A fast, automatic segmentation algorithm for locating and delineating touching cell boundaries in imaged histopathology.

BACKGROUND: Automated analysis of imaged histopathology specimens could potentially provide support for improved reliability in detection and classification in a range of investigative and clinical cancer applications. Automated segmentation of cells in the digitized tissue microarray (TMA) is often the prerequisite for quantitative analysis. However overlapping cells usually bring significant challenges for traditional segmentation algorithms. OBJECTIVES: In this paper, we propose a novel, automatic algorithm to separate overlapping cells in stained histology specimens acquired using bright-field RGB imaging. METHODS: It starts by systematically identifying salient regions of interest throughout the image based upon their underlying visual content. The segmentation algorithm subsequently performs a quick, voting based seed detection. Finally, the contour of each cell is obtained using a repulsive level set deformable model using the seeds generated in the previous step. We compared the experimental results with the most current literature, and the pixel wise accuracy between human experts' annotation and those generated using the automatic segmentation algorithm. RESULTS: The method is tested with 100 image patches which contain more than 1000 overlapping cells. The overall precision and recall of the developed algorithm is 90% and 78%, respectively. We also implement the algorithm on GPU. The parallel implementation is 22 times faster than its C/C++ sequential implementation. CONCLUSION: The proposed segmentation algorithm can accurately detect and effectively separate each of the overlapping cells. GPU is proven to be an efficient parallel platform for overlapping cell segmentation.

Viscoelasticity of the vessel wall: the role of collagen and elastic fibers.

The aortic wall contains collagen fibrils, smooth muscle cells, and elastic fibers as the primary load-bearing components. It is well known that the collagen fibrils bear loads in the circumferential direction, whereas elastic fibers provide longitudinal as well as circumferential support. Stiffening of the vessel wall is associated with loss of elastic tissue and increases in the collagen content: however, little is known about the mechanism of vessel wall stiffening with age. The purpose of this review is to attempt to relate structural changes that occur to the collagen and elastic fibers to changes in the viscoelastic behavior that are associated with aging. Analysis of the viscoelastic mechanical properties of collagen fibrils from tendon, skin, and aortic wall suggest that the collagen fibrils of aortic wall are different than those of other tissues. The elastic spring constant of the collacen fibrils in vessel walls is significantly less than that found in tendon, suggesting that the presence of type III collagen in aortic wall increases the flexibility of the collagen fibrils. Furthermore, it is hypothesized that changes in the interface between collagen fibrils, elastic fibers, and smooth muscle during aging and in connective tissue disorders leads to changes in the viscoelasticity of the vessel wall.

Computer-assisted discrimination among malignant lymphomas and leukemia using immunophenotyping, intelligent image repositories, and telemicroscopy.

The process of discriminating among pathologies involving peripheral blood, bone marrow, and lymph node has traditionally begun with subjective morphological assessment of cellular materials viewed using light microscopy. The subtle visible differences exhibited by some malignant lymphomas and leukemia, however, give rise to a significant number of false negatives during microscopic evaluation by medical technologists. We have developed a distributed, clinical decision support prototype for distinguishing among hematologic malignancies. The system consists of two major components, a distributed telemicroscopy system and an intelligent image repository. The hybrid system enables individuals located at disparate clinical and research sites to engage in interactive consultation and to obtain computer-assisted decision support. Software, written in JAVA, allows primary users to control the specimen stage, objective lens, light levels, and focus of a robotic microscope remotely while a digital representation of the specimen is continuously broadcast to all session participants. Primary user status can be passed as a token. The system features shared graphical pointers, text messaging capability, and automated database management. Search engines for the database allow one to automatically identify and retrieve images, diagnoses, and correlated clinical data of cases from a "gold standard" database which exhibit spectral and spatial profiles which are most similar to a given query image. The system suggests the most likely diagnosis based on majority logic of the retrieved cases. The system was used to discriminate among three lymphoproliferative disorders and healthy cells. The system provided the correct classification in more than 83% of the cases studied. System performance was evaluated using rigorous statistical assessment and by comparison with human observers.

Compression guidelines for diagnostic telepathology.

As the healthcare community has begun to rely increasingly upon digital technologies for acquisition, storage, and transmission of pictorial data, image compression has become an indispensable tool. We have investigated the feasibility of lossy compression in a well-defined task domain, the clinical assessment of digitized images of chromatic microscopic pathology specimens. The effect of compression was measured under two distinct perceptual criteria, just noticeable difference (j.n.d.) and largest tolerable distortion (l.t.d.), differing in the involvement required from subjects, who were experts in pathology. For standard JPEG compressed images it was found that when the experiment is performed under the l.t.d. criterion, a significantly larger compression ratio is reported as satisfactory. It is concluded that lossy compression holds promise for diagnostic telepathology.

A network-based prototype for interactive telemedicine & automated management of distributed, clinical databases.

A network-based prototype has been developed to automate the process of generating and maintaining distributed databases of medical images and clinical reports, and for conducting interactive consultation among disparate clinical and research sites irrespective of the architecture of interacting computers. Pathologists routinely interpret gross and microscopic specimens to tender diagnoses and to engage in a broad spectrum of research. This assessment process leads to clinical decisions often limited by time constraints and by the availability of local expertise. Consultation with peers at other institutions is typically achieved by direct transfer of slides rather than images. A network of heterogeneous computer platforms, graphical user interfaces, and operating systems was established to test the performance of the software. Clinical diagnoses rendered by pathologists using the prototypical system and software were consistent with those reported two years earlier using conventional light microscopy in more than 97% of the cases studied.

The role for regional autopsy centers in the evaluation of covered deaths. Survey of opinions of US and Canadian chairs of pathology and major health insurers in the United States.

OBJECTIVE: To evaluate the advantages and disadvantages of, as well as the attitudes of health care professionals and insurers toward, the development of regional autopsy services. DESIGN: Survey of 150 medical school departments of pathology in the United States and Canada and 12 representative major health insurers in the United States. RESULTS: Of the 25 respondents from the pathology departments, most were in favor of regionalization of autopsy services, if properly underwritten. Of the five respondents from the health insurers, most were disinterested in the autopsy as a measure of outcome and unwilling to provide support. CONCLUSIONS: Health care is being regionalized around networks of insurers rather than hospitals. The networks are defined by a mixture of hospitals, physician groups, and other health care professionals. Within networks, the goal is to subscribe groups of patients, covered lives, for all medical needs from primary to complex care. As the economic risk of caring for patients is shifted to physicians, the incentive to provide service at the lowest possible cost grows, as does the need to assure that medical mismanagement does not occur. To provide quality care at affordable costs, it is necessary that outcomes, including deaths, be professionally evaluated. The present system of death investigation involves hospital colleagues and is potentially biased. Regional autopsy centers that provide timely expert information should be part of the health care system. Medical schools are potential sites for regional autopsy programs because they have the personnel needed to conduct appropriate death-related studies. Most schools are affiliated programmatically and economically with surrounding hospitals and physicians in a manner in which outcomes, costs, and quality of clinical service are of common interest.

A method for quantitative image assessment based on redundant feature measurements and statistical reasoning.

Advances in computer graphics and electronics have contributed significantly to the increased utilization of digital imaging throughout the scientific community. Recently, as the volume of data being gathered for biomedical applications has begun to approach the human capacity for processing, emphasis has been placed on developing an automated approach to assist health scientists in assessing images. Methods that are currently used for analysis often lack sufficient sensitivity for discriminating among elements that exhibit subtle differences in feature measurements. In addition, most approaches are highly interactive. This paper presents an automated approach to segmentation and object recognition in which the spectral and spatial content of images is statistically exploited. Using this approach to assess noisy images resulted in correct classification of more than 97% of the pixels evaluated during segmentation and in recognition of geometric shapes irrespective of variations in size, orientation, and translation. The software was subsequently used to evaluate digitized stained blood smears.

Assessment of cell proliferation on porous microcarriers by means of image analysis.

Spherical porous microcarriers (PMCs) made from collagen-glycosaminoglycan crosslinked copolymers have exhibited considerable promise as growth surfaces for the proliferation of anchorage-dependent mammalian cell lines and have demonstrated the ability to entrap anchorage-independent cells. However, quantification of cell growth on PMCs has proved difficult. A method of measuring the proliferation of PMCs, based on image analysis, is presented. Using CV1 and CHO cell lines, samples of PMCs were removed from culture at various times, fixed, embedded and sectioned. The 2 microns sections were stained, photographed and digitized in three colors. A computer program was developed to evaluate digitized PMC cross-sections and to classify pixels as conforming to either background, cytoplasmic, matrix or nuclear parameters, based on a set of classification rules determined by statistical analysis. Growth curves were generated by relating the number of pixels occupied by cellular material to the total number of pixels in the PMC cross-section. The PMCs were found to foster cell proliferation, with cell densities approaching 100% occupancy.