Abstract
In computed tomography imaging, brain hematoma (BH) segmentation is a very challenging process due to a high variability of BH morphology, low contrast and noisy images. Because of this, BH segmentation is an open problem. In order to approach this problem, we propose an automatic technique, named nonlinear technique (NLT), based on a thresholding method, noise suppression filters, intelligent operators, a clustering strategy and a binary morphological operator. NLT performance is assessed by Jaccard’s similarity index (JSI) used to compare automatic and manual BH segmentations. This assessment allows developing a tuning process for establishing the optimal parameters of each of the algorithms which constitute the proposed technique. The results indicate a good correlation, based on JSI, between the manual segmentations and the automatic ones. Finally, the BH volume is generated considering the automatic segmentation. This volume indicates whether or not the patient must undergo a surgical intervention for BH treatment.
Highlights
Brain hematomas (BH) can be classified in several ways
The Generalized Hough Transform (GHT) allowed the automatic identification of the “seed points” for correct Region growing (RG) initialization
The Jaccard's index of similarity (JIS) value reported in this paper suggests that the nonlinear technique (NLT) has an excellent performance
Summary
Brain hematomas (BH) can be classified in several ways. For example, a very simple brain hematoma classification is presented in Figure 1 [1]. Li-Hong and Wu [3] report lesion image detection, based on k-means segmentation, in magnetic resonance imaging (MRI) They point at a very high score linked to BH segmentation. Roy et al [4] show an automatic technique for segmentation of brain hemorrhages using thresholding method, wavelet transform, convex hull technique and gamma transform in MRI. Their results are promising since they get a good similarity index value. An automatic technique based on convolutional neural networks [5] is reported They apply deep learning for the BH segmentation in MSCT and MRI images and they report a mean Dice score (Ds) of 0.90. The contributions are a) Incorporation of borders detector based on a gradient filter. b) Use of Generalized Hough Transform in order to detect the coordinates of seed points. c) Precise segmentation of epidural, intraparenchymatous and subdural hematomas
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
