Detection of malignancy in cytology specimens using spectral–spatial analysis

Abstract

Despite low sensitivity (around 60%), cytomorphologic examination of urine specimens represents the standard procedure in the diagnosis and follow-up of bladder cancer. Although color is information-rich, morphologic diagnoses are rendered almost exclusively on the basis of spatial information. We hypothesized that quantitative assessment of color (more precisely, of spectral properties) using liquid crystal-based spectral fractionation, combined with genetic algorithm-based spatial analysis, can improve the accuracy of traditional cytologic examination. Images of various cytological specimens were collected every 10 nm from 400 to 700 nm to create an image stack. The resulting data sets were analyzed using the Los Alamos-developed GENetic Imagery Exploitation (GENIE) package, a hybrid genetic algorithm that segments (classifies) images using automatically 'learned' spatio-spectral features. In an evolutionary fashion, GENIE generates a series of algorithms or 'chromosomes', keeping the one with best fitness with respect to a user-defined training set. First, we tested the system to determine if it could recognize malignant cells using artificial cytology specimens constructed to completely avoid the requirement for human interpretation. GENIE was able to differentiate malignant from benign cells and to estimate their relative proportions in controlled mixtures. We then tested the system on routine cytology specimens. When targeted to detect malignant urothelial cells in cytology specimens, GENIE showed a combined sensitivity and specificity of 85 and 95%, in samples drawn from two separate institutions over a span of 4 years. When trained on cases initially diagnosed as 'atypical' but with unequivocal follow-up by biopsy, surgical specimen or cytology, GENIE showed efficiency superior to the cytopathologist with respect to predicting the follow-up result in a cohort of 85 cases. We believe that, in future, this type of methodology could be used as an ancillary test in cytopathology, in a manner analogous to immunostaining, in those situations when a definitive diagnosis cannot be rendered based solely on the morphology. Laboratory Investigation ( Keywords: atypical; urine; bladder; cytopathology; genetic algorithm Urothelial carcinoma is diagnosed and followed by cytological evaluation of voided urine and bladder washings.1,2 The sensitivity of these tests is moderate, ranging between 60 and 80%.3,4 Low-grade tumors offer an even greater challenge to the cytopathologist, 5 resulting in the use of such terminology as 'atypical urothelial cells', leading to suboptimal patient management. 6 Morphologic diagnoses in cytopathology are primarily driven by spatial relationships, while colorbased information is relegated to a very minor role. This may be because the human eye has limited spectral resolution, viewing the world in broad, overlapping spectral bands of red, green and blue. If the spectral properties of cytological specimens are important, this fact can only be assessed using devices capable of imaging with...

A Minimum Spanning Forest-Based Method for Noninvasive Cancer Detection With Hyperspectral Imaging

“…The rationale for cancer detection with HSI is that the spectral fingerprint of light diffusely reflected from tissue is influenced by biochemical and morphological changes associated with disease progression. HSI has exhibited great potential in the detection of cancer in the cervix [5], breast [6, 7], colon [8], gastrointestine [9], skin [10], urothelial carcinoma [11], prostate [12], trachea [13], head and neck [14–19], lymph nodes [20] and brain [21], etc. A thorough review of these medical applications has previously been presented by our group [22].…”

Digital pathology and image analysis augment biospecimen annotation and biobank quality assurance harmonization

“…Due to the variation in tissue components present among different types of cancers, it is impossible to create one algorithm to analyze an entire biobank collection for various lesions, hence cancer type-specific algorithms are necessary to conduct optimum analyses. Areas containing representative features of each type of tissue present in a particular cancer are selected from WSI for training an algorithm; the approach follows parameters similar to those featured in caHUB collection guidelines (27, 38, 45, 46). Annotating biobank specimens with evidence of their component cellular makeup involved designing algorithms with mean training accuracies of > 98% and with > 95 % sensitivity and specificity.…”

Hyperspectral microscopic analysis of normal, benign and carcinoma microarray tissue sections

“…The goal is to evaluate the diagnostic efficiency of hyper-spectral microscopic analysis of normal and malignant neoplastic colon biopsies prepared as microarray tissue sections. [8][9][10][11] 2. METHODOLOGY…”