A5007205047- AI in cancer detection
- Digital Radiography and Breast Imaging
- Radiomics and Machine Learning in Medical Imaging
- Image Retrieval and Classification Techniques
- Biomedical Text Mining and Ontologies
- Brain Tumor Detection and Classification
- 3D Surveying and Cultural Heritage
- 3D Shape Modeling and Analysis
- Remote Sensing and LiDAR Applications
Severance Hospital
2024
Yonsei University
2024
Pohang University of Science and Technology
2019
Purpose To develop an artificial intelligence (AI) model for the diagnosis of breast cancer on digital tomosynthesis (DBT) images and to investigate whether it could improve diagnostic accuracy reduce radiologist reading time. Materials Methods A deep learning AI algorithm was developed validated DBT with retrospectively collected examinations (January 2010 December 2021) from 14 institutions in United States South Korea. multicenter reader study performed compare performance 15 radiologists...
To develop an efficient deep neural network model that incorporates context from neighboring image sections to detect breast cancer on digital tomosynthesis (DBT) images.
In this article, a point-wise normal estimation network for three-dimensional point cloud data called NormNet is proposed. We propose the multiscale K-nearest neighbor convolution module strengthened local feature extraction. With and PointNet-like architecture, we achieved hybrid of three features: global feature, semantic from segmentation network, module. Those features, by mutually supporting each other, not only increase performance but also enable to be robust under severe noise...
When developing Computer Aided Detection (CAD) systems for Digital Breast Tomosynthesis (DBT), the complexity arising from volumetric nature of modality poses significant technical challenges obtaining large-scale accurate annotations. Without access to annotations, resulting model may not generalize different domains. Given costly DBT how effectively increase amount data used training CAD remains an open challenge. In this paper, we present SelectiveKD, a semi-supervised learning framework...