Automatic Immunoscoring of Immunohistochemistry Images of Human Lung Cancer Tissue Samples: A Screening Tool

Computer-aided image analysis of tissue sections is a modern accepted technique for tumor pathological diagnosis. With the advents of immunoscoring in tumor outcome evaluation, image-based immunoscore calculation has gained more and more attention. A new method of immunohistochemistry sections analysis, using the freeware ImageJ, is presented which can be applied to sections with either nuclear or cytoplasmic staining. The step-by-step process is presented and the method is tested using lung cancer tissues immunostained for cytokeratin 56, 18, NAPSIN, CGA, SYN, TTF, p63. This image analysis easily discriminates the positive staining and background, and quantified histogram profiles of the tested images, showing consistency with pathological diagnosis. The Spearman correlation between immunoscore and clinical TNM stage was 0.94. The method is easy to perform, without the need for previous image transformations. Further studies are needed to evaluate whether this method is efficient enough to be applied in clinical practice.