Contextual analysis and intermediate cell markers enhance high-resolution cell image analysis for automated cervical smear diagnosis.

Until now, efforts to automate cervical smear diagnosis have focused on analyzing features of individual cells. In a complex specimen such as that obtained from a cervical scrape, diagnostically significant cells may not be adequately represented or may elude detection by the automated technology. An approach is needed that extracts additional quantitative information from cervical smears beyond what the cell-by-cell approach can provide. A new methodology, contextual analysis, was developed to extract global quantitative information about cells, cell clusters, and background debris. This pilot study was designed to compare the efficacy of contextual analysis with high-resolution, single cell analysis and the analysis of intermediate cell markers. Thirty-four samples prepared as monolayers and stained with the Feulgen-Thionin/Congo Red stain were measured. Contextual analysis alone was able to classify 91% of the smears correctly; single cell analysis classified 94% of the cells correctly; and the intermediate cell analysis correctly identified the smear diagnosis for 84% of the cells. When all three analysis methods were combined into a simple smear level classifier, the overall smear classification accuracy was improved over those obtained using the three methodologies alone.     

Evaluation of contextual analysis for computer classification of cervical smears

A procedure for automated analysis of cervical smears has been implemented in an image cytometry system. Smears are described exclusively in terms of global and contextual information extracted by pattern-recognition algorithms and represented by a vector of proportions of cellular object types. Linear discriminant functions, based on a Fisher criterion, are derived to classify smears with a cross-section of diagnoses into two broad categories, normal and abnormal. Results obtained from 83 smears indicate 78% correct classification. In contrast to most automated systems, good classification results were obtained in normal smears with benign changes caused by inflammation and with postmenopausal atrophia and in abnormals with mild dysplasia. These findings suggest that contextual analysis may be sensitive to subtle changes in cellular morphology and to progressive patterns of dysplasia. When used with standard isolated cell analysis, contextual analysis may provide additional complementary information for automated cervical prescreening.     

Computerized microscopic analysis of prostatic fine needle aspirates. Comparison with breast aspirates

Computerized image analysis was employed to analyze fine needle aspiration smears of the prostate and breast using both high-resolution images of individual cells and medium-resolution images of scenes and clusters (contextual analysis). A linear discriminant analysis was used to demonstrate the computer's ability to discriminate between benign and malignant categories for both types of tissue. Correct classification as benign or malignant using contextual analysis was achieved in 22 of 26 prostatic aspirates and in 15 of 18 breast aspirates, as determined by comparison with histology. The addition of high-resolution single-cell analysis resulted in correct classification of 24 of 26 prostatic aspirates and all breast aspirates. For virtually all features, the distinction between benign and malignant was more subtle for prostatic than for breast tissue. The data indicate that contextual analysis may be less effective as an adjunct to high-resolution single-cell microscopy of prostatic specimens than it is for breast specimens.     

Identification of components of fibroadenoma in cytology preparations using texture analysis: a morphometric study

S. Singh and R. Gupta Identification of components of fibroadenoma in cytology preparations using texture analysis: a morphometric study Objectives: To evaluate the utility of image analysis using textural parameters obtained from a co‐occurrence matrix in differentiating the three components of fibroadenoma of the breast, in fine needle aspirate smears. Methods: Sixty cases of histologically proven fibroadenoma were included in this study. Of these, 40 cases were used as a training set and 20 cases were taken as a test set for the discriminant analysis. Digital images were acquired from cytological preparations of all the cases and three components of fibroadenoma (namely, monolayered cell clusters, stromal fragments and background with bare nuclei) were selected for image analysis. A co‐occurrence matrix was generated and a texture parameter vector (sum mean, energy, entropy, contrast, cluster tendency and homogeneity) was calculated for each pixel. The percentage of pixels correctly classified to a component of fibroadenoma on discriminant analysis was noted. Results: The textural parameters, when considered in isolation, showed considerable overlap in their values of the three cytological components of fibroadenoma. However, the stepwise discriminant analysis revealed that all six textural parameters contributed significantly to the discriminant functions. Discriminant analysis using all the six parameters showed that the numbers of pixels correctly classified in training and tests sets were 96.7% and 93.0%, respectively. Conclusion: Textural analysis using a co‐occurrence matrix appears to be useful in differentiating the three cytological components of fibroadenoma. These results could further be utilized in developing algorithms for image segmentation and automated diagnosis, but need to be confirmed in further studies.     

Fine needle aspiration cytology of lobular breast carcinoma. Comparison with other breast lesions

OBJECTIVE: To analyze the detailed cytomorphology of lobular breast carcinoma and to compare the cytologic smears of benign, borderline and infiltrating duct carcinoma. STUDY DESIGN: Fine needle aspiration cytology (FNAC) smears of histopathologically proven infiltrating lobular carcinoma (ILC), infiltrating ductal carcinoma (IDC), borderline lesions and benign breast lesions were selected for study. Detailed cytomorphologic analysis of the smears was carried out on hematoxylin and eosin- and May-Grünwald-Giemsa--stained slides, and a comparison of results was done. The various cytologic features were also graded semi-quantitatively with the numerical score; logistic regression analysis was done. RESULTS: There were 25 cases of ILC, 30 of IDC, and 10 borderline and 18 benign lesions. Cytologic diagnosis of malignancy on FNAC smears of ILC was offered in 19 cases; of them, 2 cases were diagnosed as ILC. The remaining six cases were diagnosed as borderline (four) and benign lesions (two). Overall sensitivity in detection of malignancy in ILC cases was 76%. FNAC smears of ILC showed moderate (52%) to abundant (32%) cellularity. The cells of ILC were arranged both in clusters and in dissociation (72%). Individual cells were monomorphic (40%) to mildly pleomorphic (60%), and the cells were smaller. The cells showed a smooth, regular nuclear margin; bland chromatin; and indistinct nucleoli. Indian file arrangement was frequently observed (28%). Nuclear molding (28%) and intranuclear inclusions (16%) were also noted. Intracytoplasmic lumina were seen in occasional cases. Logistic regression analysis was carried out, and a comparison between lobular carcinoma and ductal carcinoma, and borderline and benign lesions was done. Logistic regression analysis of cytomorphologic features showed that cellularity and nuclear margin irregularities were the two most important features to distinguish ILC from IDC. In comparison to borderline lesions, cell dissociation was more common in ILC. The salient cytologic features that helped to distinguish ILC from benign lesions was cell size, cellularity, cell uniformity and chromatin pattern. CONCLUSION: There are overlapping cytologic features between ILC, IDC and borderline breast lesions on FNAC smears. Logistic regression analysis may be helpful in this regard.     

Application of discriminant analysis and quantitative cytologic examination to gastric lesions

OBJECTIVE: To investigate of the potential value of morphometry and discriminant analysis for the classification of benign and malignant gastric cells and lesions. STUDY DESIGN: The data set consisted of 13,300 cells from 120 cases composed of 30 cases of cancer, 26 cases of gastritis and 64 cases of ulcer according to the final histologic diagnosis. The cytologic diagnosis was divided into 5 categories (gastritis, ulcer, inflammatory dysplasia, cancer and true dysplasia). Classification was attempted at 2 levels: the cell level to classify individual cells and the case level to classify individual cases. For the cellular classification the measured cells from 50% of available cases were selected as a training set to construct a model. The cells from the remaining cases were used as a test set to validate the model. Similarly for case classification, the same 50% of cases that were used for cell classification were used as a training set and the remaining cases as a test set. Images of routinely processed gastric smears stained by the Papanicolaou technique were analyzed by a customized image analysis system. RESULTS: Application of discriminant analysis on the test set gave correct classification of 98.4% of benign cells and 67.1% of malignant cells. On case classification, 100% accuracy was achieved for benign and malignant cases, both for the training and test sets. CONCLUSION: The application of discriminant analysis described in this paper could produce significant classification results at the cellular and individual case level.     

Contextual analysis complements single-cell analysis in the diagnosis of breast cancer in fine needle aspirates

Image analysis techniques were used to characterize individual nuclei of cells and entire clusters of cells in hematoxylin-and-eosin-stained smears of fine needle aspirates of the breast to determine the ability of these techniques to distinguish benign from malignant cases. Analysis of the individual nuclear features showed significant differences in nuclear area, shape (bending energy), texture and integrated darkness between benign and malignant samples. Analysis of the clusters demonstrated that the benign clusters were fewer in number, more cellular (average gray level) and larger than malignant clusters. A statistical classifier was constructed to test the discriminatory accuracy for benign and malignant cases. Good discrimination was found for both the individual nuclei and the clusters when analyzed separately, although a few cases were misclassified by each type of analysis. When combined, the two classifiers achieved a completely accurate classification. This suggests the complementary nature of high-resolution single-cell analysis and the more global cluster analysis techniques.     

A morphologic analysis of the cells of ductal carcinoma of the breast and of adenocarcinoma of the ovary in pleural and abdominal effusions

The cells in serous effusions from 14 cases of histologically proven ductal adenocarcinoma of the breast and from an equal number of proven adenocarcinomas of the ovary were morphologically analyzed, with quantitative values assigned to various cell parameters. The resulting data were then subjected to stepwise discriminant analysis. The presence of coarse chromatin proved to be the most significant discriminating factor, resulting in a correct classification of 100% of the mammary carcinomas (14 of 14) and 71.4% (10 of 14) of the ovarian carcinomas, for an overall rate of 85.7% correct classifications. When combined with other cell parameters, such as the presence of polygonal cells, multiple nucleoli and an isolated cell arrangement, the accuracy rate increased to 92.9% correct classifications. Ovarian carcinoma was more likely to have coarse chromatin and to occur in three-dimensional cell groups, in contrast to mammary carcinoma, which tended to have fine chromatin and more polygonal cell shapes and to occur more commonly in syncytial cell groups and as isolated cells.     

Argyrophilic nucleolar organizer region (AgNOR) technique: a helpful tool for differential diagnosis in urinary cytology

The aim of this study was to investigate whether the AgNOR technique could be helpful for the cytologic diagnosis of neoplastic and non-neoplastic urinary tract lesions. We analysed the AgNOR pattern in urinary cytology in samples from 70 patients. In every case the average number of silver precipitations per nucleus was counted and the range between the minimum and maximum AgNOR value calculated. Furthermore we noted whether the AgNOR precipitations had a homogeneous or heterogeneous distribution. The diseases were classified in three groups: non-neoplastic lesions, low grade and high grade carcinoma. Linear discriminant analysis (with jack-knife procedure) was performed with the AgNOR parameters as independent variables. The final diagnosis of each patient had been established by histological analysis of bladder biopsies. We obtained a correct classification in 84.3% of the cases. All patients with normal or reactive lesions were correctly classified and only two cases of low grade malignancy were erroneously diagnosed as non-malignant. Five high grade neoplasms had been classified as low grade and four low grade carcinomas had been over-diagnosed as high grade neoplasms. We conclude that a combined qualitative and quantitative AgNOR analysis can be useful in the differential diagnosis of urinary cytology.     

Papillary breast lesions diagnosed on cytology. Profile of 65 cases

OBJECTIVE: To analyze the cytologic features of nipple discharge and fine needle aspiration (FNA) cytologic smears from breast lesions reported as showing papillary features and to correlate them with histopathologic features. STUDY DESIGN: The study group consisted of FNA smears and/or nipple discharge smears from 65 breast lesions diagnosed on cytology as duct papilloma, papillary lesion, fibrocystic condition, fibroadenoma, papillary neoplasm or papillary carcinoma. Cytomorphologic features assessed included cellularity, cell pattern (clusters, papillary, 3-dimensionality, etc.) and cell characteristics (monomorphism, pleomorphism, apocrine change, plasmacytoid features). Histological material was available for review and cytohistologic correlation in all cases. RESULTS: Forty-six specimens were FNA smears, and 16 were nipple discharge smears; in 3 cases FNA and nipple discharge cytologic smears were available for review. Cytologic study could predict the presence of a papillary pattern in all neoplasms with pure or focal papillary differentiation. There was an overlap in cytomorphologic features between papillary and nonpapillary benign lesions as well as between benign and malignant papillary neoplasms. Frank blood in the aspirate, cell dissociation and atypia, however, were more frequent in the last. CONCLUSION: Overlap of cytologic features in nonneoplastic and neoplastic benign papillary lesions and between benign and malignant papillary neoplasms necessitates histologic evaluation in all cases diagnosed as papillary on cytology. Since 49.2% of lesions showing papillary features on cytology prove to be malignant, all cases reported as papillary on cytology should be excised urgently for histologic assessment.     

Concentration of Lymph Node Aspirate Improves the Sensitivity of Acid Fast Smear Microscopy for the Diagnosis of Tuberculous Lymphadenitis in Jimma,Southwest Ethiopia

Background

Tuberculous lymphadenitis (TBLN) is the most common form of extrapulmonary tuberculosis. The cytomorphological features of lymph node smears have reduced specificity for the diagnosis of tuberculosis. The diagnosis of TBLN with direct smear microscopy lacks sensitivity due to the limited number of bacilli in lymph node aspirate. Therefore, we aimed to assess whether the concentration of lymph node aspirate improves the sensitivity of acid fast smear microscopy for the diagnosis of tuberculous lymphadenitis.

Methods

A cross-sectional comparative study was conducted on 200 patients clinically suspected for tuberculous lymphadenitis in Jimma, Ethiopia. Lymph node aspirate was collected. The first two drops were used for cytomorphological study and direct acid fast staining. The remaining aspirate was treated with N-acetyl-L-cysteine (NALC) and concentrated by centrifugation at 3000 g for 15 minutes. The sediment was used for acid fast staining and culture. Differentiation of M. tuberculosis complex (MTBC) from non-tuberculous mycobacteria (NTM) was done by para-nitrobenzoic acid susceptibility test.

Result

Complete data were available for 187 study subjects. 68% (127/187) were positive for M. tuberculosis on culture. Four isolates, 2.1% (4/187), were identified as NTM. The detection rate of direct smear microscopy was 25.1% and that of the concentration method 49.7%. Cytomorphologically, 79.7% of cases were classified as TBLN. The sensitivity of direct smear microscopy was 34.6%, for concentrated smear microscopy 66.1%, and for cytomorphology 89.8%. Two AFB positive cases on concentration method were non-tuberculosis mycobacteria (NTM). The concentration method yielded a positive result from seven cases diagnosed as suppurative abscess by cytology. Both for the direct and concentration methods the highest rate of AFB positivity was observed in smears showing caseous necrosis alone. Smear positivity rate decreased with the appearance of epithelioid cell aggregates.

Conclusion

The concentration of lymph node aspirates for acid fast smear microscopy had significantly higher sensitivity than direct microscopy.     

Endoscopic ultrasound-guided fine needle aspiration cytology of pancreatic neuroendocrine tumours: cytomorphological and immunocytochemical evaluation

OBJECTIVES: Endoscopic ultrasound (EUS)-guided fine needle aspiration (FNA) is increasingly used in preoperative localization and diagnosis of pancreatic neoplasms including neuroendocrine tumours (NETs). The objective of the present study was to identify the cytological features of pancreatic NETs obtained by EUS-FNA. METHODS: The study group consisted of nine cases of pancreatic tumours correctly diagnosed or strongly suggestive of NETs based on EUS-FNA. Cytological smears were retrospectively reviewed. The clinical data and immunocytochemical stains applied to the cell block preparations were also reviewed and examined. RESULTS: All cases except one showed characteristic cytomorphological features sufficient for their recognition and separation from pancreatic adenocarcinoma and other lesions. The most helpful cytological features that facilitated the cytological diagnosis of NET were a richly cellular aspirate with a monotonous, poorly cohesive population of small cells with a speckled or dusty chromatin pattern and plasmacytoid morphology. The neuroendocrine differentiation of these tumours was further confirmed by immunocytochemistry. CONCLUSION: EUS-FNA is a valuable method in the recognition of pancreatic NETs. By adherence to the characteristic cytomorphological criteria of pancreatic NET together with collection of suitable material for ancillary immunocytochemical stains, cytopathologists could reach a correct diagnosis in most instances.     

Diagnosis of tuberculous lymphadenitis by FNAC, microbiological methods and PCR: a comparative study

Despite its usefulness in the diagnosis of tuberculous lymphadenitis, fine needle aspiration cytology (FNAC) faces several limitations, and its sensitivity and specificity are not well established. The diagnostic accuracy and limitations of FNAC were studied in comparison with conventional microbiological methods and polymerase chain reaction (PCR). Sixty patients with lymphadenopathy and a clinical diagnosis of tuberculous lymphadenitis were subjected to FNA. The aspirate was used for cytological examination, Ziehl-Neelsen staining, mycobacterial culture and PCR. PCR was performed using two sets of oligonucleotide primers for Mycobacterium tuberculosis and a single primer for M. bovis species. The results of FNAC, microbiological methods and PCR correlated with the clinical outcome after follow-up for an average period of 24 months. Twenty-five cases (41.6%) were treated and responded well to anti-tuberculosis therapy, among them 17 were correctly diagnosed by FNAC (68%), eight by microbiological methods (32%) and 24 by PCR (96%). When PCR is considered the gold standard, FNAC predicted the correct diagnosis in 62% of cases with a high false negative rate (38%) due to the absence of granuloma/necrosis in smears from cases of early tuberculosis. In the latter group PCR proved to be the most valuable and a diagnostic success of 100% was achieved when FNAC and PCR were combined. In addition, PCR allowed immediate characterization of M. tuberculosis in the vast majority (96.2%) of cases in the study population.     

ALARM CALLS OF THE EUROPEAN GROUND SQUIRREL SPERMOPHILUS CITELLUS AND THE TAURUS GROUND SQUIRREL S. TAURENSIS ENCODE INFORMATION ABOUT CALLER IDENTITY

ABSTRACT

Vocalizations of many mammalian species have been reported to encode information about caller identity. In this study, we analyzed 300 alarm calls from 10 free-living European Ground Squirrels Spermophilus citellus (30 per individual) and 300 alarm calls from 10 free-living Taurus Ground Squirrels S. taurensis (30 per individual), and tested the potential of these calls to encode information about the callers' identities. Discriminant analysis including all 10 European Ground Squirrel individuals correctly classified 98% of calls, and cross-validation reached a classification success of 97%. Correct classification of 98% and cross-validation of 98% was assigned when the analysis included only those individuals producing calls consisting of both elements (eight individuals). For the Taurus Ground Squirrel, correct classification was 95% and cross-validation 94% for all 10 animals. When only those individuals producing calls consisting of both elements were included (eight individuals), discriminant analysis led to 94% correct classification and cross-validation produced a classification success of 93%. These analyses demonstrate that the structure of alarm calls in these two closely related species is highly variable and that it has significant potential to encode information about caller identity.     

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.     

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.     

Visual classification of erythrocytes in blood smears from normal subjects and patients

Erythrocytes on specially prepared and coloured blood smears can be classified not only by idcture analysis but also by phase contrast microscopy. Parameters of change for the peripheral zone area and pallor area (phase contrast value PW and index of erythrocyte changes Ev-I) serve as classificators of visual technique. 449 blood smears of the same number of male and female grown-up persons, whose diagnosis was unknown at the time of evaluation, were used for evaluation. In 145 cases these were healthy test persons in clinical and laboratory respect (group I). 163 test persons were ill, but without any malignous neoplasias (group II), and in 141 patients an ensured malignous neoplasia could be found (group III). From those 308 test persons or patients respectively in group I + II 11 blood smears were falsely classified as positive (= 3.6%). In 5 from 141 cases in group III blood smears were falsely evaluated as negative (= 3.6%). The findings were statistically ensured by the t-test. Clinical parameters of evaluation gained with visual techniques of classification are in accordance with those gained with automatic picture analysis. The reasons for the good separating ability of PW and Ev-I are discussed. Visual techniques of classification are suitable for institutions of all grades of equipment.     

Computational methods for gene expression-based tumor classification

Gene expression profiles may offer more or additional information than classic morphologic- and histologic-based tumor classification systems. Because the number of tissue samples examined is usually much smaller than the number of genes examined, efficient data reduction and analysis methods are critical. In this report, we propose a principal component and discriminant analysis method of tumor classification using gene expression profile data. Expression of 2000 genes in 40 tumor and 22 normal colon tissue samples is used to examine the feasibility of gene expression-based tumor classification systems. Using this method, the percentage of correctly classified normal and tumor tissue was 87.0%. The combined approach using principal components and discriminant analysis provided superior sensitivity and specificity compared to an approach using simple differences in the expression levels of individual genes.     

Breast myeloma: a report of 3 cases with fine needle aspiration cytologic findings

BACKGROUND: Multiple myeloma of the breast is very rare, and the fine needle aspiration (FNA) findings have not been reported before. CASES: Two cases of multiple myeloma presented with bilateral breast nodules during treatment with chemotherapy. One case of multiple myeloma presented initially with a left breast mass. FNA smears of all 3 cases revealed numerous plasma cells, plasmablasts and multinucleated giant plasma cells. The smears were diagnosed as plasma cell tumors. Serum immunoelectrophoresis revealed IgG myeloma in 2 cases and IgA myeloma in 1. Marrow aspirates revealed > 30% plasma cells. Two patients died, and 1 was alive at this writing. CONCLUSION: The aspiration cytology findings of myeloma can be confuse, with primary and secondary tumors of the breast. The previous clinical history and ancillary studies, such as bone marrow study and serum immunoelectrophoresis, are essential to the correct diagnosis.     

Computerized interactive morphometry as an aid in the diagnosis of pleural effusions

A morphometric study of cytologic preparations from patients with benign and malignant (mesothelioma and carcinoma) pleural effusions is reported. The routine cytologic smears from these specimens were studied with a new system of video-based computerized interactive morphometry (CIM) that allows the measurements of real-time images of cell profiles by the simple procedure of touching the two extreme points of a diameter of interest on a touch-sensitive screen. For each cell, the nuclear profile diameter (NPD) and the cytoplasmic profile diameter (CPD) are measured and categorized into classes with 2-microns intervals; the NPD/CPD ratio is also calculated. The mean NPD is calculated for the specimen after measurement of 100 cells. The data were interpreted by two independent methods: a statistical method of discriminant analysis that classifies the lesions as benign, carcinoma or mesothelioma and provides a probability statement of membership in a particular diagnostic class and an ad-hoc algorithm that categorizes the effusions as benign or malignant based on hierarchic analysis. A data base derived from study of the first 24 cases was constructed and utilized for the test classification of the second 24 cases, which were treated as specimens of unknown diagnosis. The discriminant analysis correctly classified 21 of the 24 test cases into their proper diagnostic groups. The algorithm for a computer-generated pathologic diagnosis correctly identified 47 of the 48 cases as benign or malignant. The technical advantages of video-based CIM over the existing morphometric methods are discussed.