Gert Van de Wouwer

Automated breast tumor diagnosis and grading based on wavelet chromatin texture description

In this paper, wavelets were employed for multi-scale image analysis to extract parameters for the description of chromatin texture in the cytological diagnosis and grading of invasive breast cancer. Their value was estimated by comparing the performance of co-occurrence, densitometric, and morphometric parameters in an automated K-nearest neighbor (Knn) classification scheme based on light microscopic images of isolated nuclei of paraffin-embedded tissue. This design allowed a multifaceted cytological retrospective study of which the practical value can be judged easily. Results show that wavelets perform excellently with classification scores comparable with densitometric and co-occurrence features. Moreover, because wavelets showed a high additive value with the other textural groups, this panel allowed a very profound description with higher recognition scores than previously reported (76% for individual nuclei, 100% for cases). Morphometric parameters performed less well and only slightly increased correct classification. The major drawback, besides image segmentation errors demanding operator supervision, emanated to be the few false-negative cases, which restrict the immediate practical use. However, an enlargement of the parameter set may avoid this misclassification, resulting in an applicable expert system of practical use.

Computer-assisted differential diagnosis of malignant mesothelioma based on syntactic structure analysis.

BACKGROUND Malignant mesothelioma, a mesoderm-derived tumor, is related to asbestos exposure and remains a diagnostic challenge because none of the genetic or immunohistochemical markers have yet been proven to be specific. To assist in the identification of mesothelioma and to differentiate it from other common lesions at the same location, we have tested the performance of syntactic structure analysis (SSA) in an automated classification procedure. MATERIALS AND METHODS Light-microscopic images of tissue sections of malignant mesothelioma, hyperplastic mesothelium, and adenocarcinoma were analyzed using parameters selected from the Voronoi diagram, Gabriels graph, and the minimum spanning tree which were classified with a K-nearest-neighbor algorithm. RESULTS Results showed that mesotheliomas were diagnosed correctly in 74% of the cases; 76% of the adenocarcinomas were correctly graded, and 88% of the mesotheliomas were correctly typed. The performance of the parameters was dependent on the obtained classification (i.e., tumor-tumor versus tumor-benign). CONCLUSIONS Our results suggest that SSA is valuable in the differential classification of mesothelioma and that it supplements a visually appraised diagnosis. The recognition scores may be increased by a combination of SSA with, for example, cellular or nuclear parameters, measured at higher magnifications to form a solid base for fully automated expert systems.

Automated analysis of contractility in the embryonic stem cell test, a novel approach to assess embryotoxicity

The embryonic stem cell test (EST) is an ECVAM-validated assay to detect embryotoxicity. The output of the assay is the effect of test compounds on the differentiation of murine-derived embryonic stem cells (D3 cells), recorded by visual analysis of contracting cardiomyocyte-like cells. Incorporation of a system to assess the contractility in an automated manner is proposed, to increase the throughput in the EST independent of observer bias. The automated system is based on image recording of each well, resulting in the area (pixels) and frequency of contractility (Hz). Four test compounds were assessed for their embryotoxic potency in the 96-well version of the EST, with both manual and automated analysis: 6-Aminonicotinamide, Valproic Acid, Boric Acid, and Penicillin G. There was no statistically significant difference in the outcome of both methods in the fraction of contractility (p<0.05), resulting in the same rank-order of Relative Embryotoxic Potency (REP) values: 6-aminonicotinamide (1)>valproic acid (0.007-0.013)>Boric Acid (0.002-0.005)>Penicillin G (0.00001). The automated image recording of contractile cardiomyocyte-like cells in the EST allows for an unbiased high throughput method to assess the embryotoxic potency of test compounds, resulting in an outcome comparable to manual analysis.

Value of morphometry, texture analysis, densitometry, and histometry in the differential diagnosis and prognosis of malignant mesothelioma

Malignant mesothelioma is a tumour with increasing incidence due to widespread use of its causative agent, asbestos, in the past decades. The poor survival necessitates a correct differentiation from other lesions at the same site, such as hyperplastic mesothelium and carcinomas metastatic to pleura or peritoneum. Since genetic and immunohistochemical markers are not absolutely differentiating, the diagnosis is based on the histology complemented with (immuno)histochemistry. However, as the tumour presents itself in numerous heterogeneous histological forms, visual evaluation is extremely difficult. In order to evaluate the prognostic and diagnostic performance of syntactic structure analysis (SSA), chromatin texture analysis, densitometry, and morphometry, an automated KNN‐classification system has been used to compare Feulgen‐stained tissue sections of hyperplastic mesothelium, malignant mesothelioma, and pulmonary adenocarcinoma. In addition, we also studied most discriminative aspects in the differentiation, typing, and prediction of survival. The results indicate that for the diagnosis of malignant mesothelioma, chromatin texture parameters outperform SSA, densitometry, and morphometry (recognition score=96·8 per cent). Most discriminative parameters highlight spatial patterns of the chromatin distribution that are hard to appraise visually and directly show the benefits of a quantitative approach. Typing of the tumour is best described by SSA parameters, relating to the spatial arrangement of the cells in the tissue (recognition score=94·9 per cent). In survival time classifications, chromatin texture yields the highest recognition score (82·9 per cent), although accurate estimations are unreliable due to a large degree of misclassification. Copyright

Color Texture Classification by Wavelet Energy Correlation Signatures

In the last decade, multiscale techniques for gray-level texture analysis have been intensively studied. In this paper, we aim on extending these techniques to color images. We introduce wavelet energy-correlation signatures and we derive the transformation of these signatures upon linear color space transformations. Classification experiments demonstrate that the wavelet correlation features contain more information than the intensity or the energy features of each color plane separately. The influence of image representation in color space is evaluated.

Classification of Corrosion Images by Wavelet Signatures and LVQ Networks

In this paper, a method is described for the classification of corrosion images into two distinct classes. Since segmentation is very difficult, an automatic feature selection and classification procedure is preferred. This is done by performing a wavelet decomposition of the images, and computing energy signatures from the decomposition. Compact signature vectors represent the images and effectively characterize their type. The recognition is performed with a Learning Vector Quantization network. The method is tested on a set of 398 images, 260 of which were for training. High recognition scores are obtained.

Automatic quantification of neurite outgrowth by means of image analysis

A system for quantification of neurite outgrowth in in-vitro experiments is described. The system is developed for routine use in a high-throughput setting and is therefore needs fast, cheap, and robust. It relies on automated digital microscopical imaging of microtiter plates. Image analysis is applied to extract features for characterisation of neurite outgrowth. The system is tested in a dose-response experiment on PC12 cells + Taxol. The performance of the system and its ability to measure changes on neuronal morphology is studied.

Fractal Dimension, Form and Shape Factors for the Quantification of Nuclear Signature Profiles

Patient-oriented diagnosis based on an accurate quantification of the lesion may improve the patient’s diagnosis/prognosis as compared to diagnosis/prognosis based on population statistics. A nuclear signature is a technique developed to quantify lesions with great specificity and accuracy and is an important tool for patient-oriented diagnosis. However, nuclear signatures are thus far mainly applied in visual evaluations. This paper describes a method to quantify nuclear signatures based on a fractal and geometrical analysis. The result - a new set of fractal-geometrical features - is evaluated by comparing its diagnostic performance with classical karyometric features on 3 tumour types. Results show that the diagnostic performance of the feature sets is similar but that classification scores are increased by combining the two sets. Moreover, classification rates of malignancy associated changes of colon lesions are higher by using the fractal-geometrical feature set, proving its ability to detect sub visual changes of early premalignant transformation.