Automated detection of connective tissue by tissue counter analysis and classification and regression trees.

OBJECTIVE: To evaluate the feasibility of the CART (Classification and Regression Tree) procedure for the recognition of microscopic structures in tissue counter analysis. METHODS: Digital microscopic images of H & E; stained slides of normal human skin and of primary malignant melanoma were overlayed with regularly distributed square measuring masks (elements) and grey value, texture and colour features within each mask were recorded. In the learning set, elements were interactively labeled as representing either connective tissue of the reticular dermis, other tissue components or background. Subsequently, CART models were based on these data sets. RESULTS: Implementation of the CART classification rules into the image analysis program showed that in an independent test set 94.1% of elements classified as connective tissue of the reticular dermis were correctly labeled. Automated measurements of the total amount of tissue and of the amount of connective tissue within a slide showed high reproducibility (r=0.97 and r=0.94, respectively; p<0.001). CONCLUSIONS: CART procedure in tissue counter analysis yields simple and reproducible classification rules for tissue elements.     

Evaluation of texture features in spatial and frequency domain for automatic discrimination of histologic tissue

OBJECTIVE: To investigate the applicability of different texture features in automatic discrimination of microscopic views from benign common nevi and malignant melanoma lesions. STUDY DESIGN: In tissue counter analysis (TCA) the images are dissected into square elements used for feature calculation. The first class of features is based on the histogram, the co-occurrence matrix and the texture moments. The second class is derived from spectral properties of the wavelet Daubechie 4 and the Fourier transform. Square elements from images of a training set are classified by Classification and Regression Trees analysis. RESULTS: Features from the histogram and the co-occurrence matrix enable correct classification of 94.7% of nevi elements and 92.6% of melanoma elements in the training set. Classification results are applied to individual test set cases. Discriminant analysis based on the percentage of "malignant elements" showed correct classification of all nevi cases and 95% of melanoma cases. Features derived from the wavelet and Fourier spectrum showed correct results for 88.8% and 79.3% of nevi and 85.6% and 81.5% of melanoma elements, respectively. CONCLUSION: TCA is a potential diagnostic tool in automatic analysis of melanocytic skin tumors. Histogram and co-occurrence matrix features are superior to the wavelet and the Fourier features.     

Discrimination of benign common nevi from malignant melanoma lesions by use of features based on spectral properties of the wavelet transform

OBJECTIVE: To evaluate the possibilities of describing and discriminating common nevi and malignant melanoma tissue with features based on spectral properties of the Daubechies 4 wavelet transform. STUDY DESIGN: Images of common nevi and malignant melanoma were dissected in square elements. The wavelet coefficients were calculated inside the square elements. The diagonal coefficients and related power spectra were used for further analysis. The analysis results served as guide for the selection of features, including standard deviations of wavelet coefficients inside the frequency bands and the energy of the frequency bands. These features describe properties of the frequency bands, representing information on different scales. To test the usefulness of the features for discrimination, a study set of 80 cases was classified by classification and regression trees analysis. The set was divided into a training set and a test set. RESULTS: In the case of benign common nevi, the energies of the lower frequency bands and higher, whereas malignant melanoma tissue shows more variability of the coefficients in higher-frequency bands. The influence on the detail properties of the images was studied by suppression of coefficients with low values, which are concentrated mainly in higher-frequency bands. In the case of benign common nevi the main information is contained in 15% of the coefficients and in the case of malignant melanoma, in 39%. The results of classification show a clear-cut difference between the cases. The classification correctly classified 95.78% of nevi elements and 94.22% of melanoma elements in the training set and 100% of cases of benign nevi and 80% of cases of malignant melanoma in the test set. CONCLUSION: Features based on the wavelet power spectrum contain sufficient information for differentiation between common nevi and malignant melanomas.     

Diagnostic assessment of cutaneous melanoma and common nevi using tissue counter analysis

OBJECTIVE: To test the applicability of tissue counter analysis to the diagnostic discrimination of cutaneous malignant melanoma and benign common melanocytic nevi. STUDY DESIGN: Forty cases each of melanoma and nevi were consecutively sampled. After creation of a learning set based on 20 cases each, discriminant analysis of background versus tissue elements, tumor versus other tissue elements and benign versus malignant tumor elements was performed. The discriminant functions were used to assess the amount of benign and malignant tumor elements in each case. RESULTS: In the learning set, discriminant analysis facilitated recognition of 99.6% of tissue versus background, 90.7% of tumor versus other tissue components and 85.6% of malignant versus benign tumor elements. In the whole set, the percentage of malignant tumor elements was 8.7 +/- 7.7 (range, 0.1-29.6) for benign nevi and 77.4 +/- 16.2 (43.6-99.4) for malignant melanoma. Based on these measurements, the correct diagnosis could be established in all cases (chi 2 > .0001). CONCLUSION: Tissue counter analysis may be a useful method for diagnostic purposes in histopathology.     

Classification trees: An alternative non‐parametric approach for predicting species distributions

Abstract. The use of Generalized Linear Models (GLM) in vegetation analysis has been advocated to accommodate complex species response curves. This paper investigates the potential advantages of using classification and regression trees (CART), a recursive partitioning method that is free of distributional assumptions. We used multiple logistic regression (a form of GLM) and CART to predict the distribution of three major oak species in California. We compared two types of model: polynomial logistic regression models optimized to account for non‐linearity and factor interactions, and simple CART‐models. Each type of model was developed using learning data sets of 2085 and 410 sample cases, and assessed on test sets containing 2016 and 3691 cases respectively. The responses of the three species to environmental gradients were varied and often non‐homogeneous or context dependent. We tested the methods for predictive accuracy: CART‐models performed significantly better than our polynomial logistic regression models in four of the six cases considered, and as well in the two remaining cases. CART also showed a superior ability to detect factor interactions. Insight gained from CART‐models then helped develop improved parametric models. Although the probabilistic form of logistic regression results is more adapted to test theories about species responses to environmental gradients, we found that CART‐models are intuitive, easy to develop and interpret, and constitute a valuable tool for modeling species distributions.     

Textural analysis in the diagnosis of benign and malignant breast cells

OBJECTIVE: To study the discriminatory capacity of textural variables to classify the nuclei of breast tumor cells as benign or malignant, using a statistical approach. STUDY DESIGN: Image analysis techniques were used to automatically segment nuclei of cells obtained by fine needle aspiration and Papanicolaou stained. The sample comprised 95 cases of malignant lesions and 47 cases of benign lesions (approximately 25 nuclei per case), and 27 textural variables were measured. Two methods were used to analyze the data: classification and regression trees (CART) and discriminant analysis. RESULTS: The variance in gray levels was the most decisive variable in the CART analysis, correctly classifying 57% and 97% of benign and malignant cases, respectively. Discriminant analysis yielded the best results, correctly classifying 79% and 85% of benign and malignant cases, respectively. CONCLUSION: The classifier obtained by a statistical approach to the textural analysis of Papanicolaou-stained nuclei did not prove useful for diagnostic discrimination. Staining techniques that are not chromatin specific are highly variable, and other features have proven more effective with this type of staining.     

ACOUSTIC IDENTIFICATION OF NINE DELPHINID SPECIES IN THE EASTERN TROPICAL PACIFIC OCEAN

Acoustic methods may improve the ability to identify cetacean species during shipboard surveys. Whistles were recorded from nine odontocete species in the eastern tropical Pacific to determine how reliably these vocalizations can be classified to species based on simple spectrographic measurements. Twelve variables were measured from each whistle ( n = 908). Parametric multivariate discriminant function analysis (DFA) correctly classified 41.1% of whistles to species. Non-parametric classification and regression tree (CART) analysis resulted in 51.4% correct classification. Striped dolphin whistles were most difficult to classify. Whistles of bottlenose dolphins, false killer whales, and pilot whales were most distinctive. Correct classification scores may be improved by adding prior probabilities that reflect species distribution to classification models, by measuring alternative whistle variables, using alternative classification techniques, and by localizing vocalizing dolphins when collecting data for classification models.     

Comparison of discriminant function and classification tree analyses for age classification of marmots

We evaluated the predictive power of two classification techniques, one parametric – discriminant function analysis (DFA) and the other non-parametric – classification and regression tree analysis (CART), in order to provide a non-subjective quantitative method of determining age class in Vancouver Island marmots ( Marmota vancouverensis ) and hoary marmots ( Marmota caligata ). For both techniques we used morphological measurements of known-age male and female marmots from two independent population studies to build and test predictive models of age class. Both techniques had high predictive power (69–86%) for both sexes and both species. Overall, the two methods performed identically with 81% correct classification. DFA was marginally better at discriminating among older more challenging age classes compared to CART. However, in our test samples, cases with missing values in any of the discriminant variables were deleted and hence unclassified by DFA, whereas CART used values from closely correlated variables to substitute for the missing values. Therefore, overall, CART performed better (CART 81% vs DFA 76%) because of its ability to classify incomplete cases. Correct classification rates were approximately 10% higher for hoary marmots than for Vancouver Island marmots, a result that could be attributed to different sets of morphological measurements. Zygomatic arch breadth measured in hoary marmots was the most important predictor of age class in both sexes using both classification techniques. We recommend that CART analysis be performed on data-sets with incomplete records and used as a variable screening tool prior to DFA on more complete data-sets.     

Computer-aided classification of malignancy in astrocytomas. I. The value of nuclear parameters obtained by automated black and white image analysis.

Ninety-three selected cases of astrocytomas including glioblastomas (astrocytomas grades 1-4) were evaluated by means of Feulgen-stained microscopic slides for nuclear parameters obtained by automated black and white image analysis (ABWIA). The goal was to determine to what extent nuclear features evaluated by ABWIA were applicable as classifiers for the computer-aided numerical classification of malignancy in astrocytomas. Before the automated evaluation, all tumours had been subjectively graded according to the Mayo Clinic grading rules as delineated by Ringertz. Twenty-three nuclear parameters were evaluated and tested for their classification impact. With a model of five parameters (number of nuclei per area, mean of the convex form factor, extinction sum, extinction variation, and full-width-half-maximum of the extinction distribution) the highest reclassification rate of 75% correctly reclassified cases was obtained. Although this is a good result for a classification using only nuclear parameters, it is too poor for practical application. Thus, nuclear parameters evaluated by ABWIA alone are insufficient for numerical classification models assessing the malignant expression of astrocytomas.     

Segmentation of stained blood cell images measured at high scanning density with high magnification and high numerical aperture optics

In hematological morphology, it is necessary to resolve and analyze the smallest possible cellular details appearing in the light microscope. A prerequisite for computer-aided analysis of subtle morphological features is measuring the cells at a high scanning density with high magnification and high numerical aperture optics. Contrary to visual observations, the information content in a measured picture can be increased by setting the condensor's numerical aperture (NA) greater than the objective's NA. The complexity and heterogeneity of such cell images necessitate a new segmentation method that conserves the morphological information required in the subsequent image analysis, feature extraction, and cell classification. In our segmentation strategy, characteristic color difference thresholds for each nucleus and cytoplasm are combined with geometric operations, probability functions, and a cell model. All thresholds are repeatedly recalculated during the successive improvements of the image masks. None of the thresholds are fixed. This strategy segments blood cell images containing touching cells and large variations in staining, texture, size, and shape. Biological inconsistencies in the calculated cell masks are eliminated by comparing each mask with the cell model criteria integrated into the entire segmentation process. All 20,000 leukocyte images from 120 smears in our leukemia project were segmented with this method.     

Prognosis of moderate dysplasia. Predictive value of selected markers in routinely prepared cervical smears

Digital image analysis was used to extract features from 1,123 abnormal cells in 23 routinely prepared, Papanicolaou-stained cervical smears. All slides examined had a cytologic diagnosis of moderate dysplasia. Seven slides came from patients who eventually progressed to either a severe dysplasia or carcinoma in situ; the other 16 slides came from patients whose dysplasias regressed without evidence of more serious disease. Linear discriminant analysis correctly classified approximately 73% of the cells from the regression group and 66% of the cells from the progression group. Cell features contributing to the majority of variance in the model were the mean optical density of the nucleus, an autocorrelation measure, the mean optical density of the cytoplasm and the nuclear-cytoplasmic ratio. At the patient level, 13 (81.2%) of the 16 slides from the regression group and 6 (85.7%) of the 7 slides from the progression group were correctly classified. These figures yield a sensitivity of 66.7%, a specificity of 92.9%, a predictive value of a progression prognosis of 85.9% and a predictive value of a regression prognosis of 81.2%. The overall efficiency of the model was 82.6%. These preliminary results should encourage further studies for the identification of markers to indicate which patients are at high risk for progression of their cervical dysplasias.     

Deep learning of diffraction image patterns for accurate classification of five cell types

Development of label‐free methods for accurate classification of cells with high throughput can yield powerful tools for biological research and clinical applications. We have developed a deep neural network of DINet for extracting features from cross‐polarized diffraction image (p‐DI) pairs on multiple pixel scales to accurately classify cells in five types. A total of 6185 cells were measured by a polarization diffraction imaging flow cytometry (p‐DIFC) method followed by cell classification with DINet on p‐DI data. The averaged value and SD of classification accuracy were found to be 98.9% ± 1.00% on test data sets for 5‐fold training and test. The invariance of DINet to image translation, rotation, and blurring has been verified with an expanded p‐DI data set. To study feature‐based classification by DINet, two sets of correctly and incorrectly classified cells were selected and compared for each of two prostate cell types. It has been found that the signature features of large dissimilarities between p‐DI data of correctly and incorrectly classified cell sets increase markedly from convolutional layers 1 and 2 to layers 3 and 4. These results clearly demonstrate the importance of high‐order correlations extracted at the deep layers for accurate cell classification.      

Reliability and accuracy of reporting cervical intraepithelial neoplasia (CIN) in 15 laboratories throughout Italy: phase 1 of a national programme of external quality control in cervical screening

This paper reports results of a first phase of a pilot study to assess and improve quality of diagnoses in cervical cytological laboratories located throughout Italy. It represents the first phase of an External Quality Assurance programme (EQA). In the first phase, two sets of cervical smears representing a range of diagnoses were circulated among participating laboratories. Responses were recorded on a standardized form. Participants were asked to assess the adequacy of the smear and formulate a diagnosis. They were also asked to recommend management of the patient on the basis of the smear report and judge the degree of diagnostic difficulty of each slide. Crude index of agreement, unweighted and weighted kappas, diagnostic specific kappas, sensitivity and specificity as well as clinical indices of variability were calculated. In the second phase, two additional sets of slides were circulated after discussion of the first phase. There was striking variability between laboratories, both in terms of diagnoses offered and recommendations for management on individual slides. Assessment of the degree of difficulty of each slide was also very variable. Discrimination between CINII and CINIII was poor, confirming the choice of merging these two categories in the Bethesda classification. However, discrimination between CINI and CINII was also unsatisfactory. The results were discussed in workshops and it was possible to reach a consensus diagnosis in 35 of 40 smears. This study confirms the need for external quality control programmes.     

Discrimination between benign and malignant melanocytic skin lesions by multivariate analysis, quantitative S-100 immunohistochemistry, nuclear morphometry and DNA cytometry

OBJECTIVE: To determine whether combined quantitative immunohistochemistry of S-100, nuclear morphometry and DNA image cytometry improves discrimination between benign and malignant melanocytic skin lesions (MSLs). STUDY DESIGN: S-100 protein expression was measured in tissue sections of MSLs using an image cytometry system. Localized areas of high S-100 expression were used to identify regions in sequential, facing sections in which morphometric and cytometric features of nuclei, including DNA ploidy, were also measured. RESULTS: Malignant cases had significantly higher S-100 protein staining intensity, larger nuclei and greater DNA content (P < .05). High staining intensity for S-100 protein weakly correlated with variation in size of the mean nuclear area (P = .04) and DNA content (P = .03). Combining the features of nuclear area and DNA integrated optical density in areas of high-intensity staining for S-100 protein discriminated more accurately between 12 benign and 16 malignant areas than any of the features along (P = .0003). CONCLUSION: Combined multivariate quantitative immunohistochemical, morphometric and DNA cytometric analysis greatly improves discrimination between benign MSLs and malignant melanoma. Larger test sets are required to confirm the promising results of this initial study.     

综合面向对象与决策树的毛竹林调查因子及碳储量遥感估算

综合面向对象和CART决策树方法,对浙江省安吉县山川乡毛竹林分布信息及胸径、树高、郁闭度等调查因子和地上部分碳储量进行遥感定量估算.结果表明: 综合基于多尺度分割的对象特征及决策树,能够充分利用不同尺度层次信息关联的优势,实现毛竹林专题信息高精度提取,其用户精度达到89.1%;基于对象特征构建的毛竹林调查因子回归树估算模型,其估算结果均能达到正常或较好水平,其中,郁闭度回归树模型的精度最高为67.9%,估算效果较好;而平均胸径和树高估算的总精度相对较低,这与采用光学遥感数据进行森林树高、胸径估算达不到理想结果的结论一致;毛竹林地上部分碳储量回归树模型的估算结果较好,高值区域估算精度达到80%以上.     

Automatic detection of melanoma progression by histological analysis of secondary sites

We present results from machine classification of melanoma biopsies sectioned and stained with hematoxylin/eosin (H&E) on tissue microarrays (TMA). The four stages of melanoma progression were represented by seven tissue types, including benign nevus, primary tumors with radial and vertical growth patterns (stage I) and four secondary metastatic tumors: subcutaneous (stage II), lymph node (stage III), gastrointestinal and soft tissue (stage IV). Our experiment setup comprised 14,208 image samples based on 164 TMA cores. In our experiments, we constructed an HE color space by digitally deconvolving the RGB images into separate H (hematoxylin) and E (eosin) channels. We also compared three different classifiers: Weighted Neighbor Distance (WND), Radial Basis Functions (RBF), and k-Nearest Neighbors (kNN). We found that the HE color space consistently outperformed other color spaces with all three classifiers, while the different classifiers did not have as large of an effect on accuracy. This showed that a more physiologically relevant representation of color can have a larger effect on correct image interpretation than downstream processing steps. We were able to correctly classify individual fields of view with an average of 96% accuracy when randomly splitting the dataset into training and test fields. We also obtained a classification accuracy of 100% when testing entire cores that were not previously used in training (four random trials with one test core for each of 7 classes, 28 tests total). Because each core corresponded to a different patient, this test more closely mimics a clinically relevant setting where new patients are evaluated based on training with previous cases. The analysis method used in this study contains no parameters or adjustments that are specific to melanoma morphology, suggesting it can be used for analyzing other tissues and phenotypes, as well as potentially different image modalities and contrast techniques.     

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.