Semantic segmentation of mFISH images using convolutional networks.

Multicolor in situ hybridization (mFISH) is a karyotyping technique used to detect major chromosomal alterations using fluorescent probes and imaging techniques. Manual interpretation of mFISH images is a time consuming step that can be automated using machine learning; in previous works, pixel or patch wise classification was employed, overlooking spatial information which can help identify chromosomes. In this work, we propose a fully convolutional semantic segmentation network for the interpretation of mFISH images, which uses both spatial and spectral information to classify each pixel in an end-to-end fashion. The semantic segmentation network developed was tested on samples extracted from a public dataset using cross validation. Despite having no labeling information of the image it was tested on, our algorithm yielded an average correct classification ratio (CCR) of 87.41%. Previously, this level of accuracy was only achieved with state of the art algorithms when classifying pixels from the same image in which the classifier has been trained. These results provide evidence that fully convolutional semantic segmentation networks may be employed in the computer aided diagnosis of genetic diseases with improved performance over the current image analysis methods. © 2018 International Society for Advancement of Cytometry.

Flow cytometry of duodenal intraepithelial lymphocytes improves diagnosis of celiac disease in difficult cases.

BACKGROUND: Diagnosis of celiac disease is difficult when the combined results of serology and histology are inconclusive. Studies using flow cytometry of intraepithelial lymphocytes (IELs) have found that celiac patients have increased numbers of γδ IELs, along with a decrease in CD3-CD103 + IELs. OBJECTIVE: The objective of this article is to assess the role of flow cytometric analysis of IELs in the diagnosis of celiac disease in difficult cases. METHODS: A total of 312 patients with suspicion of celiac disease were included in the study. Duodenal biopsy samples were used for histological assessment and for flow cytometric analysis of IELs. RESULTS: In 46 out of 312 cases (14.7%) the combination of serology and histology did not allow the confirmation or exclusion of celiac disease. HLA typing had been performed in 42 of these difficult cases. Taking into account HLA typing and the response to a gluten-free diet, celiac disease was excluded in 30 of these cases and confirmed in the remaining 12. Flow cytometric analysis of IELs allowed a correct diagnosis in 39 out of 42 difficult cases (92.8%) and had a sensitivity of 91.7% (95% CI: 61.5% to 99.8%) and a specificity of 93.3% (95% CI: 77.9% to 99.2%) for the diagnosis of celiac disease in this setting. CONCLUSION: Flow cytometric analysis of IELs is useful for the diagnosis of celiac disease in difficult cases.

Flow cytometry in mastocytosis: utility as a diagnostic and prognostic tool.

This article presents information for the identification and characterization of mast cells from bone marrow and other tissues using multiparametric flow cytometry. In addition, it provides guidelines for the application of this technique in the subclassification of systemic mastocytosis and assessment of the long-term prognosis of patients individually.

Immunophenotyping in systemic mastocytosis diagnosis: 'CD25 positive' alone is more informative than the 'CD25 and/or CD2' WHO criterion.

Aberrant expression of CD2 and/or CD25 by bone marrow, peripheral blood or other extracutaneous tissue mast cells is currently used as a minor World Health Organization diagnostic criterion for systemic mastocytosis. However, the diagnostic utility of CD2 versus CD25 expression by mast cells has not been prospectively evaluated in a large series of systemic mastocytosis. Here we evaluate the sensitivity and specificity of CD2 versus CD25 expression in the diagnosis of systemic mastocytosis. Mast cells from a total of 886 bone marrow and 153 other non-bone marrow extracutaneous tissue samples were analysed by multiparameter flow cytometry following the guidelines of the Spanish Network on Mastocytosis at two different laboratories. The 'CD25+ and/or CD2+ bone marrow mast cells' World Health Organization criterion showed an overall sensitivity of 100% with 99.0% specificity for the diagnosis of systemic mastocytosis whereas CD25 expression alone presented a similar sensitivity (100%) with a slightly higher specificity (99.2%). Inclusion of CD2 did not improve the sensitivity of the test and it decreased its specificity. In tissues other than bone marrow, the mast cell phenotypic criterion revealed to be less sensitive. In summary, CD2 expression does not contribute to improve the diagnosis of systemic mastocytosis when compared with aberrant CD25 expression alone, which supports the need to update and replace the minor World Health Organization 'CD25+ and/or CD2+' mast cell phenotypic diagnostic criterion by a major criterion based exclusively on CD25 expression.

Evaluation of the WHO criteria for the classification of patients with mastocytosis.

Diagnosis and classification of mastocytosis is currently based on the World Health Organization (WHO) criteria. Here, we evaluate the utility of the WHO criteria for the diagnosis and classification of a large series of mastocytosis patients (n=133), and propose a new algorithm that could be routinely applied for refined diagnosis and classification of the disease. Our results confirm the utility of the WHO criteria and provide evidence for the need of additional information for (1) a more precise diagnosis of mastocytosis, (2) specific identification of new forms of the disease, (3) the differential diagnosis between cutaneous mastocytosis vs systemic mastocytosis, and (4) improved distinction between indolent systemic mastocytosis and aggressive systemic mastocytosis. Based on our results, a new algorithm is proposed for a better diagnostic definition and prognostic classification of mastocytosis, as confirmed prospectively in an independent validation series of 117 mastocytosis patients.