Digital staining of pathological images: dye amount correction for improved classification performance

Pinky A. Bautista; Tokiya Abe; Masahiro Yamaguchi; Yukako Yagi; Nagaaki Ohyama

doi:10.1117/12.710446

30 March 2007 Digital staining of pathological images: dye amount correction for improved classification performance

Pinky A. Bautista, Tokiya Abe, Masahiro Yamaguchi, Yukako Yagi, Nagaaki Ohyama

Proceedings Volume 6514, Medical Imaging 2007: Computer-Aided Diagnosis; 651433 (2007) https://doi.org/10.1117/12.710446
Event: Medical Imaging, 2007, San Diego, CA, United States

Abstract

Physical staining is indispensable in pathology. While physical staining uses chemicals, "digital staining" exploits the differing spectral characteristics of the different tissue components to simulate the effect of physical staining. Digital staining for pathological images involves two basic processes: classification of tissue components and digital colorization whereby the classified tissue components are impressed with colors associated to their reaction to specific dyes. Spectral features, i.e. spectral transmittance, of the different tissue structures are dependent on the staining condition of the tissue slide. Thus, if the staining condition of the test image is different, classification result is affected, and the resulting digitally-stained image may not reflect the desired result. This paper shows that it is possible to obtain robust classification results by correcting the dye amount of each test-image pixel using Beer Lambert's Law. Also the effectiveness of such technique to be incorporated to the current digital staining scheme is investigated as well.

Citation Download Citation

Pinky A. Bautista, Tokiya Abe, Masahiro Yamaguchi, Yukako Yagi, and Nagaaki Ohyama "Digital staining of pathological images: dye amount correction for improved classification performance", Proc. SPIE 6514, Medical Imaging 2007: Computer-Aided Diagnosis, 651433 (30 March 2007); https://doi.org/10.1117/12.710446

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available