分割皮膚組織的光學同調斷層掃描影像以優化生醫影像轉換

Segmentation of in vivo OCT image of three-dimensional human skin structure to facilitate biomedical image conversion

黃芳源(Fang-Yuan Huang)

指導教授 ： 曾雪峰

國立臺灣大學/電機資訊學院/光電工程學研究所/碩士(2021年)

https://doi.org/10.6342/NTU202102590

摘要

皮膚的層次以及細胞核的影像分割無論在診斷還是電腦分析，都是病理學上重要的資訊及任務。本論文中，我們設計了一個可以從人類皮膚的三維光學同調斷層掃描（OCT）中獲取細胞核體機率分佈的架構，再利用得來的細胞核資訊，進一步訓練出分割細胞核的模型，以用來輔助影像轉換，該影像轉換建立在循環生成對抗網路並能將人類皮膚的光學同調斷層掃描影像轉換成蘇木精與伊紅（H E）染色。在測試影像集上，角質層的下邊界與表皮層的下邊界於影像轉換前後的位置誤差分別為±0.73μm和±4.53μm，而在加入細胞核位置資訊後，細胞核於影像轉換前後的索倫森-骰子係數從0.536上升至0.586。

關鍵字

細胞核分割 ； 影像轉換 ； 隨機射線取樣 ； 光學同調斷層掃描 ； 蘇木精與伊紅染色 ； 生成對抗網路

並列摘要

Skin layers and nuclei segmentation is a crucial task for computational pathology applications and it assists the diagnosis of skin cancers. In this research, we proposed a framework to achieve nuclei annotation of in vivo optical coherence tomography (OCT) image of three-dimensional human skin structure. Furthermore, we trained a segmentation model with the pseudo annotation of nuclei, to facilitate CycleGAN-based image conversion of human skin from OCT images to hematoxylin and eosin (H E) stain. Input OCT images and the output H E-like images match well in terms of the stratum corneum lower boundaries and dermal-epidermal junction with errors of ±0.73 μm and ±4.53μm, respectively. Dice similarity coefficients of the nuclei consistence are 0.427 and 0.536 before and after adding nuclear info.

並列關鍵字

nuclei segmentation ； image conversion ； random rayburst sampling ； optical coherence tomography ； hematoxylin and eosin stain ； generative adversarial network

參考文獻

[1] M. Titford, "The long history of hematoxylin," Biotechnic Histochemistry, vol. 80, no. 2, pp. 73-78, 2005/01/01 2005.

[2] R. W. Dapson and R. W. Horobin, "Dyes from a twenty-first century perspective," Biotechnic Histochemistry, vol. 84, no. 4, pp. 135-137, 2009/01/01 2009.

[3] C. Smith, "Our debt to the logwood tree: the history of hematoxylin," (in eng), MLO Med Lab Obs, vol. 38, no. 5, pp. 18, 20-2, May 2006.

[4] J. Rosai, "Why microscopy will remain a cornerstone of surgical pathology," Laboratory Investigation, vol. 87, no. 5, pp. 403-408, 2007/05/01 2007.

[5] J. G. Fujimoto, C. Pitris, S. A. Boppart, and M. E. Brezinski, "Optical coherence tomography: an emerging technology for biomedical imaging and optical biopsy," Neoplasia, vol. 2, no. 1-2, pp. 9-25, Jan-Apr 2000.