Development and Validation of an Interpretable Model Integrating Multimodal Information for Improving Ovarian Cancer Diagnosis

Overview

Journal Nat Commun

Specialty Biology

Date 2024 Mar 28

PMID 38538600

Authors

Huiling Xiang

Yongjie Xiao

Fang Li

Chunyan Li

Lixian Liu

Tingting Deng

Cuiju Yan

Fengtao Zhou

Xi Wang

Jinjing Ou

Qingguang Lin

Ruixia Hong

Lishu Huang

Luyang Luo

Huangjing Lin

Xi Lin

Hao Chen

Affiliations

Soon will be listed here.

Abstract

Ovarian cancer, a group of heterogeneous diseases, presents with extensive characteristics with the highest mortality among gynecological malignancies. Accurate and early diagnosis of ovarian cancer is of great significance. Here, we present OvcaFinder, an interpretable model constructed from ultrasound images-based deep learning (DL) predictions, Ovarian-Adnexal Reporting and Data System scores from radiologists, and routine clinical variables. OvcaFinder outperforms the clinical model and the DL model with area under the curves (AUCs) of 0.978, and 0.947 in the internal and external test datasets, respectively. OvcaFinder assistance led to improved AUCs of radiologists and inter-reader agreement. The average AUCs were improved from 0.927 to 0.977 and from 0.904 to 0.941, and the false positive rates were decreased by 13.4% and 8.3% in the internal and external test datasets, respectively. This highlights the potential of OvcaFinder to improve the diagnostic accuracy, and consistency of radiologists in identifying ovarian cancer.

Citing Articles

Quantitative vascular feature-based multimodality prediction model for multi-origin malignant cervical lymphadenopathy.

Li C, Li R, Ou J, Li F, Deng T, Yan C EClinicalMedicine. 2025; 81:103085.

PMID: 40026834 PMC: 11870188. DOI: 10.1016/j.eclinm.2025.103085.

Clinical Application of Artificial Intelligence in Ultrasound Imaging for Oncology.

Komatsu M, Teraya N, Natsume T, Harada N, Takeda K, Hamamoto R JMA J. 2025; 8(1):18-25.

PMID: 39926099 PMC: 11799696. DOI: 10.31662/jmaj.2024-0203.

Multimodal deep learning approaches for precision oncology: a comprehensive review.

Yang H, Yang M, Chen J, Yao G, Zou Q, Jia L Brief Bioinform. 2025; 26(1).

PMID: 39757116 PMC: 11700660. DOI: 10.1093/bib/bbae699.

Robust and interpretable deep learning system for prognostic stratification of extranodal natural killer/T-cell lymphoma.

Jiang C, Jiang Z, Zhang X, Qu L, Fu K, Teng Y Eur J Nucl Med Mol Imaging. 2024; .

PMID: 39714634 DOI: 10.1007/s00259-024-07024-x.

Development and validation of a deep learning pipeline to diagnose ovarian masses using ultrasound screening: a retrospective multicenter study.

Dai W, Wu Y, Ling Y, Zhao J, Zhang S, Gu Z EClinicalMedicine. 2024; 78:102923.

PMID: 39640935 PMC: 11617315. DOI: 10.1016/j.eclinm.2024.102923.

References

Buys S, Partridge E, Black A, Johnson C, Lamerato L, Isaacs C . Effect of screening on ovarian cancer mortality: the Prostate, Lung, Colorectal and Ovarian (PLCO) Cancer Screening Randomized Controlled Trial. JAMA. 2011; 305(22):2295-303. DOI: 10.1001/jama.2011.766. View

Amor F, Vaccaro H, Alcazar J, Leon M, Craig J, Martinez J . Gynecologic imaging reporting and data system: a new proposal for classifying adnexal masses on the basis of sonographic findings. J Ultrasound Med. 2009; 28(3):285-91. DOI: 10.7863/jum.2009.28.3.285. View

Luo L, Chen H, Xiao Y, Zhou Y, Wang X, Vardhanabhuti V . Rethinking Annotation Granularity for Overcoming Shortcuts in Deep Learning-based Radiograph Diagnosis: A Multicenter Study. Radiol Artif Intell. 2022; 4(5):e210299. PMC: 9530769. DOI: 10.1148/ryai.210299. View

Woo Y, Kyrgiou M, Bryant A, Everett T, Dickinson H . Centralisation of services for gynaecological cancers - a Cochrane systematic review. Gynecol Oncol. 2012; 126(2):286-90. DOI: 10.1016/j.ygyno.2012.04.012. View

Froyman W, Landolfo C, De Cock B, Wynants L, Sladkevicius P, Testa A . Risk of complications in patients with conservatively managed ovarian tumours (IOTA5): a 2-year interim analysis of a multicentre, prospective, cohort study. Lancet Oncol. 2019; 20(3):448-458. DOI: 10.1016/S1470-2045(18)30837-4. View

Menon U, Gentry-Maharaj A, Burnell M, Singh N, Ryan A, Karpinskyj C . Ovarian cancer population screening and mortality after long-term follow-up in the UK Collaborative Trial of Ovarian Cancer Screening (UKCTOCS): a randomised controlled trial. Lancet. 2021; 397(10290):2182-2193. PMC: 8192829. DOI: 10.1016/S0140-6736(21)00731-5. View

Zhang L, Huang J, Liu L . Improved Deep Learning Network Based in combination with Cost-sensitive Learning for Early Detection of Ovarian Cancer in Color Ultrasound Detecting System. J Med Syst. 2019; 43(8):251. DOI: 10.1007/s10916-019-1356-8. View

Timmerman D, Testa A, Bourne T, Ameye L, Jurkovic D, Van Holsbeke C . Simple ultrasound-based rules for the diagnosis of ovarian cancer. Ultrasound Obstet Gynecol. 2008; 31(6):681-90. DOI: 10.1002/uog.5365. View

Siegel R, Miller K, Fuchs H, Jemal A . Cancer Statistics, 2021. CA Cancer J Clin. 2021; 71(1):7-33. DOI: 10.3322/caac.21654. View

10.

Zech J, Badgeley M, Liu M, Costa A, Titano J, Oermann E . Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLoS Med. 2018; 15(11):e1002683. PMC: 6219764. DOI: 10.1371/journal.pmed.1002683. View

11.

Gao Y, Zeng S, Xu X, Li H, Yao S, Song K . Deep learning-enabled pelvic ultrasound images for accurate diagnosis of ovarian cancer in China: a retrospective, multicentre, diagnostic study. Lancet Digit Health. 2022; 4(3):e179-e187. DOI: 10.1016/S2589-7500(21)00278-8. View

12.

Cao L, Wei M, Liu Y, Fu J, Zhang H, Huang J . Validation of American College of Radiology Ovarian-Adnexal Reporting and Data System Ultrasound (O-RADS US): Analysis on 1054 adnexal masses. Gynecol Oncol. 2021; 162(1):107-112. DOI: 10.1016/j.ygyno.2021.04.031. View

13.

Ayhan A, Gultekin M, Dursun P, Dogan N, Aksan G, Guven S . Metastatic lymph node number in epithelial ovarian carcinoma: does it have any clinical significance?. Gynecol Oncol. 2008; 108(2):428-32. DOI: 10.1016/j.ygyno.2007.09.014. View

14.

Hack K, Gandhi N, Bouchard-Fortier G, Chawla T, Ferguson S, Li S . External Validation of O-RADS US Risk Stratification and Management System. Radiology. 2022; 304(1):114-120. DOI: 10.1148/radiol.211868. View

15.

Hiett A, Sonek J, Guy M, Reid T . Performance of IOTA Simple Rules, Simple Rules risk assessment, ADNEX model and O-RADS in differentiating between benign and malignant adnexal lesions in North American women. Ultrasound Obstet Gynecol. 2021; 59(5):668-676. DOI: 10.1002/uog.24777. View

16.

Milea D, Najjar R, Zhubo J, Ting D, Vasseneix C, Xu X . Artificial Intelligence to Detect Papilledema from Ocular Fundus Photographs. N Engl J Med. 2020; 382(18):1687-1695. DOI: 10.1056/NEJMoa1917130. View

17.

Zhang M, Cheng S, Jin Y, Zhao Y, Wang Y . Roles of CA125 in diagnosis, prediction, and oncogenesis of ovarian cancer. Biochim Biophys Acta Rev Cancer. 2021; 1875(2):188503. DOI: 10.1016/j.bbcan.2021.188503. View

18.

Pi Y, Wilson M, Katlariwala P, Sam M, Ackerman T, Paskar L . Diagnostic accuracy and inter-observer reliability of the O-RADS scoring system among staff radiologists in a North American academic clinical setting. Abdom Radiol (NY). 2021; 46(10):4967-4973. DOI: 10.1007/s00261-021-03193-7. View

19.

Andreotti R, Timmerman D, Strachowski L, Froyman W, Benacerraf B, Bennett G . O-RADS US Risk Stratification and Management System: A Consensus Guideline from the ACR Ovarian-Adnexal Reporting and Data System Committee. Radiology. 2019; 294(1):168-185. DOI: 10.1148/radiol.2019191150. View

20.

Torre L, Trabert B, DeSantis C, Miller K, Samimi G, Runowicz C . Ovarian cancer statistics, 2018. CA Cancer J Clin. 2018; 68(4):284-296. PMC: 6621554. DOI: 10.3322/caac.21456. View