TY - GEN
T1 - Med-Former
T2 - 27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024
AU - Chowdary, G. Jignesh
AU - Yin, Zhaozheng
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
PY - 2024
Y1 - 2024
N2 - In recent years, transformer-based image classification methods have demonstrated remarkable effectiveness across various image classification tasks. However, their application to medical images presents challenges, especially in the feature extraction capability of the network. Additionally, these models often struggle with the efficient propagation of essential information throughout the network, hindering their performance in medical imaging tasks. To overcome these challenges, we introduce a novel framework comprising Local-Global Transformer module and Spatial Attention Fusion module, collectively referred to as MedFormer. These modules are specifically designed to enhance the feature extraction capability at both local and global levels and improve the propagation of vital information within the network. To evaluate the efficacy of our proposed Med-Former framework, we conducted experiments on three publicly available medical image datasets: NIH Chest X-ray14, DermaMNIST, and BloodMNIST. Our results demonstrate that MedFormer outperforms state-of-the-art approaches underscoring its superior generalization capability and effectiveness in medical image classification.
AB - In recent years, transformer-based image classification methods have demonstrated remarkable effectiveness across various image classification tasks. However, their application to medical images presents challenges, especially in the feature extraction capability of the network. Additionally, these models often struggle with the efficient propagation of essential information throughout the network, hindering their performance in medical imaging tasks. To overcome these challenges, we introduce a novel framework comprising Local-Global Transformer module and Spatial Attention Fusion module, collectively referred to as MedFormer. These modules are specifically designed to enhance the feature extraction capability at both local and global levels and improve the propagation of vital information within the network. To evaluate the efficacy of our proposed Med-Former framework, we conducted experiments on three publicly available medical image datasets: NIH Chest X-ray14, DermaMNIST, and BloodMNIST. Our results demonstrate that MedFormer outperforms state-of-the-art approaches underscoring its superior generalization capability and effectiveness in medical image classification.
KW - Computer Aided Diagnosis
KW - Local-global Feature Extraction
KW - Medical Image Classification
KW - Spatial Attention Fusion
KW - Transformers
UR - https://www.scopus.com/pages/publications/105007836799
U2 - 10.1007/978-3-031-72120-5_42
DO - 10.1007/978-3-031-72120-5_42
M3 - Conference contribution
AN - SCOPUS:105007836799
SN - 9783031721199
T3 - Lecture Notes in Computer Science
SP - 448
EP - 457
BT - Medical Image Computing and Computer Assisted Intervention - MICCAI 2024 - 27th International Conference, Proceedings
A2 - Linguraru, Marius George
A2 - Feragen, Aasa
A2 - Glocker, Ben
A2 - Giannarou, Stamatia
A2 - Schnabel, Julia A.
A2 - Dou, Qi
A2 - Lekadir, Karim
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 6 October 2024 through 10 October 2024
ER -