We report results of a study utilizing a recently developed tissue diagnostic method, based on label-free spectral techniques, for the classification of lung cancer histopathological samples from a tissue microarray. The spectral diagnostic method allows reproducible and objective diagnosis of unstained tissue sections. This is accomplished by acquiring infrared hyperspectral data sets containing thousands of spectra, each collected from tissue pixels about 6 mm on edge; these pixel spectra contain an encoded snapshot of the entire biochemical composition of the pixel area. The hyperspectral data sets are subsequently decoded by methods of multivariate analysis, which reveal changes in the biochemical composition between tissue types, and between various stages and states of disease. In this study, a detailed comparison between classical and spectral histopathology (SHP) is presented, which suggests SHP can achieve levels of diagnostic accuracy that is comparable to that of multi-panel immunohistochemistry. KEYWORDS: artificial neural network analysis; histopathology; immunohistochemistry; lung cancer; spectral histopathology This paper reports a large-scale study of a new technology to classify four common forms of lung cancers, and distinguish them from normal tissues. The new methodology introduced here utilizes optical measurements on unstained tissue 1 for spectral data acquisition, and does not utilize any immunohistochemical or other stains or labels for classification. As the diagnostic procedure is instrument based and utilizes trained computer algorithms for classification, this method offers reproducibility, complete objectivity and improved accuracy over present methodology.Optical methods have been used in histology and pathology ever since these methods were first described. After all, staining tissues or cells by hematoxylin/eosin (H&E), followed by (visual) microscopic examination is a form of spectral analysis: different compartments of the cell respond differently to basophilic and eosinophilic stains and thus, allow a 'spectral analysis' using the eye as a detector. This method can reveal an amazing amount of information but is inherently subjective. More recent optical methods have used image capture at a few selected wavelengths, and computer analysis of the image planes, for tissue analysis. 2 Immunohistochemistry (IHC), to date the most advanced optical method to detect the presence of certain cancer signatures or markers 3,4 uses detection of specific antibodies labeled with easily observable stains.The new approach reported here is based on the observation of inherent spectral signatures (as opposed to any external stains or labels used to treat the sample) of cellular components to aid classical cytopathology and histopathology. 5 The paradigm for the spectral approach is that the transition from normal tissue or cells to diseased states is accompanied by changes in the overall biochemical composition of the tissue, along with well-known changes in cellular morphology and tissue archite...

We report results of a study utilizing a novel tissue classification method, based on label-free spectral techniques, for the classification of lung cancer histopathological samples on a tissue microarray. The spectral diagnostic method allows reproducible and objective classification of unstained tissue sections. This is accomplished by acquiring infrared data sets containing thousands of spectra, each collected from tissue pixels ∼6 μm on edge; these pixel spectra contain an encoded snapshot of the entire biochemical composition of the pixel area. The hyperspectral data sets are subsequently decoded by methods of multivariate analysis that reveal changes in the biochemical composition between tissue types, and between various stages and states of disease. In this study, a detailed comparison between classical and spectral histopathology is presented, suggesting that spectral histopathology can achieve levels of diagnostic accuracy that is comparable to that of multipanel immunohistochemistry.

We report results on a statistical analysis of an infrared spectral dataset comprising a total of 388 lung biopsies from 374 patients. The method of correlating classical and spectral results and analyzing the resulting data has been referred to as spectral histopathology (SHP) in the past. Here, we show that standard bio-statistical procedures, such as strict separation of training and blinded test sets, result in a balanced accuracy of better than 95% for the distinction of normal, necrotic and cancerous tissues, and better than 90% balanced accuracy for the classification of small cell, squamous cell and adenocarcinomas. Preliminary results indicate that further sub-classification of adenocarcinomas should be feasible with similar accuracy once sufficiently large datasets have been collected.

Results of a study comparing infrared imaging data sets collected on different instruments or instrument platforms are reported, along with detailed methods developed to permit such comparisons. It was found that different instrument platforms, although employing different detector technologies and pixel sizes, produce highly similar and reproducible spectral results. However, differences in the absolute intensity values of the reflectance data sets were observed that were caused by heterogeneity of the sample substrate in terms of reflectivity and planarity.