Purpose: Edge detection improves image readability and plays an important role in images preprocessing aimed to their segmentation and automatic recognition of their contents. The purpose of this study was to describe methods of edge detection in magnetic resonance images, with the emphasis on the use of discrete wavelet transform (DWT) combined with Gabor wavelets. Methods: Modulus maxima method by Mallat S (A Wavelet Tour of Signal Processing. Academic Press, 1998), provides the method for edge detection using wavelet transform. This method is based on finding local maxima of horizontal and vertical wavelet coefficients in the first level of wavelet decomposition because it is supposed that this level represents edges. This method was tested with various wavelet functions both on simulated and real medical images. A multiresolution approach using undecimated wavelet transform is also employed which allows the low‐low (LL), low‐high (LH), high‐low (HL), and high‐high (HH) sub‐bands to remain at full size. A simple peak finding algorithm is used to determine the peaks out of array of these texture features. Results: Using wavelet transform method, the decomposition was performed up to two levels. Gabor filters are then applied to the wavelet approximations at all levels to obtain the characteristic texture features such as entropy, second to fourth central moments and coefficient of variation. High values of the second central variance and fourth central variance signify images in which regions can be clearly differentiated. The corresponding filter outputs are compared to obtain an image containing minimum pixel values. Conclusion: A complex wavelet function could help to improve results of edge detection in real images. A comparison of basic edge detection methods including simple gradient operators and Gabor wavelets, and their combination with wavelet transform was presented. Mathematical principals were studied, as well as application of these methods.
Purpose: To investigate the outcome predictive power of tumor volume measured by serial MR imaging (MRI) of cervical cancer, including the sensitivity and specificity to identify patients at risk of local failure. Method and Materials: Seventy‐nine patients with cervical cancer stages IB2‐IVA, treated with radiation/chemotherapy (RT/CT), underwent serial MRI: MRI 1(pre‐RT), MRI 2(at 20–25 Gy/2 weeks), MRI 3(at 40–50 Gy/4 weeks), and MRI 4(at 1–2 months post‐RT). Mean follow up was 6.2 (0.2–9.4) years. Tumor volumes (V1,V2,V3,V4) and regression ratios (V2/V1,V3/V1,V4/V1) were measured by MRI 3D volumetry, and correlated with local tumor‐control and disease‐free survival using Mann‐Whitney rank‐sum test. Results: The volume data collected in this study were analyzed and the predictive power in terms of p‐value to discriminate local tumor‐control and disease‐free survival was computed. The absolute tumor volumes (V2,V3,V4) and the regression ratios (V2/V1,V3/V1,V4/V1) strongly correlated with local tumor‐control (p<0.001). These parameters also correlated with disease‐free survival, but only the last measurement (MRI 4) showed significant predictive value (p=0.02). Four methods had been developed to identify patients at risk for tumor recurrence (sensitivity 61%–100% and specificity 87%–100%). The most powerful method is based on the volume regression measured in MRI 3 and MRI 4 (V3/V1 >20% and V4/V1 >10%), which have a sensitivity of 89% and a specificity of 100%. Local failure can also be predicted as early as 2–3 weeks (MRI 2), the method of V1 >40 cc and V2/V1 >75% shows a sensitivity of 61% and a specificity of 93%. Conclusion: MRI‐based volumetric tumor measurement provides important predictive information about tumor response to the ongoing RT/CT. The methods developed in this study demonstrate a high specificity (87%–100%) for patients at risk of local failure based on long‐term follow‐up. These methods may classify patients who require more aggressive therapeutic intervention.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.