Using Block-based Multiparameter Representation to Detect Tumor Features on T2-weighted Brain MRI Images

Summary

Objective : The objective of this paper is to present an analytical method for digitized images to detect tumors or lesions in a medical decision support system.

Method : The authors have developed a simple method of tumor detection using three parameter values: edge (E), gray (G), and contrast (H). The method proposed here first studied the VHD (Visible Human Dataset) input brain feature using EGH parameters that divided the input image into fixed-size blocks (templates). The EGH parameters for the feature blocks were calculated and parameterized to detect the occurrences of abnormalities. These abnormal blocks were then marked for interpretation.

Results : Measurements of the following medical dataset were performed: 1) different time-interval images from the same dataset, 2) different brain disease images from multiple datasets, and 3) multiple slice images from multiple datasets. Our experimental results illustrate the ability of our proposed technique to detect tumor blocks with conceptual simplicity and computational efficiency.

Conclusion : In this paper, we present output examples from our prototype system, comparing detection accuracy and system performance.

Keywords

Decision support system - multiparameter representation - brain tumor detection - image analysis

• References

• 2. Haney SM, Thompson PM, Cloughesy TF, Alger JR, Toga AW. Tracking Tumor Growth Rates in Patients with Malignant Gliomas: A Test of Two Algorithms. AJNR Am J Neuroradiology 2001; 22: 73-82.
• 3. Bailet JW, Abemayor E, Jabour BA, Hawkins RA, Hoh CK, Ward PH. Positron emission tomography: A new precise modality for detection of primary head and neck tumors and assessment of cervical adenopathy. Laryngoscope 1992; 102: 281-288.
• 4. Miller DH, Grossman RI, Reingold SC, McFarland H. The role of magnetic resonance techniques in understanding and managing multiple sclerosis. Brain 1998; 12: 3-24.
• 5. Liem MD, Gzesh DJ, Flanders AE. MRI and angiographic diagnosis of lupus cerebral vasculitis. Neuroradiology 1996; 38: 134-136.
• 6. Hinz M, Pohle R, Shin H, Tonnies KD. Region-based interactive 3D image analysis of structures in medical data by hybrid rendering. In: Proceedings of the SPIE in Visualization, Image-Guided Procedures, and Display, San Diego 2002 4681. 388-395.
• 7. Thamburaj A. Neurology and systemic malignancy. Apollo Hospitals, Chennai, India http://www.thamburaj.com/cns_systemic_malignancy.htm
• 8. Lachmann F, Barillot C. Brain tissue classification from MRI data by means of texture analysis. In: Proceedings of the Medical Imaging VI: Image Processing, Newport Beach, CA 1992 1652. 72-83.
• 9. Krishnan K, Atkins MS. Segmentation of multiple sclerosis lesions in MRI - an image analysis approach. In: Proceedings of the SPIE Conference on Image Processing 1998, San Diego 1998 3338. 1106-1116.
• 10. Gupta R, Undrill P. The use of texture analysis to delineate suspicious masses in mammography. Physics in Medicine and Biology 1995; 40: 835-855.
• 11. Vrooman HA, Rietveld PM, van Dijk P. Semiautomated detection of white matter lesions by contrast optimization and 3D region growing in MR data of the brain. In: RSNA 2001: 87th Scientific Assembly and Annual Meeting of the Radiological Society of North America, 2001
• 12. Bergmann J. Health and clinical management - comparing the clinical outcome of computerized strategies. Findings from the section on health and clinical management. Methods Inf Med 2006; 45 (Suppl. 01) 26-28.