Publications by authors named "Muyi Mao"

Background The Ovarian-Adnexal Reporting and Data System (O-RADS) has limited specificity for malignancy. Contrast-enhanced US can help distinguish malignant from benign lesions, but its added value to O-RADS has not yet been assessed. Purpose To establish a diagnostic model combining O-RADS and contrast-enhanced US and to validate whether O-RADS plus contrast-enhanced US has a better diagnostic performance than O-RADS alone.

View Article and Find Full Text PDF

Accurate segmentation of pediatric echocardiography is an essential preprocessing step for a wide range of analysis tasks. Currently, it highly relies on sonographer's manual segmentation, which is time-consuming and redundant, and therefore might lead to mistakes. In this paper, we present a deep learning method based on Bilateral Segmentation Network (BiSeNet) to fully automatic segment pediatric echocardiography images in 4 chamber view.

View Article and Find Full Text PDF

Intravenous contrast-enhanced ultrasound (CEUS), using the second-generation ultrasound contrast agent SonoVue, has been widely used in adults. In 2016, it was approved for pediatric applications by the American Food and Drug Administration (FDA). However, it has not been approved by the Chinese Food and Drug Administration (CFDA).

View Article and Find Full Text PDF

Synopsis of recent research by authors named "Muyi Mao"

  • - Muyi Mao's research focuses on enhancing diagnostic imaging techniques, particularly in the fields of ultrasound for both adult and pediatric applications, combining methods like contrast-enhanced ultrasound (CEUS) and advanced deep learning segmentation.
  • - Recent studies by Mao investigate the integration of contrast-enhanced ultrasound with the Ovarian-Adnexal Reporting and Data System (O-RADS) to improve diagnostic accuracy for ovarian malignancies, demonstrating improved specificity and overall performance.
  • - Mao has also developed an automatic segmentation method for pediatric echocardiography using deep learning, aiming to streamline image analysis and reduce reliance on manual adjustments that can introduce errors.