Computer-assisted grading of adenocarcinoma in prostatic aspirates

Conventional cytologic grading of fine needle aspirates of prostatic adenocarcinoma has been shown neither to be reproducible nor to correlate well with histologic grading. This study developed a tumor grade classification based on computerized cytomorphometric features and compared the results to conventional grading of companion tissue sections. The image analysis system evaluated architectural features of the aspirates (mainly cell cluster features and interrelationships) as well as nuclear features. Thirty-five prostatic adenocarcinomas (8 well, 19 moderately and 8 poorly differentiated) were evaluated. Discriminant functions based on data collected at medium and high resolution distinguished between aspirates from low-grade (well-differentiated) and high-grade (poorly differentiated) adenocarcinomas with 81% accuracy. Moderately differentiated cancers could not be classified as a distinct group. This study suggests that accurate grading of prostatic adenocarcinoma in fine needle aspirate smears requires the evaluation of medium-resolution features related to specimen cellularity and uniformity or crowding of cell clusters as well as of high-resolution features of nuclear area, perimeter and coarseness of chromatin texture. These findings are compared to those of other schemes for the cytologic grading of prostatic aspirates.     

Neural network-based segmentation and classification system for automated grading of histologic sections of bladder carcinoma

OBJECTIVE: To develop an image analysis system for automated nuclear segmentation and classification of histologic bladder sections employing quantitative nuclear features. STUDY DESIGN: Ninety-two cases were classified into three classes by experienced pathologists according to the WHO grading system: 18 cases as grade 1, 45 as grade 2, and 29 as grade 3. Nuclear segmentation was performed by means of an artificial neural network (ANN)-based pixel classification algorithm, and each case was represented by 36 nuclei features. Automated grading of bladder tumor histologic sections was performed by an ANN classifier implemented in a two-stage hierarchic tree. RESULTS: On average, 95% of the nuclei were correctly detected. At the first stage of the hierarchic tree, classifier performance in discriminating between cases of grade 1 and 2 and cases of grade 3 was 89%. At the second stage, 79% of grade 1 cases were correctly distinguished from grade 2 cases. CONCLUSION: The proposed image analysis system provides the means to reduce subjectivity in grading bladder tumors and may contribute to more accurate diagnosis and prognosis since it relies on nuclear features, the value of which has been confirmed.     

Grading of ductal breast carcinoma by cytomorphology and image morphometry with histologic correlation

OBJECTIVE: To investigate the relevance of image analysis for grading breast carcinoma. STUDY DESIGN: Twenty-five ductal breast carcinoma cases were chosen randomly from routine fine needle aspiration clinics. The results of cytomorphologic grading and image morphometry were correlated with those of histologic grading. The five image morphometric parameters studied were nuclear diameter, nuclear area, nuclear roundness, nuclear perimeter and grey level to compare with chromatin texture. RESULTS: Cytologic grading alone had a high correlation with histologic grading. The lowest correlation was found in grade 2 tumors. When cytologic grading was supplemented with image morphometric parameters, the correlation was higher than that of cytologic grading alone. CONCLUSION: Cytologic grading has a high correlation with histologic grading. The correlation improves further on supplementation with image morphometric parameters.     

Image processing for accurate cell recognition and count on histologic slides

OBJECTIVE: To design an automatic system for recognition and count of two different cell families on histologic slides. STUDY DESIGN: The segmentation strategy uses color information on the image. The morphologic operations and Support Vector Machine approaches are used for each color to obtain precise segmentation of the image into separate cells for recognition. RESULTS: A large set of histologic slides of bone marrow was assessed byour system and the results compared to the score of a human expert. The results are in good agreement. The difference is within acceptable limits (below 10%). CONCLUSION: The automatic system of cell recognition and extraction is accurate and provides a useful tool for cell recognition and count on histologic slides.     

A comparative study in morphometric grading of transitional cell carcinoma of the urinary bladder

To overcome the considerable observer inconsistency in the histologic grading of transitional cell carcinomas, the value of four different morphometric grading methods was investigated in 61 tumors of the bladder. Only two methods showed satisfactory reproducibility. Both methods, one based on random nuclear sampling and the other on selective nuclear sampling, showed an increase in the mean and standard deviation of the nuclear area with higher tumor grades (P less than .00001). Morphometric classification of the learning set (44 cases) was in agreement with the unequivocally assessed histologic grade in 35 cases (79.5%) using random sampling and in 38 cases (86.4%) using selective sampling. By reducing the grading classes to "low" (grades 1 and 2) and "high" (grade 3) and by introducing a classification probability threshold (0.80), an accurate morphometric classification was achieved in 38 cases (86.4%) using random sampling and in 41 cases (93.2%) using selective sampling. Of the 17 cases with histologic grading discrepancies, all 10 low-grade tumors (with discrepancies of grade 1 versus grade 2) were correctly classified as low-grade carcinomas by both of the morphometric methods; in the remaining 7 cases, with low-versus-high discrepancies (grade 2 versus grade 3), the selective method yielded better correlation with the tumor stage and clinical follow-up. It is concluded that morphometric classification is an acceptable alternative for histologic grading by pathologists, provided that the reproducibility of the method is confirmed. Although both random and selective sampling yielded satisfactory classifications, the selective method gave more reliable results as confirmed by the clinical behavior.     

The Reading of Components of Diabetic Retinopathy: An Evolutionary Approach for Filtering Normal Digital Fundus Imaging in Screening and Population Based Studies

In any diabetic retinopathy screening program, about two-thirds of patients have no retinopathy. However, on average, it takes a human expert about one and a half times longer to decide an image is normal than to recognize an abnormal case with obvious features. In this work, we present an automated system for filtering out normal cases to facilitate a more effective use of grading time. The key aim with any such tool is to achieve high sensitivity and specificity to ensure patients'' safety and service efficiency. There are many challenges to overcome, given the variation of images and characteristics to identify. The system combines computed evidence obtained from various processing stages, including segmentation of candidate regions, classification and contextual analysis through Hidden Markov Models. Furthermore, evolutionary algorithms are employed to optimize the Hidden Markov Models, feature selection and heterogeneous ensemble classifiers. In order to evaluate its capability of identifying normal images across diverse populations, a population-oriented study was undertaken comparing the software''s output to grading by humans. In addition, population based studies collect large numbers of images on subjects expected to have no abnormality. These studies expect timely and cost-effective grading. Altogether 9954 previously unseen images taken from various populations were tested. All test images were masked so the automated system had not been exposed to them before. This system was trained using image subregions taken from about 400 sample images. Sensitivities of 92.2% and specificities of 90.4% were achieved varying between populations and population clusters. Of all images the automated system decided to be normal, 98.2% were true normal when compared to the manual grading results. These results demonstrate scalability and strong potential of such an integrated computational intelligence system as an effective tool to assist a grading service.     

Application of different methods for nuclear shape analysis with special reference to the differentiation of brain tumors

OBJECTIVE: To study the discriminatory power of different methods designed for nuclear shape analysis with reference to the differentiation and grading of brain tumors and the differentiation between proliferating and nonproliferating nuclei. STUDY DESIGN: At least 300 tumor cell nuclei per case were measured by means of a digital image analysis system. Fourier amplitudes no. 1 to 15, moments no. 1 to 7 according to Hu, roundness factor, ellipse shape factor, concavity factor, Feret ratio, fractal dimension and bending energy were determined for each nucleus. The discriminatory power of these parameters was tested in three pairwise comparisons: (1) oligodendrogliomas WHO grade II (n = 13) vs. grade III (n = 11), (2) medulloblastomas WHO grade IV (n = 14) vs. anaplastic ependymomas WHO grade III (n = 12), (3) Ki-67-positive vs. Ki-67-negative tumor cell nuclei in the 14 medulloblastomas. RESULTS: When data from Fourier analysis were included in statistical analysis, cross-validated discriminant analysis led to a 100% correct reclassification for the first and for the second pairwise comparison and to a 75% correct reclassification when comparing Ki-67-positive and Ki-67-negative nucleifrom medulloblastomas. Different combinations of the other shape parameters led to a lower percentage of correctly reclassified cases for all three pairwise comparisons, especially when Fourier analysis was not included in the analysis. CONCLUSION: Fourier analysis provided an optimal statistical discrimination between different brain tumor entities and between data sets from proliferating and nonproliferating tumor cell nuclei. Since nuclear shape is an important criterion for the investigation of tumors, the application of Fourier analysis is therefore recommended for quantitative histologic investigations in neuro-oncology.     

一种非酒精性脂肪性肝病的超声影像人工智能辅助诊断系统开发

摘要 目的：结合人工智能方法设计针对肝脏超声影像的辅助诊断系统，辅助医生对大样本肝脏超声影像数据的标准化和高效化诊断，实现基于肝脏超声图像的非酒精性脂肪性肝病的精准诊断。方法：通过开发肝脏超声影像的识别与分类、脂肪肝分级分析和肝脏脂肪含量定量分析三个模块，建立一套非酒精性脂肪性肝病的超声影像人工智能辅助诊断系统，该系统能够自动区分输入到系统中不同采样视野的超声影像类型，并对肝脏超声图像进行数字化分析，给出待测超声图像是否呈现脂肪肝以及其肝脏脂肪含量的百分比值。结果：本研究中的超声图像识别分类模块可高通量区分出肝肾比图像和衰减率图像的两类超声影像，其分类的准确率达100%。脂肪肝分级分析模块在测试集数据的准确率达到84%，展现出可胜任辅助医生诊断的能力。基于人工肝脏脂肪含量定量方法开发的肝脏脂肪含量定量分析模块的准确率达到67.74%。结论：本研究已开发出一套基于肝脏超声影像的智能辅助诊断系统，可以辅助医生快速、简单、无创地筛选出潜在患有脂肪肝的患者，虽然现阶段实现肝脏脂肪定量分析仍有难度，但已展现出较大的临床应用潜力。     

利用GIS对吉林针阔混交林TM遥感图像分类方法的初探

为提高林区TM遥感图像自动分类识别精度,在GIS技术辅助下,以吉林省汪清林业局针阔混交林TM遥感图像为例,对研究区DEM、坡向等地理因子和土壤类型等环境因子与森林植被分布之间的内在规律进行了定量分析,并结合对遥感图像预分类的定性分析,形成分类知识库,建立了适用于针阔混交林的自动分类识别专家系统.分类试验证明,该系统能比较明显地削弱混合像元和地形阴影的影响,分类精度较无监督分类法提高了14.22%,Kappa指数为0.7556,达到区别森林类型的分类目的.将GIS数据引入专家系统,应用先验知识建立推理机制,可以解决遥感图像中云区和云阴影区由于不能接收到正确的光谱值而无法进行分类的问题.     

Image understanding system for histopathology

An image understanding machine vision system for histological diagnoses is based on three interacting expert systems: a diagnostic expert system utilizing terms familiar to pathologists, an interpretive expert system relating human diagnostic concepts to computable histometric features and a scene segmentation expert system which extracts the diagnostic information from the imagery. The control software for the image understanding system resides on a multiprocessor computer. This article details measures to maintain system efficiency and to accommodate the requirements of interprocess communication and processing task scheduling.     

Standardized AgNOR analysis as a prognostic parameter in endometrial carcinoma, endometrioid type

OBJECTIVE: To evaluate interobserver reproducibility of histologic grade in endometrial adenocarcinomas of endometrioid type (EC), to assess the relationships between nuclear grade and the amount of argyrophilic nucleolar organizer region (AgNOR) proteins and to determine the prognostic value of AgNOR proteins and the main clinicopathologic parameters. STUDY DESIGN: Architectural and nuclear grading were independently assessed by two pathologists in 64 formalin-fixed, paraffin-embedded surgical samples of EC obtained from an equal number of patients (age range, 38-84 years; mean, 63.5). Interobserver agreement was determined using the kappa statistic; discrepant cases were reviewed, and a consensus was reached. Standardized AgNOR analysis was performed according to the guidelines of the Committee on AgNOR Quantification, measuring the mean area of AgNORs per nucleus (NORA) by an image analysis system. RESULTS: The kappa values for interobserver agreement were substantial for architectural grading and moderate for nuclear grading. When NORA values were compared to the nuclear grade assessed by different observers, the most significant linear correlation (r = .713, P < .001) was found for the nuclear assessment obtained by consensus of the two pathologists. Moreover, statistical analysis allowed discrimination of architectural grade 1 from grade 2 and 3 EC. By the Kaplan-Meier method, the prognosis was worse for patients with higher NORA values (> 4.212 micron 2), while, by Cox multivariate analysis, AgNOR quantity emerged as an independent prognostic variable. CONCLUSION: Use of standardized AgNOR analysis may be an additional and objective tool in the assessment of histologic grade as well as a reliable method of determining prognosis in EC.     

Histometric features for the grading of prostatic carcinoma

Histometric features for the objective grading of prostatic adenocarcinoma in histologic specimens were analyzed in five cases each of well, moderately and poorly differentiated lesions. Tissue sections from the selected cases were stained by the Feulgen method and digitized by a video-based microphotometer. Twenty total fields were recorded for each grade: ten at high resolution (an image sampling of 0.5 micron per pixel) and ten at low resolution (0.8 micron per pixel), with two fields per case recorded at each resolution. The images were segmented by an automated expert system-guided scene segmentation procedure. The performance of that procedure was measured by comparing the automated counts of nuclei in the segmented fields to the visual counts made by a pathologist in the same fields. For well, moderately and poorly differentiated cases, respectively, the nuclear counts made by the expert system at high resolution were 2.7%, 4.2% and 4.7% higher than the visual counts (as estimated from a total of 6,628 nuclei), but 1.2%, 2.5% and 1.1% lower at low resolution (10,329 nuclei). High-resolution features and tissue textural features were computed for each case. The high-resolution features showed good separation between the three groups of cases. The tissue textural features showed consistent separation between well and moderately differentiated cases. The relaxation of the spatial resolution (to 0.8 micron/pixel spacing) did not affect the selection of features, but led to less separation between the data from different grades. In conclusion, the automated system performed satisfactorily in distinguishing sections of prostatic tumors of varying degrees of differentiation.     

Morphometry, densitometry and pattern analysis of plastic-embedded histologic material from urothelial cell carcinoma of the bladder.

An image analysis method of grading histologic sections of bladder carcinoma was tested. The method was new in four respects. First, for fixation of the biopsies a coagulant fixative was used. Second, 2-microns plastic sections were used to ensure the reproducibility of nuclear imaging. Third, a new stereologic approach was used for calculation of the nuclear volume and DNA content. Fourth, for the classification rule the morphometric, densitometric and texture features were used in concert. The IBAS 2000 instrument was used for the measurements. Texture analysis of the chromatin patterns was performed using Markovian texture features. Using discriminant analysis, of 22 parameters, 2 morphometric, 2 densitometric and 3 texture features were selected for the classification rule. With them, 89% of the bladder carcinomas were correctly classified into the three grades. All grade III tumors were classified correctly. Among the features tested, the densitometry of the DNA had the highest F values. All of the grade III tumors and 45% of the grade II tumor group had DNA histograms indicating aneuploidy. This study showed that plastic-embedded material is well suited to morphometry and densitometry and can be used for quantitative grading of bladder carcinoma.     

Apoptosis in breast cancer

OBJECTIVE: To evaluate apoptotic rates on fine needle aspiration (FNA) samples of infiltrating duct carcinoma of the breast and to determine whether cytologic grading improved with consideration of the apoptotic rate in comparison with histologic grading. STUDY DESIGN: We studied 35 women who underwent mastectomy following an FNA diagnosis of infiltrating ductal carcinoma. Concordance between cytologic and histologic grades was calculated. Next, cytologic grades were considered with the apoptotic rates and compared with the histologic grades. RESULTS: An overall concordance of 82.9% was noted between the cytologic and histologic grading systems, with maximum concordance in grade 1 and minimum in grade 3 breast cancers. A highly significant difference in the apoptotic rates, as calculated on cytology, existed between the three histologic grades, indicating a significant increase in apoptosis with rising histologic grade. Applying multiple regression analysis, a significant improvement of cytologic grade with consideration of the apoptotic rate was observed. CONCLUSION: Employing histologic grade as the yardstick, cytology was less sensitive for the purpose of grading breast ductal carcinoma. However, by considering the apoptotic rates, the sensitivity of cytologic grading significantly rose in relation to histologic grade. Larger studies are required to determine whether apoptosis can be incorporated into the existing cytologic grading systems to increase their sensitivity.     

Karyometric features of low and high grade glial tumors as compared with their MRI appearance

OBJECTIVE: To compare the results of a magnetic resonance imaging (MRI) grading designed to identify low and high grade gliomas with karyometry used as a tool to grade primary brain tumors. STUDY DESIGN: A consecutive series of 23 primary brain tumors was selected for this study. The neuroradiologist, not knowing the histologic diagnoses, divided the cases into low and high grade categories on the basis of the following 7 features: border sharpness, heterogeneity without contrast, cavitation, contrast enhancement, hypervascularity, mass effect and perifocal T2 hyperintensity. To each feature was given a numerical value, ranging from 1 to 3. All the cases were reviewed and classified by the same pathologist, blinded to the MRI diagnosis. Two hundred nuclei per case were recorded, and 93 karyometric features related to nuclear area, total optical density and chromatin distribution were analyzed for each nucleus. Statistical analysis included discriminant analysis, Kruskal-Wallis test, nonsupervised learning algorithm P-index and Beale statistic. RESULTS: Ten cases were classified as low grade on the basis of their MRI features. The corresponding histopathologic diagnoses were: grade 2 astrocytoma in 2 cases and grade 2 oligodendroglioma in 8 cases. An MRI diagnosis of high grade tumor was made in 13 cases. In 10 cases it was confirmed by the histopathologic diagnosis (3 grade 3 astrocytomas, 1 grade 3 oligodendroglioma and 6 glioblastomas). In the remaining 3 cases the histologic examination revealed a low grade tumor, 1 grade 2 astrocytoma and 2 grade 2 oligodendrogliomas. For the purposes of the karyometric analysis the cases were allocated to the low or high grade category according to their histologic diagnosis (13 cases low grade and 10 cases high grade). Nuclei from low and high grade tumors showed clearly different karyometric characteristics. The oligodendroglioma nuclei had abnormality values close to the low grade standard, while the astrocytoma nuclei were a highly dispersed group with characteristics indicative of a higher degree of nuclear abnormality than the oligodendroglioma nuclei. The results of karyometric analysis showed that grade 2 tumors, corresponding to the low grade group, form a rather distinct category from grade 3 and 4 tumors belonging to the high grade group. CONCLUSION: The results of MRI grading based on a series of features that are routinely assessed by the neuroradiologist to reach a final diagnosis correlate highly with the histopathologic diagnosis. Karyometry can be a useful adjunct to histologic grading.     

Algorithms for quantitation of protein expression variation in normal versus tumor tissue as a prognostic factor in cancer: Met oncogene expression, and breast cancer as a model

BACKGROUND: Immunohistochemistry and immunofluorescence (IF) assays frequently rely on subjective observer evaluation for grading. The aim of our study was to develop an objective quantitative index based on confocal laser scanning microscopy (CLSM) and image analysis of an IF assay to determine alteration in protein expression levels in normal versus tumor tissue. The relative levels of Met expression, a prognostic factor in breast cancer, were used as a model for evaluating image analysis algorithms. METHODS: Primary human breast cancer biopsies were collected. Sections containing tumor and adjacent uninvolved normal regions were immunostained for Met and digital images were acquired by CLSM. Subsequently, the digital data were manipulated using several different algorithms to calculate prognostic indexes. The results were correlated with the clinical outcome to determine the prognostic value of these indexes. RESULTS: Different algorithms were used to obtain quantitative indexes to evaluate the relative levels of Met expression. We report a statistical correlation between patient prognosis and relative Met level in normal versus tumor tissue as determined by three distinct algorithms using Kaplan-Meier analysis (log-rank): calculations based on intensity levels differences DV (P = 0.002), DIntensity (P = 0.014), and entropy divergence (Dentropy; P = 0.0023). CONCLUSIONS: Using adjacent normal tissue as an internal reference, a quantitative index of tumor Met level divergence can be objectively determined to have a prognostic value. Moreover, this methodology can be used for other proteins in a variety of different diseases.     

Cytologic evaluation of prognostic markers in breast carcinoma

To type breast carcinomaon on fine needle aspiration cytology (FNAC) material and correlate the results with histologic typing, to grade breast carcinoma on FNAC material and correlate the findings with Bloom-Richardson histologic grading, and to determine the estrogen receptor (ER) status in cases of breast carcinoma by immunocytochemical (ICC) staining of FNA cytologic material and correlate the findings with ER status, as determined by immunohistochemical (IHC) staining of tissue sections. STUDY DESIGN: Seventy-seven cases of breast carcinoma diagnosed on FNAC formed the basis of this study. Typing was done in all cases on the basis of cytologic features and grading in 62. (Fifteen cases were special types of breast carcinoma). In all cases, ER status was determined by immunostaining of cytologic smears. Results of tumor typing, grading and ER status on cytologic material were compared with the results of histologic typing, grading and immunostaining of histologic material obtained from mastectomy or wide excision specimens. RESULTS: Tumor typing was accurate in 73 of 77 cases (94.8%). Fifteen of 18 cases that were cytologically grade 3 were confirmed on histology, while 3 proved to be grade 2. Of 40 cytologic grade 2 cases, 26 were confirmed on histology, while 14 cases were grade 3. Three of 4 cytologically grade 1 cases were confirmed on histology while 1 was grade 2. The overall accuracy for cytologic grading was 71% (44 of 62 cases). Thirty-seven of 40 ER-positive cases (92.5%) were labeled ER positive on ICC. One case was ER negative on cytology, while in 2 cases the cellularity of the cytologic smear was insufficient to assess ER expression. Thirty-seven cases were negativefor ER on IHC. Nine of these showed ER positivity on ICC, 26 were negative, and 2 had cellularity that was inadequate for assessment of ER. Sensitivity and specificity rates for ER detection on ICC were 97.4% and 74.3%, respectively. CONCLUSION: Tumor typing, grading and evaluation of ER status on FNA C material in breast carcinomas are simple, quick and moderately reliable techniques that compare and correlate favorably with histologic typing, grading and ER status on IHC.     

Clinical aspects for the use of DNA image cytometry in detection of bladder cancer: a valuable tool?

The employment of DNA flow or image cytometry for oncological diagnostic procedures is favored because of its high correlation to tumor biological behavior. Prognostic statements and therapeutic strategies therefore are based on the high validity of DNA cytometric measurements. Using 151 bladder washings from patients suspected of bladder cancer for this study, we examined the clinical value of various common methods of DNA single cell (SCI) and stemline interpretations (SLI). Comparing the specificity and sensitivity of DNA image cytometry in detection of bladder tumors, we found 81 and 52%, respectively, for SCI of Boecking, 84 and 45% for SLI of Boecking, 61 and 58% for SLI of Fu, and 82 and 40% for conventional stemline interpretation. To improve diagnostic and prognostic validity of DNA image cytometry, we designed our own method of interpretation. In consequence, we identified six single DNA parameters out of all recorded measurements that correlated most to histopathological grading (G1-G3). Creating reference values at random and rating by points, we used a cytometric grading system for ranking. In detection of bladder cancer specificity and sensitivity ultimately arrived at almost 70% in application of our method. Thus, by this study, we were able to show that sensitivity of DNA examination can be increased by combining various DNA parameters. Apart from our own scheme, the discrepancy in interpretation of DNA image cytometry does not allow us to recommend this procedure as the only diagnostic in detection of bladder cancer. However, in regard to prognostic statements, particularly tumor biological behavior, DNA image cytometry appears to be useful.     

Correlated immunohistochemical and cytological assays for the prediction of hematogenous dissemination of breast cancer

Although metastasis is a major cause of death from breast cancer, our ability to predict which tumors will metastasize is limited (American Cancer Society 2010). Proper assessment of metastatic risk and elucidating the underlying mechanisms of metastasis will help personalize therapy and may provide insight into potential therapeutic targets. Traditionally, histologic grading, staging, hormone receptors, HER2/Neu, and proliferation assays have been the gold standard on which oncologists based their treatment decisions. However, all of these are indirect measures of metastatic risk. Recent insights from intravital imaging directly address questions of mechanism and have led to a new way of using histologic and cytologic material to assess metastatic risk. This review describes the tumor microenvironment model of invasion and intravasation, as well as an emerging histopathologic application based on this model. In particular, the authors describe a new immunohistochemical approach to the assessment of metastatic risk based on the density of intravasation microenvironment sites called the tumor microenvironment of metastasis. In addition, they describe an isoform assay for the actin regulatory protein Mena using fine needle aspiration samples and the details about how these 2 assays may be applied in clinical practice in a synergistic way to assess the risk of metastasis.