Confocal DNA cytometry: a contour-based segmentation algorithm for automated three-dimensional image segmentation

BACKGROUND: Confocal laser scanning microscopy (CLSM) presents the opportunity to perform three-dimensional (3D) DNA content measurements on intact cells in thick histological sections. So far, these measurements have been performed manually, which is quite time-consuming. METHODS: In this study, an intuitive contour-based segmentation algorithm for automatic 3D CLSM image cytometry of nuclei in thick histological sections is presented. To evaluate the segmentation algorithm, we measured the DNA content and volume of human liver and breast cancer nuclei in 3D CLSM images. RESULTS: A high percentage of nuclei could be segmented fully automatically (e.g., human liver, 92%). Comparison with (time-consuming) interactive measurements on the same CLSM images showed that the results were well correlated (liver, r = 1.00; breast, r = 0.92). CONCLUSIONS: Automatic 3D CLSM image cytometry enables measurement of volume and DNA content of large numbers of nuclei in thick histological sections within an acceptable time. This makes large-scale studies feasible, whereby the advantages of CLSM can be exploited fully. The intuitive modular segmentation algorithm presented in this study detects and separates overlapping objects, also in two-dimensional (2D) space. Therefore, this algorithm may also be suitable for other applications.     

Mathematical morphologic segmentation dedicated to quantitative immunohistochemistry

OBJECTIVE: To develop automatic segmentation sequences for fully automated quantitative immunohistochemistry of cancer cell nuclei by image analysis. STUDY DESIGN: The study focused on the automated delineation of cancer cell lobules and nuclei, taking breast carcinoma as an example. A hierarchic segmentation was developed, employing mainly the chaining of mathematical morphology operators. The proposed sequence was tested on 22 images of various situations, collected from 18 different cases of breast carcinoma. A quality control procedure was applied, comparing the automated method with manual outlining of cancer cell foci and with manual pricking of cancer cell nuclei. RESULTS: Good concordance was found between automated and manual segmentation procedures (90% for cancer cell clumps, 97% for cancer cell nuclei on average), but the rate of false positive nuclei (small regions labeled as nuclei by the segmentation procedure) could be relatively high (11% on average, with a maximum of 35%) and can result in underestimation of the immunostaining ratio. CONCLUSION: This study examined a preliminary approach to automated immunoquantification, limited to automated segmentation without any color characterization. The automated hierarchic segmentation presented here leads to good discrimination of cancer cell nuclei at the chosen magnification.     

Criteria for the diagnosis of fibroepithelial lesions of the breast with liquid-based cytology

OBJECTIVE: To establish diagnostic criteria for diagnosing and differentiating fibroepithelial lesions of the breast on ThinPrep (Cytyc Corp., Boxborough, Massachusetts, U.S.A.). STUDY DESIGN: Eighty-four fibroepithelial lesions were sampled by ultrasound-guided aspiration biopsy. Based on smears and histologic correlates, there were 55 fibroadenomas, 26 papillary neoplasms and 3 phyllodes tumors. The ThinPrep slides for each sample were reviewed retrospectively and evaluated for specific morphologic and cytologic features. RESULTS: On ThinPrep slides, 95% of the fibroadenomas had a predominance of single myoepithelial nuclei, 89% had staghorn clusters, and 47% had myxoid stroma. Among the papillary neoplasms, 8% had a predominance of single columnar ductal cells, 31% had papillary groups, 23% had vessels, and 27% had collagenous spherulosis. The ThinPrep preparations of the phyllodes tumors showed that 67% had single myoepithelial nuclei, 33% had a predominance of single ductal cells, 67% had staghorn clusters, and 0% had myxoid stroma. A majority of the fibroadenomas and the papillary neoplasms showed mild to moderate ductal epithelial hyperplasia. A majority of the phyllodes tumors showed moderate ductal epithelial hyperplasia. CONCLUSION: Fibroepithelial lesions of the breast can be accurately differentiated using ThinPrep samples based on the evaluation of specific cytologic and morphologic features, including the presence of staghorn clusters, fibromyxoid stroma, vessels, collagenous spherulosis, papillary clusters and predominance of myoepithelial nuclei or columnar cells in the background. However, the degree of ductal epithelial hyperplasia does not aid in the diagnosis.     

Automatic image segmentation of nuclear stained breast tissue sections using color active contour model and an improved watershed method

Automatic image segmentation of immunohistologically stained breast tissue sections helps pathologists to discover the cancer disease earlier. The detection of the real number of cancer nuclei in the image is a very tedious and time consuming task. Segmentation of cancer nuclei, especially touching nuclei, presents many difficulties to separate them by traditional segmentation algorithms. This paper presents a new automatic scheme to perform both classification of breast stained nuclei and segmentation of touching nuclei in order to get the total number of cancer nuclei in each class. Firstly, a modified geometric active contour model is used for multiple contour detection of positive and negative nuclear staining in the microscopic image. Secondly, a touching nuclei method based on watershed algorithm and concave vertex graph is proposed to perform accurate quantification of the different stains. Finally, benign nuclei are identified by their morphological features and they are removed automatically from the segmented image for positive cancer nuclei assessment. The proposed classification and segmentation schemes are tested on two datasets of breast cancer cell images containing different level of malignancy. The experimental results show the superiority of the proposed methods when compared with other existing classification and segmentation methods. On the complete image database, the segmentation accuracy in term of cancer nuclei number is over than 97%, reaching an improvement of 3–4% over earlier methods.     

A Pulse Coupled Neural Network Segmentation Algorithm for Reflectance Confocal Images of Epithelial Tissue

Automatic segmentation of nuclei in reflectance confocal microscopy images is critical for visualization and rapid quantification of nuclear-to-cytoplasmic ratio, a useful indicator of epithelial precancer. Reflectance confocal microscopy can provide three-dimensional imaging of epithelial tissue in vivo with sub-cellular resolution. Changes in nuclear density or nuclear-to-cytoplasmic ratio as a function of depth obtained from confocal images can be used to determine the presence or stage of epithelial cancers. However, low nuclear to background contrast, low resolution at greater imaging depths, and significant variation in reflectance signal of nuclei complicate segmentation required for quantification of nuclear-to-cytoplasmic ratio. Here, we present an automated segmentation method to segment nuclei in reflectance confocal images using a pulse coupled neural network algorithm, specifically a spiking cortical model, and an artificial neural network classifier. The segmentation algorithm was applied to an image model of nuclei with varying nuclear to background contrast. Greater than 90% of simulated nuclei were detected for contrast of 2.0 or greater. Confocal images of porcine and human oral mucosa were used to evaluate application to epithelial tissue. Segmentation accuracy was assessed using manual segmentation of nuclei as the gold standard.     

Fine needle aspiration of breast lesions in women aged 30 and under

Fine needle aspiration (FNA) biopsies of 1,598 breast masses were performed between 1983 and 1989, and of them, 48 were from women aged 30 and under for whom a cytologic diagnosis was made by FNA and histologic follow-up was available. In 37 (77%) of the cases, both the cytologic and histologic diagnoses were benign. Fibroadenoma (20/37) and fibrocystic changes (14/37) were the most common benign lesions aspirated. Eight (17%) FNAs showed cytologic atypia. Four of these atypical lesions proved to be benign (two fibroadenomas, two fibrocystic changes). Epithelial proliferation in fibroadenomas and fibrocystic changes and cellular stroma in a fibroadenoma mimicking phylloides tumor were the causes of atypia in these biopsies. Four of the eight atypical lesions were shown to be carcinoma at biopsy (three infiltrating duct, one atypical medullary). Low cellularity, epithelial cohesiveness mimicking a fibroadenoma and background lactational changes in a pregnant patient were the causes of the atypical, rather than unequivocally malignant, diagnoses in these cases. In three patients (6%), a diagnosis of carcinoma was made by FNA and confirmed histologically (all were infiltrating duct carcinoma). Although most breast masses in women aged 30 and under are benign, cytologic atypia in a breast fine needle aspirate in this age group warrants a surgical biopsy. Clinical follow-up alone may be appropriate for young women with clinically nonsuspicious breast masses without cytologic atypia.     

An edge relocation segmentation algorithm

An automated procedure that refines the nuclear contour of a previously segmented nucleus is described. The algorithm makes use of intensity information, edge magnitude information and both object and edge connectivity information. This automated procedure generates a closed contour precisely along the edge of the nucleus. The procedure was tested on a database of 3,680 red-green-blue images of thionin-SO2 and orange II-stained cervical cells obtained from normal and dysplastic samples. When used in conjunction with a simple threshold selection algorithm and an artifact removal routine, this edge relocation algorithm resulted in the correct segmentation of over 98% of the nuclei. Only 63 (1.7%) of all nuclei were incorrectly segmented.     

A comparison of some quick and simple threshold selection methods for stained cells

The segmentation accuracy of four fast and simple gray-scale threshold selection methods were compared using a data base of stained cervical cell images. Some postprocessing was applied to the segmented images to increase the accuracy of the nuclear segmentation. The most accurate method correctly segmented the cytoplasm of 81% of the cell images and the nuclei of 78% of the cell images in the data base.     

Automatic segmentation and supervised learning-based selection of nuclei in cancer tissue images

Analysis of preferential localization of certain genes within the cell nuclei is emerging as a new technique for the diagnosis of breast cancer. Quantitation requires accurate segmentation of 100-200 cell nuclei in each tissue section to draw a statistically significant result. Thus, for large-scale analysis, manual processing is too time consuming and subjective. Fortuitously, acquired images generally contain many more nuclei than are needed for analysis. Therefore, we developed an integrated workflow that selects, following automatic segmentation, a subpopulation of accurately delineated nuclei for positioning of fluorescence in situ hybridization-labeled genes of interest. Segmentation was performed by a multistage watershed-based algorithm and screening by an artificial neural network-based pattern recognition engine. The performance of the workflow was quantified in terms of the fraction of automatically selected nuclei that were visually confirmed as well segmented and by the boundary accuracy of the well-segmented nuclei relative to a 2D dynamic programming-based reference segmentation method. Application of the method was demonstrated for discriminating normal and cancerous breast tissue sections based on the differential positioning of the HES5 gene. Automatic results agreed with manual analysis in 11 out of 14 cancers, all four normal cases, and all five noncancerous breast disease cases, thus showing the accuracy and robustness of the proposed approach. ? Published 2012 Wiley Periodicals, Inc.     

Fine needle aspiration cytology of sclerosing lobular hyperplasia of the breast: a case report

BACKGROUND: Sclerosing lobular hyperplasia presenting as a palpable, circumscribed nodular mass in a young female's breast is characterized histologically by prominent hyperplasia of the lobules and sclerosis of the intralobular connective tissue. The cytomorphologic features and differential diagnosis of the lesion are presented. CASE: A 14-year-old female presented with a painless, progressively increasing, nodular, firm, mobile lump measuring 5 x 5 cm in the right breast. The clinical and radiologic diagnosis was fibroadenoma. Fine needle aspiration smears showed a clean background with uniform, round to oval epithelial cells in flat sheets, round clusters and rosettelike (acinar) arrangements. A few naked nuclei were present, while stromal fragments were not seen. CONCLUSION: When analyzed in the context of the clinical findings, the cytologic features of sclerosing lobular hyperplasia help to differentiate it from other benign palpable nodular lesions of the juvenile breast.     

Fine needle aspiration of benign and malignant breast masses associated with pregnancy.

Of 1,612 fine needle aspirates (FNA) of breast lesions performed over a seven-year period, 25 cases (1.5%) were identified as breast masses associated with pregnancy. Patients ranged in age from 16 to 46 years, with a mean of 27. Gestational age at the time of FNA ranged from three months to three months postpartum or following breast-feeding. Cytologic diagnoses of these pregnancy-associated breast masses were: galactocele (5 cases, 20%), lactating adenoma (9 cases, 36%), fibroadenoma with lactational change (7 cases, 28%), juvenile fibroadenoma with lactational change (1 case, 4%), atypical reactive duct cells with lactational change (1 case, 4%) and infiltrating duct carcinoma (2 cases, 8%). The degree of lactational change varied proportionately with gestational age. None of the 22 patients with benign cytologic diagnoses of galactocele, lactating adenoma or fibroadenoma subsequently developed carcinoma. The mean clinical follow-up for these 22 patients was 27 months. Three cases of fibroadenoma and the case of juvenile fibroadenoma were confirmed by surgical excision. Biopsy of the lesion cytologically diagnosed as atypical reactive duct cells with lactational change revealed infiltrating duct carcinoma (IDC). All three patients with IDC had involvement of multiple axillary lymph nodes, and 1 patient had widely metastatic disease. In two cases of IDC the background lactational breast epithelium exhibited marked cytologic atypia that closely resembled the IDC. Pregnancy-related cellular atypia potentially results in a false-positive diagnosis of breast carcinoma on FNA. FNA is useful in distinguishing benign breast masses of pregnancy from those with marked cytologic atypia requiring surgical biopsy and may minimize the delayed diagnosis of carcinoma associated with pregnancy.     

Cascade pattern recognition structure for improving quantitative assessment of estrogen receptor status in breast tissue carcinomas

OBJECTIVE: To develop and validate a computer-based approach for the quantitative assessment of estrogen receptor (ER) status in breast tissue specimens for breast cancer management. STUDY DESIGN: Microscopy images of 32 immunohistochemically (IHC) stained specimens of breast cancer biopsies were digitized and were primarily assessed for ER status (percentage of positively stained nuclei) by a histopathologist. A pattern recognition system was designed for automatically assessing the ER status of the IHC-stained specimens. Nuclei were automatically segmented from background by a pixel-based unsupervised clustering algorithm and were characterized as positively stained or unstained by a supervised classification algorithm. This cascade structure boosted the system's classification accuracy. RESULTS: System performance in correctly characterizing the nuclei was 95.48%. When specifying each case's ER status, system performance was statistically not significantly different to the physician's assessment (p = 0.13); when ranking each case to a particular 5-scale ER-scoring system (giving the chance of response to endocrine treatment), the system's score and the physician's score were in agreement in 29 of 32 cases. CONCLUSION: The need for reliable and operator independent ER-status estimation procedures may be served by the design of efficient pattern recognition systems to be employed as support opinion tools in clinical practice.     

Segmentation of color images from serous cytology for automated cell classification

OBJECTIVE: To design an automated system for the classification of cells based on analysis of serous cytology, with the aim of segmenting both cytoplasm and nucleus using color information from the images as the main characteristic of the cells. STUDY DESIGN: The segmentation strategy uses color information coupled with mathematical morphology tools, such as watersheds. Cytoplasm and nuclei of all diagnostic cells are retained; erythrocytes and debris are eliminated. Special techniques are used for the separation of clustered cells. RESULTS: A large set of cells was assessed by experts to score the segmentation success rate. All cells were segmented whatever their spatial configurations. The average success rate was 92.5% for nuclei and 91.1% for cytoplasm. CONCLUSION: This color information-based segmentation of images of serous cells is accurate and provides a useful tool. This segmentation strategy will improve the automated classification of cells.     

Automatic segmentation of cell nuclei in Feulgen-stained histological sections of prostate cancer and quantitative evaluation of segmentation results

Digital image analysis of cell nuclei is useful to obtain quantitative information for the diagnosis and prognosis of cancer. However, the lack of a reliable automatic nuclear segmentation is a limiting factor for high-throughput nuclear image analysis. We have developed a method for automatic segmentation of nuclei in Feulgen-stained histological sections of prostate cancer. A local adaptive thresholding with an object perimeter gradient verification step detected the nuclei and was combined with an active contour model that featured an optimized initialization and worked within a restricted region to improve convergence of the segmentation of each nucleus. The method was tested on 30 randomly selected image frames from three cases, comparing the results from the automatic algorithm to a manual delineation of 924 nuclei. The automatic method segmented a few more nuclei compared to the manual method, and about 73% of the manually segmented nuclei were also segmented by the automatic method. For each nucleus segmented both manually and automatically, the accuracy (i.e., agreement with manual delineation) was estimated. The mean segmentation sensitivity/specificity were 95%/96%. The results from the automatic method were not significantly different from the ground truth provided by manual segmentation. This opens the possibility for large-scale nuclear analysis based on automatic segmentation of nuclei in Feulgen-stained histological sections.     

Malignant fibrous histiocytoma,giant cell type,of the breast mimicking metaplastic carcinoma. A case report

BACKGROUND: We report a case of malignant fibrous histiocytoma, giant cell type (MFHGC), of the breast. A review of the literature failed to reveal cytology-based reports on this entity. The cytologic similarity of breast MFHGC on fine needle aspiration biopsy (FNAB) to other malignant breast neoplasms, including carcinoma with osteoclastlike giant cells, metaplastic carcinoma and breast sarcomas, as well as benign reactive processes, makes the recognition of this tumor challenging. CASE: A 72-year-old woman presented with a 5-month history of an enlarging breast mass. FNAB of the mass showed a hypercellular smear composed of cohesive, branching clusters of spindle cells with ovoid, focally hyperchromatic nuclei and inconspicuous nucleoli. Interspersed osteoclastlike giant cells, some associated with clusters of spindle cells, were uniformly seen throughout the smear. The background was hemorrhagic, with cellular debris and occasional spindle cells and lymphocytes. No ductal epithelial or myoepithelial cells were seen. An incisional biopsy was performed, followed by radical mastectomy. The histologic examination was diagnostic of MFHGC. The diagnosis was supported by immunohistochemical and electron microscopic studies. CONCLUSION: MFHGC, also called primary giant cell tumor of soft tissues, is composed of a mixture of histiocytes, fibroblasts and bland-appearing osteoclastlike giant cells with a multinodular growth pattern. Although MFHGC rarely occurs in the breast and the definitive diagnosis is difficult based on cytology alone, the diagnosis can be considered when a cytologic examination reveals a hypercellular, spindle cell smear with osteoclastlike giant cells in the absence of ductal epithelial or myoepithelial cells.     

Aspiration biopsy of pleomorphic lipoma of the breast. A case report

BACKGROUND: It is well known that subcutaneous lumps in the breast may create diagnostic confusion. We report, for the first time in the cytologic literature, the features of a pleomorphic lipoma in the breast. CASE: Pleomorphic lipoma of the breast was aspirated, showing typical floret cells and mononuclear, hyperchromatic cells with scalloped nuclei, masquerading as malignancy. CONCLUSION: Pleomorphic lipoma has rather typical cytologic features that may allow its recognition when they are present in the proper clinical setting. This report illustrates another diagnostic pitfall in fine needle aspiration biopsy of the breast.     

Image preprocessing improves Fourier-based texture analysis of nuclear chromatin

OBJECTIVE: To investigate whether preprocessing of digitized images can improve the image analysis of chromatin of cytologic preparations using Fast Fourier Transformation (FFT). STUDY DESIGN: In a preprocessing step the nuclear borders of the segmented nuclei were smoothed, thus avoiding the Airy ring artifact. We tested this method, comparing the inertia values of digitalized cardiomyocyte nuclei of rats of different ages. Furthermore, we created in silicio nuclear images with chromatin alterations at or nearby the nuclear edge in order to investigate the robustness of our method. RESULTS: After preprocessing, the FFT-derived variable inertia discriminated significantly better the chromatin structure of the nuclei at different ages in every frequency range. The investigation on simulated nuclei revealed that within the frequency ranges from 1.8 microm to 0.72 microm smoothing of the borders does not interfere with the detection of chromatin changes at the nuclear border. CONCLUSION: Smoothing of borders in segmented images can improve the analysis of Fourier-derived variables of the chromatin texture.     

Fine needle aspiration of myofibroblastoma of the breast in a man. A report of two cases.

The cytopathologic features of fine needle aspiration biopsy of two myofibroblastomas of the breast in men are described. The cytologic findings consisted of monomorphic spindle cells with ovoid, grooved nuclei, isolated or in clusters, with an ill-defined, short fascicular pattern and abundant acellular, myxoid-appearing material. Atypical features were absent. No epithelial elements were present. We emphasize the value of aspiration cytology in association with clinical and mammographic data to establish a definitive diagnosis of this uncommon entity. This benign tumor should be considered in pure spindle cell, nontypical fine needle aspiration biopsy specimens of breast masses with sharp demarcation from the surrounding tissue, especially in men.