Discrete tortuosity as a morphometric measure in brain tumors

Alternative Procedure ◽

Resonance Imaging ◽

Chain Code ◽

Necrotic Region ◽

Morphometric Measure ◽

Morphometric Index

Morphological changes in brain tumors may be related to their malignancy. The objective of this work is to be able to detect and quantify these changes in a magnetic resonance imaging, since it can represent an important advantage for the noninvasive diagnosis in patients. One way to identify such morphological changes can be through the measurement of their tortuosity. The discrete tortuosity is a descriptor that characterizes bi-dimensional curves, as the contour of a region. In this work an alternative procedure for calculating the volumetric tortuosity of a surface is proposed. This technique is based in the slope chain code of the surface contour of a volume, and here we call it tridimensional discrete tortuosity. This descriptor is used as a morphometric index to study the tortuosity of brain tumors. For this, magnetic resonance images from 20 patients with low and high malignancy levels were analyzed, considering four regions: edema, whole tumor, enhancing region, and necrotic region. As a result, the tortuosities of the different regions are presented, with significant differences only in some of them. It should be noted that a disadvantage that is present, is the dependence of the measurement to the use of a robust method of segmentation, nevertheless the proposal of the discrete tortuosity for volumetric surfaces is satisfactory.

Xác định thể tích chiếu xạ các khối u não dựa vào hình ảnh cắt lớp vi tính và cộng hưởng từ

Journal of Clinical Medicine- Hue Central Hospital ◽

10.38103/jcmhch.2020.66.2 ◽

2020 ◽

Author(s):

Tuong Pham Nguyen

Keyword(s):

Computed Tomography ◽

Magnetic Resonance ◽

Brain Tumors ◽

Cerebral Edema ◽

Resonance Imaging ◽

Cross Sectional ◽

Computed Tomography Images ◽

Bone Changes

Purpose: Compare Computed Tomography and Magnetic Resonance Imaging to accurately determine the volume of brain tumors for radiotherapy. Methods and Materials: Cross-sectional descriptive study on 38 patients with brain tumors indicated for radiation therapy, underwent Magnetic Resonance Imaging and CT scans at Hue Central Hospital from January 2018 to July 2019. Data processed with MS Excel 2013, SPSS 20.0 and statistical algorithms. Results: The Magnetic Resonance Imaging has a rate of brain tumor detection of 100% while that of computed tomography only reached 60.5%. The average difference in tumor size is 0.66 cm, the size of the tumor is larger on the magnetic resonance images. There is a close agreement on Magnetic Resonance Imaging and computer tomography on the level of cerebral edema (kappa = 0.735, p <0.001), on the amount of mid line shift of the tumor (kappa = 0.775, p <0.001); and detected cocoons in tumor (kappa = 1.000, p <0.001). Conclusions: Magnetic Resonance has advantages over computed tomography in the ability to detect brain tumors, tumor margin, the ability to detect the level of cerebral edema, invasive properties and identify cocoons in tumors. Computed Tomography is more advantageous than Magnetic Resonance in cases with calcification in the tumors or bone changes. Fusing computed tomography images and Magnetic Resonance Imaging together is a more effective method of determining the volume of brain tumors for radiotherapy.

Functional information from magnetic resonance imaging

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100136799 ◽

1995 ◽

Vol 53 ◽

pp. 84-85

Author(s):

Alan P. Koretsky ◽

Afonso Costa e Silva ◽

Yi-Jen Lin

Keyword(s):

Magnetic Resonance ◽

High Resolution ◽

Cancer Biology ◽

Imaging Modality ◽

Great Success ◽

Functional Information ◽

Resonance Imaging ◽

High Resolution Mri

Magnetic resonance imaging (MRI) has become established as an important imaging modality for the clinical management of disease. This is primarily due to the great tissue contrast inherent in magnetic resonance images of normal and diseased organs. Due to the wide availability of high field magnets and the ability to generate large and rapidly switched magnetic field gradients there is growing interest in applying high resolution MRI to obtain microscopic information. This symposium on MRI microscopy highlights new developments that are leading to increased resolution. The application of high resolution MRI to significant problems in developmental biology and cancer biology will illustrate the potential of these techniques.In combination with a growing interest in obtaining high resolution MRI there is also a growing interest in obtaining functional information from MRI. The great success of MRI in clinical applications is due to the inherent contrast obtained from different tissues leading to anatomical information.

Radiological Evaluation of Primary Brain Tumors Using Computed Tomography and Magnetic Resonance Imaging

International Journal of Innovative Research in Medical Science ◽

10.23958/ijirms/vol02-i02/03 ◽

2016 ◽

Vol 02 (02) ◽

pp. 505-508

Author(s):

Khulod Alsaadi ◽

◽

Amal Alkhaldi ◽

Fahad Alhazmi ◽

◽

...

Keyword(s):

Computed Tomography ◽

Magnetic Resonance ◽

Brain Tumors ◽

Radiological Evaluation ◽

Resonance Imaging ◽

Primary Brain Tumors

Imaging findings of cerebral fat embolism syndrome: a case report

Journal of International Medical Research ◽

10.1177/0300060520950559 ◽

2020 ◽

Vol 48 (9) ◽

pp. 030006052095055

Author(s):

Yali Wang ◽

Zhihua Si ◽

Jingzhe Han ◽

Shuangqing Cao

Keyword(s):

Magnetic Resonance ◽

Fat Embolism ◽

Resonance Imaging ◽

Diffusion Weighted Images ◽

Embolism Syndrome ◽

Imaging Characteristics ◽

Fluid Attenuated Inversion Recovery ◽

Cerebral Fat Embolism Syndrome ◽

Head Computed Tomography

Cerebral fat embolism (CFE) syndrome is relatively rare in clinical practice. Currently, there is no uniform standard of magnetic resonance imaging for the diagnosis of the disease. In this report, we present head computed tomography and magnetic resonance images (T2-weighted images, fluid-attenuated inversion recovery images, diffusion-weighted images, and susceptibility-weighted images) in a case of CFE. This report explains the imaging characteristics of CFE and improves the clinician’s understanding of this disease and its etiology.

Application of deep learning for automatic segmentation of brain tumors on magnetic resonance imaging: a heuristic approach in the clinical scenario

Neuroradiology ◽

10.1007/s00234-021-02649-3 ◽

2021 ◽

Author(s):

Antonio Di Ieva ◽

Carlo Russo ◽

Sidong Liu ◽

Anne Jian ◽

Michael Y. Bai ◽

...

Keyword(s):

Deep Learning ◽

Magnetic Resonance ◽

Brain Tumors ◽

Automatic Segmentation ◽

Heuristic Approach ◽

Clinical Scenario ◽

Resonance Imaging

Differential Deep Convolutional Neural Network Model for Brain Tumor Classification

Brain Sciences ◽

10.3390/brainsci11030352 ◽

2021 ◽

Vol 11 (3) ◽

pp. 352

Author(s):

Isselmou Abd El Kader ◽

Guizhi Xu ◽

Zhang Shuai ◽

Sani Saminu ◽

Imran Javaid ◽

...

Keyword(s):

Neural Network ◽

Brain Tumor ◽

Magnetic Resonance ◽

Brain Tumors ◽

Medical Image ◽

Resonance Imaging ◽

Feature Maps ◽

Deep Cnn

The classification of brain tumors is a difficult task in the field of medical image analysis. Improving algorithms and machine learning technology helps radiologists to easily diagnose the tumor without surgical intervention. In recent years, deep learning techniques have made excellent progress in the field of medical image processing and analysis. However, there are many difficulties in classifying brain tumors using magnetic resonance imaging; first, the difficulty of brain structure and the intertwining of tissues in it; and secondly, the difficulty of classifying brain tumors due to the high density nature of the brain. We propose a differential deep convolutional neural network model (differential deep-CNN) to classify different types of brain tumor, including abnormal and normal magnetic resonance (MR) images. Using differential operators in the differential deep-CNN architecture, we derived the additional differential feature maps in the original CNN feature maps. The derivation process led to an improvement in the performance of the proposed approach in accordance with the results of the evaluation parameters used. The advantage of the differential deep-CNN model is an analysis of a pixel directional pattern of images using contrast calculations and its high ability to classify a large database of images with high accuracy and without technical problems. Therefore, the proposed approach gives an excellent overall performance. To test and train the performance of this model, we used a dataset consisting of 25,000 brain magnetic resonance imaging (MRI) images, which includes abnormal and normal images. The experimental results showed that the proposed model achieved an accuracy of 99.25%. This study demonstrates that the proposed differential deep-CNN model can be used to facilitate the automatic classification of brain tumors.

Clinical relevance of diffusion and perfusion magnetic resonance imaging in assessing intra-axial brain tumors

Neuroradiology ◽

10.1007/s00234-005-0030-7 ◽

2006 ◽

Vol 48 (3) ◽

pp. 150-159 ◽

Cited By ~ 129

Author(s):

N. Rollin ◽

J. Guyotat ◽

N. Streichenberger ◽

J. Honnorat ◽

V.-A. Tran Minh ◽

...

Keyword(s):

Magnetic Resonance ◽

Brain Tumors ◽

Clinical Relevance ◽

Perfusion Magnetic Resonance Imaging ◽

Resonance Imaging

Hepatic epithelioid hemangioendothelioma: a report from three university centers

Radiologia Brasileira ◽

10.1590/0100-3984.2015.0059 ◽

2016 ◽

Vol 49 (5) ◽

pp. 288-294 ◽

Cited By ~ 13

Author(s):

Antonello Giardino ◽

Frank H. Miller ◽

Bobby Kalb ◽

Miguel Ramalho ◽

Diego R. Martin ◽

...

Keyword(s):

Magnetic Resonance ◽

Epithelioid Hemangioendothelioma ◽

Central Core ◽

Magnetic Resonance Imaging Examination ◽

High Signal ◽

Resonance Imaging ◽

Peripheral Ring ◽

Venous Phase

Abstract Objective: To determine common imaging findings of hepatic epithelioid hemangioendothelioma on magnetic resonance images. Materials and Methods: A search was made of three institutional databases between January 2000 and August 2012. Seven patients (mean age, 47 years; range, 21-66 years; 6 women) with pathology-confirmed diagnosis of hepatic epithelioid hemangioendothelioma who had undergone magnetic resonance imaging were identified. None of the patients had received any treatment for hepatic epithelioid hemangioendothelioma at the time of the initial magnetic resonance imaging examination. Results: Hepatic epithelioid hemangioendothelioma tumors appeared as focal masses in 7/7 patients, greater than 5 in number, with a coalescing lesion in 1/5, and peripheral localization in 6/7. Capsular retraction was present in 4/7, and was associated with peripherally located lesions. Early ring enhancement was appreciated in the majority of lesions in 7/7 patients. Centripetal progressive enhancement was shown in 5/7 patients on venous phase that exhibited a distinctive thick inner border of low signal on venous phase images, and a central core of delayed enhancement. Small lesions did not show this. Conclusion: The combination of multifocal round-configuration lesions that are predominantly peripheral and exhibit early peripheral ring enhancement and late appearance of an inner thick border of low signal and central core of high signal may represent an important feature for hepatic epithelioid hemangioendothelioma.