Toward a multimodal cell analysis of brush biopsies for the early detection of oral cancer.

BACKGROUND: This report describes what to the authors' knowledge is the first clinical application of semiautomated multimodal cell analysis (MMCA), a novel technique for the early detection of cancer for cases with a limited number of suspicious cells. In this clinical study, MMCA was applied to oral cancer diagnostics on brush biopsies. The MMCA approach was based on the sequential application of multiple stainings of identical, slide-based cells and repeated relocalizations and measurements of their diagnostic features, resulting in multiparametric features of individual cells. Data integration of the variously stained cells increased diagnostic accuracy. The implementation of MMCA also enabled fully automatic, adaptive image preprocessing, including registration of multimodal images and segmentation of cell nuclei. METHODS: In a preliminary clinical trial, 47 slides from brush biopsies of suspicious oral lesions were analyzed. The final histologic diagnoses included 20 squamous cell carcinomas, 7 hyperkeratotic leukoplakias, and 20 lichen planus mucosae. RESULTS: The stepwise application of 2 additional approaches (morphology, DNA content, argyrophilic nucleolar organizer region counts) increased the specificity of conventional cytologic diagnosis from 92.6% to 100%. This feasibility study provided a proof of concept, demonstrating efficiency, robustness, and diagnostic accuracy on slide-based cytologic specimens. CONCLUSIONS: The authors concluded that MMCA may become a sensitive and highly specific, objective, and reproducible adjuvant diagnostic tool for the identification of neoplastic changes in oral smears that contain only a few abnormal cells.

Towards fully automatic acquisition of multimodal cytopathological microscopy images with autofocus and scene managing.

OBJECTIVES: To increase the chance for a cure, cancer must be detected as early as possible. This can be achieved with cytopathological diagnostic methods. For a further increase of the diagnostic accuracy of these methods we introduced the multimodal cell analysis, viz, cells on the slide have to be relocalized to enable successive analysis of identical cells in different stains. For practical reasons the relocalization step must be automated. METHODS: For a fully automatic acquisition of successive cell images we use a passive autofocus that is adaptive to the material, i.e., to the cells, followed by a comparison of the scenes, i.e., the cell constellation, of two such obtained images from different stains. In case that no sub-scene match can be found the search is extended to the surrounding area. A set of 1556 scenes from seven specimens have been subject to our algorithm. The automatically relocalized and acquired images from a second stain have been manually compared to the images from a first stain. RESULTS: An overall relocalization rate of 85.4% is achieved. 14.3% of the images could not be relocalized and are lost for the following diagnostic process, while the critical case of erroneously matched images was observed in only 0.3% of cases. CONCLUSIONS: We could show that it is possible to automatically acquire images of successive stains of identical cells on cytopathological specimens. The method presented achieves acceptable relocalization rates. Wrong image acquisitions are very rare and can mostly be ascribed to images with single cells, i.e., without scene information.