TY - JOUR
T1 - Volumetric Model Genesis in Medical Domain for the Analysis of Multimodality 2-D/3-D Data Based on the Aggregation of Multilevel Features
AU - Owais, Muhammad
AU - Cho, Se Woon
AU - Park, Kang Ryoung
N1 - Publisher Copyright:
© 2023 The Authors.
PY - 2023/12/1
Y1 - 2023/12/1
N2 - The automatic and accurate classification of medical imaging data has potential applications in computer-aided disease diagnosis, prognosis, and treatment. However, it remains a challenge to optimize recent deep learning algorithms in the medical domain for the accurate classification of large-scale three-dimensional (3-D) volumetric data. To address these challenges, we propose an efficient deep volumetric classification network based on the aggregation of multilevel deep features for the accurate classification of large-scale medical 2-D/3-D imaging data. To perform a detailed quantitative analysis of our method, 26 different datasets were fused to construct a single large-scale multimodal database that comprises a total of seventy different classes, including 151,095 data samples. Additionally, 15 different baseline methods were configured under the same experimental protocol for volumetric model genesis and extensive performance comparison with our method. The experimental results of our method exhibited promising performance as an area under the curve of 93.66% and outperformed various state-of-the-art methods.
AB - The automatic and accurate classification of medical imaging data has potential applications in computer-aided disease diagnosis, prognosis, and treatment. However, it remains a challenge to optimize recent deep learning algorithms in the medical domain for the accurate classification of large-scale three-dimensional (3-D) volumetric data. To address these challenges, we propose an efficient deep volumetric classification network based on the aggregation of multilevel deep features for the accurate classification of large-scale medical 2-D/3-D imaging data. To perform a detailed quantitative analysis of our method, 26 different datasets were fused to construct a single large-scale multimodal database that comprises a total of seventy different classes, including 151,095 data samples. Additionally, 15 different baseline methods were configured under the same experimental protocol for volumetric model genesis and extensive performance comparison with our method. The experimental results of our method exhibited promising performance as an area under the curve of 93.66% and outperformed various state-of-the-art methods.
KW - Computer-aided diagnosis (CAD)
KW - medical data analysis
KW - three-dimensional (3-D) deep learning (DL)
KW - volumetric model genesis
UR - http://www.scopus.com/inward/record.url?scp=85149829942&partnerID=8YFLogxK
U2 - 10.1109/TII.2023.3252541
DO - 10.1109/TII.2023.3252541
M3 - Article
AN - SCOPUS:85149829942
SN - 1551-3203
VL - 19
SP - 11809
EP - 11822
JO - IEEE Transactions on Industrial Informatics
JF - IEEE Transactions on Industrial Informatics
IS - 12
ER -