Computer-assisted Diagnosis for Precancerous Lesions in the Esophagus

Summary

Objectives: The interpretation of endoscopic findings by gastroenterologists is still a difficult and highly subjective task. Despite important developments such as chromo-endoscopy, pit pattern analysis, fluorescence imaging as well as narrow band imaging it still requires lots of experience and training with a certain tentativeness until the final biopsy. By the development of computer-assisted diagnosis (CAD) systems this process can be supported.

Methods: This paper presents a new approach to CAD for precancerous lesions in the esophagus based on color-texture analysis in a content-based image retrieval (CBIR) framework. The novelty of our approach lies in the combination of newly developed color-texture features with the interactive feedback loop provided by a relevance feedback algorithm. This allows the expert to steer the query and is still robust against accidental false decisions.

Results: We reached an inter-rater reliability of κ = 0.71 on a database of 390 endoscopic images. The retrieval accuracy didn’t change significantly until a wrong decision rate of 20%.

Conclusions: Thus, the system could be able to support practitioners with less experience or in private practice. In combination with a connected case database it can also support case-based reasoning for the diagnostic decision process.

Keywords

Computer-assisted diagnosis - gastroenterology - color-texture

• References

• 1 Fennerty MB. Chromoscopy in the diagnosis and management of Barrett’s esophagus. In: Jung M, Riemann JF. editors. Internationales Symposium Chromoendoskopie;. Mainz: 2000. pp 40-46.
• 2 Rajan E, Burgart L, Gostout C. Endoscopic and histologic diagnosis of Barrett esophagus. Mayo Clin Proc 2001; 76: 217-225.
• 3 Mayinger B, Öztürk Y, Stolte M, Faller G, Benninger J, Schwab D. et al. Evaluation of sensitivity and inter-and intra-observer variability in the detection of intestinal metaplasia and dysplasia in Barrett’s esophagus with enhanced magnification endoscopy. Scandinavian Journal of Gastroenterology 2006; 41 (Suppl. 03) 349-356.
• 4 Ji Q, Engel J, Craine E. Texture analysis for classification of cervix lesions. IEEE Trans. on Medical Imaging 2000; 19 (11) 1144-1149.
• 5 Häfner M, Brunauer L, Payer H, Resch R, Wrba F, Gangl A. et al. Pit pattern classification of zoom-endoscopical colon images using DCT and FFT. In: Proc’s 20th IEEE Int Symposium on Computer-Based Medical Systems 2007
• 6 Häfner M, Gangl A, Wrba F, Kastinger C, Uhl A, Thonhauser K. et al. Comparison of k-NN, SVM, and NN in pit pattern classification of zoom-endoscopic colon images using co-occurrence histograms. In: Proc’s of the 5th Int Symposium on Image and Signal Processing and Analysis 2007 pp 516-521.
• 7 Krishnan SM, Goh PM. Quantitative parameterization of colonoscopic images by applying fuzzy technique. In: Proc’s 19th IEEE Int Conf Engineering in Medicine and Biology Society (EMBS) 1997 pp 1121-23.
• 8 Krishnan SM, Yang X, Chan KL, Kumar S, Goh PM. Intestinal Abnormality Detection from Endoscopic Images. In: Proc’s 20th IEEE Int Conf Engineering in Medicine and Biology Society (EMBS) 1998 pp 895-898.
• 9 Wang P, Krishnan SM, Kugean C, Tjoa MP. Classification of Endoscopic Images Based on Texture and Neural Network. In: Proc. of the 23rd Annual EMBS Int Conf, 2001 Oct 25-28 Istanbul; Turkey: 2001. pp 3691-3695.
• 10 Tjoa MP, Krishnan SM, Doraiswami R. Automated diagnosis for segmentation of colonoscopic images using chromatic features. In: Proc’S IEEE Canadian Conf on Electrical and Computer Engineering 2002 pp 1177-1180.
• 11 Tjoa MP, Krishnan SM. Feature extraction for the analysis of colon status from the endoscopic images. BioMedical Engineering OnLine 2003; 2 (Suppl. 09) 1-17.
• 12 Karkanis SA, Iakovidis DK, Maroulis DE, Karras DA, Tzivras M. Computer-aided tumor detection in endoscopic video using color wavelet features. IEEE Trans on Informatics Technology in Biomedicine 2003; 7 (Suppl. 03) 141-151.
• 13 Maroulis DE, Iakovidis DK, Karkanis SA, Karras DA. ColD: a versatile detection system for colorectal lesions in endoscopy video-frames. Computer Methods and Programs in Biomedicine 2003; 70: 151-166.
• 14 Alexandre LA, Casteleiro J, Nobre N. Polyp detection in endoscopic video using svms. In: Proc’s 11th European Conference on Principles and Practice of Knowledge Discovery in Databases Warsaw, Poland ser. Lect. Notes AI J. K. et al, Ed., vol. 4702. Heidelberg; Springer: 2007. pp 358-365.
• 15 Palm C, Lehmann T, Spitzer K. Color texture analysis of moving vocal cords using approaches from statistics and signal theory. In: Braunschweig T, Schellhorn-Neise P, Witte H. editors. Advances in Quantitative Laryngoscopy. University Jena; 2000. pp 49-56.
• 16 Illgner JH, Palm C, Schütz A, Spitzer K, Westhofen M, Lehmann TM. Colour texture analysis for quantitative laryngoscopy. Acta Oto-Laryngologica 2003; 123: 730-734.
• 17 Kage A, Münzenmayer C, Wittenberg T. A knowledge-based system for the computer assisted diagnosis of endoscopic images. In: Tolxdorff T, Braun J, Deserno T, Handels H, Horsch A, Meinzer HP. editors. Bildverarbeitung für die Medizin 2008, Reihe Informatik Aktuell. Heidelberg: Springer; 2008. pp 272-276.
• 18 Münzenmayer C. Color texture analysis in medical applications. Tönning: Der Andere Verlag; 2006
• 19 Chen YQ, Nixon MS, Thomas DW. Statistical geometrical features for texture classification. Pat Rec 1995; 28 (Suppl. 04) 537-552.
• 20 Münzenmayer C, Volk H, Paulus D, Vogt F, Wittenberg T. Statistical Geometrical Features for Texture Analysis and Classification. In: Proc 8th Workshop Farbbildverarbeitung. 2002. pp 87-94.
• 21 Stransky P. Adaptive Texturanalyse in der Bildverarbeitung. Diplomarbeit, Universität ErlangenNürnberg; 1995
• 22 Rui Y, Huang T, Mehrotra S. Content-based image retrieval with relevance feedback in MARS. In: Proc of IEEE International Conference on Image Processing. 1997. pp 815-818.
• 23 Lehmann T, Wein B, Dahmen J, Bredno J, Vogelsang F, Kohnen M. Content-based image retrieval in medical applications: a novel multi-step approach. In: Proc of IS & T / SPIE Conference on Storage and Retrieval for Media Databases. 2000. pp 312-320.
• 24 Rocchio J. Relevance feedback in information retrieval. In: The SMART Retrieval System: Experiments in Automatic Document Processing. Englewood Cliffs; 1971. pp 313-323.