Investigation of multimodal deep learning models for predicting ovarian tumor malignancy based on ultrasound images and clinical information - a comprehensive comparative study against readers and O-RADS.
Authors
Affiliations (12)
Affiliations (12)
- Department of Health Management, Affiliated Hangzhou First People's Hospital, School of Medicine, Westlake University, Hangzhou, 310022, China.
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, 310022, China.
- Research Center of Interventional Medicine and Engineering, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, 310018, China.
- Zhejiang Provincial Research Center for Innovative Technology and Equipment in Interventional Oncology, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, 310022, China.
- Wenling Institute of Big Data and Artificial Intelligence in Medicine, Taizhou, 317502, China.
- Department of Ultrasound Medicine, The First Affiliated Hospital of Zhejiang Chinese Medical University (Zhejiang Provincial Hospital of Chinese Medicine), Hangzhou, 310022, China.
- Department of Ultrasound Medicine, Shaoxing People's Hospital, Shaoxing, 312000, China.
- Department of Ultrasound Medicine, Xianju People's Hospital, Zhejiang Southeast Campus of Zhejiang Provincial People's Hospital, Affiliated Xianju's Hospital, Hangzhou Medical College, Xianju, 317300, China.
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, 310022, China. [email protected].
- Research Center of Interventional Medicine and Engineering, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, 310018, China. [email protected].
- Wenling Institute of Big Data and Artificial Intelligence in Medicine, Taizhou, 317502, China. [email protected].
- Zhejiang Provincial Research Center for Innovative Technology and Equipment in Interventional Oncology, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, 310022, China. [email protected].
Abstract
As the second deadly cancer affecting women globally, precise and timely classification of ovarian tumors plays an instrumental role in improving the rate of curing and reducing the rate of mortality. This study was set out to comprehensively investigate the effectiveness of deep learning model for classifying benign and malignant ovarian tumors, utilizing multimodal ultrasound images and clinical data, in comparison to traditional methods such as manual assessment by radiologists and those based on O-RADS. This retrospective multicenter study recruited women diagnosed with ovarian tumors between January 2022 and June 2023, with histopathological examination results as the reference diagnoses. The dataset was divided into three subsets: training (70%), validation (10%), and test (20%). Employing the Dense Convolutional Network algorithm, we constructed and investigated two fusion models: DL<sub>M2F</sub>, integrating multimodal features extracted ultrasound (grayscale ultrasound, color Doppler flow imaging), and DL<sub>M3F</sub>, integrating DL<sub>M2F</sub> with clinical data (e.g. age, CA125, CA199, HE4, SCC, ROMA index, menopausal state, and mass volume). The outcome measure was the area under the receiver operating characteristic curve (AUC). We compared the models' performance in the test dataset against both radiologists, O-RADS and single-mode models. A total of 508 patients with ovarian tumors (mean age: 44.3 ± 15.9 years) were enrolled, including 327 benign and 181 malignant tumors. In the test set, the DL<sub>M2F</sub> model demonstrated an AUC of 0.919, sensitivity of 0.865 and specificity of 0.879, while the DL<sub>M3F</sub> model showed an AUC of 0.951, sensitivity of 0.865 and specificity of 0.939. Comparatively, radiologists scored AUC of 896 (Expert level III) and 0.827 (Expert level I), while O-RADS was able to achieve an AUC of 0.835. Evaluation of confusion matrices revealed that DL<sub>M3F</sub> model exhibited almost identical accuracy as a level III expert, demonstrating its promising potential as an clinical diagnostic tool to assist junior radiologists. The deep learning model integrating multimodal ultrasound images and clinical information is capable of discriminating between benign and malignant ovarian tumors, exceeding the diagnostic capabilities of both radiologists and O-RADS assessments.