Metin N. Gurcan

Histopathological Image Analysis: A Review

Over the past decade, dramatic increases in computational power and improvement in image analysis algorithms have allowed the development of powerful computer-assisted analytical approaches to radiological data. With the recent advent of whole slide digital scanners, tissue histopathology slides can now be digitized and stored in digital image form. Consequently, digitized tissue histopathology has now become amenable to the application of computerized image analysis and machine learning techniques. Analogous to the role of computer-assisted diagnosis (CAD) algorithms in medical imaging to complement the opinion of a radiologist, CAD algorithms have begun to be developed for disease detection, diagnosis, and prognosis prediction to complement the opinion of the pathologist. In this paper, we review the recent state of the art CAD technology for digitized histopathology. This paper also briefly describes the development and application of novel image analysis technology for a few specific histopathology related problems being pursued in the United States and Europe.

Lung nodule detection on thoracic computed tomography images: preliminary evaluation of a computer-aided diagnosis system.

We are developing a computer-aided diagnosis (CAD) system for lung nodule detection on thoracic helical computed tomography (CT) images. In the first stage of this CAD system, lung regions are identified by a k-means clustering technique. Each lung slice is classified as belonging to the upper, middle, or the lower part of the lung volume. Within each lung region, structures are segmented again using weighted k-means clustering. These structures may include true lung nodules and normal structures consisting mainly of blood vessels. Rule-based classifiers are designed to distinguish nodules and normal structures using 2D and 3D features. After rule-based classification, linear discriminant analysis (LDA) is used to further reduce the number of false positive (FP) objects. We performed a preliminary study using 1454 CT slices from 34 patients with 63 lung nodules. When only LDA classification was applied to the segmented objects, the sensitivity was 84% (53/63) with 5.48 (7961/1454) FP objects per slice. When rule-based classification was used before LDA, the free response receiver operating characteristic (FROC) curve improved over the entire sensitivity and specificity ranges of interest. In particular, the FP rate decreased to 1.74 (2530/1454) objects per slice at the same sensitivity. Thus, compared to FP reduction with LDA alone, the inclusion of rule-based classification lead to an improvement in detection accuracy for the CAD system. These preliminary results demonstrate the feasibility of our approach to lung nodule detection and FP reduction on CT images.

Computer-aided characterization of mammographic masses: accuracy of mass segmentation and its effects on characterization

Mass segmentation is used as the first step in many computer-aided diagnosis (CAD) systems for classification of breast masses as malignant or benign. The goal of this paper was to study the accuracy of an automated mass segmentation method developed in our laboratory, and to investigate the effect of the segmentation stage on the overall classification accuracy. The automated segmentation method was quantitatively compared with manual segmentation by two expert radiologists (R1 and R2) using three similarity or distance measures on a data set of 100 masses. The area overlap measures between R1 and R2, the computer and R1, and the computer and R2 were 0.76/spl plusmn/0.13,0.74 /spl plusmn/0.11, and 0.74/spl plusmn/0.13, respectively. The interobserver difference in these measures between the two radiologists was compared with the corresponding differences between the computer and the radiologists. Using three similarity measures and data from two radiologists, a total of six statistical tests were performed. The difference between the computer and the radiologist segmentation was significantly larger than the interobserver variability in only one test. Two sets of texture, morphological, and spiculation features, one based on the computer segmentation, and the other based on radiologist segmentation, were extracted from a data set of 249 films from 102 patients. A classifier based on stepwise feature selection and linear discriminant analysis was trained and tested using the two feature sets. The leave-one-case-out method was used for data sampling. For case-based classification, the area A/sub z/ under the receiver operating characteristic (ROC) curve was 0.89 and 0.88 for the feature sets based on the radiologist segmentation and computer segmentation, respectively. The difference between the two ROC curves was not statistically significant.

Computer-aided prognosis of neuroblastoma on whole-slide images: Classification of stromal development

We are developing a computer-aided prognosis system for neuroblastoma (NB), a cancer of the nervous system and one of the most malignant tumors affecting children. Histopathological examination is an important stage for further treatment planning in routine clinical diagnosis of NB. According to the International Neuroblastoma Pathology Classification (the Shimada system), NB patients are classified into favorable and unfavorable histology based on the tissue morphology. In this study, we propose an image analysis system that operates on digitized H&E stained whole-slide NB tissue samples and classifies each slide as either stroma-rich or stroma-poor based on the degree of Schwannian stromal development. Our statistical framework performs the classification based on texture features extracted using co-occurrence statistics and local binary patterns. Due to the high resolution of digitized whole-slide images, we propose a multi-resolution approach that mimics the evaluation of a pathologist such that the image analysis starts from the lowest resolution and switches to higher resolutions when necessary. We employ an offine feature selection step, which determines the most discriminative features at each resolution level during the training step. A modified k-nearest neighbor classifier is used to determine the confidence level of the classification to make the decision at a particular resolution level. The proposed approach was independently tested on 43 whole-slide samples and provided an overall classification accuracy of 88.4%.

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

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%.

Partitioning Histopathological Images: An Integrated Framework for Supervised Color-Texture Segmentation and Cell Splitting

For quantitative analysis of histopathological images, such as the lymphoma grading systems, quantification of features is usually carried out on single cells before categorizing them by classification algorithms. To this end, we propose an integrated framework consisting of a novel supervised cell-image segmentation algorithm and a new touching-cell splitting method. For the segmentation part, we segment the cell regions from the other areas by classifying the image pixels into either cell or extra-cellular category. Instead of using pixel color intensities, the color-texture extracted at the local neighborhood of each pixel is utilized as the input to our classification algorithm. The color-texture at each pixel is extracted by local Fourier transform (LFT) from a new color space, the most discriminant color space (MDC). The MDC color space is optimized to be a linear combination of the original RGB color space so that the extracted LFT texture features in the MDC color space can achieve most discrimination in terms of classification (segmentation) performance. To speed up the texture feature extraction process, we develop an efficient LFT extraction algorithm based on image shifting and image integral. For the splitting part, given a connected component of the segmentation map, we initially differentiate whether it is a touching-cell clump or a single nontouching cell. The differentiation is mainly based on the distance between the most likely radial-symmetry center and the geometrical center of the connected component. The boundaries of touching-cell clumps are smoothed out by Fourier shape descriptor before carrying out an iterative, concave-point and radial-symmetry based splitting algorithm. To test the validity, effectiveness and efficiency of the framework, it is applied to follicular lymphoma pathological images, which exhibit complex background and extracellular texture with nonuniform illumination condition. For comparison purposes, the results of the proposed segmentation algorithm are evaluated against the outputs of superpixel, graph-cut, mean-shift, and two state-of-the-art pathological image segmentation methods using ground-truth that was established by manual segmentation of cells in the original images. Our segmentation algorithm achieves better results than the other compared methods. The results of splitting are evaluated in terms of under-splitting, over-splitting, and encroachment errors. By summing up the three types of errors, we achieve a total error rate of 5.25% per image.

Computer-aided evaluation of neuroblastoma on whole-slide histology images: Classifying grade of neuroblastic differentiation

Neuroblastoma (NB) is one of the most frequently occurring cancerous tumors in children. The current grading evaluations for patients with this disease require pathologists to identify certain morphological characteristics with microscopic examinations of tumor tissues. Thanks to the advent of modern digital scanners, it is now feasible to scan cross-section tissue specimens and acquire whole-slide digital images. As a result, computerized analysis of these images can generate key quantifiable parameters and assist pathologists with grading evaluations. In this study, image analysis techniques are applied to histological images of haematoxylin and eosin (H&E) stained slides for identifying image regions associated with different pathological components. Texture features derived from segmented components of tissues are extracted and processed by an automated classifier group trained with sample images with different grades of neuroblastic differentiation in a multi-resolution framework. The trained classification system is tested on 33 whole-slide tumor images. The resulting whole-slide classification accuracy produced by the computerized system is 87.88%. Therefore, the developed system is a promising tool to facilitate grading whole-slide images of NB biopsies with high throughput.

Computerized classification of intraductal breast lesions using histopathological images

In the diagnosis of preinvasive breast cancer, some of the intraductal proliferations pose a special challenge. The continuum of intraductal breast lesions includes the usual ductal hyperplasia (UDH), atypical ductal hyperplasia (ADH), and ductal carcinoma in situ (DCIS). The current standard of care is to perform percutaneous needle biopsies for diagnosis of palpable and image-detected breast abnormalities. UDH is considered benign and patients diagnosed UDH undergo routine follow-up, whereas ADH and DCIS are considered actionable and patients diagnosed with these two subtypes get additional surgical procedures. About 250 000 new cases of intraductal breast lesions are diagnosed every year. A conservative estimate would suggest that at least 50% of these patients are needlessly undergoing unnecessary surgeries. Thus, improvement in the diagnostic reproducibility and accuracy is critically important for effective clinical management of these patients. In this study, a prototype system for automatically classifying breast microscopic tissues to distinguish between UDH and actionable subtypes (ADH and DCIS) is introduced. This system automatically evaluates digitized slides of tissues for certain cytological criteria and classifies the tissues based on the quantitative features derived from the images. The system is trained using a total of 327 regions of interest (ROIs) collected across 62 patient cases and tested with a sequestered set of 149 ROIs collected across 33 patient cases. An overall accuracy of 87.9% is achieved on the entire test data. The test accuracy of 84.6% is obtained with borderline cases (26 of the 33 test cases) only, when compared against the diagnostic accuracies of nine pathologists on the same set (81.2% average), indicates that the system is highly competitive with the expert pathologists as a stand-alone diagnostic tool and has a great potential in improving diagnostic accuracy and reproducibility when used as a “second reader” in conjunction with the pathologists.

Content-Based Microscopic Image Retrieval System for Multi-Image Queries

In this paper, we describe the design and development of a multitiered content-based image retrieval (CBIR) system for microscopic images utilizing a reference database that contains images of more than one disease. The proposed CBIR system uses a multitiered approach to classify and retrieve microscopic images involving their specific subtypes, which are mostly difficult to discriminate and classify. This system enables both multi-image query and slide-level image retrieval in order to protect the semantic consistency among the retrieved images. New weighting terms, inspired from information retrieval theory, are defined for multiple-image query and retrieval. The performance of the system was tested on a dataset including 1666 imaged high power fields extracted from 57 follicular lymphoma (FL) tissue slides with three subtypes and 44 neuroblastoma (NB) tissue slides with four subtypes. Each slide is semantically annotated according to their subtypes by expert pathologists. By using leave-one-slide out testing scheme, the multi-image query algorithm with the proposed weighting strategy achieves about 93% and 86% of average classification accuracy at the first rank retrieval, outperforming the image-level retrieval accuracy by about 38 and 26 percentage points, for FL and NB diseases, respectively.

Mitosis detection in breast cancer histological images An ICPR 2012 contest.

Introduction: In the framework of the Cognitive Microscope (MICO) project, we have set up a contest about mitosis detection in images of H and E stained slides of breast cancer for the conference ICPR 2012. Mitotic count is an important parameter for the prognosis of breast cancer. However, mitosis detection in digital histopathology is a challenging problem that needs a deeper study. Indeed, mitosis detection is difficult because mitosis are small objects with a large variety of shapes, and they can thus be easily confused with some other objects or artefacts present in the image. We added a further dimension to the contest by using two different slide scanners having different resolutions and producing red-green-blue (RGB) images, and a multi-spectral microscope producing images in 10 different spectral bands and 17 layers Z-stack. 17 teams participated in the study and the best team achieved a recall rate of 0.7 and precision of 0.89. Context: Several studies on automatic tools to process digitized slides have been reported focusing mainly on nuclei or tubule detection. Mitosis detection is a challenging problem that has not yet been addressed well in the literature. Aims: Mitotic count is an important parameter in breast cancer grading as it gives an evaluation of the aggressiveness of the tumor. However, consistency, reproducibility and agreement on mitotic count for the same slide can vary largely among pathologists. An automatic tool for this task may help for reaching a better consistency, and at the same time reducing the burden of this demanding task for the pathologists. Subjects and Methods: Professor Frιdιrique Capron team of the pathology department at Pitiι-Salpκtriθre Hospital in Paris, France, has selected a set of five slides of breast cancer. The slides are stained with H and E. They have been scanned by three different equipments: Aperio ScanScope XT slide scanner, Hamamatsu NanoZoomer 2.0-HT slide scanner and 10 bands multispectral microscope. The data set is made up of 50 high power fields (HPF) coming from 5 different slides scanned at ×40 magnification. There are 10 HPFs/slide. The pathologist has annotated all the mitotic cells manually. A HPF has a size of 512 μm × 512 μm (that is an area of 0.262 mm 2 , which is a surface equivalent to that of a microscope field diameter of 0.58 mm. These 50 HPFs contain a total of 326 mitotic cells on images of both scanners, and 322 mitotic cells on the multispectral microscope. Results : Up to 129 teams have registered to the contest. However, only 17 teams submitted their detection of mitotic cells. The performance of the best team is very promising, with F-measure as high as 0.78. However, the database we provided is by far too small for a good assessment of reliability and robustness of the proposed algorithms. Conclusions : Mitotic count is an important criterion in the grading of many types of cancers, however, very little research has been made on automatic mitotic cell detection, mainly because of a lack of available data. A main objective of this contest was to propose a database of mitotic cells on digitized breast cancer histopathology slides to initiate works on automated mitotic cell detection. In the future, we would like to extend this database to have much more images from different patients and also for different types of cancers. In addition, mitotic cells should be annotated by several pathologists to reflect the partial agreement among them.