An analysis of scale and rotation invariance in the bag-of-features method for histopathological image classification.

The bag-of-features method has emerged as a useful and flexible tool that can capture medically relevant image characteristics. In this paper, we study the effect of scale and rotation invariance in the bag-of-features framework for Renal Cell Carcinoma subtype classification. We estimated the performance of different features by linear support vector machine over 10 iterations of 3-fold cross validation. For a very heterogeneous dataset labeled by an expert pathologist, we achieve a classification accuracy of 88% with four subtypes. Our study shows that rotation invariance is more important than scale invariance but combining both properties gives better classification performance.

Improving Renal Cell Carcinoma Classification by Automatic Region of Interest Selection.

In this paper, we present an improved automated system for classification of pathological image data of renal cell carcinoma. The task of analyzing tissue biopsies, generally performed manually by expert pathologists, is extremely challenging due to the variability in the tissue morphology, the preparation of tissue specimen, and the image acquisition process. Due to the complexity of this task and heterogeneity of patient tissue, this process suffers from inter-observer and intra-observer variability. In continuation of our previous work, which proposed a knowledge-based automated system, we observe that real life clinical biopsy images which contain necrotic regions and glands significantly degrade the classification process. Following the pathologist's technique of focusing on selected region of interest (ROI), we propose a simple ROI selection process which automatically rejects the glands and necrotic regions thereby improving the classification accuracy. We were able to improve the classification accuracy from 90% to 95% on a significantly heterogeneous image data set using our technique.

Using spiral intensity profile to quantify head and neck cancer.

During the analysis of microscopy images, researchers locate regions of interest (ROI) and extract relevant information within it. Identifying the ROI is mostly done manually and subjectively by pathologists. Computer algorithms could help in reducing their workload and improve reproducibility. In particular, we want to assess the validity of the folic acid receptor as a biomarker for head and neck cancer. We are only interested in folic acid receptors appearing in cancerous tissue. Therefore, the first step is to segment images into cancerous and noncancerous regions. We propose to use a spiral intensity profile for segmentation of light microscopy images. Many algorithms identify objects in an image by considering pixel intensity and spatial information separately. Our algorithm integrates intensity and spatial information by considering the change, or profile, of pixel intensity in a spiral fashion. Using a spiral intensity profile can also perform segmentation at different scales from cancer regions to nuclei cluster to individual nuclei. We compared our algorithm with manually segmented image and obtained a specificity of 83.7% and sensitivity of 61.1%. Spiral intensity profiles can be used as a feature to improve other segmentation algorithms. Segmentation of cancerous images at different scales allows effective quantification of folic acid receptor inside cancerous regions, nuclei clusters, or individual cells.

PASuite: a preprocessing algorithm suite for cellular and molecular image classification in cancer diagnosis and treatment.

We present a generalized tool to mark and preprocess cancerous regions in an image. Currently, tissue biopsies are analyzed and graded manually by expert pathologists and thus can be time consuming and challenging due to variations in tissue morphology, inconsistencies in preparation of tissue specimen and errors in the image acquisition process. Our tool is designed to automatically standardize the variations in different images due to changing illumination and experimental conditions. Segregating cancerous regions from non-cancerous areas is a mandatory step before extracting relevant information from cancer images such as the number and size of nuclei and subsequently using it for classification and quantitative analysis. We tested our tool for two completely different cancers: Head and Neck Cancer (HNC) and Renal Cell Carcinoma (RCC). The tool enables the user to successfully segment the cancerous areas for both types of cancers and our results match with the manual validation by a pathologist.