How to measure image quality in tissue-based diagnosis (diagnostic surgical pathology)

UICC-TPCC, Institute of Pathology, Charite, Berlin, Germany.
Diagnostic Pathology (Impact Factor: 2.6). 07/2008; 3 Suppl 1(Suppl 1):S11. DOI: 10.1186/1746-1596-3-S1-S11
Source: PubMed


Automated image analysis, measurements of virtual slides, and open access electronic measurement user systems require standardized image quality assessment in tissue-based diagnosis.
To describe the theoretical background and the practical experiences in automated image quality estimation of colour images acquired from histological slides. THEORY, MATERIAL AND MEASUREMENTS: Digital images acquired from histological slides should present with textures and objects that permit automated image information analysis. The quality of digitized images can be estimated by spatial independent and local filter operations that investigate in homogenous brightness, low peak to noise ratio (full range of available grey values), maximum gradients, equalized grey value distribution, and existence of grey value thresholds. Transformation of the red-green-blue (RGB) space into the hue-saturation-intensity (HSI) space permits the detection of colour and intensity maxima/minima. The feature distance of the original image to its standardized counterpart is an appropriate measure to quantify the actual image quality. These measures have been applied to a series of H&E stained, fluorescent (DAPI, Texas Red, FITC), and immunohistochemically stained (PAP, DAB) slides. More than 5,000 slides have been measured and partly analyzed in a time series.
Analysis of H&E stained slides revealed low shading corrections (10%) and moderate grey value standardization (10 - 20%) in the majority of cases. Immunohistochemically stained slides displayed greater shading and grey value correction. Fluorescent stained slides are often revealed to high brightness. Images requiring only low standardization corrections possess at least 5 different statistically significant thresholds, which are useful for object segmentation. Fluorescent images of good quality only possess one singular intensity maximum in contrast to good images obtained from H&E stained slides that present with 2 - 3 intensity maxima.
Evaluation of image quality and creation of formally standardized images should be performed prior to automatic analysis of digital images acquired from histological slides. Spatial dependent and local filter operations as well as analysis of the RGB and HSI spaces are appropriate methods to reproduce evaluated formal image quality.

Download full-text


Available from: Torsten Goldmann,
  • Source
    • "We did not perform standardization of the tissue appearance [28], in as much as the techniques we used aim for robustness with respect to variation in the preparation of the samples that is within the “nominal range”. However, it should be noted that very poor sample preparation (such as very thick sections, overstraining, poorly fixed tissue etc.) or poor digitization (failed autofocusing, stitching artifacts etc.) can adversely affect the segmentation technique. "
    [Show abstract] [Hide abstract]
    ABSTRACT: The introduction of fast digital slide scanners that provide whole slide images has led to a revival of interest in image analysis applications in pathology. Segmentation of cells and nuclei is an important first step towards automatic analysis of digitized microscopy images. We therefore developed an automated nuclei segmentation method that works with hematoxylin and eosin (H&E) stained breast cancer histopathology images, which represent regions of whole digital slides. The procedure can be divided into four main steps: 1) pre-processing with color unmixing and morphological operators, 2) marker-controlled watershed segmentation at multiple scales and with different markers, 3) post-processing for rejection of false regions and 4) merging of the results from multiple scales. The procedure was developed on a set of 21 breast cancer cases (subset A) and tested on a separate validation set of 18 cases (subset B). The evaluation was done in terms of both detection accuracy (sensitivity and positive predictive value) and segmentation accuracy (Dice coefficient). The mean estimated sensitivity for subset A was 0.875 (±0.092) and for subset B 0.853 (±0.077). The mean estimated positive predictive value was 0.904 (±0.075) and 0.886 (±0.069) for subsets A and B, respectively. For both subsets, the distribution of the Dice coefficients had a high peak around 0.9, with the vast majority of segmentations having values larger than 0.8.
    PLoS ONE 07/2013; 8(7):e70221. DOI:10.1371/journal.pone.0070221 · 3.23 Impact Factor
    • "In addition, there are images which display “a strong association with a certain disease”, or allow an “easy” detection of information, others “might be related with a broad variety of diseases”, and it is difficult to derive a diagnosis. Commonly, an image is called to be of “good quality”, if its presented information can be “easily” derived.[14–16] On the other hand, those images are of “poor quality” if it is difficult (or even impossible) to detect a correlation with a diagnosis.[17] "
    [Show abstract] [Hide abstract]
    ABSTRACT: Virtual microscopy, which is the diagnostic work on completely digitized histological and cytological slides as well as blood smears, is at the stage to be implemented in routine diagnostic surgical pathology (tissue-based diagnosis) in the near future, once it has been accepted by the US Food and Drug Administration. The principle of content-based image information, its mandatory prerequisites to obtain reproducible and stable image information as well as the different compartments that contribute to image information are described in detail. Automated extraction of content-based image information requires shading correction, constant maximum of grey values, and standardized grey value histograms. The different compartments to evaluate image information include objects, structure, and texture. Identification of objects and derived structure depend on segmentation accuracy and applied procedures; textures contain pixel-based image information only. All together, these image compartments posses the discrimination power to distinguish between object space and background, and, in addition, to reproducibly define regions of interest (ROIs). ROIs are image areas which display the information that is of preferable interest to the viewing pathologist. They contribute to the derived diagnosis to a higher level when compared with other image areas. The implementation of content-based image information algorithms to be applied for predictive tissue-based diagnoses is described in detail.
    01/2011; 2(1):2. DOI:10.4103/2153-3539.74945
  • Source
    • "Computer scientists first approached the challenge of automating the reading of samples on glass slides from a pattern-recognition angle. Digital pathology is an emerging clinical practice in which a pathologist makes diagnoses using digital images of tissues acquired with an automated high-throughput microscope and stored and viewed using a medical image database [48] [49]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Pathology is a bridging discipline that involves both basic and clinical biomedical sciences. In this context, it includes both descriptive and mechanistic approaches, with the final goals of further understanding the anatomic and functional changes and underlying molecular events involved in disease-related processes. Pathology studies mainly comprise macroscopic and microscopic examinations, and involve the visual recognition of different patterns in cells and tissues. In time elapsed to this end, it has adopted a dazzling array of methods and techniques from the most varied fields of natural and engineering sciences in order to optimize tissue analysis, which will be summarized in this article.
    Romanian journal of morphology and embryology = Revue roumaine de morphologie et embryologie 01/2011; 52(1 Suppl):223-30. · 0.66 Impact Factor
Show more