Automatic Detection and Segmentation of Kidneys in Magnetic Resonance Images Using Image Processing Techniques

Surgical robots are gaining increasing popularity because of their capability to improve the precision of pedicle screw placement. However, current surgical robots rely on unimodal computed tomography (CT) images as baseline images, limiting their visualization to vertebral bone structures and excluding soft tissue structures such as intervertebral discs and nerves. This inherent limitation significantly restricts the applicability of surgical robots. To address this issue and further enhance the safety and accuracy of robot-assisted pedicle screw placement, this study will develop a software system for surgical robots based on multimodal image fusion. Such a system can extend the application range of surgical robots, such as surgical channel establishment, nerve decompression, and other related operations. Initially, imaging data of the patients included in the study are collected. Professional workstations are employed to establish, train, validate, and optimize algorithms for vertebral bone segmentation in CT and magnetic resonance (MR) images, intervertebral disc segmentation in MR images, nerve segmentation in MR images, and registration fusion of CT and MR images. Subsequently, a spine application model containing independent modules for vertebrae, intervertebral discs, and nerves is constructed, and a software system for surgical robots based on multimodal image fusion is designed. Finally, the software system is clinically validated. We will develop a software system based on multimodal image fusion for surgical robots, which can be applied to surgical access establishment, nerve decompression, and other operations not only for robot-assisted nail placement. The development of this software system is important. First, it can improve the accuracy of pedicle screw placement, percutaneous vertebroplasty, percutaneous kyphoplasty, and other surgeries. Second, it can reduce the number of fluoroscopies, shorten the operation time, and reduce surgical complications. In addition, it would be helpful to expand the application range of surgical robots by providing key imaging data for surgical robots to realize surgical channel establishment, nerve decompression, and other operations.

The brain is considered a main important part of human body as it participate to control all the activities of human. Under some unhealthy conditions the abnormal and uncontrolled growth of tissue may take place which is unnatural process. This kind of process taking place in human brain is referred as “brain tumor”. The brain tumor may be of cancerous (malignant) or may be of non-cancerous (Benign) and its detection is a very much important to reduced the death rate of humans suffering from tumor. The detection of brain tumor can be performed by using various image processing techniques like brain magnetic resonance imaging (MRI), Computed Tomography (CT), Electroencephalography (EEG), Positron Emission Tomography (PET), Magneto Encephalography (MEG) etc. Among these techniques the brain MRI is widely adopted in the world due to its significant features. But to detect tumor in the brain MRI, the processes like preprocessing, segmentation and classification are must. This paper deals with the various aspects of the brain tumor detection. The paper discusses the significant researches which are meant for brain tumor detection through MRI quality enhancement, MRI segmentation and MRI classification (as cancerous or not). The outcome of the paper discussed that there were no proper researches are performed to detect the brain tumor, focused on good quality of image, less researches on segmentation and classification of brain tumor. Finally the paper gives the future research scope to overcome the addressed research gap.

In this paper, a new method is proposed to decrease sensitiveness to motion noise and uncertainty in magnetic resonance imaging (MRI) segmentation especially when only one brain image is available. The method is approached with considering spatial neighborhood information by fusing the information of pixels with their neighbors with Dempster–Shafer (DS) theory. The basic probability assignment (BPA) of each single hypothesis is obtained from the membership function of applying fuzzy c-means (FCM) clustering to the gray levels of the MRI. Then multiple hypotheses are generated according to the single hypothesis. Then we update the objective pixel’s BPA by fusing the BPA of the objective pixel and those of its neighbors to get the final result. Some examples in MRI segmentation are demonstrated at the end of the paper, in which our method is compared with some previous methods. The results show that the proposed method is more effective than other methods in motion-blurred MRI segmentation.

Brain tumor segmentation in Magnetic Resonance Imaging (MRI) scans provides vital information to radiologists in the diagnosis and staging of disease. However, these MRI scans are often corrupted with noise during its acquisition. Traditional approaches to this problem employ denoising which leads, in general, to edge smoothing and development of artifacts in MRI slices, thereby affecting tumor segmentation performance. In this paper, we employed graph signal processing (GSP) theory to first segment tumor core in each MRI slice using graph Laplacian followed by edge-aware denoising which is performed in synergy. The paper aims to present a novel technique to tackle the two problems of segmentation and denoising both under the GSP framework. The experimental results demonstrated on simulated and clinical brain MRI datasets, show highly competitive performance both in terms of tumor core segmentation under Dice and Sensitivity measures, and in terms of edge-aware denoising under PSNR and SSIM measures.

Adolescent growth provides a unique opportunity for the growing body to adapt to external stimuli. A positive association between site-specific mechanical loading and increases in regional bone mineral content (BMC) during adolescence is established. Mechanical loads associated with middle-distance running expose the skeleton to a combination of compressive ground reaction forces and muscular contraction. Previous studies concerning musculoskeletal health in active adolescents are largely limited to planar, two-dimensional measures of bone mineral status, using Dual X-ray Absorptiometry (DXA). Intrinsic bone material properties are accurately measured using DXA. However, the interaction between bone material and structural properties that reflects the mechanical integrity of bone require a combination of imaging modalities. Magnetic Resonance Imaging (MRI) provides a three-dimensional geometric and biomechanical assessment of bone. When MRI is integrated with DXA technology, an effective non-invasive method of assessing in vivo bone strength is achieved. The impact of high training volumes on musculoskeletal development of male and female adolescent athletes engaged in repetitive, high magnitude mechanical loading has not been investigated. Specifically, differences in total body and regional bone mineral, bone and muscle geometry, bone biomechanical indices and bone strength at differentially-loaded skeletal sites have not been compared between adolescent middle-distance runners and age- and gender-matched non-athletic controls.;Objectives: (i) to investigate the effects of intense sports participation involving mechanical loading patterns on bone mineral, bone and muscle geometry, biomechanical indices and estimated regional bone strength between elite adolescent male and female middle-distance runners and age- and gender-matched controls (ii) to examine factors predictive of total body BMC, distal tibial bone geometry, distal tibial bone strength, and Hip Strength Analysis (HSA)- derived indicators of bone strength at the femoral neck. Methods: Four groups of 20 adolescents were comprised of male (mean (SD) age 16.8 REPLACE2 0.6 yr, physical activity 14.1 REPLACE2 5.7 hr.wk-1) and female (age 16 REPLACE2 1.7 yr, physical activity 8.9 REPLACE2 2.1 hr.wk-1) middle-distance runners, and male (16.4 REPLACE2 0.7 yr, physical activity 2.2 REPLACE2 0.7 hr.wk-1) and female (age 16 REPLACE2 1.8 yr, physical activity 2.0 REPLACE2 0.07 hr.wk-1) controls. Total body and regional BMC were calculated using DXA. Distal tibial bone and muscle cross-sectional areas (CSA) were assessed using MRI. To calculate distal tibial bone strength index (BSI), a region of interest representing 10% of the mid distal tibia was analysed for DXA-derived bone mineral and was combined with bone geometry and biomechanical properties from MRI assessments. Calculations for femoral neck strength were acquired from DXA-derived HSA software. Results: No differences were found between male athletes and controls for unadjusted BMC at total body or regional sites. After covarying for fat mass (kg), male athletes displayed greater BMC at the lumbar spine (p = 0.001), dominant proximal femur (p = 0.001) and dominant leg (p = 0.03) than male controls. No differences were found in distal tibial bone geometry, bone strength at the distal tibia or HSA-derived indicators of bone strength at the femoral neck between male athletes and controls.;Lean tissue mass and fat mass were the strongest predictors of total body BMC (R2 = 0.71), total muscle CSA explained 43.5% of variance in BSI at the distal tibia, and femur length and neck of femur CSA explained 33.4% of variance at the femoral neck. In females, athletes displayed greater unadjusted BMC at the proximal femur (+3.9 REPLACE21.4 g, p = 0.01), dominant femoral neck (+0.5 REPLACE2 0.12 g, p = 0.01) and dominant tibia (+4.1 REPLACE2 2.1 g, p = 0.05) than female controls. After covarying for fat mass (kg), female athletes displayed greater (p = 0.001) total body, dominant proximal femur and dominant leg BMC than female controls. Female athletes also showed greater distal tibial cortical CSA (+30.9 REPLACE2 9.5 mm2, p = 0.003), total muscle (+240.2 REPLACE2 86.4 mm2, p = 0.03) and extensor muscle (+46.9 REPLACE219.5 mm2, p = 0.02) CSA, smaller medullary cavity (-32.3 REPLACE2 14.7 mm2, p = 0.03) CSA and greater BSI at the distal tibia (+28037 REPLACE2 8214.7 g/cm3.mm4, p = 0.002) than female controls. Lean tissue mass and fat mass were the strongest predictors of total body BMC (R2 = 65), hours of physical weekly activity and total muscle CSA explained 58.3% of the variance of distal tibial BSI, and neck of femur CSA accounted for 64.6% of the variance in a marker of femoral neck HSA. Conclusion: High training loads are associated with positive musculoskeletal outcomes in adolescent middle-distance runners compared to non-athletic controls. Exposure to similar high training loads may advantage female adolescent athletes, more than male adolescent athletes compared with less active peers in bone strength at the distal tibia.

Bone segmentation in magnetic resonance imaging (MRI) is crucial for clinical and research applications, including diagnosis, surgical planning, and treatment monitoring. However, it remains challenging due to anatomical variability and complex bone morphology. Manual segmentation is time-consuming and operator-dependent, fostering interest in automated methods. This study proposes an automated segmentation method based on a 3D U-Net convolutional neural network to segment the femur, tibia, and patella from low-field MRI scans. Low-field MRI offers advantages in cost, patient comfort, and accessibility but presents challenges related to lower signal quality. Our method achieved a Dice Similarity Coefficient (DSC) of 0.9838, Intersection over Union (IoU) of 0.9682, and Average Hausdorff Distance (AHD) of 0.0223, with an inference time of approximately 3.96 s per volume on a GPU. Although post-processing had minimal impact on metrics, it significantly enhanced the visual smoothness of bone surfaces, which is crucial for clinical use. The final segmentations enabled the creation of clean, 3D-printable bone models, beneficial for preoperative planning. These results demonstrate that the model achieves accurate segmentation with a high degree of overlap compared to manually segmented reference data. This accuracy results from meticulous fine-tuning of the network, along with the application of advanced data augmentation and post-processing techniques.

A Fuzzy C-Means (FCM)-Based Approach for Computerized Segmentation of Breast Lesions in Dynamic Contrast-Enhanced MR Images 1

Accurate and fast segmentation of magnetic resonance (MR) images with volumetric brain formations, such as glioblastomas and meningiomas, helps plan surgical and radiation treatment, increase the safety and radicality of surgical intervention, which in turn allows to increase the overall life expectancy of patients and the disease-free period. It is required for the development and evaluation of the effectiveness of a deep convolutional neural network with transmission connections for automatic segmentation of volumetric brain formations (meningiomas and glioblastomas) on postoperative MR images, as well as analysis of its accuracy in comparison with manual expert segmentation and existing methods. Material and methods . The paper considers the creation of an architecture inspired by the SegResNet model, training on BraTS2024-GLI and BraTS2024-MEN-RT, describes a method for compiling a training sample that reduces class imbalance, and analyzes the results in comparison with participants in the BraTS 2024 competition. Results and discussion . The developed model was trained and tested on two datasets of postoperative images of glioblastoma and meningioma. Several metrics are analyzed to compare the model with the methods described in the literature, as well as to evaluate it in the context of the variability of manual segmentation by different experts. The model achieves a Sorensen coefficient 0.8299 for meningioma segmentation and 0.7028 for glioblastoma contrast-accumulating region segmentation. In addition, the segmentation of the model provides an accurate estimate of the volume of the tumor area, as evidenced by the high values of the coefficient of intra-class correlation – 0.9661 for meningioma and 0.8339 for glioblastoma. Overall, the developed model requires fewer resources for learning and getting results. Conclusions. Model performs segmentation at least at the expert level, but with significantly less variability, especially when assessing the volume of the tumor after surgical treatment.

In this paper, various medical software tools, which have been developed for the manual, semi-automatic or fully-automatic segmentation of magnetic resonance (MR) images, and some features of these software tools are presented and discussed. MR imaging is one of the medical imaging modalities which are frequently preferred by the clinicians and surgeons. Segmentation of the MR images in clinical researches and in clinical engineering-based studies is emerging as a considerable requirement for the analysis of the disease images and the diseases. Medical software tools have been developed to meet this need and to provide facilities for the clinicians, surgeons and researchers in computer-aided research projects they conduct. Currently available MR image segmentation tools have many differences when considering criteria such as design, graphical-user interface and functions they provide. In this short review study, we briefly summarized 10 different MR image segmentation software tools highlighted in clinical researches and engineering studies and these software tools have been introduced.

Recent retrospective studies have proposed a high correlation between atrophy of swallowing muscles, age, severity of dysphagia and aspiration status based on computed tomography (CT). However, ionizing radiation poses an ethical barrier to research in prospective non-patient populations. Hence, there is a need to prove the efficacy of techniques that rely on noninvasive methods and produce high-resolution soft tissue images such as magnetic resonance imaging (MRI). The objective of this study was therefore to compare the segmentation results of swallowing muscles using CT and MRI. Retrospective study of 21 patients (median age: 46.6; gender: 11 female) who underwent CT and MRI of the head and neck region within a time frame of less than 50 days because of suspected head and neck cancer using contrast agent. CT and MR images were segmented by two blinded readers using Medical Imaging Toolkit (MITK) and both modalities were tested (with the equivalence test) regarding the segmented muscle volumes. Adjustment for multiple testing was performed using the Bonferroni test and the potential time effect of the muscle volumes and the time interval between the modalities was assessed by a spearman correlation. The study was approved by the local ethics committee. The median volumes for each muscle belly of the digastric muscle derived from CT were 3051 mm3 (left) and 2969 mm3 (right), and from MRI they were 3218 mm3 (left) and 3027 mm3 (right). The median volume of the geniohyoid muscle was 6580 mm3 on CT and 6648 mm3 on MRI. The interrater reliability was high for all segmented muscles. The mean time interval between the CT and MRI examinations was 34 days (IQR 25; 41). The muscle differences of each muscle between the two modalities did not reveal significant correlation to the time interval between the examinations (digastric left r = 0.003 and digastric right r = -0.008; geniohyoid muscle r = 0.075). CT-based segmentation and MRI-based segmentation of the digastric and geniohyoid muscle are equally feasible. The potential advantage of MRI for prospective studies is the absence of ionizing radiation. · CT-based segmentation and MRI-based segmentation of the swallowing muscles are equally feasible.. · The advantage of MRI is the absence of ionizing radiation.. · MRI should therefore be deployed for future prospective studies.. · Sporns KB, Hanning U, Schmidt R et al. Volumetric Assessment of Swallowing Muscles: A Comparison of CT and MRI Segmentation. Fortschr Röntgenstr 2018; 190: 441 - 446.

Breast cancer is one of the most common cancer types especially met in women. The number of breast cancer patients increases every year. Thus, to detect breast cancer at its early stages gains importance. Breast region detection is the pioneering step of breast cancer diagnosis researches performed via image processing techniques. The performance of computer-aided breast cancer diagnosis systems can be improved by exactly determining the breast region of interest. In this study, the goal is to determine a region of interest for breast MR images, in which one or more lesion can appear. The achieved region includes two breasts and lymph nodes. The proposed region of interest detection system is fully automatic and it utilizes several image processing techniques. At first, the local adaptive thresholding technique is applied to the noise-filtered grey level breast magnetic resonance images taken with ethical permissions from Sakarya Education and Research Hospital. After adaptive thresholding, connected component analysis is performed to exclude extra structures around the breast region as thorax area. This analysis selects the largest area in the binary image which corresponds to a gyrate region including breast area and lymph nodes over the backbone. Then, the integral of horizontal projection is calculated to determine an optimum horizontal line that allows setting the region of interest apart. In the following step, sternum midpoint is detected to separate the right breast from the left one. Finally, a masking operation is applied to get corresponding right and left breast regions in the original MR image. To evaluate the performance of the proposed study, the results of automatic region of interest detection system are compared with the manual region of interest selection performed by an expert radiologist. Dice similarity coefficient and Jaccard coefficient are used as performance criteria. According to the results, the proposed system can detect region of interest for computer-aided breast cancer diagnosis researches, exactly.

In this paper, we developed a new deformable model, the charged fluid model (CFM), that uses the simulation of a charged fluid to segment anatomic structures in magnetic resonance (MR) images of the brain. Conceptually, the charged fluid behaves like a liquid such that it flows through and around different obstacles. The simulation evolves in two steps governed by Poisson's equation. The first step distributes the elements of the charged fluid within the propagating interface until an electrostatic equilibrium is achieved. The second step advances the propagating front of the charged fluid such that it deforms into a new shape in response to the image gradient. This approach required no prior knowledge of anatomic structures, required the use of only one parameter, and provided subpixel precision in the region of interest. We demonstrated the performance of this new algorithm in the segmentation of anatomic structures on simulated and real brain MR images of different subjects. The CFM was compared to the level-set-based methods [Caselles et al. (1993) and Malladi et al (1995)] in segmenting difficult objects in a variety of brain MR images. The experimental results in different types of MR images indicate that the CFM algorithm achieves good segmentation results and is of potential value in brain image processing applications.

Objective To explore the value of susceptibility weighted imaging (SWI) in the quantitative analysis of ischemia- reperfusion injury (IRI) of the rabbit kidneys. Methods Thirty New Zealand white rabbits were randomly assigned to IRI group (n=24, operation with clamping) and Sham group (n=6, operation without clamping). Left renal ischemia-reperfusion was performed by occlusion (calmping) of the left renal arterial for 60 minutes, followed by reperfusion. All the rabbits underwent MRI including T2WI and SWI before and 0.5 h, 12 h, 24 h and 48 h after the establishments of models. Three rabbits in IRI group were randomly sacrificed 0.5 h, 12 h, and 24 h after the establishment of model. The rest of the rabbits in IRI group and 6 rabbits in sham group were sacrificed for pathological examination 48 h after the establishment of model All specimen were cut into slices and stained with hematoxylin-eosin (HE). Region of interest (ROI) was manually created by outlining the inner medulla, inner stripe of outer medulla, outer stripe of outer medulla, and cortex, then relative signal-to-noise ratio of the kidney (rSNR) to muscle in SWI sequence was recorded. and compared with histopathologic features. One- way ANOVA was performed to compare difference of rSNR to muscle in respective location at 5 time-points between Sham group and IRI group, and the differences between groups were tested using repetitive measure analysis of variance, repetitive measure analysis of variance was performed to compare difference of rSNR to muscle in respective location at respective time- points between Sham group and IRI group. Results rSNR value in the inner medulla 0.5 h, 12 h, 24 h and 48 h after the establishments of models were 0.28±0.04, 0.98±0.14, 0.69±0.07, 0.57±0.06, 0.43±0.03, respectively (F=69.82,P<0.01), the inner stripe of outer medulla at the five timepoints 0.08±0.03, 0.57±0.05, 0.32±0.07, 0.16±0.02, 0.04±0.01, respectively (F=16.59,P<0.01), the outer stripe of outer medulla were 0.31±0.04, 0.86±0.09, 0.65±0.07, 0.55±0.06 0.43±0.04 (F=67.52,P<0.01), respectively,the cortex 0.05±0.01, 0.80±0.04, 0.68±0.07, 0.47±0.07, 0.36±0.08, respectively (F=118.96, P< 0.01). The difference of the rSNR was statistically significant in the inner medulla, inner stripe of outer medulla, outer stripe of outer medulla, and cortex at the five different time-points. The differences between two groups were significant (F=206.29, 14.25, 42.8, 39.12,P all<0.05). The pathological findings in Sham group included normalglomerular structure l, clear cavity of tubular, no interstitial hyperemia and edema. The pathological findings in IRI group demonstated, at 0.5 h after IRI, Bowman's capsule cavity expansion, glomerular shrinkage, swelling of renal tubular epithelial cells, vacuoles degeneration, the tube cavity expansion, interstitial edema and congestion ecta became slender, andat 12 h after IR, Bowman's capsule expansion became more obvious, foam degeneration of renal tubular epithelial cells, apoptosis, partial loss of the brush border of the proximal convoluted tubule, formation of protein cast, and a small amount of inflammatory cells appeared in the renal interstitium, swelling of endothelial cells of the vasa recta, congestion of small vessels, and at 24 and 48 h after IRI, more serious injury of renal tubular in the outer stripe of outer medulla , massive necrosis of renal tubular epithelial cells, apoptosis, parts of the renal tubular had the contour lines, and renal tubular outline, increment in inflammatory cells, red cell and protein cast. Conclusion rSNR of SWI in the inner medulla, inner stripe of outer medulla, outer stripe of outer medulla, and cortex of the kidney varies with the degree of IRI over time, and is consistent with corresponding pathological feature, suggesting SWI is useful imaging tool to detect early damage of renal IRI quantitatively. Key words: Reperfusion injury; Magnetic resonance imaging; Pathology

Joint-label fusion brain atlases for dementia research in Down syndrome.

Objectives: Non-small cell lung cancer (NSCLC), the most prevalent type of lung cancer, includes subtypes such as adenocarcinoma (ADC) and squamous cell carcinoma (SCC), which require distinct management approaches. Accurately differentiating NSCLC subtypes based on diagnostic imaging remains challenging. However, the extraction of radiomic features—such as first-order statistics (FOS), second-order statistics (SOS), and fractal dimension texture analysis (FDTA) features—from magnetic resonance (MR) images supports the development of quantitative NSCLC assessments. Methods: This study aims to evaluate whether the integration of FDTA features with FOS and SOS texture features in MR image analysis improves machine learning classification of NSCLC into ADC and SCC subtypes. The study was conducted on 274 MR images, comprising ADC (n = 122) and SCC (n = 152) cases. From the segmented MR images, 93 texture features were extracted. The random forest algorithm was used to identify informative features from both FOS/SOS and combined FOS/SOS/FDTA datasets. Subsequently, the k-nearest neighbors (kNN) algorithm was applied to classify MR images as ADC or SCC. Results: The highest performance (accuracy = 0.78, precision = 0.81, AUC = 0.89) was achieved using 37 texture features selected from the combined FOS/SOS/FDTA dataset. Conclusions: Incorporating fractal descriptors into the texture-based classification of lung MR images enhances the differentiation of NSCLC subtypes.