scholarly journals Multiple instance learning for computer aided detection and diagnosis of gastric cancer with dual-energy CT imaging

2015 ◽  
Vol 57 ◽  
pp. 358-368 ◽  
Author(s):  
Chao Li ◽  
Cen Shi ◽  
Huan Zhang ◽  
Yazhu Chen ◽  
Su Zhang
Keyword(s):  
Gastric Cancer ◽  
Dual Energy ◽  
Multiple Instance Learning ◽  
Ct Imaging ◽  
Dual Energy Ct ◽  
Computer Aided Detection ◽  
Computer Aided ◽  
Detection And Diagnosis

Computer-Aided Diagnosis for Preoperative Invasion Depth of Gastric Cancer with Dual-Energy Spectral CT Imaging

2015 ◽  
Vol 22 (2) ◽  
pp. 149-157 ◽  
Author(s):  
Chao Li ◽  
Cen Shi ◽  
Huan Zhang ◽  
Chun Hui ◽  
Kin Man Lam ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Dual Energy ◽  
Computer Aided Diagnosis ◽  
Ct Imaging ◽  
Spectral Ct ◽  
Invasion Depth ◽  
Computer Aided ◽  
Aided Diagnosis

scholarly journals Improved computer-aided detection of pulmonary nodules via deep learning in the sinogram domain

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Yongfeng Gao ◽  
Jiaxing Tan ◽  
Zhengrong Liang ◽  
Lihong Li ◽  
Yumei Huo
Keyword(s):  
Deep Learning ◽  
Area Under The Curve ◽  
Pulmonary Nodules ◽  
Ct Image ◽  
Computer Aided Detection ◽  
Ct Scanner ◽  
Human Visual Perception ◽  
Computer Aided ◽  
Detection And Diagnosis ◽  
Cade System

AbstractComputer aided detection (CADe) of pulmonary nodules plays an important role in assisting radiologists’ diagnosis and alleviating interpretation burden for lung cancer. Current CADe systems, aiming at simulating radiologists’ examination procedure, are built upon computer tomography (CT) images with feature extraction for detection and diagnosis. Human visual perception in CT image is reconstructed from sinogram, which is the original raw data acquired from CT scanner. In this work, different from the conventional image based CADe system, we propose a novel sinogram based CADe system in which the full projection information is used to explore additional effective features of nodules in the sinogram domain. Facing the challenges of limited research in this concept and unknown effective features in the sinogram domain, we design a new CADe system that utilizes the self-learning power of the convolutional neural network to learn and extract effective features from sinogram. The proposed system was validated on 208 patient cases from the publicly available online Lung Image Database Consortium database, with each case having at least one juxtapleural nodule annotation. Experimental results demonstrated that our proposed method obtained a value of 0.91 of the area under the curve (AUC) of receiver operating characteristic based on sinogram alone, comparing to 0.89 based on CT image alone. Moreover, a combination of sinogram and CT image could further improve the value of AUC to 0.92. This study indicates that pulmonary nodule detection in the sinogram domain is feasible with deep learning.

Benefits of texture analysis of dual energy CT for Computer-Aided pulmonary embolism detection

2013 ◽  
Author(s):  
Antonio Foncubierta-Rodriguez ◽  
Oscar Alfonso Jimenez del Toro ◽  
Alexandra Platon ◽  
Pierre-Alexandre Poletti ◽  
Henning Muller ◽  
...  
Keyword(s):  
Pulmonary Embolism ◽  
Texture Analysis ◽  
Dual Energy ◽  
Dual Energy Ct ◽  
Computer Aided

Abstract P327: Utilizing Iodine Contrast Extravasation Post Reperfusion and Dual Energy Ct Imaging to Predict Risk of Hemorrhagic Conversion in Acute Stroke Patients

Stroke ◽  
2021 ◽  
Vol 52 (Suppl_1) ◽  
Author(s):  
Tri Huynh* ◽  
Niran Vijayaraghavan* ◽  
Hannah Branstetter ◽  
Natalie Buchwald ◽  
Justin De Prey ◽  
...  
Keyword(s):  
Acute Stroke ◽  
Infarct Volume ◽  
Reperfusion Therapy ◽  
Dual Energy ◽  
Ct Imaging ◽  
Dual Energy Ct ◽  
Stroke Patients ◽  
Post Intervention ◽  
Contrast Extravasation ◽  
Post Contrast

Introduction: Hyperintense acute reperfusion marker (HARM) has been identified on post-contrast magnetic resonance imaging (MRI) to be a marker of hemorrhagic conversion (HC) post reperfusion therapy in acute stroke patients. We have previously described a case where MRI HARM was mimicked on post contrast computed topography (CT) imaging in an acute stroke patient post reperfusion. Dual-Energy (DECT) allows for differentiation between acute blood and iodine contrast extravasation (ICE), and thus can have utility when ICE is present. Here we sought to validate whether post-intervention ICE/CT hyperdensity reperfusion maker (CT HARM), and contrast subtracted on DECT is associated with HC in acute stroke patients. Method: Data was obtained from our Institutional Review Board approved stroke admission database from January 2017 to November 2019, including ischemic stroke patients that received thrombolysis or thrombectomy, had evaluable images within 24 hours of admission, and received a DECT. Ischemic volumes of the stroke was measured on diffusion-weighted image (DWI). ICE was measured on CT head and DECT using the freehand 3D region of interest tool on the Visage Imaging PACS System. Susceptibility weighted MRI sequences were used to grade HC. Data analysis was conducted with regression modeling. Results: A total of 82 patients were included, 49% women, median age 73 (interquartile range (IQR), 61- 77), admission NIHSS 12 (IQR, 7 - 21), 24 hour change in NIHSS 4 (IQR, 0 -13), glucose 125 (IQR, 106 -158), creatinine 1.0 (IQR, 0.8 - 1.2), infarct volume 50.6 ± 7.1 mL, 48% treated with thrombectomy, 7% with PH-1 or PH-2 identified on MRI, and 56% with MCA infarcts. ICE volume was 2.6 ± 1.0 mL and DECT volume was 2.2 ± 1.1mL. ICE increased the likelihood of MRI confirmed PH-1 or PH-2 hemorrhagic conversion (odds ratio (OR) 14.34, 95% confidence interval (CI) 5.74 - 22.94) and decreased likelihood of increase in NIHSS at 24 hours (OR 0.20, 95% CI 0.01 to 0.40). There were no other significant associations with ICE or DECT volumes. Conclusion: Our results are supportive of our proposed association between CT HARM and risk of HC. More studies are needed to study whether quantitative of DECT can be predictive of stroke outcomes post reperfusion therapy.

scholarly journals Clinical Value of Energy Spectrum Curves of Dual-energy CT in Evaluating Pathological Grading of Gastric Adenocarcinoma

2019 ◽  
Author(s):  
Zhihua Lu ◽  
Suying Wu ◽  
Jianwei Chen ◽  
Chuan Yan ◽  
Yueming Li
Keyword(s):  
Gastric Cancer ◽  
Energy Spectrum ◽  
Gastric Adenocarcinoma ◽  
Dual Energy ◽  
Dual Energy Ct ◽  
Clinical Value ◽  
Pathological Differentiation ◽  
Dual Source ◽  
Venous Phase ◽  
Poorly Differentiated

Abstract Backgroud: Accurate diagnosis of cancer staging and pathological differentiation are critical for the formulation of individualized treatment and prognosis of gastric cancer. It is vital to explore non-invasive preoperative imaging techniques to evaluate the pathological differentiation degree of gastric cancer tissues, and provide better diagnostic basis and decision-making reference for treatment. The purpose of this study was to explore the clinical value of energy spectrum curves of dual-source dual-energy CT in the quantitative evaluation of different pathological grades of gastric adenocarcinoma. Methods: A total of 62 patients with 1 well, 25 moderately and 36 poorly differentiated gastric adenocarcinomas pathologically confirmed by surgery were collected, and they underwent dual-source dual-energy CT plain scanning and enhanced scanning before operation. Dual-Energy software was used to measure the slope of the energy spectrum curves (λ) in arterial and venous phases after image reconstruction. Patients were divided into two groups according to the pathological results, including well and moderately differentiated gastric adenocarcinoma group and poorly differentiated gastric adenocarcinoma group. Data of each group were analyzed by independent sample t-test. The receiver operating characteristic curve was plotted to evaluate the diagnostic efficiency of the corresponding parameters. Results: There were significant differences in λ values of 40-50keV, 40-60keV, 40-80keV, 40-90keV, 40-100keV, 40-120keV, 40-130keV, 40-140keV and 40-150keV energy ranges in venous phase between the well and moderately differentiated group and poorly differentiated group (P<0.05), but no significant differences in λ values of different energy ranges in arterial phase between the two groups (P>0.05). And the area under curve in 40-120keV energy range was the largest in venous phase. K40-120keV =2.69 was selected as the diagnostic threshold with the maximum Youden index, the sensitivity and specificity were 61.1% and 76%, respectively. Conclusion: The energy spectrum curve of dual-energy CT had certain diagnostic value in the quantitative evaluation of pathological grading of gastric adenocarcinoma.

Computer-Aided Detection and Diagnosis for 3D X-Ray Based Breast Imaging

2012 ◽  
pp. 66-85
Author(s):  
Gautam S. Muralidhar ◽  
Alan C. Bovik ◽  
Mia K. Markey
Keyword(s):  
Breast Imaging ◽  
Digital Breast Tomosynthesis ◽  
Future Research ◽  
Computer Aided Detection ◽  
Breast Tomosynthesis ◽  
X Ray ◽  
Computer Aided ◽  
Recent Developments ◽  
Initial Work ◽  
Detection And Diagnosis

The last 15 years has seen the advent of a variety of powerful 3D x-ray based breast imaging modalities such as digital breast tomosynthesis, digital breast computed tomography, and stereo mammography. These modalities promise to herald a new and exciting future for early detection and diagnosis of breast cancer. In this chapter, the authors review some of the recent developments in 3D x-ray based breast imaging. They also review some of the initial work in the area of computer-aided detection and diagnosis for 3D x-ray based breast imaging. The chapter concludes by discussing future research directions in 3D computer-aided detection.

Sign in / Sign up

Export Citation Format

Share Document