Performance of radiomics analysis in ultrasound imaging for differentiating benign from malignant adnexal masses: A systematic review and meta‐analysis
Abstract Introduction We present the state of the art of ultrasound‐based machine learning (ML) radiomics models in the context of ovarian masses and analyze their accuracy in differentiating between benign and malignant adnexal masses. Material and Methods Web of Science, PubMed, and Scopus databas...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-08-01
|
| Series: | Acta Obstetricia et Gynecologica Scandinavica |
| Subjects: | |
| Online Access: | https://doi.org/10.1111/aogs.15146 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839619846168379392 |
|---|---|
| author | Francesca Moro Marianna Ciancia Maria Sciuto Giulia Baldassari Huong Elena Tran Antonella Carcagnì Anna Fagotti Antonia Carla Testa |
| author_facet | Francesca Moro Marianna Ciancia Maria Sciuto Giulia Baldassari Huong Elena Tran Antonella Carcagnì Anna Fagotti Antonia Carla Testa |
| author_sort | Francesca Moro |
| collection | DOAJ |
| description | Abstract Introduction We present the state of the art of ultrasound‐based machine learning (ML) radiomics models in the context of ovarian masses and analyze their accuracy in differentiating between benign and malignant adnexal masses. Material and Methods Web of Science, PubMed, and Scopus databases were searched. All studies were imported into RAYYAN QCRI software. All studies that developed and internally or externally validated ML models using only radiomics features extracted from ultrasound images were included. The overall quality of the included studies was assessed using the QUADAS‐AI tool. Summary sensitivity and specificity analyses with corresponding 95% confidence intervals (CIs) were reported. Results 12 studies developed ML models including only radiomics features extracted from ultrasound images, and six of them were included in the meta‐analysis. The overall sensitivity and specificity for differentiating benign from malignant adnexal masses were 0.80 (95% CI 0.74–0.87) and 0.86 (95% CI 0.80–0.90), respectively, in the validation set. All studies demonstrated a high risk of bias in subject selection (e.g., lack of details on image sources or scanner models; absence of image preprocessing), and the majority also showed a high risk in the index test (e.g., models were not validated on external datasets) domain. In contrast, the risk of bias was generally low for the reference standard (i.e., most studies used a reference that accurately identified the target condition) and the testing workflow (i.e., the time interval between the index test and reference standard was appropriate) domains. Conclusions The good performance of ultrasound‐based radiomics models in the validation set supports that radiomics is worth exploring to improve the diagnosis of adnexal masses. So far, the studies have a high risk of bias due to the small sample size, single‐setting design, and no external validation included. |
| format | Article |
| id | doaj-art-ba3187fd83804951a146d8975670a19c |
| institution | Matheson Library |
| issn | 0001-6349 1600-0412 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | Acta Obstetricia et Gynecologica Scandinavica |
| spelling | doaj-art-ba3187fd83804951a146d8975670a19c2025-07-23T01:11:19ZengWileyActa Obstetricia et Gynecologica Scandinavica0001-63491600-04122025-08-0110481433144210.1111/aogs.15146Performance of radiomics analysis in ultrasound imaging for differentiating benign from malignant adnexal masses: A systematic review and meta‐analysisFrancesca Moro0Marianna Ciancia1Maria Sciuto2Giulia Baldassari3Huong Elena Tran4Antonella Carcagnì5Anna Fagotti6Antonia Carla Testa7UniCamillus‐International Medical University Rome ItalyDepartment of Women's, Child and Public Health Sciences Fondazione Policlinico Universitario A. Gemelli, IRCCS Rome ItalyDepartment of Life Sciences and Public Health Università Cattolica del Sacro Cuore Rome ItalyRadiomics G‐STeP Research Core Facility Fondazione Policlinico Universitario A. Gemelli, IRCCS Rome ItalyRadiomics G‐STeP Research Core Facility Fondazione Policlinico Universitario A. Gemelli, IRCCS Rome ItalyEpidemiology and Biostatistics Facility, G‐STeP Generator Fondazione Policlinico Universitario A. Gemelli, IRCCS Rome ItalyDepartment of Women's, Child and Public Health Sciences Fondazione Policlinico Universitario A. Gemelli, IRCCS Rome ItalyDepartment of Women's, Child and Public Health Sciences Fondazione Policlinico Universitario A. Gemelli, IRCCS Rome ItalyAbstract Introduction We present the state of the art of ultrasound‐based machine learning (ML) radiomics models in the context of ovarian masses and analyze their accuracy in differentiating between benign and malignant adnexal masses. Material and Methods Web of Science, PubMed, and Scopus databases were searched. All studies were imported into RAYYAN QCRI software. All studies that developed and internally or externally validated ML models using only radiomics features extracted from ultrasound images were included. The overall quality of the included studies was assessed using the QUADAS‐AI tool. Summary sensitivity and specificity analyses with corresponding 95% confidence intervals (CIs) were reported. Results 12 studies developed ML models including only radiomics features extracted from ultrasound images, and six of them were included in the meta‐analysis. The overall sensitivity and specificity for differentiating benign from malignant adnexal masses were 0.80 (95% CI 0.74–0.87) and 0.86 (95% CI 0.80–0.90), respectively, in the validation set. All studies demonstrated a high risk of bias in subject selection (e.g., lack of details on image sources or scanner models; absence of image preprocessing), and the majority also showed a high risk in the index test (e.g., models were not validated on external datasets) domain. In contrast, the risk of bias was generally low for the reference standard (i.e., most studies used a reference that accurately identified the target condition) and the testing workflow (i.e., the time interval between the index test and reference standard was appropriate) domains. Conclusions The good performance of ultrasound‐based radiomics models in the validation set supports that radiomics is worth exploring to improve the diagnosis of adnexal masses. So far, the studies have a high risk of bias due to the small sample size, single‐setting design, and no external validation included.https://doi.org/10.1111/aogs.15146artificial intelligencemachine learningovarian cancerradiomicsultrasonography |
| spellingShingle | Francesca Moro Marianna Ciancia Maria Sciuto Giulia Baldassari Huong Elena Tran Antonella Carcagnì Anna Fagotti Antonia Carla Testa Performance of radiomics analysis in ultrasound imaging for differentiating benign from malignant adnexal masses: A systematic review and meta‐analysis Acta Obstetricia et Gynecologica Scandinavica artificial intelligence machine learning ovarian cancer radiomics ultrasonography |
| title | Performance of radiomics analysis in ultrasound imaging for differentiating benign from malignant adnexal masses: A systematic review and meta‐analysis |
| title_full | Performance of radiomics analysis in ultrasound imaging for differentiating benign from malignant adnexal masses: A systematic review and meta‐analysis |
| title_fullStr | Performance of radiomics analysis in ultrasound imaging for differentiating benign from malignant adnexal masses: A systematic review and meta‐analysis |
| title_full_unstemmed | Performance of radiomics analysis in ultrasound imaging for differentiating benign from malignant adnexal masses: A systematic review and meta‐analysis |
| title_short | Performance of radiomics analysis in ultrasound imaging for differentiating benign from malignant adnexal masses: A systematic review and meta‐analysis |
| title_sort | performance of radiomics analysis in ultrasound imaging for differentiating benign from malignant adnexal masses a systematic review and meta analysis |
| topic | artificial intelligence machine learning ovarian cancer radiomics ultrasonography |
| url | https://doi.org/10.1111/aogs.15146 |
| work_keys_str_mv | AT francescamoro performanceofradiomicsanalysisinultrasoundimagingfordifferentiatingbenignfrommalignantadnexalmassesasystematicreviewandmetaanalysis AT mariannaciancia performanceofradiomicsanalysisinultrasoundimagingfordifferentiatingbenignfrommalignantadnexalmassesasystematicreviewandmetaanalysis AT mariasciuto performanceofradiomicsanalysisinultrasoundimagingfordifferentiatingbenignfrommalignantadnexalmassesasystematicreviewandmetaanalysis AT giuliabaldassari performanceofradiomicsanalysisinultrasoundimagingfordifferentiatingbenignfrommalignantadnexalmassesasystematicreviewandmetaanalysis AT huongelenatran performanceofradiomicsanalysisinultrasoundimagingfordifferentiatingbenignfrommalignantadnexalmassesasystematicreviewandmetaanalysis AT antonellacarcagni performanceofradiomicsanalysisinultrasoundimagingfordifferentiatingbenignfrommalignantadnexalmassesasystematicreviewandmetaanalysis AT annafagotti performanceofradiomicsanalysisinultrasoundimagingfordifferentiatingbenignfrommalignantadnexalmassesasystematicreviewandmetaanalysis AT antoniacarlatesta performanceofradiomicsanalysisinultrasoundimagingfordifferentiatingbenignfrommalignantadnexalmassesasystematicreviewandmetaanalysis |