An Adaptive Fuzzy Segmentation Algorithm for Three-Dimensional Magnetic Resonance Images

Using endoanal magnetic resonance imaging, atrophy of the external anal sphincter can be established. This aspect has not been thoroughly investigated using three-dimensional anal endosonography. The purpose of this study was to compare prospectively three-dimensional anal endosonography to magnetic resonance imaging in the detection of atrophy and defects of the external anal sphincter in patients with fecal incontinence. In addition, we compared both techniques for anal sphincter thickness and length measurements. Patients with fecal incontinence underwent three-dimensional anal endosonography and magnetic resonance imaging. Images of both endoluminal techniques were evaluated for atrophy and defects of the external anal sphincter. External anal sphincter atrophy scoring with three-dimensional anal endosonography depended on the distinction of the external anal sphincter and its reflectivity. External anal sphincter atrophy scoring with magnetic resonance imaging depended on the amount of muscle and the presence of fat replacement. Atrophy score was defined as none, moderate, and severe. A defect was defined at anal endosonography by a hypoechogenic zone and at magnetic resonance imaging as a discontinuity of the sphincteric ring and/or scar tissue. Differences between three-dimensional anal endosonography and magnetic resonance imaging for the detection of external anal sphincter atrophy and defects were calculated. In addition, we compared external anal sphincter thickness and length measurements in three-dimensional anal endosonography and magnetic resonance imaging. Eighteen patients were included (median age, 58 years; range, 27-80; 15 women). Three-dimensional anal endosonography and magnetic resonance imaging did not significantly differ for the detection of external anal sphincter atrophy (P = 0.25) and defects (P = 0.38). Three-dimensional anal endosonography demonstrated atrophy in 16 patients, magnetic resonance imaging detected atrophy in 13 patients. Three-dimensional anal endosonography agreed with magnetic resonance imaging in 15 of 18 patients for the detection of external anal sphincter atrophy. Using the grading system, 8 of the 18 patients scored the same grade. Three-dimensional anal endosonography detected seven external anal sphincter defects and magnetic resonance imaging detected ten. Three-dimensional anal endosonography and magnetic resonance imaging agreed on the detection of external anal sphincter defects in 13 of 18 patients. Comparison between three-dimensional anal endosonography and magnetic resonance imaging for sphincter thickness and length measurements showed no statistically significant concordance and had no correlation with external anal sphincter atrophy. This is the first study that shows that three-dimensional anal endosonography can be used for detecting external anal sphincter atrophy. Both endoanal techniques are comparable in detecting atrophy and defects of the external anal sphincter, although there is a substantial difference in grading of external anal sphincter atrophy. Correlation between three-dimensional anal endosonography and magnetic resonance imaging for thickness and length measurements is poor. Inconsistency between the two methods needs to be evaluated further.

In this study, segmentation of Multiple Sclerosis (MS) lesions from synthetic brain MRI images was aimed by using fuzzy clustering algorithms. The performances of fuzzy c-means algorithm and type-2 fuzzy c-means algorithm were compared. After several experiments it was shown that, the type-2 fuzzy c-means algorithm performed better than the standard fuzzy c-means algorithm.

Children with acute lymphoblastic leukemia (ALL) require neurotoxic treatment during critical periods of brain development. Multispectral magnetic resonance imaging (MRI) offers opportunities to characterize the impact of chemotherapy on the developing brain, but this has been constrained by concerns regarding feasibility of obtaining quality MRIs from these critically ill children at a young age. Our goal is to demonstrate a framework for improving the feasibility of non-sedated, multispectral MRI in newly diagnosed ALL patients. Participants were enrolled from August 2023 through February 2026, and included newly diagnosed ALL patients and controls recruited from the community ages 3-10 years old. Participants completed a series of three non-sedated MRI without contrast on a 3T scanner over 12 months. Sequences included anatomical T1-weighted and QALAS sequences for quantitative mapping, diffusion weighted MRI (DWI), MR Spectroscopy (MRS), and resting-state functional MRI (rs-fMRI). A sequence was considered complete if data quality was sufficient for successful image processing. Mixed-effects logistic regression models were used determine if group and study visit were associated with MRI success rates across sequences. The sample included 17 ALL patients and 30 controls, who contributed to 38 and 75 observations, respectively. Of 113 attempted scans, 105 had ≥1 sequence completed (93%). Across assessments, ALL patients were less likely to complete a scan (31 of 38 attempts; raw rate: 82%) relative to controls (73 of 75; raw rate: 96%; model-estimated difference=-14.1%, 95%CI=-27.1%; -1.1%, p=0.033). Baseline success rate was 65% (11 of 17) for ALL patients and 93% (28 of 30) for controls (model-estimated difference=-26.8%, 95%CI=-52.7%; -0.9%, p=0.42); however, nearly all T1w scans in ALL patients were successful at follow-up visits (20 of 21; 95%), with no significant differences between groups (model-estimated difference at follow-up 1=-2.1%, 95%CI=-11.7%; 7.6%; model-estimated difference at follow-up 2=-8.3%, 95%CI=-26.3%; 9.6%). A similar pattern was observed for DWI, MRS and rs-fMRI sequences with relatively high completion rates at follow-up assessments. Non-sedated multispectral MRI is feasible in young children with newly diagnosed ALL, particularly with repeated visits and structured behavioral preparation. These results highlight opportunities to capture the scope and depth of neurodevelopmental changes concurrent with ALL treatment.

Accurate and robust image segmentation was identified as one of the most challenging issues facing PET quantification in oncological imaging. This difficulty is compounded by the low spatial resolution and high noise characteristics of PET images. The fuzzy C-means (FCM) clustering algorithm was largely used in various medical image segmentation approaches. However, the algorithm is sensitive to both noise and intensity heterogeneity since it does not take into account spatial contextual information. To overcome this limitation, a new fuzzy segmentation technique adapted to typical noisy and low resolution oncological PET data is proposed. PET images smoothed using a nonlinear anisotropic diffusion filter are added as a second input to the proposed FCM algorithm to incorporate spatial information (FCM-S). In addition, a methodology was developed to integrate the a trous wavelet transform in the standard FCM algorithm (FCM-SW) to allow handling of heterogeneous lesions' uptake. The algorithm was applied to the simulated data of the NCAT phantom, incorporating heterogeneous lesions in the lung and clinical PET/CT images of 21 patients presenting with histologically proven nonsmall-cell lung cancer (NSCLC) and 7 patients presenting with laryngeal squamous cell carcinoma (LSCC) to assess its performance for segmenting tumors with arbitrary size, shape, and tracer uptake. For NSCLC patients, the maximal tumor diameters measured from the macroscopic examination of the surgical specimen served as the ground truth for comparison with the maximum diameter estimated by the segmentation technique, whereas for LSCC patients, the 3D macroscopic tumor volume was considered as the ground truth for comparison with the corresponding PET-based volume. The proposed algorithm was also compared to the classical FCM segmentation technique. There is a good correlation (R2 = 0.942) between the actual maximal diameter of primary NSCLC tumors estimated using the proposed PET segmentation procedure and those measured from the macroscopic examination, and the regression line agreed well with the line of identity (slope = 1.08) for the group analysis of the clinical data. The standard FCM algorithm seems to underestimate actual maximal diameters of the clinical data, resulting in a mean error of -4.6 mm (relative error of -10.8 +/- 23.1%) for all data sets. The mean error of maximal diameter estimation was reduced to 0.1 mm (0.9 +/- 14.4%) using the proposed FCM-SW algorithm. Likewise, the mean relative error on the estimated volume for LSCC patients was reduced from 21.7 +/- 22.0% for FCM to 8.6 +/- 28.3% using the proposed FCM-SW technique. A novel unsupervised PET image segmentation technique that allows the quantification of lesions in the presence of heterogeneity of tracer uptake was developed and evaluated. The technique is being further refined and assessed in clinical setting to delineate treatment volumes for the purpose of PET-guided radiation therapy treatment planning but could find other applications in clinical oncology such as the assessment of response to treatment.

Since the phenomena of intensity inhomogeneity in MR images are prominent and adversely affect quantitative image analysis .In this paper ,we propose a novel magnetic resonance (MR) image segmentation approach based on the kernel graph cuts technique .Because of automatic multiregion segmentation and global energy minimization ,the kernel graph cuts method can be applied to many kinds of images segmentation ,such as MR images and so on . To reduce or eliminate intensity inhomogeneity in MR images ,we add the intensity inhomogeneity correction step which is based on fuzzy c-means (FCM) algorithm before the segment procedure .Firstly , the real MR image data obtained after bias corrected by FCM algorithm .Secondly ,we segment the real MR image data by kernel graph cuts method .Experiments show that the kernel graph cuts method with intensity inhomogeneity correction have a better segment result in accuracy and over-segmentation .

The clustering methods based on Fuzzy C-Means (FCM) are frequently used in image-segmentation. But the standard FCM algorithm has some defects, especially ignoring the pixel spatial information's influence on the classification result. For the sake of a more reasonable objective function, an improved FCM algorithm is proposed in this paper, which uses spatial information and S-function to determine the weight coefficients of the objective function. Experimental results show that the proposed algorithm has better performance than the standard FCM algorithm.

Fuzzy c-means (FCM) clustering algorithm has been widely used in automated image segmentation. However, the standard FCM algorithm is sensitive to noise because of taking no into account the gray and spatial information of pixel. The paper proposes an improved FCM algorithm for image segmentation. We use the degree of gray similarity and distribution statistics of the neighbor pixels to form a new membership function for clustering. Not only it is effective to remove the noise spots and reduce the spurious blobs, but also it is ease to correct the misclassified pixels. Experimental results on three types of image indicate that the propose algorithm is more accurate and robust than the standard FCM algorithm

Image segmentation is a classic problem in computer image comprehension and related fields. Up to now, there are not any general and valid partition methods which could satisfy different purposes, especially for medical images such as magnetic resonance images, which often corrupted by multiple imaging artifacts, for example intensity inhomogeneity, noise and partial volume effects. In this paper, we propose an improved fuzzy c-means image segmentation algorithm with more accurate results and faster computation. Considering two voxels with the same intensity belonging to the same tissue, we use q intensity levels instead of n intensity values in the objective function of the fuzzy c-means algorithm, which makes the algorithm clusters much faster since q is much smaller than n. Furthermore, a gain field is incorporate in the objective function to compensate for the inhomogeneity. In addition, we use c-means clustering algorithm to initialize the centroids. This can further accelerate the clustering. The test results show that the proposed algorithm not only gives more accurate results but also makes the computation faster.

The change in osteosarcoma tumor volume after preoperative adjuvant chemotherapy and its relationship to the histopathologic response was investigated using various reproducible volumetric methods. Tumor volume was measured before and after chemotherapy in 41 patients with osteosarcoma using an ellipsoid formula in plain radiography and magnetic resonance imaging and three-dimensional magnetic resonance imaging measurement. Based on intraobserver and interobserver variability for the volumetric measurements of each method, three-dimensional magnetic resonance imaging measurement was the most reproducible. In three-dimensional magnetic resonance measurements, the correlation of the histopathologic response with absolute and relative total tumor volume changes and extraosseous volume change were significant. The good responder group showed a greater reduction in tumor volume after chemotherapy, although there was no significant difference in pretreatment tumor volume between the good and poor responder groups. The group with a decreased or stable tumor volume represented a good histopathologic response with a sensitivity of 85%, specificity of 76%, and positive predictive value of 88%. The change in tumor volume of osteosarcoma measured by three-dimensional magnetic resonance imaging could predict histopathologic response after three cycles of neoadjuvant chemotherapy.

Computer based diagnosis of Alzheimer's disease can be performed by dint of the analysis of the functional and structural changes in the brain. Multispectral image fusion deliberates upon fusion of the complementary information while discarding the surplus information to achieve a solitary image which encloses both spatial and spectral details. This paper presents a Non-Sub-sampled Contourlet Transform (NSCT) based multispectral image fusion model for computer-aided diagnosis of Alzheimer's disease. The proposed fusion methodology involves color transformation of the input multispectral image. The multispectral image in YIQ color space is decomposed using NSCT followed by dimensionality reduction using modified Principal Component Analysis algorithm on the low frequency coefficients. Further, the high frequency coefficients are enhanced using non-linear enhancement function. Two different fusion rules are then applied to the low-pass and high-pass sub-bands: Phase congruency is applied to low frequency coefficients and a combination of directive contrast and normalized Shannon entropy is applied to high frequency coefficients. The superiority of the fusion response is depicted by the comparisons made with the other state-of-the-art fusion approaches (in terms of various fusion metrics).

To verify the hypothesis that intravenous frusemide reduces endolymphatic hydrops, as evaluated by three-dimensional fluid-attenuated inversion recovery magnetic resonance imaging following intratympanic gadolinium administration. The study comprised 12 patients (7 females and 5 males, aged 19-74 years) with Ménière's disease. Disease duration ranged from 0.5 to 8 years, with a frequency of 0.5 to 6 vertigo spells per month, as calculated in the last 6 months. Three-dimensional fluid-attenuated inversion recovery magnetic resonance imaging was performed 24 hours after intratympanic injection of gadobutrol diluted eight-fold. Frusemide 20 mg was given intravenously immediately after imaging. Magnetic resonance imaging was repeated after 1 hour, using the same parameters and sequence. All patients showed enhancement defects, indicating endolymphatic hydrops of variable degrees. No modifications occurred at the second magnetic resonance imaging performed 1 hour after frusemide administration. There was no evidence of endolymphatic hydrops modification 1 hour after intravenously administered frusemide. Therefore, loop diuretics in Ménière's disease, which are today used on an empirical basis, must be reconsidered. Implications of these outcomes are discussed and related to the role of endolymphatic hydrops in the development of Ménière's disease.

Three-Dimensional Volumetric Magnetic Resonance Imaging Analysis of Syringomyelia Evolution After Posterior Fossa Decompression for Chiari Malformation Type1

This study quantified the error in anterior cruciate ligament (ACL) insertion site location and area estimated from three-dimensional (3D) isotropic magnetic resonance imaging (MRI) by comparing to native insertion sites determined via 3D laser scanning. Isotropic 3D DESS MRI was acquired from twelve fresh-frozen, ACL-intact cadaver knees. ACL insertion sites were manually outlined in each MRI slice, and the resulting contours combined to determine the 3D insertion site shape. Specimens were then disarticulated, and the boundaries of the ACL insertion sites were digitized using a high-accuracy laser scanner. MRI and laser scan insertion sites were co-registered to determine the percent overlapping area and difference in insertion centroid location. Femoral ACL insertion site area averaged 112.7±17.9mm2 from MRI and 109.7±10.9mm2 from laser scan (p=0.345). Tibial insertion area was 134.7±22.9mm2 from MRI and 135.2±15.1mm2 from laser scan (p=0.881). Percentages of overlapping area between modalities were 82.2±10.2% for femurs and 81.0±9.0% for tibias. The root-mean-square differences for ACL insertion site centroids were 1.87mm for femurs and 2.49mm for tibias. The MRI-estimated ACL insertion site centroids were biased on average 0.6±1.6mm proximally and 0.3±1.9mm posteriorly for femurs, and 0.3±1.1mm laterally and 0.5±1.5mm anteriorly for tibias. Errors in ACL insertion site location and area estimated from 3D-MRI were determined via comparison with a high-accuracy 3D laser scanning. Results indicate that MRI can provide estimates of ACL insertion site area and centroid location with clinically applicable accuracy. MRI-based assessment can provide a reliable estimate of the native ACL anatomy, which can be helpful for surgical planning as well as assessment of graft tunnel placement.

Prostate cancer is a leading cause of cancer death for men in the United States. There is currently no widely adopted accurate noninvasive method for localizing prostate cancer using imaging. If such as technique were available it could be used to guide biopsy, radiotheraphy and surgery. However, current imaging techniques are limited due to inability to detect cancers, intensity changes related to non-malignant pathologies and interobserver variability. Recently, multispectral magnetic resonance imaging (MRI) has emerged as a promising noninvasive method for the localization of prostate cancer alternative to transrectal ultrasound (TRUS). This paper develops automated methods for prostate cancer localization with conditional random fields using multispectral MRI. We propose to combine cost-sensitive Support Vector Machines with Conditional Random Fields and show that this method results in higher accuracy of localization compared to other common methods. Our results also show that multispectral modality images helps to increase the accuracy of prostate cancer localization. Using multispectral MR images, we demonstrate the effectiveness of each algorithm by testing them on real data sets and compare them to recently proposed SVMstruct and Conditional Random Fields.

Regarding “Noncontrast three-dimensional magnetic resonance imaging vs lymphoscintigraphy in the evaluation of lymph circulation disorders: A comparative study”