curve (AUC), accuracy, sensitivity and specificity. We compared these results to those of subjective assessment by the original ultrasound examiner and to those of two independent expert ultrasound examiners who, blinded to clinical history, reviewed the same grayscale ultrasound images as those used for the radiomics analysis. Results: Sixty-three radiomics features were extracted. Of these, eight differed statistically significantly between sarcomas and leiomyomas and were not correlated, so were selected for inclusion in model building. In the validation set, the model that performed best in differentiating between sarcomas and leiomyomas was an XGBoost model integrating patient age and radiomics features. In the validation set, this model had an AUC of 0.93, sensitivity of 0.93 and specificity of 0.83, at a risk-of-malignancy cut-off of 47% (the cut-off that yielded the highest number of correct classifications based on Youden's index in the training set). The corresponding results for the model integrating only the radiomics features were: AUC of 0.87, sensitivity of 0.87 and specificity of 0.83. Subjective assessment by the original ultrasound examiner had a sensitivity of 0.87 and specificity of 1 in the validation set, while retrospective review of grayscale ultrasound images by ultrasound experts had a sensitivity of 0.87 and specificity of 0.80 (same results for both reviewers). Conclusion: A model including eight radiomics features and patient age demonstrated reasonably good discriminative and classification performance for distinguishing uterine sarcomas from leiomyomas. Its classification ability was similar to that of subjective assessment by the original ultrasound examiner, being more sensitive but less specific. To confirm the role of radiomics for discriminating between uterine sarcomas and leiomyomas, large prospective studies including benign leiomyoma variants are needed. If good performance of radiomics models can be confirmed, integrating automated radiomics analysis into ultrasound machine software may help ultrasound examiners to discriminate between sarcomas and benign leiomyomas.</p>}},
author = {{Ciccarone, F. and Rizzi, A. and Biscione, A. and Baldassari, G. and Tran, E. H. and Pasciuto, T. and Moro, F. and Zinicola, G. and Buonomo, F. and Colombin, M. and Ghezzi, F. and Casarin, J. and Mancari, R. and Borella, F. and Kardhashi, A. and Roccio, M. and Savelli, L. and Cioffi, R. and Fanfani, F. and Ferrandina, G. and Scambia, G. and Valentin, L. and Lorusso, D. and Testa, A. C.}},
issn = {{0960-7692}},
keywords = {{artificial intelligence; leiomyoma; radiomics; sarcomas; ultrasonography; uterine neoplasms}},
language = {{eng}},
number = {{4}},
pages = {{530--541}},
publisher = {{John Wiley & Sons Inc.}},
series = {{Ultrasound in Obstetrics and Gynecology}},
title = {{Radiomics-based ultrasOund Model for differentiating Uterine Sarcomas from leiomyomas (ROMUS) : a retrospective pilot Multicenter Italian Trials in Ovarian Cancer (MITO) study}},
url = {{http://dx.doi.org/10.1002/uog.70187}},
doi = {{10.1002/uog.70187}},
volume = {{67}},
year = {{2026}},
}