Delineation of Hemorrhagic Mass from CT Volume
- 636 Downloads
Computed tomography (CT) is the preferred imaging modality for diagnosis of hemorrhage. The hematoma appears as hyper intense mass in the image. Computer aided diagnosis assists clinicians for making a better prediction and helps in surgery planning. Computer assistive method based on random walker is proposed for detection and delineation of hemorrhagic mass or hematoma from Computed Tomography (CT) volumes. 20 patients affected by hemorrhage is considered for this study. Each subject’s image has a size of 512 × 512 × 96. Every case has 96 images. In a CT volume each case has 96 slices. Each slice is of 512 × 512. The slice, which contains hematoma mass or ischemic lesion, is selected using one layer autoencoder. 60% of the patient volume is used for training and 40% of the patient volume is used for testing. The training accuracy of auto encoder was 100%, and testing accuracy was 99.5%. After the slices are classified as healthy and non-healthy, k-means clustering was applied on non-healthy slices for localization of hematoma. Random walker algorithm was applied on the localized lesion for delineation of hematoma from CT images. The computer generated output is compared with the manually delineated output with the help of similarity indices. The Dice similarity index and Jaccard coefficient was calculated as 0.768 ± 0.101 and 0.634 ± 0.128 respectively. The proposed algorithm suggests an alternate method for detection of hematoma using CT images.
KeywordsCT Hemorrhagic mass Random walker Dice similarity index
MK Nag would like to acknowledge Council of Scientific and Industrial Research, New Delhi, Senior research fellowship grant (No: 9/81(1296)/17) for financial assistance. All the authors would like to acknowledge EKO diagnostics for clinical inputs and providing the data for accomplishing this study.
- 2.Matesin, M., Loncaric, S., Petravic, D.: A rule-based approach to stroke lesion analysis from CT brain images. In: Proceedings of the 2nd International Symposium on Image and Signal Processing and Analysis ISPA 2001, pp. 219–223 (2001)Google Scholar
- 3.Maldjian, J.A., Chalela, J., Kasner, S.E., Liebeskind, D., Detre, J.A.: Automated CT segmentation and analysis for acute middle cerebral artery stroke. Am. J. Neuroradiol. 22(6), 1050–1055 (2001)Google Scholar
- 7.Chawla, M., Sharma, S., Sivaswamy, J., Kishore, L.T.: A method for automatic detection and classification of stroke from brain CT images. In: Annual International Conference of the IEEE Engineering in Medicine and Biology Society EMBC 2009, pp. 3581–3584 (2009)Google Scholar
- 10.Prakash, K.N.B., Zhou, S., Morgan, T.C., Hanley, D.F., Nowinski, W.L.: Segmentation and quantification of intra-ventricular/cerebral hemorrhage in CT scans by modified distance regularized level set evolution technique. Int. J. Comput. Assist. Radiol. Surg. 7(5), 785–798 (2012)CrossRefGoogle Scholar