Development and validation of an interpretable model integrating multimodal information for improving ovarian cancer diagnosis

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 () and Hao Chen ()
Additional contact information
Huiling Xiang: Sun Yat-sen University Cancer Center
Yongjie Xiao: Nanshan
Fang Li: Chongqing University Cancer Hospital
Chunyan Li: Sun Yat-sen University Cancer Center
Lixian Liu: Guangdong Second Provincial General Hospital
Tingting Deng: Sun Yat-sen University Cancer Center
Cuiju Yan: Sun Yat-sen University Cancer Center
Fengtao Zhou: The Hong Kong University of Science and Technology
Xi Wang: Zhejiang Lab
Jinjing Ou: Sun Yat-sen University Cancer Center
Qingguang Lin: Sun Yat-sen University Cancer Center
Ruixia Hong: Chongqing University Cancer Hospital
Lishu Huang: Chongqing University Cancer Hospital
Luyang Luo: The Hong Kong University of Science and Technology
Huangjing Lin: Nanshan
Xi Lin: Sun Yat-sen University Cancer Center
Hao Chen: The Hong Kong University of Science and Technology

Nature Communications, 2024, vol. 15, issue 1, 1-12

Abstract: 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.

Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-46700-2 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-46700-2

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-024-46700-2

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().