Histopathological Image Analysis Using Model-Based Intermediate Representations and Color Texture: Follicular Lymphoma Grading

Abstract

Follicular lymphoma (FL) is a cancer of lymph system and it is the second most common lymphoid malignancy in the western world. Currently, the risk stratification of FL relies on histological grading method, where pathologists evaluate hematoxilin and eosin (H&E) stained tissue sections under a microscope as recommended by the World Health Organization. This manual method requires intensive labor in nature.Due to the sampling bias, it also suffers from inter-and intra-reader variability and poor reproducibility. We are developing a computer-assisted system to provide quantitative assessment of FL images for more consistent evaluation of FL. In this study, we proposed a statistical framework to classify FL images based on their histological grades. We introduced model-based intermediate representation (MBIR) of cytological components that enables higher level semantic description of tissue characteristics. Moreover, we introduced a novel color-texture analysis approach that combines the MBIR with low level texture features, which capture tissue characteristics at pixel level. Experimental results on real follicular lymphoma images demonstrate that the combined feature space improved the accuracy of the system significantly. The implemented system can identify the most aggressive FL (grade III) with 98.9% sensitivity and 98.7% specificity and the overall classification accuracy of the system is 85.5%.

Multi-scale directional-filtering-based method for follicular lymphoma grading

“…This is obviously time consuming. Some computerized methods mimic this approach [16,19,25]. Instead of counting the centroblasts individually, we can treat images as textures and try to classify the texture formed by centroblasts in this article.…”

Performance Evaluation of Cancer Diagnostics Using Autoregressive Features with SVM Classifier: Applications to Brain Cancer Histopathology

“…For textural feature extraction, many researchers have attempted work on texture properties mentioned in Section 2. It shows work has been done with textural features, mainly considering the co-occurring matrix features, fractal features, run length features, wavelet features, entropy and chromatin-specific features, compactness, number of regions, distance, model-based intermediate representation are discussed by [19]. The work by Weyn et al represents the use of wavelet coefficients for textural analysis of histopathology image.…”

“…Object-level features are further categorized based on the (i) size and shape, (ii) radiometry and densitometry, (iii) texture and (iv) chromatin specific. [ [19] in spatial feature analysis, the graph theory plays a vital role. The use of spatial arrangements for evaluating cellular arrangements was first proposed by R. Albert et al [20] Different states of tissues are modelled through graph and then used for classification.…”

Pattern Recognition in Histopathological Images: An ICPR 2010 Contest

“…Based on this method FL is stratified into three histological grades: FL grade I (0-5 centroblasts/HPF), FL grade II (6-15 centroblasts/HPF) and FL grade III (>15 centroblasts/HPF) ordered from the least to the most malignant subtypes, respectively. Further information about this problem and some previous work in this area can be found in the References [8][9][10][11][12][13][14][15][16][17].…”