PV Modeling of Medical Imaging Systems

Benford's Law ◽  
2015 ◽  
Author(s):  
John Chiverton ◽  
Kevin Wells
Keyword(s):  
Medical Imaging ◽  
Gold Standard ◽  
Ground Truth ◽  
Imaging Data ◽  
Nuclear Medicine Imaging ◽  
Phantom Imaging ◽  
Positron Emission ◽  
Pet Ct ◽  
Many Sources

This chapter applies a Bayesian formulation of the Partial Volume (PV) effect, based on the Benford distribution, to the statistical classification of nuclear medicine imaging data: specifically Positron Emission Tomography (PET) acquired as part of a PET-CT phantom imaging procedure. The Benford distribution is a discrete probability distribution of great interest for medical imaging, because it describes the probabilities of occurrence of single digits in many sources of data. The chapter thus describes the PET-CT imaging and post-processing process to derive a gold standard. Moreover, this chapter uses it as a ground truth for the assessment of a Benford classifier formulation. The use of this gold standard shows that the classification of both the simulated and real phantom imaging data is well described by the Benford distribution.

Nearest Neighbor-Based Strategy to Optimize Multi-View Triplet Network for Classification of Small-Sample Medical Imaging Data

2021 ◽  
pp. 1-15
Author(s):  
Phawis Thammasorn ◽  
Wanpracha A. Chaovalitwongse ◽  
Daniel S. Hippe ◽  
Landon S. Wootton ◽  
Eric C. Ford ◽  
...  
Keyword(s):  
Medical Imaging ◽  
Nearest Neighbor ◽  
Small Sample ◽  
Imaging Data ◽  
Medical Imaging Data

scholarly journals Convolutional Neural Networks Promising in Lung Cancer T-Parameter Assessment on Baseline FDG-PET/CT

2018 ◽  
Vol 2018 ◽  
pp. 1-6 ◽  
Author(s):  
Margarita Kirienko ◽  
Martina Sollini ◽  
Giorgia Silvestri ◽  
Serena Mognetti ◽  
Emanuele Voulaz ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Fdg Pet ◽  
Area Under The Curve ◽  
Ct Images ◽  
Tnm System ◽  
Positron Emission ◽  
Pet Ct ◽  
Test Sets ◽  
Fdg Pet Ct

Aim. To develop an algorithm, based on convolutional neural network (CNN), for the classification of lung cancer lesions as T1-T2 or T3-T4 on staging fluorodeoxyglucose positron emission tomography (FDG-PET)/CT images. Methods. We retrospectively selected a cohort of 472 patients (divided in the training, validation, and test sets) submitted to staging FDG-PET/CT within 60 days before biopsy or surgery. TNM system seventh edition was used as reference. Postprocessing was performed to generate an adequate dataset. The input of CNNs was a bounding box on both PET and CT images, cropped around the lesion centre. The results were classified as Correct (concordance between reference and prediction) and Incorrect (discordance between reference and prediction). Accuracy (Correct/[Correct + Incorrect]), recall (Correctly predicted T3-T4/[all T3-T4]), and specificity (Correctly predicted T1-T2/[all T1-T2]), as commonly defined in deep learning models, were used to evaluate CNN performance. The area under the curve (AUC) was calculated for the final model. Results. The algorithm, composed of two networks (a “feature extractor” and a “classifier”), developed and tested achieved an accuracy, recall, specificity, and AUC of 87%, 69%, 69%, and 0.83; 86%, 77%, 70%, and 0.73; and 90%, 47%, 67%, and 0.68 in the training, validation, and test sets, respectively. Conclusion. We obtained proof of concept that CNNs can be used as a tool to assist in the staging of patients affected by lung cancer.

scholarly journals Review and Prospect: Artificial Intelligence in Advanced Medical Imaging

2021 ◽  
Vol 1 ◽  
Author(s):  
Shanshan Wang ◽  
Guohua Cao ◽  
Yan Wang ◽  
Shu Liao ◽  
Qian Wang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Image Reconstruction ◽  
Medical Imaging ◽  
Imaging Data ◽  
Resonance Imaging ◽  
Volumetric Imaging ◽  
Positron Emission ◽  
Potential Applications ◽  
Magnetic Resonance Imaging Mri

Artificial intelligence (AI) as an emerging technology is gaining momentum in medical imaging. Recently, deep learning-based AI techniques have been actively investigated in medical imaging, and its potential applications range from data acquisition and image reconstruction to image analysis and understanding. In this review, we focus on the use of deep learning in image reconstruction for advanced medical imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET). Particularly, recent deep learning-based methods for image reconstruction will be emphasized, in accordance with their methodology designs and performances in handling volumetric imaging data. It is expected that this review can help relevant researchers understand how to adapt AI for medical imaging and which advantages can be achieved with the assistance of AI.

scholarly journals Accelerometer-Based Method for Extracting Respiratory and Cardiac Gating Information for Dual Gating during Nuclear Medicine Imaging

2014 ◽  
Vol 2014 ◽  
pp. 1-11 ◽  
Author(s):  
Mojtaba Jafari Tadi ◽  
Tero Koivisto ◽  
Mikko Pänkäälä ◽  
Ari Paasio
Keyword(s):  
Nuclear Medicine ◽  
Medical Imaging ◽  
Cardiac Cycle ◽  
Pearson Correlation ◽  
Motion Artifacts ◽  
Accurate Information ◽  
Nuclear Medicine Imaging ◽  
Cardiac Positron Emission Tomography ◽  
Positron Emission ◽  
Dual Gating

Both respiratory and cardiac motions reduce the quality and consistency of medical imaging specifically in nuclear medicine imaging. Motion artifacts can be eliminated by gating the image acquisition based on the respiratory phase and cardiac contractions throughout the medical imaging procedure. Electrocardiography (ECG), 3-axis accelerometer, and respiration belt data were processed and analyzed from ten healthy volunteers. Seismocardiography (SCG) is a noninvasive accelerometer-based method that measures accelerations caused by respiration and myocardial movements. This study was conducted to investigate the feasibility of the accelerometer-based method in dual gating technique. The SCG provides accelerometer-derived respiratory (ADR) data and accurate information about quiescent phases within the cardiac cycle. The correct information about the status of ventricles and atria helps us to create an improved estimate for quiescent phases within a cardiac cycle. The correlation of ADR signals with the reference respiration belt was investigated using Pearson correlation. High linear correlation was observed between accelerometer-based measurement and reference measurement methods (ECG and Respiration belt). Above all, due to the simplicity of the proposed method, the technique has high potential to be applied in dual gating in clinical cardiac positron emission tomography (PET) to obtain motion-free images in the future.

scholarly journals Imaging in diagnostics and management of extramedullary lesions in a patient with multiple myeloma

2019 ◽  
Vol 1 (1) ◽  
pp. 74-87
Author(s):  
Sergey Kozyrev ◽  
Daniil Korabelnikov ◽  
Vasiliy Pop ◽  
Vladimir Troyan ◽  
Oleg Rukavicyn
Keyword(s):  
Multiple Myeloma ◽  
Peripheral Blood Stem Cell ◽  
Clinical Signs ◽  
Conventional Radiography ◽  
Extramedullary Plasmacytoma ◽  
Nuclear Medicine Imaging ◽  
X Ray ◽  
Positron Emission ◽  
Pet Ct ◽  
Magnetic Resonance Imaging Mri

Extraosseous manifestations are found in less than 5% of patients with multiple myeloma. Involvement of the gastrointestinal system in the course of multiple myeloma (MM) is extremely rare. Imaging is required for correct staging, in the followup after treatment and is predictor of prognosis. Several imaging technologies are used for the diagnosis and management of patients with MM. Conventional radiography, computed tomography (CT), magnetic resonance imaging (MRI) and nuclear medicine imaging - positron emission tomography (PET) combined with CT (PET/CT) and PET combined with MRI (PET/MRI) are all used in clarifying the extent of bone and soft tissue lesions in MM. The brief literature review on extramedullary lesions in MM and their imaging with recommendations is given. We describe the imaging in diagnostics and management of an rare case of secondary extramedullary plasmacytoma (EMP) in relapse involving the pancreas and duodenum with the bleeding in a patient with MM, IgA lambda, stage II, after 6-years treatment with chemotherapy, autologous peripheral blood stem cell transplantation and radiotherapy. EMP was detected by PET/CT before the appearance of obvious clinical signs, and then EMP was monitoring by PET/CT, X-ray and ultrasound.

scholarly journals To Enhance or Not to Enhance? The Role of Contrast Medium 18F-FDG PET/CT in Recurrent Ovarian Carcinomas

Medicina ◽  
2021 ◽  
Vol 57 (6) ◽  
pp. 561
Author(s):  
Michela Massollo ◽  
Francesco Fiz ◽  
Gianluca Bottoni ◽  
Martina Ugolini ◽  
Francesco Paparo ◽  
...  
Keyword(s):  
Ovarian Cancer ◽  
Positive Predictive Value ◽  
Contrast Medium ◽  
Predictive Value ◽  
Ground Truth ◽  
Ovarian Carcinomas ◽  
Positron Emission ◽  
Pet Ct ◽  
Lesion Level ◽  
Sensitivity Specificity

Background and Objectives: 18F-fluorodeoxyglucose (FDG) positron emission tomography/X-ray computed tomography (PET/CT) represents the mainstay diagnostic procedure for suspected ovarian cancer (OC) recurrence. PET/CT can be integrated with contrast medium and in various diagnostic settings; however, the effective benefit of this procedure is still debated. We aimed to compare the diagnostic capabilities of low-dose and contrast-enhanced PET/CT (PET/ldCT and PET/ceCT) in patients with suspected ovarian cancer relapse. Materials and Methods: 122 OC patients underwent both PET/ldCT and PET/ceCT. Two groups of nuclear medicine physicians and radiologists scored the findings as positive or negative. Clinical/radiological follow-up was used as ground truth. Sensitivity, specificity, negative/positive predictive value, and accuracy were calculated at the patient and the lesion level. Results: A total of 455 and 474 lesions were identified at PET/ldCT and PET/ceCT, respectively. At the lesion level, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were not significantly different between PET/ldCT and PET/ceCT (98%, 93.3%, 97.4%, 94.9%, and 96.9% for PET/ldCT; 99%, 95.5%, 98.3%, 97%, and 98% for PET/ceCT, p = ns). At the patient level, no significant differences in these parameters were identified (e.g., p = 0.22 and p = 0.35 for accuracy, in the peritoneum and lymph nodes, respectively). Smaller peritoneal/lymph node lesions close to physiological FDG uptake sources were found in the cases of misidentification by PET/ldCT. PET/ceCT prompted a change in clinical management in four cases (3.2%) compared to PET/ldCT. Conclusions: PET/ceCT does not perform better than PET/ldCT but can occasionally clarify doubtful peritoneal findings on PET/ldCT. To avoid unnecessary dose to the patient, PET/ceCT should be excluded in selected cases.

scholarly journals Recommendations for Standardizing Thorax PET–CT in Non-Human Primates by Recent Experience from Macaque Studies

Animals ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 204 ◽  
Author(s):  
Marieke A. Stammes ◽  
Jaco Bakker ◽  
Richard A. W. Vervenne ◽  
Dian G. M. Zijlmans ◽  
Leo van Geest ◽  
...  
Keyword(s):  
Relevant Information ◽  
Lessons Learned ◽  
Recent Experience ◽  
Imaging Data ◽  
Preclinical Research ◽  
Pet Tracer ◽  
Positron Emission ◽  
Pet Ct ◽  
Clinical Measures

Despite the possibilities of routine clinical measures and assays on readily accessible bio-samples, it is not always essential in animals to investigate the dynamics of disease longitudinally. In this regard, minimally invasive imaging methods provide powerful tools in preclinical research. They can contribute to the ethical principle of gathering as much relevant information per animal as possible. Besides, with an obvious parallel to clinical diagnostic practice, such imaging platforms are potent and valuable instruments leading to a more refined use of animals from a welfare perspective. Non-human primates comprise highly relevant species for preclinical research to enhance our understanding of disease mechanisms and/or the development of improved prophylactic or therapeutic regimen for various human diseases. In this paper, we describe parameters that critically affect the quality of integrated positron emission tomography and computed tomography (PET–CT) in non-human primates. Lessons learned are exemplified by results from imaging experimental infectious respiratory disease in macaques; specifically tuberculosis, influenza, and SARS-CoV-2 infection. We focus on the thorax and use of 18F-fluorodeoxyglucose as a PET tracer. Recommendations are provided to guide various stages of PET–CT-supported research in non-human primates, from animal selection, scan preparation, and operation, to processing and analysis of imaging data.

Sign in / Sign up

Export Citation Format

Share Document