Journal
COMPUTERS IN BIOLOGY AND MEDICINE
Volume 149, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.compbiomed.2022.105920
Keywords
Deep learning; Multimodal; Point-wise gated deep network (PGDN); Computer-aided diagnosis (CAD); Breast cancer; Radiomics
Categories
Funding
- National Natural Science Foundation of China [62071285]
Ask authors/readers for more resources
The study proposed a multi-region radiomics approach with multimodal ultrasound for AI diagnosis of breast tumors. Results showed that information from multiple regions on breast tumors is useful for diagnosis, and the multi-region multimodal radiomics model achieved the best classification results.
Purpose: The ultrasound (US) diagnosis of breast cancer is usually based on a single-region of a whole breast tumor from a single ultrasonic modality, which limits the diagnostic performance. Multiple regions on multi -modal US images of breast tumors may all have useful information for diagnosis. This study aimed to propose a multi-region radiomics approach with multimodal US for artificially intelligent diagnosis of malignant and benign breast tumors. Materials and methods: Firstly, radiomics features were extracted from five regions of interest (ROIs) on B-mode US and contrast-enhanced ultrasound (CEUS) images, including intensity statistics, gray-level co-occurrence matrix texture features and binary texture features. The multiple ROIs included the whole tumor region, strongest perfusion region, marginal region and surrounding region. Secondly, a deep neural network, composed of the point-wise gated Boltzmann machine and the restricted Boltzmann machine, was adopted to comprehensively learn and select features. Thirdly, the support vector machine was used for classification between benign and malignant breast tumors. Finally, five single-region classification models were generated from five ROIs, and they were fused to form an integrated classification model. Results: Experimental evaluation was conducted on multimodal US images of breast from 187 patients with breast tumors (68 malignant and 119 benign). Under five-fold cross-validation, the classification accuracy, sensitivity, specificity, Youden's index and area under the receiver operating characteristic curve (AUC) with our model were 87.1% +/- 3.3%, 77.4% +/- 11.8%, 92.4% +/- 7.2%, 69.8% +/- 8.6% and 0.849 +/- 0.043, respectively. Our model was significantly better than single-region single-modal methods in terms of the AUC and accuracy (p < 0.05). Conclusion: In addition to the whole tumor region, the other regions including the strongest perfusion region, marginal region and surrounding region on US images can assist breast cancer diagnosis. The multi-region multimodal radiomics model achieved the best classification results. Our artificially intelligent model would be potentially useful for clinical diagnosis of breast cancer.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available