Single-Shot Object Detection and Supervised Image Segmentation for Analysing Cell Images Obtained by Immunohistochemistry
Resumo
Analyzing cell images and identifying them correctly is a fundamental task in the immunohistochemical exam. In this paper we propose a novel method to segment FoxP3+ Regulatory T cells (Treg) images automatically, in order to assist healthcare professionals in the task of identifying and counting potentially cancerous cells. The proposed method relies on combining an object detection network, which is tailor-made for microscopy images, with a marker-based image segmentation method to produce the final segmentation, while requiring only a 50x50 training patch to do so. Our pipeline consists on predicting the location of the cells, applying morphological operations on the prediction weights to transform them into markers, and finally using the segmentation method iDISF to generate high quality segmentations. We also propose a new FoxP3+ Treg cells dataset containing 10 high resolution images, with a qualitative and quantitative analysis of our segmentation methods for this dataset.
Referências
Szylberg, D. Karbownik, and A. Marszałek, “The role of foxp3 in human cancers,” Anticancer Research, vol. 36, no. 8, pp. 3789–3794, 2016.
O. Stasikowska-Kanicka, M. Wagrowska-Danilewicz, and M. Danilewicz, “Immunohistochemical analysis of foxp3+, cd4+, cd8+ cell infiltrates and pd-l1 in oral squamous cell carcinoma,” Pathology Oncology Research, vol. 24, no. 3, pp. 497–505, July 2018.
N. Hiraoka, K.-I. Onozato, T. Kosuge, and et al, “Prevalence of foxp3+ regulatory t cells increases during the progression of pancreatic ductal adenocarcinoma and its premalignant lesions,” Clinical Cancer Research, vol. 12, pp. 5423–5434, 2006.
N. Kobayashi, N. Hiraoka, W. Yamagami, and et al, “Foxp3+ regulatory t cells affect the development and progression of hepatocarcinogenesis,” Clinical Cancer Research, vol. 13, pp. 902–911, 2007.
N. Altini, A. Brunetti, E. Puro, M. G. Taccogna, C. Saponaro, F. A. Zito, S. De Summa, and V. Bevilacqua, “Ndg-cam: Nuclei detection in histopathology images with semantic segmentation networks and grad-cam,” Bioengineering, vol. 9, no. 9, 2022. [Online]. Available: https://www.mdpi.com/2306-5354/9/9/475
M. S. E. Rabbi, N. Ironside, J. A. Ozolek, R. Singh, L. Pantanowitz, and G. K. Rohde, “Transport-based morphometry of nuclear structures of digital pathology images in cancers,” 2023.
I. B. Barcelos, F. Belém, P. Miranda, A. X. Falcão, Z. K. do Patrocínio, and S. J. F. Guimarães, “Towards interactive image segmentation by dynamic and iterative spanning forest,” in International Conference on Discrete Geometry and Mathematical Morphology, Springer. Springer International Publishing, 2021, pp. 351–364.
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.
A. X. 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.
B. Midtvedt, J. Pineda, F. Skärberg, E. Olsén, H. Bachimanchi, E. Wesén, E. K. Esbjörner, E. Selander, F. Höök, D. Midtvedt, and G. Volpe, “Single-shot self-supervised object detection in microscopy,” Nature Communications, vol. 13, no. 1, p. 7492, 2022. [Online]. Available: https://doi.org/10.1038/s41467-022-35004-y
