What question did this study set out to answer?

The aim is to evaluate deep learning models for classifying ovarian tumors as benign or malignant using multimodal data.

April 8, 2026Open Access

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

Key Points

The aim is to evaluate deep learning models for classifying ovarian tumors as benign or malignant using multimodal data.
Retrospective multicenter study involving 508 women diagnosed with ovarian tumors.
Utilized Dense Convolutional Network to create two fusion models: DLM2F and DLM3F.
Compared performance of models against radiologists and O-RADS using area under the receiver operating characteristic curve (AUC).
DLM2F achieved an AUC of 0.919, sensitivity of 0.865, specificity of 0.879.
DLM3F reached an AUC of 0.951, sensitivity of 0.865, specificity of 0.939.
Radiologists' AUC scores were 0.896 (Expert level III) and 0.827 (Expert level I), while O-RADS scored 0.835.

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: DLM2F, integrating multimodal features extracted ultrasound (grayscale ultrasound, color Doppler flow imaging), and DLM3F, integrating DLM2F 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 DLM2F model demonstrated an AUC of 0.919, sensitivity of 0.865 and specificity of 0.879, while the DLM3F 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 DLM3F 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.

Ask AI

Helpful

Bookmark

View Full Paper