Medical image segmentation using fast discrete curvelet transform and classification methods for MRI brain images

Krishnammal, P. Muthu; Raja, S. Selvakumar

doi:10.1007/s11042-019-08089-9

Cited by 9 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The brightness component I and the infrared image are decomposed by two-dimensional discrete Curvelet transform [ 22 , 23 ]. Their low-frequency coefficients and multiple high-frequency coefficients at different scales and directions are obtained as follows:

where f [ t 1 , t 2 ] is the input of the Cartesian coordinate system,

is the Curvelet function, where D represents discretization, l represents direction, k represents position, and j represents the scale of Curvelet decomposition.…”

Section: Fusion Strategy Of Frame Selection Based On Inter-frame Diff...mentioning

confidence: 99%

Night Vision Anti-Halation Method Based on Infrared and Visible Video Fusion

Guo

Wang

Yang

2022

Sensors

View full text Add to dashboard Cite

In order to address the discontinuity caused by the direct application of the infrared and visible image fusion anti-halation method to a video, an efficient night vision anti-halation method based on video fusion is proposed. The designed frame selection based on inter-frame difference determines the optimal cosine angle threshold by analyzing the relation of cosine angle threshold with nonlinear correlation information entropy and de-frame rate. The proposed time-mark-based adaptive motion compensation constructs the same number of interpolation frames as the redundant frames by taking the retained frame number as a time stamp. At the same time, considering the motion vector of two adjacent retained frames as the benchmark, the adaptive weights are constructed according to the interframe differences between the interpolated frame and the last retained frame, then the motion vector of the interpolated frame is estimated. The experimental results show that the proposed frame selection strategy ensures the maximum safe frame removal under the premise of continuous video content at different vehicle speeds in various halation scenes. The frame numbers and playing duration of the fused video are consistent with that of the original video, and the content of the interpolated frame is highly synchronized with that of the corresponding original frames. The average FPS of video fusion in this work is about six times that in the frame-by-frame fusion, which effectively improves the anti-halation processing efficiency of video fusion.

show abstract

where f [ t 1 , t 2 ] is the input of the Cartesian coordinate system,

is the Curvelet function, where D represents discretization, l represents direction, k represents position, and j represents the scale of Curvelet decomposition.…”

Section: Fusion Strategy Of Frame Selection Based On Inter-frame Diff...mentioning

confidence: 99%

Night Vision Anti-Halation Method Based on Infrared and Visible Video Fusion

Guo

Wang

Yang

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…It was shown that the PNN outperforms the SVM and ANFIS in terms of classification accuracy. Deep CNN features were extracted and an SVM was used for classification in [18]. An ada-boost ensemble neural classifier was used with fast boosting and pre-trained network for brain tumor classification [19].…”

Section: Literature Reviewmentioning

confidence: 99%

Segmentation and classification of brain tumor images using statistical feature extraction and deep neural networks

Joshi¹,

Kumar²,

Chauhan³

2021

IJATEE

View full text Add to dashboard Cite

Cancer cases are increasing worldwide, primarily due to unhealthy lifestyles, poor dietary choices, lack of physical activity, increasing pollution levels and exposure to radiation [1]. Early and accurate diagnosis of brain cancers is critical for saving the life of patients. Brain cancer has one of least survival rates for the next 5-10 years from the time of detection of malignant tumours. The cancer progresses from initially being a benign lesion to becoming a cancerous tumor. Cancer causes severe mental trauma, financial strain and social stigma mainly in developing countries.Brain cancer has one of the highest mortalities among all cancers with very low five-year and ten-year survival rates [2]. *Author for correspondenceThe fact is evident from Figure 1 which depicts the Standardized Mortality Ratio (SMR) for different cancer sub-sites. Thus, early detection and correct diagnosis of brain cancer is mandatory for possible chances of recover. This serves as a fundamental motivation for several researchers to develop techniques which could augment early and accurate detection of brain tumors along with a classification of the type of tumor. Early detection is often hindered due to patients overlooking initial symptoms of the disease such as headaches, muscle twitches, occasional unconsciousness and seizures. This causes a delay in the start of diagnosis, which may prove to be lethal owing to the aggressive nature of progress of malignant brain tumors [3]. Typically, the benign tumors exhibit a clear or sharp boundary with respect to the neighboring regions and have a relatively slower spreading rate compared to the malignant tumors. The malignant tumors are much more invasive and exhibit a blurred boundary or distinction and have a much faster spreading rate. The brain

show abstract