Infrared spectral histopathology for cancer diagnosis: a novel approach for automated pattern recognition of colon adenocarcinoma

Abstract

Histopathology remains the gold standard method for colon cancer diagnosis. Novel complementary approaches for molecular level diagnosis of the disease are need of the hour. Infrared (IR) imaging could be a promising candidate method as it probes the intrinsic chemical bonds present in a tissue, and provides a "spectral fingerprint" of the biochemical composition. To this end, IR spectral histopathology, which combines IR imaging and data processing techniques, was employed on seventy seven paraffinized colon tissue samples (48 tumoral and 29 non-tumoral) in the form of tissue arrays. To avoid chemical deparaffinization, a digital neutralization of the spectral interference of paraffin was implemented. Clustering analysis was used to partition the spectra and construct pseudo-colored images, for assigning spectral clusters to various tissue structures (normal epithelium, malignant epithelium, connective tissue etc.). Based on the clustering results, linear discriminant analysis was then used to construct a stringent prediction model which was applied on samples without a priori histopathological information. The predicted spectral images not only revealed common features representative of the colonic tissue biochemical make-up, but also highlighted additional features like tumor budding and tumor-stroma association in a label-free manner. This novel approach of IR spectral imaging on paraffinized tissues showed 100% sensitivity and allowed detection and differentiation of normal and malignant colonic features based purely on their intrinsic biochemical features. This non-destructive methodology combined with multivariate statistical image analysis appears as a promising tool for colon cancer diagnosis and opens up the way to the concept of numerical spectral histopathology.

High-resolution FTIR imaging of colon tissues for elucidation of individual cellular and histopathological features

“…27 If mucin associated changes can be characterized using such technology at cellular level, it could provide vital information related to the characteristics of cancers being investigated. Previous IR spectroscopy studies on colon tissues were undertaken to identify the abnormalities in colon epithelial regions [4][5][6] and the secreted mucin 7 as potential indicators of cancer. These were carried out using the conventional IR set ups.…”

“…IR spectroscopy can provide information about these variations that can be used to identify, understand and in some cases even predict the possibility of the occurrence of a disease. In this regard, IR spectroscopy has been investigated as a potential cancer diagnostic tool in various tissue types including some highly prevalent cancers such as lung, 2 colon, [3][4][5][6][7] oral cavity, 8 liver, 9 prostate, [10][11][12] breast, [13][14][15] lymphnode, 16,17 cervix, 18 etc. Using IR spectroscopic imaging approaches, biological material can be imaged to obtain bio-molecular information, where each pixel of the image constitutes a spectrum with a specific bio-molecular signature.…”

Label‐free Raman spectroscopic imaging to extract morphological and chemical information from a formalin‐fixed, paraffin‐embedded rat colon tissue section

“…2007) and infrared (IR) spectral imaging (Nallala et al . 2014). However, MALDI IMS is limited to protein‐ and lipid‐based analysis and excludes the vital nucleic acid components.…”

Automated Quantification of Tumor Viability in a Rabbit Liver Tumor Model after Chemoembolization Using Infrared Imaging

“…26,29,30 In this study, the predictive model was applied to infrared images of 24 new test tumor sections (Table 1) from the 20 remaining tumors. Unidentified test spectra were analyzed by the PCA-LDA model that identified their tissue classes and colored them in accordance with their class color (dark blue color to represent tumor necrosis, yellow for viable tumor, blue for the fibrosis, green for liver parenchyma, and orange for liver parenchyma necrosis).…”

“…42e44 We only found two studies in which the authors applied their model to new tissue sections that have been used for neither model construction nor model internal validation. 29,30 The different structures of their samples could be identified on the infrared processed image, and the visual comparison to a control HES-stained section revealed good resemblance between the two images, but it was not assessed quantitatively.…”