Pseudo CT Generation Based on 3D Group Feature Extraction and Alternative Regression Forest for MRI-Only Radiotherapy

2018 ◽  
Vol 32 (06) ◽  
pp. 1855009 ◽  
Author(s):  
Yongsheng Hu ◽  
Liyi Zhang
Keyword(s):  
Random Forest ◽  
Ct Scan ◽  
Feature Space ◽  
Block Matching ◽  
Resonance Imaging ◽  
Mr Images ◽  
Random Forest Regression ◽  
Tissue Contrast ◽  
Magnetic Resonance Imaging Mri ◽  
The One

In recent decades, magnetic resonance imaging (MRI) has attracted attention in radiation therapy as the only modality. This nontrivial task requires the application of pseudo computed tomography (PCT) generation methods. On the one hand, the electron density information provided by the CT scan is critical for calculating the 3D dose distribution of tissues. On the other hand, the bone image provided by the CT is precise enough for the construction of a radiograph. Lately, the use of MRI/CT has combined all of the soft tissue contrast merits which are contributed by the MRI and the virtue of CT imaging. However, owing to the unbalance of voxel-intensities in the MRI and CT scan, the MRI/CT workflow also has shortcomings. Inspired by the random forest-based PCT estimation, this paper investigated the potential of the 3D group feature as the input of the random forest regression, which is based on the 3D block-matching method, taking the correlated central voxel as the target. Four types of features including the voxel level, sub-regional level, whole cubic level with adaptive weighted conjunction and compressed level were introduced to attain the robust features. The group-based random forest regression was then utilized to obtain the approximated PCT only from corresponding MRI, and the feature is extracted from the 3D cubic MRI patches and mapped to the 3D cubic CT patch, which helps in decreasing the computation difficulty, representing the MR patches into an anatomical feature space. The alternative regression forest was used in solving the regression task for enhancing the prediction power compared with the random forest. The proposed method could efficiently capture the correlation that is observable between the CT as well as the MR images on the basis of the alternative random forest (ARF) with cubic features, and the experimental results show the performance and effectiveness of the proposed method compared with the recent learning-based and atlas-based (AB) methods

MRI-only Radiation Therapy: Pseudo-CT Based on Cubic-Feature Extraction and Alternative Regression Forest

2020 ◽  
Vol 34 (14) ◽  
pp. 2054033
Author(s):  
Yongsheng Hu ◽  
Liyi Zhang
Keyword(s):  
Radiation Therapy ◽  
Ct Scan ◽  
Local Binary Pattern ◽  
Mapping Method ◽  
Random Forest Regression ◽  
Tissue Contrast ◽  
Gabor Feature ◽  
Magnetic Resonance Imaging Mri ◽  
Ct And Mri ◽  
Better Than

Despite the extensive attention attracted by magnetic resonance imaging (MRI) in the radiation therapy, computed tomography was reintroduced by the researchers. During the calculation process of the 3D dose distribution of tissues, there were some arguments about the electron density information obtained from the CT scan. However, the CT-provided bones are accurate for constructing a radiograph. Recently, the advantages boosted by the soft tissue contrast relying on MRI and as well as the advantages boosted by CT imaging have been combined by the using of MRI/CT. Unfortunately, disadvantages still exist in the MRI/CT workflow because the voxel-intensities are unbalanced in the MRI and the CT scan. Here, based on the mapping method of CT and MRI, the potential of pseudo-CT (PCT) instead of CT planning was studied. The estimated PCT only from the corresponding MRI was obtained by using the patch-based random forest regression. The CT voxel target was trained by 3D Gabor feature in the MRI cube and the Local Binary Pattern (LBP). Besides, the regression task was solved by the alternative regression forest. According to the experiment, the method performs better than the current dictionary learning-based (DLB) method or atlas-based (AB) method.

Optimization of T2-weighted imaging for shoulder magnetic resonance arthrography by synthetic magnetic resonance imaging

2017 ◽  
Vol 59 (8) ◽  
pp. 959-965
Author(s):  
Seung Hyun Lee ◽  
Young Han Lee ◽  
Seok Hahn ◽  
Jaemoon Yang ◽  
Ho-Taek Song ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Supraspinatus Tendon ◽  
Joint Fluid ◽  
Resonance Imaging ◽  
Mr Images ◽  
Diagnostic Agreement ◽  
Tissue Contrast ◽  
Synthetic Images ◽  
Synthetic Mri

Background Synthetic magnetic resonance imaging (MRI) allows reformatting of various synthetic images by adjustment of scanning parameters such as repetition time (TR) and echo time (TE). Optimized MR images can be reformatted from T1, T2, and proton density (PD) values to achieve maximum tissue contrast between joint fluid and adjacent soft tissue. Purpose To demonstrate the method for optimization of TR and TE by synthetic MRI and to validate the optimized images by comparison with conventional shoulder MR arthrography (MRA) images. Material and Methods Thirty-seven shoulder MRA images acquired by synthetic MRI were retrospectively evaluated for PD, T1, and T2 values at the joint fluid and glenoid labrum. Differences in signal intensity between the fluid and labrum were observed between TR of 500–6000 ms and TE of 80–300 ms in T2-weighted (T2W) images. Conventional T2W and synthetic images were analyzed for diagnostic agreement of supraspinatus tendon abnormalities (kappa statistics) and image quality scores (one-way analysis of variance with post-hoc analysis). Results Optimized mean values of TR and TE were 2724.7 ± 1634.7 and 80.1 ± 0.4, respectively. Diagnostic agreement for supraspinatus tendon abnormalities between conventional and synthetic MR images was excellent (κ = 0.882). The mean image quality score of the joint space in optimized synthetic images was significantly higher compared with those in conventional and synthetic images (2.861 ± 0.351 vs. 2.556 ± 0.607 vs. 2.750 ± 0.439; P < 0.05). Conclusion Synthetic MRI with optimized TR and TE for shoulder MRA enables optimization of soft-tissue contrast.

scholarly journals Magnetic resonance imaging of salivary glands

2019 ◽  
Author(s):  
Danielle Ayumi Nishimura ◽  
Ana Luiza Esteves Carneiro ◽  
Kaisermann Costa ◽  
Wladimir Gushiken de Campos ◽  
Jefferson Xavier de Oliveira ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Salivary Glands ◽  
Imaging Techniques ◽  
Neck Region ◽  
Evaluation Instrument ◽  
Resonance Imaging ◽  
Tissue Contrast ◽  
Excellent Method ◽  
Magnetic Resonance Imaging Mri

Salivary glands tumors account for 2-5% of tumors in the head and neck region, possibly being benign or malignant. Magnetic resonance imaging (MRI) presents high soft tissue contrast resolution, thus being an excellent method for salivary gland analysis. The objective of this literature review is to analyze MRI as an evaluation instrument for the diagnosis of salivary glands lesions. Compared to other imaging techniques, MRI can better evaluate the relationship between adjacent anatomical structures, presenting greater sensitivity and specificity.

scholarly journals GH-Producing Pituitary Adenoma and Concomitant Rathke’s Cleft Cyst: A Case Report and Short Review

2015 ◽  
Vol 2015 ◽  
pp. 1-6 ◽  
Author(s):  
Ryota Tamura ◽  
Satoshi Takahashi ◽  
Katsura Emoto ◽  
Hideaki Nagashima ◽  
Masahiro Toda ◽  
...  
Keyword(s):  
Pituitary Adenoma ◽  
Sella Turcica ◽  
Short Review ◽  
Pituitary Hormones ◽  
Rathke’S Cleft Cyst ◽  
Resonance Imaging ◽  
Mr Images ◽  
Rathke's Cleft Cyst ◽  
Magnetic Resonance Imaging Mri ◽  
Rathke's Cleft

Concomitant pituitary adenoma (PA) and Rathke’s cleft cyst (RCC) are rare. In some cases, such PA is known to produce pituitary hormones. A 53-year-old man was admitted to our hospital with a diagnosis of lacunar infarction in the left basal ganglia. Magnetic resonance imaging (MRI) incidentally showed a suprasellar mass with radiographic features of RCC. When he consulted with a neurosurgical outpatient clinic, acromegaly was suspected based on his appearance. A diagnosis of growth hormone- (GH-) producing PA was confirmed from hormonal examinations and additional MRI. Retrospectively, initial MR images also showed intrasellar mass that is compatible with the diagnosis of PA other than suprasellar RCC. The patient underwent endonasal-endoscopic removal of the PA. Since we judged that the RCC of the patient was asymptomatic, only the PA was completely removed. The postoperative course of the patient was uneventful and GH levels gradually normalized. Only 40 cases of PA with concomitant RCC have been reported to date, including 13 cases of GH-producing PA. In those 13 cases, RCC tended to be located in the sella turcica, and suprasellar RCC like this case appears rare. In a few cases, concomitant RCCs were fenestrated, but GH levels normalized postoperatively as in the cases without RCC fenestration. If radiographic imaging shows typical RCC, and PA is not obvious at first glance, the possibility of concomitant PA still needs to be considered. In terms of treatment, removal of the RCC is not needed to achieve hormone normalization.

Magnetic Resonance Imaging of the Facial Nerve

1989 ◽  
Vol 101 (3) ◽  
pp. 295-301 ◽  
Author(s):  
Donald G. Wortham ◽  
Louis M. Teresi ◽  
Robert B. Lufkin ◽  
William N. Hanafee ◽  
Paul H. Ward
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Facial Nerve ◽  
Temporal Bone ◽  
Resonance Imaging ◽  
Mr Images ◽  
Beam Hardening ◽  
Parotid Tumors ◽  
Seventh Nerve ◽  
Magnetic Resonance Imaging Mri

Magnetic resonance imaging (MRI) of the facial nerve was evaluated by studying normal volunteers and patients with diseases of the facial nerve with a 0.3 Tesla permanent-magnet MRI system with special surface colls. The normal MR images were correlated with the anatomy of thin cryosection specimens of fresh cadavers. The seventh nerve was followed from its nucleus in the brainstem through the temporal bone to the parotid gland bed. The entire labyrinth and tympanic portions, as well as the geniculate ganglion, could be shown with appropriate scan planes. Examples of brainstem diseases affecting the facial nerve and nucleus, facial neuromas, parotid tumors involving the facial nerve, and other diseases were studied. MRI is a technique that allows unique evaluation of the entire course of the facial nerve. It produces superior Images of the facial nerve with high-contrast resolution. Unlike computed tomography, there is no beam-hardening artifact from the temporal bone or exposure to ionizing radiation and contrast agents. MRI also allows visualization of the main trunks of the facial nerve in the parotid bed not possible with any other imaging technique.

Enhanced magnetic resonance imaging in multiple sclerosis

2000 ◽  
Vol 6 (5) ◽  
pp. 320-326 ◽  
Author(s):  
M Filippi
Keyword(s):  
Magnetic Resonance Imaging ◽  
Multiple Sclerosis ◽  
Magnetic Resonance ◽  
Tissue Loss ◽  
Resonance Imaging ◽  
The Past ◽  
Magnetic Resonance Imaging Mri ◽  
The One ◽  
The Relationship

Gadolinium-enhanced magnetic resonance imaging (MRI) is very sensitive in the detection of active lesions of multiple sclerosis (MS) and has become a valuable tool to monitor the evolution of the disease either natural or modified by treatment. In the past few years, several studies, on the one hand, have assessed several ways to increase the sensitivity of enhanced MRI to disease activity and, on the other, have investigated in vivo the nature and evolution of enhancing lesions using different non-conventional MR techniques to better define the relationship between enhancement and tissue loss in MS. The present review is a summary of these studies whose results are discussed in the context of MS clinical trial planning and monitoring.

scholarly journals Sequential MR Images and Radiographs of Epiphyseal Osteomyelitis in the Distal Femur of an Infant

2013 ◽  
Vol 2013 ◽  
pp. 1-4
Author(s):  
Hitomi Hara ◽  
Toshihiro Akisue ◽  
Teruya Kawamoto ◽  
Masahiro Kurosaka
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Early Diagnosis ◽  
Early Phase ◽  
Therapeutic Response ◽  
Distal Femur ◽  
Acute Osteomyelitis ◽  
Resonance Imaging ◽  
Mr Images ◽  
Magnetic Resonance Imaging Mri

Magnetic resonance imaging (MRI) plays an important role in the diagnosis of osteomyelitis, especially during the early phase of the disease. The findings of sequential MRIs during the course of treatment in acute osteomyelitis in children have not yet been reported in the literature. We present a case of acute epiphyseal osteomyelitis in the distal femur of an infant. We monitored imaging changes by sequential MRIs and radiographs. MRI was more useful than radiograph for early diagnosis and evaluation of therapeutic response.

scholarly journals Segmentation of elongated structures processed on breast MRI for the detection of vessels

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Marco Gierlinger ◽  
Dinah M. Brandner ◽  
Bernhard G. Zagar
Keyword(s):  
Breast Magnetic Resonance Imaging ◽  
Breast Mri ◽  
Region Growing ◽  
Seed Region ◽  
Resonance Imaging ◽  
Mr Images ◽  
Pixel Intensity ◽  
Breast Magnetic Resonance ◽  
Magnetic Resonance Imaging Mri ◽  
Diagnosis Of Diseases

Abstract The multi-seed region growing (MSRG) algorithm from previous work is extended to extract elongated segments from breast Magnetic Resonance Imaging (MRI) stacks. A model is created to adjust the MSRG parameters such that the elongated segments may reveal vessels that can support clinicians in their diagnosis of diseases or provide them with useful information before surgery during e. g. a neoadjuvant therapy. The model is a pipeline of tasks and contains user-defined parameters that influence the segmentation result. A crucial task of the model relies on a skeletonization-like algorithm that collects useful information about the segments’ thickness, length, etc. Length, thickness, and gradient information of the pixel intensity along the segment helps to determine whether the extracted segments have a tubular structure, which is assumed to be the case for vessels. In this work, we show how the results are derived and that the MSRG algorithm is capable of extracting vessel-like segments even from noisy MR images.

scholarly journals Deep Learning-Based Acute Ischemic Stroke Lesion Segmentation Method on Multimodal MR Images Using a Few Fully Labeled Subjects

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Bin Zhao ◽  
Zhiyang Liu ◽  
Guohua Liu ◽  
Chen Cao ◽  
Song Jin ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Segmentation Method ◽  
Lesion Segmentation ◽  
Resonance Imaging ◽  
Mr Images ◽  
Dice Coefficient ◽  
Automatic Methods ◽  
Stroke Lesion ◽  
Magnetic Resonance Imaging Mri

Acute ischemic stroke (AIS) has been a common threat to human health and may lead to severe outcomes without proper and prompt treatment. To precisely diagnose AIS, it is of paramount importance to quantitatively evaluate the AIS lesions. By adopting a convolutional neural network (CNN), many automatic methods for ischemic stroke lesion segmentation on magnetic resonance imaging (MRI) have been proposed. However, most CNN-based methods should be trained on a large amount of fully labeled subjects, and the label annotation is a labor-intensive and time-consuming task. Therefore, in this paper, we propose to use a mixture of many weakly labeled and a few fully labeled subjects to relieve the thirst of fully labeled subjects. In particular, a multifeature map fusion network (MFMF-Network) with two branches is proposed, where hundreds of weakly labeled subjects are used to train the classification branch, and several fully labeled subjects are adopted to tune the segmentation branch. By training on 398 weakly labeled and 5 fully labeled subjects, the proposed method is able to achieve a mean dice coefficient of 0.699 ± 0.128 on a test set with 179 subjects. The lesion-wise and subject-wise metrics are also evaluated, where a lesion-wise F1 score of 0.886 and a subject-wise detection rate of 1 are achieved.

scholarly journals Evaluation of the Impact of Magnetic Resonance Imaging (MRI) on Gross Tumor Volume (GTV) Definition for Radiation Treatment Planning (RTP) of Inoperable High Grade Gliomas (HGGs)

2019 ◽  
Vol 2019 ◽  
pp. 1-7 ◽  
Author(s):  
Omer Sager ◽  
Ferrat Dincoglan ◽  
Selcuk Demiral ◽  
Hakan Gamsiz ◽  
Bora Uysal ◽  
...  
Keyword(s):  
Gross Tumor Volume ◽  
Tumor Volume ◽  
Radiation Treatment ◽  
Resonance Imaging ◽  
Mr Images ◽  
Radiation Treatment Planning ◽  
Target Definition ◽  
Ct Simulation ◽  
Magnetic Resonance Imaging Mri ◽  
The Impact

Aim and Background. Inoperable high-grade gliomas (HGGs) comprise a specific group of brain tumors portending a very poor prognosis. In the absence of surgical management, radiation therapy (RT) offers the primary local treatment modality for inoperable HGGs. Optimal target definition for radiation treatment planning (RTP) of HGGs is a difficult task given the diffusely infiltrative nature of the disease. In this context, detailed multimodality imaging information may add to the accuracy of target definition in HGGs. We evaluated the impact of Magnetic Resonance Imaging (MRI) on Gross Tumor Volume (GTV) definition for RTP of inoperable HGGs in this study. Materials and Methods. Twenty-five inoperable patients with a clinical diagnosis of HGG were included in the study. GTV definition was based on Computed Tomography- (CT-) simulation images only or both CT-simulation and MR images, and a comparative assessment was performed to investigate the incorporation of MRI into RTP of HGGs. Results. Median volume of GTV acquired by using CT-simulation images only and by use of CT and MR images was 65.3 (39.6-94.3) cc and 76.1 (46.8-108.9) cc, respectively. Incorporation of MRI into GTV definition has resulted in a median increase of 12.61% (6%-19%) in the volume of GTV defined by using the CT-simulation images only, which was statistically significant (p < 0.05). Conclusion. Incorporation of MRI into RTP of inoperable HGGs may improve GTV definition and may have implications for dose escalation/intensification strategies despite the need for further supporting evidence.

Sign in / Sign up

Export Citation Format

Share Document