TY - GEN
T1 - A Novel Weakly Supervised Semantic Segmentation Ensemble Framework for Medical Imaging
AU - Ostrowski, Erik
AU - Prabakaran, Bharath Srinivas
AU - Shafique, Muhammad
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - The use of deep learning networks for vision based computer aided diagnostics (CAD) offers a tremendous opportunity for medical practitioners. However, state-of-the-art vision-based CAD systems rely on huge pixel-wise annotated datasets. Such datasets are rarely available, thus severely limiting the applicability of vision-based CAD systems. Hence, semantic segmentation with image labels offers a viable alternative. Semantic segmentation with image labels is well studied in a general context but seldom applied in the medical sector. The major challenge in applying semantic segmentation with image labels in the medical sector is that predicting on medical datasets is more complex than in the general context. Thus, directly applying methods for semantic segmentation with image labels like class activation maps (CAMs) on medical data generates insufficient results. However, state-of-the-art approaches rely on CAMs as a foundation. To address this problem, we propose a framework to extract useful information from particular low-quality segmentation masks. We achieve this by using our observations that the low-quality predictions have very low false negative detections, and multiple low-quality predictions show high variance among each other. We evaluated our framework on the popular multi-modal BRATS and prostate DECATHLON segmentation challenge datasets to demonstrate an improved dice score of up to 8% on BRATS and 6% on DECATHLON datasets compared to the previous state-of-the-art.
AB - The use of deep learning networks for vision based computer aided diagnostics (CAD) offers a tremendous opportunity for medical practitioners. However, state-of-the-art vision-based CAD systems rely on huge pixel-wise annotated datasets. Such datasets are rarely available, thus severely limiting the applicability of vision-based CAD systems. Hence, semantic segmentation with image labels offers a viable alternative. Semantic segmentation with image labels is well studied in a general context but seldom applied in the medical sector. The major challenge in applying semantic segmentation with image labels in the medical sector is that predicting on medical datasets is more complex than in the general context. Thus, directly applying methods for semantic segmentation with image labels like class activation maps (CAMs) on medical data generates insufficient results. However, state-of-the-art approaches rely on CAMs as a foundation. To address this problem, we propose a framework to extract useful information from particular low-quality segmentation masks. We achieve this by using our observations that the low-quality predictions have very low false negative detections, and multiple low-quality predictions show high variance among each other. We evaluated our framework on the popular multi-modal BRATS and prostate DECATHLON segmentation challenge datasets to demonstrate an improved dice score of up to 8% on BRATS and 6% on DECATHLON datasets compared to the previous state-of-the-art.
KW - CAMs
KW - Deep Learning
KW - Deep Neural Networks
KW - DNN
KW - GradCAM
KW - Machine Learning
KW - Medical Imaging
KW - Semantic Segmentation
KW - Weakly Supervised Semantic Segmentation
UR - http://www.scopus.com/inward/record.url?scp=85205011119&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85205011119&partnerID=8YFLogxK
U2 - 10.1109/IJCNN60899.2024.10650217
DO - 10.1109/IJCNN60899.2024.10650217
M3 - Conference contribution
AN - SCOPUS:85205011119
T3 - Proceedings of the International Joint Conference on Neural Networks
BT - 2024 International Joint Conference on Neural Networks, IJCNN 2024 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 International Joint Conference on Neural Networks, IJCNN 2024
Y2 - 30 June 2024 through 5 July 2024
ER -