Prediction of cervical neoplasia diagnosis groups. Discriminant analysis on digitized cell images

The purpose of this study was to develop discriminant analysis models for predicting cervical dysplasia/neoplasia case diagnoses using cytometric features derived from the digital image analysis of cell monolayers. The data base consisted of 925 cells from 27 cases diagnosed either as moderate dysplasia (n = 10), severe dysplasia (n = 5), carcinoma in situ (n = 8) or invasive carcinoma (n = 4) on both tissue biopsy and monolayer preparations. Cell features examined were cell diameter, nuclear diameter, nuclear mean optical density (OD), nuclear integrated OD (IOD), nuclear OD standard deviation, normalized IOD, nuclear texture and nuclear-cytoplasmic ratio. Features derived from cells visually classified as moderate dysplasia correctly predicted the case diagnosis of moderate dysplasia versus more severe disease for 85% of the cells. Prediction models using summary measures (mean and variance) derived from all visually classified abnormal cells within each case correctly separated all cases into their respective diagnostic categories. These findings suggest that dysplastic cells in a cytologic sample have features that collectively reflect the tissue diagnosis, regardless of the visual differences among the cells. Such information has potential use for diagnosis and possibly for prognosis.     

Marker features for malignancy in ectocervical cells. Statistical evaluation

Marker features for malignancy have recently been observed in ectocervical cells, even in cells that are visually normal in appearance. This study assessed the statistical significance of these marker features using a mixed-model nested-design analysis of variance (ANOVA). Features in blue intermediate cells from patients with normal cytology, moderate dysplasia, and severe dysplasia/carcinoma in situ, nonkeratinizing cells from patients with moderate dysplasia, severe dysplasia/carcinoma in situ, and invasive cancer, and dysplastic cells from areas of metaplasia from patients with moderate dysplasia, severe dysplasia/carcinoma in situ, and invasive cancer were tested. ANOVA clearly demonstrated that the marker features differentiate between cells of the same cell type originating from patients in different diagnostic categories. In every instance, the differences owing to the diagnostic category were statistically significantly greater than those caused by patient-to-patient variability. Although the discriminating marker features in the intermediate cells were almost exclusively spectral features reflecting staining differences, morphometric features were also marker features in the dysplastic cells.     

Prediction of various grades of cervical neoplasia on plastic-embedded cytobrush samples. Discriminant analysis with qualitative and quantitative predictors.

The purpose of this study was to investigate whether discrimination into five groups of various grades of cervical preneoplasia and neoplasia is possible using discriminant analysis models. Data were analyzed for 242 cases diagnosed as either slight dysplasia (n = 50), moderate dysplasia (n = 50), severe dysplasia (n = 50), carcinoma in situ (n = 50) or invasive carcinoma (n = 42) and consisted of qualitative and quantitative features of cells derived from a repeat sample taken from the ectocervix as well as the endocervix using Cytobrushes. The samples were embedded in plastic, and thin sections were prepared, resulting in a monolayer of cut nuclei. The percentages of expected correct prediction were obtained by using 10,000 double cross-validation samples; the mean percentage of correct prediction into five groups using cross-validation was 65% (in the original analysis, 72%) and into two groups (dysplasia versus carcinoma in situ and invasive carcinoma) was 91% (93%). The results reflect group discrimination potential; we do not claim reliability of prediction for an individual patient. The patients were not a representative sample of the population; to investigate whether groups of patients could be discriminated on the basis of both qualitative and quantitative features, the data analyzed contain an almost equal number of observations in each of the five groups. The results indicate that features do not classify the cases in the same way; the discriminant analyses suggest that quantitative features play an important role in the discrimination of dysplasia from carcinoma cases, while the majority of the qualitative features are important in discrimination within the three dysplasia groups.     

Clinical evaluation of the EA-rosette test in the early detection of cervical cancer

It was previously found that a negative EA-rosette test, showing EA-rosette-forming cells in a cervical cell suspension, excluded the presence of cells of invasive carcinoma (predictive value of 99.9%). This study on 2,462 patients confirmed the applicability of the EA-rosette test in screening for precancerous as well as cancerous lesions. In 98.6% of the cases of dysplasia, carcinoma in situ and invasive carcinoma, the cervical cell suspensions contained EA-rosette forming cells (the rosette test was positive). With a negative EA-rosette test, the probability of missing a specimen with class III cytology (mild/moderate dysplasia) was 1.4%, of missing one with class IV cytology (severe dysplasia/carcinoma in situ) was 0.8% and of missing one with class V cytology (invasive carcinoma) was 0.25%. The predictive value of a negative EA-rosette test was 98.6%. The false-negative rate for negative EA-rosette tests was 3.7% for invasive carcinoma, 17.5% for carcinoma in situ and severe dysplasia and 41.4% for mild to moderate dysplasia.     

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.     

Early progression stage of malignancy of uterine cervical dysplasia as revealed by immunohistochemical demonstration of increased DNA-instability

The degree of DNA-instability as revealed by the immunohistochemical staining with anti-single-stranded DNA antibody after acid hydrolysis (DNA-instability test) was used as a marker of malignancy. This was applied to mild dysplasia (42 cases), moderate dysplasia (43 cases), severe dysplasia (27 cases), squamous cell carcinoma in situ (CIS) (21 cases), invasive squamous cell carcinoma (SCC) (31 cases) and normal (7 cases) human uterine cervix. The expression of tumour suppressor gene p53 and oncogene bcl-2 was detected immunohistochemically. Proliferative activity was evaluated by PCNA immumohistochemistry and the quantitative analysis of the number, mean area, the largest area and maximum shape irregularities of AgNOR in a nucleus were performed for all these cases. The distribution of numeric chromosomal aberrations of chromosome 17 was also investigated in some of these cases. The results showed that 31 SCC (100%), 21 CIS (100%), 21 severe dysplasia (77.77%), 28 moderate dysplasia (65.11%), and 14 mild dysplasia (33.33%) were positively stained by the DNA-instability test diffusely or sporadically, indicating their malignancy. Reflecting the malignant character, these cases showed a remarkable increase in the PCNA-index with the loss of polarity of PCNA positive cell distribution and also an increase in number, mean and largest sizes and maximum shape irregularity of AgNOR dots. The mean chromosome index for chromosome 17, p53 and bcl-2 immunostaining positivity were also found to be significantly increased in moderate and severe dysplasia and in cancerous cases in comparison to normal and mild dysplasia cases. Moreover, the DNA-instability-test positive dysplasia cases showed statistically significant increased values of PCNA-index, AgNOR parameters, mean chromosome index, p53 and bcl-2 expression in comparison to those of DNA-instability-test negative dysplasia cases. In conclusion, some mild dysplasia (33.33%) and most of the moderate (65.11%) and severe dysplasia (77.77%) were regarded as malignant in nature, existing at an early stage of progression of malignancy.     

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.     

Flow cytometric classification of biopsy specimens from cervical intraepithelial neoplasia

The distribution of single-cell DNA content was investigated in biopsy specimens from the human cervix of 121 women suspected of having intraepithelial neoplasia. Comparison of the results of the histopathological examination with the ploidy level showed that all normal specimens were diploid. Thus, no false-positive results occurred. Most of the specimens classified as mild and moderate dysplasia were diploid as well. Aneuploid cell populations occurred in 78% of the lesions classified as severe dysplasia and carcinoma in situ. The ploidy level distribution permitted a natural division of the aneuploid cell populations into two groups with DNA indices either above or below 1.5. The importance of the aneuploidy in carcinogenesis is discussed.     

Marker features for malignancy in ectocervical cells

Marker features for malignancy have recently been observed in ectocervical cells, even in cells that are visually normal in appearance. This study assessed the statistical significance of these marker features using a mixed-model nested-design analysis of variance (ANOVA). Features in blue intermediate cells from patients with normal cytology, moderate dysplasia, and severe dysplasia/carcinomain situ, nonkeratinizing cells from patients with moderate dysplasia, severe dysplasia/carcinomain situ, and invasive cancer, and dysplastic cells from areas of metaplasia from patients with moderate dysplasia, severe dysplasia/carcinomain situ, and invasive cancer were tested. ANOVA clearly demonstrated that the marker features differentiate between cells of the same cell type originating from patients in different diagnostic categories. In every instance, the differences owing to the diagnostic category were statistically significantly greater than those caused by patient-to-patient variability. Although the discriminating marker features in the intermediate cells were almost exclusively spectral features reflecting staining differences, morphometric features were also marker features in the dysplastic cells.     

Morphologic scales and relative distances between lesions identified on Papanicolaou smears.

We fit a Gaussian-type curve to a nonmonotonic transform of initial arbitrarily given scales (pseudoscalar transform) of a two-way discrete classification table by maximizing the likelihood (entropy) and computing morphologic scales of clusters of objects identified by visual judgments. The scales give the relative distance between pairs of categories or states. Morphologic scales of histologic lesions (states) identified on Papanicolaou smears were computed from a confusion matrix consisting of 3,545 matched pairs of observations on Papanicolaou smears and colposcopically directed biopsies available from the Gynecologic Cytology Laboratory, University of Minnesota, between 1985 and 1987. The original (uncollapsed) confusion matrix consisted of eight cytologic categories and histologic states: normal plus atypical benign, reactive atypia (including condylomatous changes); mild, moderate and severe dysplasia; squamous carcinoma in situ; invasive squamous cell carcinoma; and other malignancies. The morphologic scales are expressed numerically, which reflects a degree of confusion between two diagnostic categories or states. Except for malignancies other than squamous cell carcinoma, morphologic scales of histologic states seen from cytology retained the order of clinical severity. We detected a high degree of confusion between severe dysplasia and carcinoma in situ. Malignancies other than squamous cell carcinoma fell between moderate and severe dysplasia. Such a transposition of the scales in this group containing adenocarcinoma was likely due to frequent association of adenocarcinoma with cervical intraepithelial neoplasia. Morphologic scales of cytologic categories seen from histology showed high degrees of confusion and transpositions between mild and moderate dysplasia and between severe dysplasia and carcinoma in situ.(ABSTRACT TRUNCATED AT 250 WORDS)     

Cytomorphometric differences among individual "moderate dysplasia" cells derived from cervical intraepithelial neoplasia

Individual abnormal cervical epithelial cells can be categorized either by the lesion from which they are derived or by their unique cytologic characteristics. In building a data base for image analysis of cervical epithelial cells, categories of cells were defined according to distinct cytomorphologic characteristics, without knowledge of the lesion of origin. The three individual scorers, two cytopathologists and one senior cytotechnologist, most frequently agreed upon the cells classified as "moderate dysplasia." The measurements of digitized cells in this category had the smallest confidence intervals of any of the abnormal cell categories. For these two reasons, as well as the ubiquitous nature of "moderate dysplasia" cells in smears obtained from all patients with cervical epithelial neoplasia, cells in this category were studied in greater detail. Significant differences were noted in cell measurements among cells in this class when the cells came from patients with different grades of cervical neoplasia. The findings indicate that visually similar "moderate dysplasia" cells can be separated by digitized measurements into clusters dependent upon the parent lesion. The biologic implications are not yet clear, but such findings suggest that each disease is perhaps a committed lesion from inception. Therefore, predictability of ultimate outcome could be based on image analysis of cells derived from early cervical lesions, which would allow therapy to be performed on a more logical basis.     

Immunohistochemical detection of early-stage carcinogenesis of oral leukoplakia by increased DNA-instability and various malignancy markers

The degree of DNA instability as determined by immunohistochemical staining with anti-single-stranded DNA antibody after acid hydrolysis (the DNA instability test) was used as a marker of malignancy. The test was applied to tissues of oral leukoplakia assessed histopathologically as hyperplasia (38 cases), mild (12 cases), moderate (11 cases) and severe (8 cases) dysplasia, and invasive squamous cell carcinoma (SCC, 20 cases). Tissues were subjected to immunohistochemical staining for proliferating cell nuclear antigen (PCNA), p53, DNA-fragmentation factor 45 (DFF45), analysis of various AgNORs parameters, and triple immunostaining for vascular endothelial growth factor (VEGF), CD34, and PCNA. The DNA instability test was positive in 20 (100%) SCC cases, 8 (100%) severe dysplasia cases, 8 (72.7%) moderate dysplasia cases, 6 (50.0%) mild dysplasia cases, and 9 (23.7%) hyperplasia cases, indicating malignancy. The proportion of lesions positive for PCNA, p53, DFF45, and values of AgNORs parameters steadily increased from hyperplasia to mild, moderate and severe dysplasia, and SCC, especially in those showing positive DNA instability test, indicative of malignancy. Based on these results, 44.9% of leukoplakia were malignant tissues, namely carcinoma in situ. The proportion of PCNA-positive vascular endothelial cells in the vicinity of VEGF-positive epithelial lesion was significantly higher than that of negative DNA instability lesions, as revealed by immunohistochemical triple staining for VEGF, CD34, and PCNA. Our results suggest that increased DNA instability, enhanced proliferative activity, p53 mutation, and induction of DFF45 and VEGF may allow cancer cell proliferation, enhance their survival by escaping apoptosis, and provide abundant nutrients during early-stage carcinogenesis of oral leukoplakia.     

3p21, 5q21, 9p21 and 17p13 allelic deletions accumulate in the dysplastic spectrum of laryngeal carcinogenesis and precede malignant transformation

A tissue field of somatic genetic alterations precede the histopathological phenotypic changes of carcinoma. Loss of Heterozygosity (LOH) at the sites of known or putative tumor suppressor genes is a common genetic abnormality detected in precancerous conditions. These genomic changes could be of potential use in the diagnosis and prognosis of pre-malignant laryngeal lesions. Recently the concept of laryngeal intraepithelial neoplasia (LIN) was introduced. To evaluate patients with an increased risk of developing invasive laryngeal carcinoma via a dysplasia-carcinoma progression we investigated 102 microdissected cell populations. Cell populations were procured from 15 laryngectomy specimens with different peritumoral histological changes adjacent to the squamous cell carcinoma cells and 15 laryngeal endoscopic biopsies with no evidence of malignant transformation in a 6-10-year follow-up period. Histological diagnoses were subdivided into keratosis without dysplasia (KWD), with mild dysplasia (LIN 1), with moderate dysplasia (LIN 2), and with severe dysplasia or carcinoma in situ (LIN 3). Microsatellite analysis was performed with the aim of studying LOH of 5q21 (APC), 9p21 (p16), 3p21 and 17p13 (p53) chromosomal regions. Frequent allelic losses were found in carcinoma cells at p53 (54%), p16 (66%), 3p21(87%) and 5q21(58%). Identical LOH patterns were determined in 100% of the LIN3 peritumoral cells, 60% of LIN2, 50% of LIN 1 and 25% of KWD. In contrast, histologically normal mucosae, KWD and LIN1 lesions without malignant progression showed no allelic loss. These results show that dysplasia correlates with LOH at 3p21, 5q21, 9p21 and 17p13 in early laryngeal carcinogenesis. These genomic changes in pre-malignant laryngeal lesions could be of potential use as markers for cancer risk assessment.     

FURTHER OBSERVATIONS ON THE OCCURRENCE OF NEXUSES IN BENIGN AND MALIGNANT HUMAN CERVICAL EPITHELIUM

An estimate is made of the frequency of occurrence of nexuses ("gap junctions") in a spectrum of human cervical epithelia, ranging from normal to malignant, since a deficiency of nexuses may be important in abnormal cell-to-cell communication in malignant tissues. The normal cervical epithelium has approximately ten nexuses per cell in the basal layer of proliferating cells and 200 nexuses per cell in the more differentiated intermediate zone. Nexuses are rare between invasive malignant epithelial cells (carcinoma cells). In many areas of cell proliferation near the edge of the tumor mass, fewer than one nexus per cell is present. However, up to four nexuses per cell can be found in some well differentiated regions of invasive carcinoma. Preinvasive malignant epithelia (severe dysplasia and carcinoma-in situ) have as few nexuses as invasive carcinoma. In abnormal but benign epithelia (squamous metaplasia and mild dysplasia), nexuses are abundant. The data indicate that a decrease in number of nexuses correlates with the severity of the morphological alteration in the dysplastic epithelium. Also the deficiency of nexuses in groups of carcinoma cells can occur many cell generations before the development of invasion of the malignant epithelium into the connective tissue. The diminution of nexuses before invasion suggests that a deficiency of nexuses may be one of the important factors in eventually permitting the development of the diffusely infiltrating type of invasion which is characteristic of highly malignant tumors such as squamous carcinomas.     

Early detection of precancerous lesions in dysplasias of the lung by rapid DNA image cytometry

Hematoxylin-and-eosin-stained cytologic smears of sputum from 28 patients with dysplastic and suspicious cell findings were subjected to DNA image cytometry after Feulgen restaining. The nuclear DNA contents were measured with a TV-based image-analysis system, the Leitz TAS plus, combined with an automatic microscope. Computation of DNA data was performed according to an algorithm for the diagnosis and grading of malignancy. Of the 19 cases that were proven to be malignant in the follow-up, either by histologic examination, sputum cytology, fine needle aspiration biopsy or autopsy, the algorithm identified 17 as malignant in a stage (dysplasia) in which cytology was not yet able to present a definite diagnosis of malignancy. Only two cases of bronchial carcinoma were not detected in the state of dysplasia by this procedure. The periods between the DNA diagnosis of malignancy in dysplasia and the morphologic evidence of cancer varied from three days up to six months. Of the 11 cases that had been classified as benign by the algorithm, 9 were confirmed as benign during the clinical follow-up. Rapid DNA image cytometry appears able to separate squamous dysplasias of the lung into precancerous and nonprecancerous lesions.     

Quantitative cell-cycle protein expression in oral cancer assessed by computer-assisted system

The knowledge of cell-cycle control has shown that the capacity of malignant growth is acquired by the stepwise accumulation of defects in specific genes regulating cell growth. Histologic diagnosis might be improved by a quantitative evaluation of more specific diagnosis biomarkers, which could help to precisely identify pre-malignant and malignant oral lesions. The aim of the present study is to evaluate whether computer-based quantitative assessment of p53, PCNA and Ki-67 immunohistochemical expression, could be used clinically to foresee the risk of oral malignant transformation. This retrospective study was carried out in ninety-five oral biopsies, 27 were classified as fibrous inflammatory hyperplasia, 40 as leukoplakia and 28 as oral squamous cell carcinoma. Sixteen out of the 40 leukoplakia were diagnosed as non-dysplastic leukoplakia, the other 24 being dysplastic leukoplakia, of which 50.0% were classified as moderate to severe dysplasia. Comparison of the four groups of oral tissues showed significant rises in p53 and Ki-67 positivity index, which increased steadily in the order benign, pre-malignant, and malignant. In contrast, it was not possible to relate higher PCNA levels with pre-malignant and malignant oral lesions. We therefore conclude that PCNA immunohistochemistry expression is probably an inappropriate marker to identify oral carcinogenesis, whereas joint quantitative evaluation of p53 and Ki-67, appears to be useful as a tumor marker, providing a pre-diagnostic estimate of the potential for cell-cycle deregulation of the oral proliferate status.     

Comparative cytology of mucocelelike lesion and mucinous carcinoma of the breast in fine needle aspiration

OBJECTIVE: To study the fine needle aspiration cytology (FNAC) features of mucocelelike lesion (MLL) of the breast and to compare them to those of mucinous carcinoma. STUDY DESIGN: The fine needle aspiration (FNA) smears of 7 cases of histologically proven MLL (2 malignant and 5 benign, including 4 associated with atypical ductal hyperplasia) were reviewed and compared to those of 14 mucinous carcinoma cases. RESULTS: In all cases, grossly visible thick, mucoid material was obtained from FNA. The most important features for distinguishing benign MLL from mucinous carcinoma were: (1) scant cellularity; (2) no or rare single, intact tumor cells; (3) tumor cells arranged in cohesive monolayers; and (4) absence of significant nuclear atypia. In contrast, mucinous carcinoma in general showed higher cellularity; abundant single, intact cells; three-dimensional cellular clusters in most cases; and nuclear atypia ranging from mild to severe. CONCLUSION: Mucinous lesions of the breast should be divided into MLL and frank mucinous carcinoma based on FNAC. However, FNAC diagnosis of malignant MLL has yet to be defined. Excisional biopsy is advised for all hypocellular cases for further separation into benign and malignant MLL and to rule out the possibility of hypocellular mucinous carcinoma.     

Clinical and cytologic features of papillary neoplasms of the breast

OBJECTIVE: To compare the cytologic features benign and malignant papillary breast lesions. STUDY DESIGN: We reviewed the clinical and cytologic features in 29 cases of intraductal papilloma and 26 cases of atypical papilloma or papillary carcinoma that had been diagnosed by histologic examination. The diameter of the mass was examined as a clinical feature. The cytologic features evaluated were as follows: bloody background, row of tall columnar cells, naked bipolar nuclei, hemosiderin-laden macrophages, myoepithelial cells, single scattered atypical cells, cellularity, nuclear atypia, nuclear grade, apocrine metaplasia, eosinophilic cytoplasmic granules, papillary clusters, small papillae, cell balls and large sheets. RESULTS: Of the features evaluated, the diameter of the mass, naked bipolar nuclei and cell balls differed significantly between benign and atypical or malignant papillary neoplasms. The average diameter of a benign papillary neoplasm was 1.8 cm, and that of an atypical or malignant papillary neoplasm was 2.2 cm (p = 0.042). Naked bipolar nuclei were found in 27 cases of benign papillary neoplasm (93.1%) versus 19 cases of atypical or malignant papillary neoplasm (73.1%) (p = 0.050). Cell balls were found in 14 (48.3%) and 21 (80.8%) cases, respectively (p = 0.012). All 6 cases in which cell balls were present and naked bipolar nuclei were absent proved to be atypical or malignant papillary neoplasms. Of 17 cases in which cell balls were absent and naked bipolar nuclei present, 13 (76.5%) were benign papillary neoplasms. CONCLUSION: Most cytologic features overlapped in benign and atypical or malignant papillary neoplasms. Although they were not pathognomonic, naked bipolar nuclei and cell balls were cytologic features that differed significantly between benign and atypical or malignant papillary neoplasms. When papillary neoplasms of the breast are suspected in a cytologic smear, the combination of clinical examination, mammography and cytologic features should be considered to make the correct diagnosis.     

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.