Calcifications Attenuation in Left Coronary Artery CT Images Using FDA Domain

2014 ◽  
Vol 3 (2) ◽  
pp. 14-32
Author(s):  
Mithun Kumar PK ◽  
Mohammad Motiur Rahman
Keyword(s):  
Computed Tomography ◽  
Threshold Value ◽  
Disease Diagnosis ◽  
Ct Images ◽  
Input Image ◽  
Medical Image Segmentation ◽  
Optimal Threshold ◽  
High Attenuation ◽  
Magnetic Resonance Imaging Mri ◽  
Fisher’S Discriminant Analysis

The calcification plaque is a one kind of artifacts or noises, which is occurred in the Computed Tomography (CT) images as a very high attenuation coefficient. Computed Tomography (CT) images are more helpful than other modalities (e.g. Ultrasonic Imaging, Magnetic Resonance Imaging (MRI) etc.) for disease diagnosis but unfortunately, CT image is an affected sometime by calcification plaque. Medical image segmentation cannot be optimum because of having calcification in the CT images, which is absolutely unexpected. The calcification plaque is the major problem for optimal organ segmentation and detection. This proposed task is a subjective as well as an effective for calcification alleviation from CT images. In this paper, Firstly, we applied the Fisher's Discriminant Analysis (FDA) for optimal threshold value estimation. Secondly, the proposed optimal threshold value is used for the optimal threshold image extraction. After this, the morphological operation is used for heavy calcification erosion and the XOR operation is used for adjusting the optimal threshold image with the input image. Finally, we implemented the Extra-Energy Reduction (EER) Function to smooth the desired image. Therefore, our investigated method is the most significant and articulate in order to attenuate calcification plaque from CT images.

Calcifications Attenuation in Left Coronary Artery CT Images Using FDA Domain

2017 ◽  
pp. 1258-1280
Author(s):  
Mithun Kumar PK ◽  
Mohammad Motiur Rahman
Keyword(s):  
Computed Tomography ◽  
Threshold Value ◽  
Disease Diagnosis ◽  
Ct Images ◽  
Input Image ◽  
Medical Image Segmentation ◽  
Optimal Threshold ◽  
Value Estimation ◽  
Magnetic Resonance Imaging Mri ◽  
Fisher’S Discriminant Analysis

The calcification plaque is a one kind of artifacts or noises, which is occurred in the Computed Tomography (CT) images as a very high attenuation coefficient. Computed Tomography (CT) images are more helpful than other modalities (e.g. Ultrasonic Imaging, Magnetic Resonance Imaging (MRI) etc.) for disease diagnosis but unfortunately, CT image is an affected sometime by calcification plaque. Medical image segmentation cannot be optimum because of having calcification in the CT images, which is absolutely unexpected. The calcification plaque is the major problem for optimal organ segmentation and detection. This proposed task is a subjective as well as an effective for calcification alleviation from CT images. In this paper, Firstly, we applied the Fisher's Discriminant Analysis (FDA) for optimal threshold value estimation. Secondly, the proposed optimal threshold value is used for the optimal threshold image extraction. After this, the morphological operation is used for heavy calcification erosion and the XOR operation is used for adjusting the optimal threshold image with the input image. Finally, we implemented the Extra-Energy Reduction (EER) Function to smooth the desired image. Therefore, our investigated method is the most significant and articulate in order to attenuate calcification plaque from CT images.

scholarly journals A Deep Learning Framework for Segmenting Brain Tumors Using MRI and Synthetically Generated CT Images

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 523
Author(s):  
Kh Tohidul Islam ◽  
Sudanthi Wijewickrema ◽  
Stephen O’Leary
Keyword(s):  
Image Segmentation ◽  
Three Dimensional ◽  
Disease Diagnosis ◽  
Ct Images ◽  
Medical Image Segmentation ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Learning Framework ◽  
Guided Surgery ◽  
Magnetic Resonance Imaging Mri

Multi-modal three-dimensional (3-D) image segmentation is used in many medical applications, such as disease diagnosis, treatment planning, and image-guided surgery. Although multi-modal images provide information that no single image modality alone can provide, integrating such information to be used in segmentation is a challenging task. Numerous methods have been introduced to solve the problem of multi-modal medical image segmentation in recent years. In this paper, we propose a solution for the task of brain tumor segmentation. To this end, we first introduce a method of enhancing an existing magnetic resonance imaging (MRI) dataset by generating synthetic computed tomography (CT) images. Then, we discuss a process of systematic optimization of a convolutional neural network (CNN) architecture that uses this enhanced dataset, in order to customize it for our task. Using publicly available datasets, we show that the proposed method outperforms similar existing methods.

scholarly journals Computed Tomography Evaluation of Unilateral Chronic Maxillary Sinusitis With Osteitis

2021 ◽  
pp. 014556132199393
Author(s):  
Zigang Che ◽  
Qingxiang Zhang ◽  
Pengfei Zhao ◽  
Han Lv ◽  
Heyu Ding ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Chronic Sinusitis ◽  
Maxillary Sinusitis ◽  
Disease Diagnosis ◽  
High Attenuation ◽  
Significant Difference ◽  
Bone Changes ◽  
Chronic Maxillary Sinusitis ◽  
Nasal Region ◽  
Severity Of The Disease

Background: Computed tomography (CT) is the preferred noninvasive method for the evaluation of osteitis in chronic sinusitis. Some scholars believe that the bone changes associated with chronic sinusitis always show high attenuation (high density) and are positively correlated with the severity of the disease. However, sinus bone remodeling is a complex process that may cause high or low attenuation. There have been few reports on the spread of osteitis. Therefore, additional research on sinus CT is necessary. Objective: To observe bony changes in chronic maxillary sinusitis (CMS) by CT and reveal the mechanism. Methods: A retrospective study was conducted in 45 patients with unilateral CMS with bony changes in the sinus walls. The patients’ clinical data and CT results were analyzed and compared between the affected and normal sides. We propose the location, involvement, attenuation, and thickness method to evaluate CMS with osteitis. Results: Of the 45 patients, 40 (88.9%), 2, 12, and 7 had posterior external, medial, anterior, and superior lesions, respectively. The nasal region, sphenoid bone, palatine bone, and zygomatic arch were involved in 3, 12, 8, and 18 (40%) patients, respectively. Computed tomography indicated high attenuation in 30 (75.0%) and low attenuation in 10 (25.0%) patients; 6 (15.0%) showed new bone marrow cavities. The bone thickness was significantly different between the affected and normal sides in 40 patients ( P < .001), including members of both the high- and low-attenuation groups (high-attenuation group: P < .001; low-attenuation group: P < .01). However, there was no significant difference in the thickness of the affected side between the high- and low-attenuation groups ( P > .05). Conclusions: Chronic rhinosinusitis with bony changes may occur in the maxillary sinus walls and spread to adjacent bones. Both increased and decreased attenuation may occur in these circumstances. Analyzing the CT features of bone changes in unilateral CMS can improve the accuracy of disease diagnosis.

scholarly journals Whole Heart Segmentation Using 3D FM-Pre-ResNet Encoder–Decoder Based Architecture with Variational Autoencoder Regularization

2021 ◽  
Vol 11 (9) ◽  
pp. 3912
Author(s):  
Marija Habijan ◽  
Irena Galić ◽  
Hrvoje Leventić ◽  
Krešimir Romić
Keyword(s):  
Three Dimensional ◽  
Disease Diagnosis ◽  
Input Image ◽  
Medical Image Segmentation ◽  
Training Data ◽  
Treatment Manual ◽  
Latent Space ◽  
Variational Autoencoder ◽  
Low Dimensional ◽  
Whole Heart

An accurate whole heart segmentation (WHS) on medical images, including computed tomography (CT) and magnetic resonance (MR) images, plays a crucial role in many clinical applications, such as cardiovascular disease diagnosis, pre-surgical planning, and intraoperative treatment. Manual whole-heart segmentation is a time-consuming process, prone to subjectivity and error. Therefore, there is a need to develop a quick, automatic, and accurate whole heart segmentation systems. Nowadays, convolutional neural networks (CNNs) emerged as a robust approach for medical image segmentation. In this paper, we first introduce a novel connectivity structure of residual unit that we refer to as a feature merge residual unit (FM-Pre-ResNet). The proposed connectivity allows the creation of distinctly deep models without an increase in the number of parameters compared to the pre-activation residual units. Second, we propose a three-dimensional (3D) encoder–decoder based architecture that successfully incorporates FM-Pre-ResNet units and variational autoencoder (VAE). In an encoding stage, FM-Pre-ResNet units are used for learning a low-dimensional representation of the input. After that, the variational autoencoder (VAE) reconstructs the input image from the low-dimensional latent space to provide a strong regularization of all model weights, simultaneously preventing overfitting on the training data. Finally, the decoding stage creates the final whole heart segmentation. We evaluate our method on the 40 test subjects of the MICCAI Multi-Modality Whole Heart Segmentation (MM-WHS) Challenge. The average dice values of whole heart segmentation are 90.39% (CT images) and 89.50% (MRI images), which are both highly comparable to the state-of-the-art.

scholarly journals A deep learning method for automatic segmentation of the bony orbit in MRI and CT images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jared Hamwood ◽  
Beat Schmutz ◽  
Michael J. Collins ◽  
Mark C. Allenby ◽  
David Alonso-Caneiro
Keyword(s):  
Deep Learning ◽  
Human Performance ◽  
Automatic Segmentation ◽  
Ct Images ◽  
Human Observer ◽  
In Series ◽  
Magnetic Resonance Imaging Mri ◽  
High Degree ◽  
Orbital Region ◽  
Ct And Mri

AbstractThis paper proposes a fully automatic method to segment the inner boundary of the bony orbit in two different image modalities: magnetic resonance imaging (MRI) and computed tomography (CT). The method, based on a deep learning architecture, uses two fully convolutional neural networks in series followed by a graph-search method to generate a boundary for the orbit. When compared to human performance for segmentation of both CT and MRI data, the proposed method achieves high Dice coefficients on both orbit and background, with scores of 0.813 and 0.975 in CT images and 0.930 and 0.995 in MRI images, showing a high degree of agreement with a manual segmentation by a human expert. Given the volumetric characteristics of these imaging modalities and the complexity and time-consuming nature of the segmentation of the orbital region in the human skull, it is often impractical to manually segment these images. Thus, the proposed method provides a valid clinical and research tool that performs similarly to the human observer.

scholarly journals Modified Crack Detection of Sewer Conduit with Low-Resolution Images

2021 ◽  
Vol 11 (5) ◽  
pp. 2263
Author(s):  
Byung Jik Son ◽  
Taejun Cho
Keyword(s):  
Image Processing ◽  
Crack Detection ◽  
Threshold Value ◽  
Optimal Threshold ◽  
Optimal Parameters ◽  
Low Resolution ◽  
The Subject ◽  
Low Resolution Images

Imaging devices of less than 300,000 pixels are mostly used for sewage conduit exploration due to the petty nature of the survey industry in Korea. Particularly, devices of less than 100,000 pixels are still widely used, and the environment for image processing is very dim. Since the sewage conduit images covered in this study have a very low resolution (240 × 320 = 76,800 pixels), it is very difficult to detect cracks. Because most of the resolutions of the sewer conduit images are very low in Korea, this problem of low resolution was selected as the subject of this study. Cracks were detected through a total of six steps of improving the crack in Step 2, finding the optimal threshold value in Step 3, and applying an algorithm to detect cracks in Step 5. Cracks were effectively detected by the optimal parameters in Steps 2 and 3 and the user algorithm in Step 5. Despite the very low resolution, the cracked images showed a 96.4% accuracy of detection, and the non-cracked images showed 94.5% accuracy. Moreover, the analysis was excellent in quality. It is believed that the findings of this study can be effectively used for crack detection with low-resolution images.

scholarly journals A243 A RETROSPECTIVE REVIEW OF THE RADIOGRAPHIC DIAGNOSIS AND SURGICAL RESECTION RATES OF PANCREATIC SEROUS CYSTS

2021 ◽  
Vol 4 (Supplement_1) ◽  
pp. 300-301
Author(s):  
M Monachese ◽  
S Li ◽  
M Salim ◽  
L Guimaraes ◽  
P D James
Keyword(s):  
Magnetic Resonance Imaging ◽  
Computed Tomography ◽  
Magnetic Resonance ◽  
Surgical Resection ◽  
Predictive Value ◽  
Resected Specimen ◽  
Cystic Lesions ◽  
Resonance Imaging ◽  
Guided Biopsy ◽  
Magnetic Resonance Imaging Mri

Abstract Background Pancreatic cystic lesions are increasingly identified in persons undergoing abdominal imaging. Serous cystic neoplasms (SCNs) have a very low risk of malignant transformation. Resection of SCNs is not recommended in the absence of related symptoms. The accuracy of computed tomography (CT) and magnetic resonance imaging (MRI) to identify SCNs is not known and may impact clinical care. Aims To evaluate the accuracy of computed tomography (CT) and magnetic resonance imaging (MRI) for the diagnosis of SCN. To see how this can impact the decision to resect suspected SCNs. Methods Retrospective cohort study of patients from the University Health Network with suspected SCNs from 2017–2020 who underwent either a CT or MRI of the abdomen. Reports noting pancreatic cystic lesions were identified and reviewed. Only cases with suspected SCNs were included. Clinical (age, sex, symptoms, treatment) and radiographic (type of imaging, reported cyst characteristics) data was collected. Pathology was reviewed for all cases where the cysts was biopsied or resected during follow-up. The gold standard for the diagnosis for SCN was pathology of resected specimen or EUS-guided biopsy cytopathology showing no evidence of a mucinous lesion, CEA level below 10ug per L and amylase level below 50 U/L. Results 163 patients were included in the study. 99 (61%) were female and 98 (60%) underwent CT scan. EUS-guided biopsy was performed in 24 (15%) of patients and 8 (5%) had surgical resection. Multidisciplinary review was performed in 6 of the 8 cases that went to surgery. Of the resected specimens, 5 (63%) were SCN, 1 was a mucinous cystic lesion, 1 was a neuroendocrine tumor and 1 was a carcinoma. Two patients underwent EUS evaluation prior to surgical resection. In one case SCN was resected when EUS reported an undetermined cyst type. Reasons for surgical resection were: the diagnosis of serous cyst was not definitive (n=5), symptoms (n=2), and high-risk mucinous cystic neoplasm identified on EUS (n=1). Of 30 patients with pathology available, 15 (50%) were confirmed to have a SCN. CT and MRI had a sensitivity, specificity, positive predictive value and negative predictive value of 93%, 25%, 52% and 80%, respectively. Conclusions Surgical resection for SCN lesions is driven by diagnostic uncertainty after cross-sectional imaging. Multidisciplinary review and EUS evaluation may improve diagnostic accuracy and should be considered prior to surgical resection of possible SCN lesions. Funding Agencies None

scholarly journals Multi-Cycle-Consistent Adversarial Networks for Edge Denoising of Computed Tomography Images

2021 ◽  
Vol 17 (4) ◽  
pp. 1-16
Author(s):  
Xiaowe Xu ◽  
Jiawei Zhang ◽  
Jinglan Liu ◽  
Yukun Ding ◽  
Tianchen Wang ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Image Denoising ◽  
Ct Images ◽  
High Dose ◽  
Ct Image ◽  
Paired Data ◽  
High Quality ◽  
Computed Tomography Images ◽  
Significant Difference ◽  
Global Cycle

As one of the most commonly ordered imaging tests, the computed tomography (CT) scan comes with inevitable radiation exposure that increases cancer risk to patients. However, CT image quality is directly related to radiation dose, and thus it is desirable to obtain high-quality CT images with as little dose as possible. CT image denoising tries to obtain high-dose-like high-quality CT images (domain Y ) from low dose low-quality CT images (domain X ), which can be treated as an image-to-image translation task where the goal is to learn the transform between a source domain X (noisy images) and a target domain Y (clean images). Recently, the cycle-consistent adversarial denoising network (CCADN) has achieved state-of-the-art results by enforcing cycle-consistent loss without the need of paired training data, since the paired data is hard to collect due to patients’ interests and cardiac motion. However, out of concerns on patients’ privacy and data security, protocols typically require clinics to perform medical image processing tasks including CT image denoising locally (i.e., edge denoising). Therefore, the network models need to achieve high performance under various computation resource constraints including memory and performance. Our detailed analysis of CCADN raises a number of interesting questions that point to potential ways to further improve its performance using the same or even fewer computation resources. For example, if the noise is large leading to a significant difference between domain X and domain Y , can we bridge X and Y with a intermediate domain Z such that both the denoising process between X and Z and that between Z and Y are easier to learn? As such intermediate domains lead to multiple cycles, how do we best enforce cycle- consistency? Driven by these questions, we propose a multi-cycle-consistent adversarial network (MCCAN) that builds intermediate domains and enforces both local and global cycle-consistency for edge denoising of CT images. The global cycle-consistency couples all generators together to model the whole denoising process, whereas the local cycle-consistency imposes effective supervision on the process between adjacent domains. Experiments show that both local and global cycle-consistency are important for the success of MCCAN, which outperforms CCADN in terms of denoising quality with slightly less computation resource consumption.

Sign in / Sign up

Export Citation Format

Share Document