前列腺癌切片影像中正常腺體切割之研究

A Study of Prostate Cancer Slice Images On Normal Gland Cutting

葉宗裕(Tsung-Yu Yeh)

指導教授 ： 戴紹國

朝陽科技大學/資訊學院/資訊管理系/碩士(2011年)

摘要

前列腺癌是近年來男性癌症主要死因之一，因此前列腺癌的診斷和治療是非常重要的。罹患前列腺癌的患者在做完前列腺全切除手術之後，醫師仍必須根據所切下來的整顆前列腺檢體做出預後以及治療計畫，而在各種的診斷手段中全量前列腺病理切片是可以讓醫師做出最準確的診斷。
然而，病理醫師因此必須擔負著沉重且龐大的工作量，花很長的時間將大量切片一一的檢視並標示腫瘤位置和估量。如此重複性過高的工作對病理醫師是一個不小的困擾，而且不同的病理醫師對於同一張病理切片會有不同的定義，很明顯是會存在著很大的誤差。因此全量前列腺病理切片的自動化輔助診斷是一個不可忽視的議題，而這個議題成敗最主要的關鍵是在於是否能夠自動化的切割出前列腺癌的腺體區域作為分級辨識之用。
本碩士論文中，我們提出一個影像切割技術，以形態學方法作為基礎，全自動化的自一張前列腺全量切片中辨識出正常腺體以及非腺體區域，藉此留下前列腺癌腺體的區域。而這些區域將可更便利前列腺癌分級輔助診斷系統的運作，希望能夠讓病理醫師在做診斷時能得到正確的結果。

關鍵字

前列腺癌腺體 ； 前列腺癌 ； 前列腺病理切片 ； 影像切割

並列摘要

Prostate cancer is one of the leading causes of cancer death in men in recent years, so diagnosis and treatment of prostate cancer are very important. After the total perineal prostatomy, physicians have to review the whole mount prostate Biopsy to make the prognosis and treatment plan.

However, It is a heavy loading to pathologists. They have to spend a lot of time to examine a large number of biopsies one by one and mark the location of the tumor and make the diagnosis. Such a high repetitive work will cause a large disturbance for pathologists. Besides, there are different definitions for the same biopsy by different pathologists. Thus, the automatic diagnosis system for the whole prostate biopsy is thus needed. The key issue for this system is whether the area of the prostate gland can be well segmented automatically.

In this paper, we propose an image segmentation method based on morphology method. It segmented normal prostate gland and break regions from whole prostate biopsy automatically and leave the areas of the prostate cancer. These areas can be adopted as the input of the automatic diagnosis system and help pathologists to make the diagnosis more accuracy.

並列關鍵字

Prostate cancer ； Prostate biopsy ； Image Segmentation ； Prostate gland

參考文獻

[1] [Online].行政院衛生署國民健康局: http://www.tnanping.gov.tw

[3] Lewis, J. J., O’Callaghan, R. J., Nikolov, S. G., Bull, D. R., and Canagarajah, N. (2007), “Pixel- and region-based image fusion with complex wavelets,” Information Fusion, Vol. 8, No. 2, pp. 119-130.

[4] Shao-Kuo Tai; Cheng-Yi Li; Yen-Chih Wu; Yee-Jee Jan; Shu-Chuan Lin; Dept. of Inf. Manage., Chaoyang Univ. of Technol., Taichung, Taiwan

[8] GonzalezR.C.(2002), Woods R. E., Digital Image Processing, Prentice-Hall, New Jersey.

[11] Canny, J.(1986), A Computational Approach To Edge Detection, IEEE Trans. Pattern Analysis and Machine Intelligence, 8:679-714.