Ahmad Chaddad1,2, Christian Desrosiers1, Ahmed Bouridane3, Matthew Toews1, Lama Hassan2, Camel Tanougast2. 1. Laboratory for Imagery, Vision and Artificial Intelligence, École de Technologie Supérieure, Montréal, Québec, Canada. 2. Laboratory of Conception, Optimization and Modelling of Systems, University of Lorraine, Metz, Lorraine, France. 3. School of Computing, Engineering and Information Sciences, Northumbria University, Newcastle, United Kingdom.
Abstract
PURPOSE: This paper proposes to characterize the continuum of colorectal cancer (CRC) using multiple texture features extracted from multispectral optical microscopy images. Three types of pathological tissues (PT) are considered: benign hyperplasia, intraepithelial neoplasia and carcinoma. MATERIALS AND METHODS: In the proposed approach, the region of interest containing PT is first extracted from multispectral images using active contour segmentation. This region is then encoded using texture features based on the Laplacian-of-Gaussian (LoG) filter, discrete wavelets (DW) and gray level co-occurrence matrices (GLCM). To assess the significance of textural differences between PT types, a statistical analysis based on the Kruskal-Wallis test is performed. The usefulness of texture features is then evaluated quantitatively in terms of their ability to predict PT types using various classifier models. RESULTS: Preliminary results show significant texture differences between PT types, for all texture features (p-value < 0.01). Individually, GLCM texture features outperform LoG and DW features in terms of PT type prediction. However, a higher performance can be achieved by combining all texture features, resulting in a mean classification accuracy of 98.92%, sensitivity of 98.12%, and specificity of 99.67%. CONCLUSIONS: These results demonstrate the efficiency and effectiveness of combining multiple texture features for characterizing the continuum of CRC and discriminating between pathological tissues in multispectral images.
PURPOSE: This paper proposes to characterize the continuum of colorectal cancer (CRC) using multiple texture features extracted from multispectral optical microscopy images. Three types of pathological tissues (PT) are considered: benign hyperplasia, intraepithelial neoplasia and carcinoma. MATERIALS AND METHODS: In the proposed approach, the region of interest containing PT is first extracted from multispectral images using active contour segmentation. This region is then encoded using texture features based on the Laplacian-of-Gaussian (LoG) filter, discrete wavelets (DW) and gray level co-occurrence matrices (GLCM). To assess the significance of textural differences between PT types, a statistical analysis based on the Kruskal-Wallis test is performed. The usefulness of texture features is then evaluated quantitatively in terms of their ability to predict PT types using various classifier models. RESULTS: Preliminary results show significant texture differences between PT types, for all texture features (p-value < 0.01). Individually, GLCM texture features outperform LoG and DW features in terms of PT type prediction. However, a higher performance can be achieved by combining all texture features, resulting in a mean classification accuracy of 98.92%, sensitivity of 98.12%, and specificity of 99.67%. CONCLUSIONS: These results demonstrate the efficiency and effectiveness of combining multiple texture features for characterizing the continuum of CRC and discriminating between pathological tissues in multispectral images.
Authors: Sheng-Xiang Rao; Doenja Mj Lambregts; Roald S Schnerr; Wenzel van Ommen; Thiemo Ja van Nijnatten; Milou H Martens; Luc A Heijnen; Walter H Backes; Cornelis Verhoef; Meng-Su Zeng; Geerard L Beets; Regina Gh Beets-Tan Journal: United European Gastroenterol J Date: 2014-12 Impact factor: 4.623
Authors: Daniel J Sargent; Smitha Patiyil; Greg Yothers; Daniel G Haller; Richard Gray; Jacqueline Benedetti; Marc Buyse; Roberto Labianca; Jean Francois Seitz; Christopher J O'Callaghan; Guido Francini; Axel Grothey; Michael O'Connell; Paul J Catalano; David Kerr; Erin Green; Harry S Wieand; Richard M Goldberg; Aimery de Gramont Journal: J Clin Oncol Date: 2007-09-17 Impact factor: 44.544
Authors: Lee A D Cooper; Jun Kong; David A Gutman; William D Dunn; Michael Nalisnik; Daniel J Brat Journal: Lab Invest Date: 2015-01-19 Impact factor: 5.662
Authors: Valerio Nardone; Alfonso Reginelli; Fernando Scala; Salvatore Francesco Carbone; Maria Antonietta Mazzei; Lucio Sebaste; Tommaso Carfagno; Giuseppe Battaglia; Pierpaolo Pastina; Pierpaolo Correale; Paolo Tini; Gianluca Pellino; Salvatore Cappabianca; Luigi Pirtoli Journal: Gastroenterol Res Pract Date: 2019-01-17 Impact factor: 2.260
Authors: Ji Eun Oh; Min Ju Kim; Joohyung Lee; Bo Yun Hur; Bun Kim; Dae Yong Kim; Ji Yeon Baek; Hee Jin Chang; Sung Chan Park; Jae Hwan Oh; Sun Ah Cho; Dae Kyung Sohn Journal: Cancer Res Treat Date: 2019-05-07 Impact factor: 4.679