Domain-Specific Seed Removal for Biomedical Image Segmentation using SICLE

• Fábio F. Kochem PUC Minas
• Felipe Belém PUC Minas
• Alexandre X. Falcão UNICAMP
• Zenilton K. G. do P. Jr. PUC Minas
• Silvio Jamil F. Guimarães PUC Minas

Resumo

Superpixels through Iterative CLEarcutting (SICLE) is an efficient framework for image segmentation that operates on an iterative principle of seed removal to refine the final result. While effective for general purposes, its reliance on standard seed removal criteria limits its performance in specialized domains. This is particularly evident in biomedical analysis, where the goal is often to isolate a single object of interest using a low number of superpixels, a task where generic criteria often fail. To address this limitation, this work proposes two seed removal criteria: (i) a Position-Based Criterion that leverages prior anatomical knowledge to guide segmentation in medical images; (ii) a Color-Based Criterion specialized for identifying targets in pathological images based on their distinct color signature. By replacing generic heuristics with these domain-specific functions, we demonstrate that SICLE can be transformed into a more robust and specialized tool for targeted biomedical image analysis, significantly improving object delineation accuracy, including situations with a small quantity of superpixels.

Palavras-chave: Flow Matching, Discrete Generative Models, Deep Learning

Referências

G.-C. Xu, P.-J. Lee, T.-A. Bui, B.-H. Chang, and K.-M. Lee, “Superpixel algorithm for objects tracking in satellite video,” in 2021 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW). IEEE, 2021, pp. 1–2.

J. Long et al., “A graph neural network for superpixel image classification,” in Journal of Physics: Conference Series, vol. 1871, no. 1. IOP Publishing, 2021, p. 012071.

R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Süsstrunk, “Slic superpixels compared to state-of-the-art superpixel methods,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2274–2282, 2012.

X. Wei, Q. Yang, Y. Gong, M.-H. Yang, and N. Ahuja, “Superpixel hierarchy,” IEEE Transactions on Image Processing, vol. PP, 05 2016.

F. C. Belém, I. B. Barcelos, L. M. João, B. Perret, J. Cousty, S. J. F. Guimarães, and A. X. Falcão, “Novel arc-cost functions and seed relevance estimations for compact and accurate superpixels,” Journal of Mathematical Imaging and Vision, vol. 65, no. 5, pp. 770–786, 2023.

A. Falcao, J. Stolfi, and R. de Alencar Lotufo, “The image foresting transform: theory, algorithms, and applications,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 1, pp. 19–29, 2004.

J. E. Vargas-Muñoz, A. S. Chowdhury, E. B. Alexandre, F. L. Galvão, P. A. Vechiatto Miranda, and A. X. Falcão, “An iterative spanning forest framework for superpixel segmentation,” IEEE Transactions on Image Processing, vol. 28, no. 7, pp. 3477–3489, 2019.

F. Belém, S. J. F. Guimarães, and A. X. Falcão, “Superpixel segmentation by object-based iterative spanning forest,” in Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, R. Vera-Rodriguez, J. Fierrez, and A. Morales, Eds. Cham: Springer International Publishing, 2019, pp. 334–341.