Kraisorn Chaisaowong

Computer-assisted Diagnosis for Early Stage Pleural Mesothelioma: Towards Automated Detection and Quantitative Assessment of Pleural Thickenings from Thoracic CT Images

OBJECTIVES Pleural thickenings as biomarker of exposure to asbestos may evolve into malignant pleural mesothelioma. For its early stage, pleurectomy with perioperative treatment can reduce morbidity and mortality. The diagnosis is based on a visual investigation of CT images, which is a time-consuming and subjective procedure. Our aim is to develop an automatic image processing approach to detect and quantitatively assess pleural thickenings. METHODS We first segment the lung areas, and identify the pleural contours. A convexity model is then used together with a Hounsfield unit threshold to detect pleural thickenings. The assessment of the detected pleural thickenings is based on a spline-based model of the healthy pleura. RESULTS Tests were carried out on 14 data sets from three patients. In all cases, pleural contours were reliably identified, and pleural thickenings detected. PC-based Computation times were 85 min for a data set of 716 slices, 35 min for 401 slices, and 4 min for 75 slices, resulting in an average computation time of about 5.2 s per slice. Visualizations of pleurae and detected thickenings were provided. CONCLUSION Results obtained so far indicate that our approach is able to assist physicians in the tedious task of finding and quantifying pleural thickenings in CT data. In the next step, our system will undergo an evaluation in a clinical test setting using routine CT data to quantify its performance.

Effects of Plectin Depletion on Keratin Network Dynamics and Organization

The keratin intermediate filament cytoskeleton protects epithelial cells against various types of stress and is involved in fundamental cellular processes such as signaling, differentiation and organelle trafficking. These functions rely on the cell type-specific arrangement and plasticity of the keratin system. It has been suggested that these properties are regulated by a complex cycle of assembly and disassembly. The exact mechanisms responsible for the underlying molecular processes, however, have not been clarified. Accumulating evidence implicates the cytolinker plectin in various aspects of the keratin cycle, i.e., by acting as a stabilizing anchor at hemidesmosomal adhesion sites and the nucleus, by affecting keratin bundling and branching and by linkage of keratins to actin filament and microtubule dynamics. In the present study we tested these hypotheses. To this end, plectin was downregulated by shRNA in vulvar carcinoma-derived A431 cells. As expected, integrin β4- and BPAG-1-positive hemidesmosomal structures were strongly reduced and cytosolic actin stress fibers were increased. In addition, integrins α3 and β1 were reduced. The experiments furthermore showed that loss of plectin led to a reduction in keratin filament branch length but did not alter overall mechanical properties as assessed by indentation analyses using atomic force microscopy and by displacement analyses of cytoplasmic superparamagnetic beads using magnetic tweezers. An increase in keratin movement was observed in plectin-depleted cells as was the case in control cells lacking hemidesmosome-like structures. Yet, keratin turnover was not significantly affected. We conclude that plectin alone is not needed for keratin assembly and disassembly and that other mechanisms exist to guarantee proper keratin cycling under steady state conditions in cultured single cells.

Detection and follow-up assessment of pleural thickenings from 3D CT data

Pleural thickenings as biomarker of exposure to asbestos may evolve into malignant pleural mesothelioma. The diagnosis is based on a visual investigation of CT images, which is a time consuming and subjective procedure. Our image processing system segments the lung areas, and identifies the pleural contours using thresholding and contour relaxation. A convexity model is then used together with a Hounsfield unit threshold to detect pleural thickenings. The assessment of the detected pleural thickenings is based on a spline-based model of the healthy pleura. Follow-up study between two consecutive data, carried out by normalizing the coordinate system, leads to a diagnosis supporting tool to detect pleural mesothelioma in its early stage.

An approach to segment lung pleura from CT data with high precision

A new approach to segment pleurae from CT data with high precision is introduced. This approach is developed in the segmentations framework of an image analysis system to automatically detect pleural thickenings. The new technique to carry out the 3D segmentation of lung pleura is based on supervised range-constrained thresholding and a Gibbs-Markov random field model. An initial segmentation is done using the 3D histogram by supervised range-constrained thresholding. 3D connected component labelling is then applied to find the thorax. In order to detect and remove trachea and bronchi therein, the 3D histogram of connected pulmonary organs is modelled as a finite mixture of Gaussian distributions. Parameters are estimated using the Expectation-Maximization algorithm, which leads to the classification of that pulmonary region. As consequence left and right lungs are separated. Finally we apply a Gibbs-Markov random field model to our initial segmentation in order to achieve a high accuracy segmentation of lung pleura. The Gibbs- Markov random field is combined with maximum a posteriori estimation to estimate optimal pleural contours. With these procedures, a new segmentation strategy is developed in order to improve the reliability and accuracy of the detection of pleural contours and to achieve a better assessment performance of pleural thickenings.

Volume-preserving correction for image registration using free-form deformations

Registration of an image non-rigidly to another one causes deformations, which generally do not preserve the initial volume. Volume preservation is however indispensable for observing tumors in medical images. This paper presents the correction of B-spline based registration to preserve the volume in observed regions. In contrast to other approaches, our solution is not obtained through energy minimization, but by calculating the correction parameters for the deformation directly. Especially for high resolution image data this strategy is very efficient in terms of computational expenses. We derive a closed form solution to optimize the registration with respect to the compression at a single point and then extend the problem to multiple points. Finally we prove also that the correction terms do not have any significant influence on the registration quality.

Markov-Gibbs model based registration of CT lung images using subsampling for the follow-up assessment of pleural thickenings

Examining the growth rate of pleural thickenings in consecutive 3D-CT images requires the matching of identical thickenings in lung images acquired at two different points in time. The thickenings can be subject to strong deformations caused by their growth. This implies that position information should play a major role in finding correspondences. Here, a MGRF approach is presented to determine a rigid transformation. It aligns the lung volumes by maximizing the probability of the regarded lung tissue to fit an offline trained model. To ensure a symmetrical matching of lung surfaces this probability is calculated reciprocally. Using precalculation, strong sub-sampling and a multiscale approach, the required time can be reduced by a factor of about 80, depending on the image resolution. Due to this speed-up, online follow-up assessment is feasible. We show that this approach results in precise registrations which can be used for a reliable matching of lung thickenings.

Automatic 3D modeling of pleural thickening through thin plate spline interpolation

Pleuramesothelioma is malignant tumor on the pleura, caused by asbestos exposure. Computer-assisted diagnosis system shall support physicians to assess the growth rate of detected pleural thickenings from CT data. This paper describes a new, improved method to automatically assess the size of detected thickening using thin plate spline interpolation which then leads to the 3D modeling of thickening. First, we detect each pleural thickening. Second, an automatic coordinate transformation is applied to enable the numeric calculation of the spline. Next, the appropriate landmark points are then automatically selected by using the newly applied chain-code concavity analysis and used as the constraint points for the interpolation. Numerical integration is applied to calculate area by slice. In the final step, the spline interpolation between layers is applied to calculate volume of each thickening. The results show that the thin plate spline interpolated boundary is suitable for 3D modeling of the thickening.

A fully automatic probabilistic 3D approach for the detection and assessment of pleural thickenings from CT data

Pleural thickenings are caused by asbestos exposure and may evolve into malignant pleural mesothelioma. The detection of pleural thickenings is today done by visual inspection of CT data, which is time-consuming and underlies the subjective judgment. In this work, thickenings are initially detected as the differences between the original contours and the healthy model of the pleura. A subsequent tissue-specific segmentation using the 3D Gibbs-Markov random field (GMRF) within the initially detected region-of-interest separates thickenings from thoracic tissue. Morphometric analysis leads then to 3D modeling and volumetric assessment. Both automatic detection and morphometric modeling of pleural thickenings proposed in this work assure not only reproducible detection but also precise measurement, hence this automated approach can assist physicians to diagnose pleural mesothelioma in its early stage.

Fast virtual destaining of immunocytological specimens

Microscopy-based diagnosis of certain diseases or infections, e.g. with human papilloma viruses (HPV) for the identification of high risk patients for cervical cancer, relies more and more often on immunocytochemical marker stains. These markers stain cells that exhibit a particular protein. In addition to one or more marker stains, pathologists need to simultaneously assess the morphology of the cell. Therefore the specimens are commonly also stained with a counter stain.

3D modeling of detected pleural thickenings through thin plate spline interpolation

Pleuramesothelioma is a malignant tumor. A computer-assisted diagnosis system shall provide physicians with the assessment of the detected pleural thickening from the 3D CT data. This paper describes a new, improved method to assess the size of detected thickening using both the 2D and 3D thin plate spline. First, a coordinate transformation was applied. Next, set of landmarks was selected as input for the thin plate spline. The final step is the numerical area integration. The results show that the calculated area was more accurate than the former pixel counting technique, and promise further automatic development.