Morphological abstraction of thyroid tumor cell nuclei using morphometry with factor analysis

Abstract

Various morphonuclear studies by digital image analysis have successfully been applied to quantify the nuclear morphology, including chromatin distribution pattern, in cytology of various organs; however, the majority of past reports have not shown correlation between the quantitative data by digital image analysis and cytological findings in practical diagnosis. In this report, we present the usefulness of morphological abstraction to combine the objective data and subjective observation in cytological diagnosis. Randomly selected, 100 cells in each Papanicolaou-stained ABC smear samples of 39 benign and malignant thyroid tumor cases were studied. Gray-level image data provided seven parameters for nuclear size, four parameters for nuclear shape, and 16 parameters showing the nuclear chromatin patterns from high-dimensional texture analysis of using co-occurrence and run-length matrices. To statistically abstract nuclear morphology, factor analysis was used. Factor analysis classified morphological nuclear characters as abstraction parameter into five abstract parameters composed of nuclear size, shape, heterogeneity, and contrast and homogeneity of chromatin pattern. The nuclei of papillary carcinoma showed larger size, more irregular shape, and higher contrast of chromatin pattern than those of the benign group. The follicular carcinomas have larger nucleus in each cell and more monotonous chromatin pattern among cells in each case than those of the benign group. Morphological abstraction by morphometry with factor analysis may provide a practical approach to the detection of the underlying characteristics of nuclear morphology in aspiration biopsy cytology.

Evaluation of Pre-Malignant and Malignant Lesions in Cervico Vaginal ( P AP ) Smears by Nuclear Morphometry

“…In addition to these basic nuclear morphometric parameters, Murata et al, reported 27 morphological nuclear parameters which were categorized into more reasonable cytological features to achieve better clinical understanding of computed morphometric features [20].…”

Impact of the accuracy of automatic segmentation of cell nuclei clusters on classification of thyroid follicular lesions

“…The primary aim of this study is to investigate the "actual impact" of accurate segmentation of cell nuclei clusters on classification of thyroid follicular lesions, and for this purpose an automated system to classify thyroid follicular lesions has been implemented in this article. In literature, many methods for computerized classification of lesions using microscopy cell images have been presented (23)(24)(25)(26). Building on the findings, we design a baseline system to distinguish between follicular adenoma of the thyroid and follicular carcinoma of the thyroid.…”

“…In this case study, we have used a set of popular image features [which are reported in the literature (23,24,26,28)]. Table 2 summarizes numerical features used in the baseline classification system.…”

“…We note that the deployment of a more advanced feature [e.g., (25)] could enhance the classification accuracy, but as aforementioned, our goal in this study is not to provide a method for quantifying nuclear features. It is important to note that, as recommended in the literature (23,24,26,28), we have used four statistical features (namely, mean, standard deviation, median, and mode) of the numerical signatures given in Table 2. In summary, given a digitized biopsy specimen, a 92-dimensional (23 [5 13(morphological) 1 10(textural)] 34 5 92) feature vector is generated in the system.…”

Contribuição da análise de textura do núcleo celular para o diagnóstico diferencial de lesões foliculares da tireoide: comparação com marcadores imunoistoquímicos

“…Vá-rios estudos morfonucleares por análise de imagem digital têm sido aplicados para análise do aspecto nuclear e do padrão de distribuição de cromatina em diversas neoplasias, incluindo tireoidianas (19)(20)(21)(22). Como alterações do metabolismo celular influem diretamente na distribuição da cromatina, o estudo da textura nuclear permite detectar pequenas alterações que não são óbvias ao olho humano (23)(24)(25)(26).…”