Lung cancer is the deadliest form of cancer mainly because of the absence of reliable early diagnostic protocols. Therefore, there is increasing interest in the development of novel diagnostic noninvasive technologies that may improve the early detection of the disease. Bronchoscope-guided bronchoalveolar lavage (BAL) is a minimally invasive diagnostic technique that is based on the extraction and analysis of cellular material from the bronchial epithelium of patients that present suspicious lung masses on low-dose screening X-ray-computed tomography images. Together with a novel staining technique that combines immunophenotyping of a lung cancer biomarker with fluorescent in situ hybridization of genetically abnormal DNA loci, BAL promises a powerful early diagnostic tool for lung carcinomas. The sensitivity of this method, however, is highly dependent on the pathologist's ability to reliably and repeatedly examine thousands of cells under the microscope. This is an extremely labor-intensive and error-prone task. We have developed a multiscale multidimensional integrated microscopy computer-aided detection platform that autonomously scans and analyzes BAL samples. In this paper, we describe its software architecture and validate the specific image analysis protocols that are developed for this particular application.

The ample variety of labeling dyes and staining methods available in fluorescence microscopy has enabled biologists to advance in the understanding of living organisms at cellular and molecular level. When two or more fluorescent dyes are used in the same preparation, or one dye is used in the presence of autofluorescence, the separation of the fluorescent emissions can become problematic. Various approaches have been recently proposed to solve this problem. Among them, blind non-negative matrix factorization is gaining interest since it requires little assumptions about the spectra and concentration of the fluorochromes. In this paper, we propose a novel algorithm for blind spectral separation that addresses some of the shortcomings of existing solutions: namely, their dependency on the initialization and their slow convergence. We apply this new algorithm to two relevant problems in fluorescence microscopy: autofluorescence elimination and spectral unmixing of multi-labeled samples. Our results show that our new algorithm performs well when compared with the state-of-the-art approaches for a much faster implementation.

The widespread use of fluorescence microscopy along with the vast library of available fluorescent stains and staining methods has been extremely beneficial to researchers in many fields, ranging from material sciences to plant biology. In clinical diagnostics, the ability to combine different markers in a given sample allows the simultaneous detection of the expression of several different molecules, which in turn provides a powerful diagnostic tool for pathologists, allowing a better classification of the sample at hand. The correct detection and separation of multiple stains in a sample is achieved not only by the biochemical and optical properties of the markers, but also by the use of appropriate hardware and software tools. In this chapter, we will review and compare these tools along with their advantages and limitations.