Abstract:Image processing by segmentation technique is an important phase in medical imaging such as MRI. Its objective is to analyze the different tissues in human body. In research area, Fuzzy set is one of the most successful techniques that guarantees a robust classification. Spatial FCM (SFCM); one of the fuzzy c-means variants; considers spatial information to deal with the noisy images. To reduce this iterative algorithm’s execution time, a hard SIMD architecture has been planted named the Graphical Processing U… Show more
“…Highlighting SFCM's robustness across different types of noise, the study underscores the parallel implementations' effectiveness in noise handling and processing speed, contributing valuable insights for medical image segmentation techniques. [16] The paper presents a Modified Fuzzy C-Means Algorithm for Bias Field Estimation and MRI Data Segmentation, which effectively addresses intensity inhomogeneities in MRI images by modifying the goal function and incorporating a neighborhood effect. This approach yields superior segmentation performance compared to FCM segmentation, with faster convergence, particularly in noisy images, as verified through comparisons with the EM algorithm and typical FCM segmentation.…”
Medical image segmentation plays a crucial role in various clinical applications, including disease diagnosis and treatment planning. In the context of spine imaging, accurate segmentation is essential for precise analysis and intervention. This study presents a comparative analysis of two prominent segmentation algorithms: fuzzy c-means (FCM) and region growing, applied to spine image segmentation. The dataset consists of spine images obtained from medical imaging modalities, preprocessed to enhance clarity and remove noise. Both FCM and region-growing algorithms are implemented with appropriate parameter settings and evaluated using quantitative metrics such as the Dice similarity coefficient, sensitivity, and specificity. Additionally, qualitative assessments are conducted through visual inspection of segmented images. The results reveal distinct performance characteristics of each algorithm, highlighting their respective strengths and weaknesses in spine image segmentation tasks. Through comprehensive analysis and discussion, this study provides valuable insights into the effectiveness of FCM and region-growing algorithms, aiding clinicians and researchers in selecting suitable segmentation approaches for spine imaging applications.
“…Highlighting SFCM's robustness across different types of noise, the study underscores the parallel implementations' effectiveness in noise handling and processing speed, contributing valuable insights for medical image segmentation techniques. [16] The paper presents a Modified Fuzzy C-Means Algorithm for Bias Field Estimation and MRI Data Segmentation, which effectively addresses intensity inhomogeneities in MRI images by modifying the goal function and incorporating a neighborhood effect. This approach yields superior segmentation performance compared to FCM segmentation, with faster convergence, particularly in noisy images, as verified through comparisons with the EM algorithm and typical FCM segmentation.…”
Medical image segmentation plays a crucial role in various clinical applications, including disease diagnosis and treatment planning. In the context of spine imaging, accurate segmentation is essential for precise analysis and intervention. This study presents a comparative analysis of two prominent segmentation algorithms: fuzzy c-means (FCM) and region growing, applied to spine image segmentation. The dataset consists of spine images obtained from medical imaging modalities, preprocessed to enhance clarity and remove noise. Both FCM and region-growing algorithms are implemented with appropriate parameter settings and evaluated using quantitative metrics such as the Dice similarity coefficient, sensitivity, and specificity. Additionally, qualitative assessments are conducted through visual inspection of segmented images. The results reveal distinct performance characteristics of each algorithm, highlighting their respective strengths and weaknesses in spine image segmentation tasks. Through comprehensive analysis and discussion, this study provides valuable insights into the effectiveness of FCM and region-growing algorithms, aiding clinicians and researchers in selecting suitable segmentation approaches for spine imaging applications.
“…Spatial Kernel Fuzzy C Means is one of the Fuzzy C Means variants which considers spatial information to handle the images with artifacts/noise. Further, to reduce the execution time of the iterative algorithm a parallel implementation of Spatial Kernel Fuzzy C Means (SKFCM) over the GPU is implemented [30]. This parallel implementation of SKFCM over GPU illustrated a significant decrease in terms of running time of the proposed algorithm.…”
Computational Intelligence (CI) techniques are used in Microarray image processing which is useful for gene profiling in the medical field, drug discovery and industrial research. The paper discusses microarray image processing technique specifically spot segmentation using clustering techniques. This interdisciplinary approach helps in analyzing biological sequences and genome content to identify the function of macro molecules. The fast-evolving techniques of CI with Fuzzy Intelligence (FI) paradigms helps in distinguishing gene information, protein expression calculation, molecular information discovery and genetic study from segmented spots of microarray images. The clustering methods proposed in this paper provide support in analyzing characteristics of data point which belong to particular cluster. The limitation of evolutionary Fuzzy C-Means (FCM) method is discussed in the paper. A significant approach is discussed to overcome above said limitations with two variants of FCM being proposed -Robust Spatial Kernel FCM (RSKFCM) and Generalized Spatial Kernel FCM (GSKFCM). The iterative approach converges the spots of microarray image to the aligned membership values of neighborhood which leads to clustering of spots. The discussed method uses Gaussian kernel function which helps in reducing noise impact amicably.
“…Early image segmentation techniques, such as statistical shape [1][2], level set [3][4], fuzzy clustering [5][6]. Each approach has its own unique set of parameters that can be fine-tuned to meet the specific needs of different medical image scenarios.…”
Accurate segmentation of organs and lesions from medical images holds paramount importance in aiding physicians with diagnosis and monitor diseases. At present, the widespread application of deeplearning in medical image segmentation is primarily attributed to its exceptional feature extraction capability. Nonetheless, due to blurred target boundary, wide range of changes and chaotic background, the segmentation of medical images is still faced with great challenges. To address these issues, we present a multi-level feature integration network (MFI-Net) with SE-Res2Conv encoder for jaw cyst segmentation. Specifically, we replace the original convolution operation with SE-Res2Conv to better maintain model's capacity for extracting features across multiple scales. Then, a novel context extractor module including multi-scale pooling block (MPB) and position attention module (PAM), which aims to generate more discriminative features. Finally, a multi-level feature integration block (MFIB) is implemented within the decoder to efficiently integrate low-level detail features with high-level semantic features. Numerous experiments were conducted on both the original and augmented datasets of jaw cyst to demonstrate the advantages of MFI-Net, with results consistently superior to all competitors. The Dice, IoU and Jaccard values of our method reached 93.06%, 93.47%, 87.06% in the original database and 91.25%, 91.94%, 84.06% in the augmented database. Furthermore, the computational efficiency of MFI-Net is impressive, with a speed of 106 FPS at the input size of 3×256×256 on a NVIDIA RTX6000 graphics card.
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.