TY - GEN
T1 - Automated Data Adaptation for the Segmentation of Blood Vessels
AU - Haghofer, Andreas
AU - Ebner, Thomas
AU - Kainz, Philipp
AU - Weißensteiner, Michael
AU - Ghaffari-Tabrizi-Wizsy, Nassim
AU - Hatab, Isra
AU - Scharinger, Josef
AU - Winkler, Stephan
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - In the field of image analysis used for diagnostic processes, domain shifts constitute a significant obstacle. Domain shifts lead to an incompatibility of an otherwise well-performing AI model for image segmentation. Accordingly, if two different machines image the same tissue, the model may provide better results for one of the two images depending on the similarity of the image data compared to the training data for generating the AI model. In this paper, we analyzed how the input images of a neural network have to be adapted to provide better segmentation results for images which are previously not compatible with the used model. Therefore, we developed two approaches to increase a model’s segmentation quality for a dataset with initially poor results. The first approach is based on heuristic optimization and creates a set of image processing algorithms for the data adaptation. Our algorithm selects the best combination of algorithms and generates the most suitable parameters for them regarding the resulting segmentation quality. The second approach uses an additional neural network for learning the incompatible dataset’s recoloring based on the resulting segmentation quality. Both methods increase the segmentation quality significantly without the need for changes to the segmentation model itself.
AB - In the field of image analysis used for diagnostic processes, domain shifts constitute a significant obstacle. Domain shifts lead to an incompatibility of an otherwise well-performing AI model for image segmentation. Accordingly, if two different machines image the same tissue, the model may provide better results for one of the two images depending on the similarity of the image data compared to the training data for generating the AI model. In this paper, we analyzed how the input images of a neural network have to be adapted to provide better segmentation results for images which are previously not compatible with the used model. Therefore, we developed two approaches to increase a model’s segmentation quality for a dataset with initially poor results. The first approach is based on heuristic optimization and creates a set of image processing algorithms for the data adaptation. Our algorithm selects the best combination of algorithms and generates the most suitable parameters for them regarding the resulting segmentation quality. The second approach uses an additional neural network for learning the incompatible dataset’s recoloring based on the resulting segmentation quality. Both methods increase the segmentation quality significantly without the need for changes to the segmentation model itself.
KW - Heuristic optimization
KW - Image processing
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=85172269125&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-38854-5_4
DO - 10.1007/978-3-031-38854-5_4
M3 - Conference contribution
AN - SCOPUS:85172269125
SN - 9783031388538
T3 - Communications in Computer and Information Science
SP - 53
EP - 72
BT - Biomedical Engineering Systems and Technologies - 15th International Joint Conference, BIOSTEC 2022, Revised Selected Papers
A2 - Roque, Ana Cecília A.
A2 - Gracanin, Denis
A2 - Lorenz, Ronny
A2 - Tsanas, Athanasios
A2 - Bier, Nathalie
A2 - Fred, Ana
A2 - Gamboa, Hugo
PB - Springer
T2 - Proceedings of the 15th International Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2022
Y2 - 9 February 2022 through 11 February 2022
ER -