In this study, researchers developed a method to create a synthetic dataset of facial acne images using generative techniques, achieving 97.6% classification accuracy with InceptionResNetv2, which helps overcome privacy concerns in biomedical applications by using anonymized data.
5 citations
,
June 2023 in “Engineering Technology & Applied Science Research” This study developed a new neural network model (AA-GAN-AB-MTEDeep) to enhance Alopecia Areata classification using synthetic scalp images, achieving an accuracy of 96.94%.
180 citations
,
February 2023 in “Journal of Chemical Information and Modeling” In this paper, Chemistry42—a software integrating AI with computational and medicinal chemistry—demonstrated efficiency in designing novel molecular structures targeting DDR1 and CDK20, with properties validated in both in vitro and in vivo studies.
This study aims to use a comprehensive health data set to develop a statistical model that can improve personalized and preventive health care by understanding relationships between various health parameters in individuals.
April 2026 in “Scientific Reports” In this study, the proposed MSF-VMDNet, combining dual encoder networks with a multi-frequency domain mechanism, significantly outperformed existing methods in segmenting skin cancer tissues from histological slide images, achieving high accuracy with an MIoU of 95.37% and a Dice coefficient of 95.11%.