Ultrasonic image analysis and image-guided interventions

The fields of medical image analysis and computer-aided interventions deal with reducing the large volume of digital images (X-ray, computed tomography, magnetic resonance imaging (MRI), positron emission tomography and ultrasound (US)) to more meaningful clinical information using software algorithms. US is a core imaging modality employed in these areas, both in its own right and used in conjunction with the other imaging modalities. It is receiving increased interest owing to the recent introduction of three-dimensional US, significant improvements in US image quality, and better understanding of how to design algorithms which exploit the unique strengths and properties of this real-time imaging modality. This article reviews the current state of art in US image analysis and its application in image-guided interventions. The article concludes by giving a perspective from clinical cardiology which is one of the most advanced areas of clinical application of US image analysis and describing some probable future trends in this important area of ultrasonic imaging research.

Download Full-text

Metal-Based Complexes as Pharmaceuticals for Molecular Imaging of the Liver

Pharmaceuticals ◽

10.3390/ph12030137 ◽

2019 ◽

Vol 12 (3) ◽

pp. 137 ◽

Cited By ~ 1

Author(s):

Julia Greiser ◽

Wolfgang Weigand ◽

Martin Freesmeyer

Keyword(s):

Magnetic Resonance Imaging ◽

Positron Emission Tomography ◽

Metal Complexes ◽

Imaging Technique ◽

Imaging Modality ◽

Emission Tomography ◽

Resonance Imaging ◽

Positron Emission ◽

Magnetic Resonance Imaging Mri ◽

Uptake Mechanisms

This article reviews the use of metal complexes as contrast agents (CA) and radiopharmaceuticals for the anatomical and functional imaging of the liver. The main focus was on two established imaging modalities: magnetic resonance imaging (MRI) and nuclear medicine, the latter including scintigraphy and positron emission tomography (PET). The review provides an overview on approved pharmaceuticals like Gd-based CA and 99mTc-based radiometal complexes, and also on novel agents such as 68Ga-based PET tracers. Metal complexes are presented by their imaging modality, with subsections focusing on their structure and mode of action. Uptake mechanisms, metabolism, and specificity are presented, in context with advantages and limitations of the diagnostic application and taking into account the respective imaging technique.

Download Full-text

The Role of Imaging in Radiation Therapy Planning: Past, Present, and Future

BioMed Research International ◽

10.1155/2014/231090 ◽

2014 ◽

Vol 2014 ◽

pp. 1-9 ◽

Cited By ~ 31

Author(s):

Gisele C. Pereira ◽

Melanie Traughber ◽

Raymond F. Muzic

Keyword(s):

Treatment Planning ◽

Planning Process ◽

Imaging Modality ◽

Imaging Techniques ◽

Treatment Options ◽

Three Dimensional ◽

Dose Calculation ◽

Positron Emission ◽

Tissue Contrast ◽

Anatomical Information

The use of ionizing radiation for cancer treatment has undergone extraordinary development during the past hundred years. The advancement of medical imaging has been critical in helping to achieve this change. The invention of computed tomography (CT) was pivotal in the development of treatment planning. Despite some disadvantages, CT remains the only three-dimensional imaging modality used for dose calculation. Newer image modalities, such as magnetic resonance (MR) imaging and positron emission tomography (PET), are also used secondarily in the treatment-planning process. MR, with its better tissue contrast and resolution than those of CT, improves tumor definition compared with CT planning alone. PET also provides metabolic information to supplement the CT and MR anatomical information. With emerging molecular imaging techniques, the ability to visualize and characterize tumors with regard to their metabolic profile, active pathways, and genetic markers, both across different tumors and within individual, heterogeneous tumors, will inform clinicians regarding the treatment options most likely to benefit a patient and to detect at the earliest time possible if and where a chosen therapy is working. In the post-human-genome era, multimodality scanners such as PET/CT and PET/MR will provide optimal tumor targeting information.

Download Full-text

Three-Dimensional Convolutional Autoencoder Extracts Features of Structural Brain Images With a “Diagnostic Label-Free” Approach: Application to Schizophrenia Datasets

Frontiers in Neuroscience ◽

10.3389/fnins.2021.652987 ◽

2021 ◽

Vol 15 ◽

Author(s):

Hiroyuki Yamaguchi ◽

Yuki Hashimoto ◽

Genichi Sugihara ◽

Jun Miyata ◽

Toshiya Murai ◽

...

Keyword(s):

Psychiatric Disorders ◽

Brain Imaging ◽

Spatial Information ◽

Three Dimensional ◽

Clinical Information ◽

Label Free ◽

Brain Images ◽

Convolutional Autoencoder ◽

Mri Scans ◽

Magnetic Resonance Imaging Mri

There has been increasing interest in performing psychiatric brain imaging studies using deep learning. However, most studies in this field disregard three-dimensional (3D) spatial information and targeted disease discrimination, without considering the genetic and clinical heterogeneity of psychiatric disorders. The purpose of this study was to investigate the efficacy of a 3D convolutional autoencoder (3D-CAE) for extracting features related to psychiatric disorders without diagnostic labels. The network was trained using a Kyoto University dataset including 82 patients with schizophrenia (SZ) and 90 healthy subjects (HS) and was evaluated using Center for Biomedical Research Excellence (COBRE) datasets, including 71 SZ patients and 71 HS. We created 16 3D-CAE models with different channels and convolutions to explore the effective range of hyperparameters for psychiatric brain imaging. The number of blocks containing two convolutional layers and one pooling layer was set, ranging from 1 block to 4 blocks. The number of channels in the extraction layer varied from 1, 4, 16, and 32 channels. The proposed 3D-CAEs were successfully reproduced into 3D structural magnetic resonance imaging (MRI) scans with sufficiently low errors. In addition, the features extracted using 3D-CAE retained the relation to clinical information. We explored the appropriate hyperparameter range of 3D-CAE, and it was suggested that a model with 3 blocks may be related to extracting features for predicting the dose of medication and symptom severity in schizophrenia.

Download Full-text

Renal radiology

10.1093/med/9780199592548.003.0009 ◽

2015 ◽

Author(s):

Michael J. Weston

Keyword(s):

Clinical Information ◽

Emission Tomography ◽

Resonance Imaging ◽

Imaging Studies ◽

Specific Question ◽

Radionuclide Studies ◽

Image Guided ◽

Image Guided Intervention ◽

Positron Emission ◽

Ultrasound Computed Tomography

This chapter acts as an introduction to Chapters 10–16 and highlights the uses of plain radiography, fluoroscopy, ultrasound, computed tomography, positron emission tomography, magnetic resonance imaging, radionuclide studies, and image-guided intervention. All imaging studies work best if a specific question is asked. This helps to choose both the best modality and protocol to answer the question. The clinical information given will often assist the interpretation of the findings. The more vague the indication for a scan, the less likely that useful information will be provided. Both the requesting clinician and the radiologist need to be clear how the scan result will alter management. Performing imaging procedures that will not alter the outcome is wasteful and unkind to the patient.

Download Full-text

Dual-Contrast Cellular Magnetic Resonance Imaging

Molecular Imaging ◽

10.2310/7290.2009.00024 ◽

2009 ◽

Vol 8 (5) ◽

pp. 7290.2009.00024 ◽

Cited By ~ 1

Author(s):

Rohan Dharmakumar ◽

Zhouli Zhang ◽

Ioannis Koktzoglou ◽

Sotirios A. Tsaftaris ◽

Debiao Li

Keyword(s):

Magnetic Resonance Imaging ◽

Magnetic Resonance ◽

Three Dimensional ◽

Negative Contrast ◽

Cellular Imaging ◽

Resonance Imaging ◽

Specificity And Sensitivity ◽

Contrast Magnetic Resonance ◽

Imaging Research ◽

Magnetic Resonance Imaging Mri

Negative contrast magnetic resonance imaging (MRI) methods using magnetic susceptibility shifting agents have become one of the most important approaches in cellular imaging research. However, visualizing and tracking labeled cells on the basis of negative contrast is often met with limited specificity and sensitivity. Here we report on a MRI method for cellular imaging that generates a new contrast with a distinct topology for identifying labeled cells that has the potential to significantly improve both the sensitivity and the specificity. Specifically, we show that low flip-angle steady-state free precession MRI can be used to generate fast three-dimensional images of tissue that can be rapidly processed to generate quantitative metrics enabling color overlays indicative of regions containing labeled cells. The technique substantially improves the ability of MRI for detecting labeled cells by overcoming the fundamental limits that currently plague negative contrast methods.

Download Full-text

Quantitative Musculoskeletal Tumor Imaging

Seminars in Musculoskeletal Radiology ◽

10.1055/s-0040-1708825 ◽

2020 ◽

Vol 24 (04) ◽

pp. 428-440

Author(s):

B Matthew Howe ◽

Stephen M. Broski ◽

Laurel A. Littrell ◽

Kay M. Pepin ◽

Doris E. Wenger

Keyword(s):

Tumor Imaging ◽

Three Dimensional ◽

Musculoskeletal Tumor ◽

Dynamic Contrast Enhancement ◽

Three Dimensional Printing ◽

Musculoskeletal Tumors ◽

Quantitative Pet ◽

Positron Emission ◽

Pet Ct ◽

Magnetic Resonance Imaging Mri

AbstractThe role of quantitative magnetic resonance imaging (MRI) and positron emission tomography/computed tomography (PET/CT) techniques continues to grow and evolve in the evaluation of musculoskeletal tumors. In this review we discuss the MRI quantitative techniques of volumetric measurement, chemical shift imaging, diffusion-weighted imaging, elastography, spectroscopy, and dynamic contrast enhancement. We also review quantitative PET techniques in the evaluation of musculoskeletal tumors, as well as virtual surgical planning and three-dimensional printing.

Download Full-text

A Survey on Adversarial Deep Learning Robustness in Medical Image Analysis

Electronics ◽

10.3390/electronics10172132 ◽

2021 ◽

Vol 10 (17) ◽

pp. 2132

Author(s):

Kyriakos D. Apostolidis ◽

George A. Papakostas

Keyword(s):

Neural Networks ◽

Image Analysis ◽

Deep Learning ◽

Language Processing ◽

Medical Image ◽

Medical Image Analysis ◽

Attack Detection ◽

Detection Methods ◽

Proper Function ◽

Magnetic Resonance Imaging Mri

In the past years, deep neural networks (DNN) have become popular in many disciplines such as computer vision (CV), natural language processing (NLP), etc. The evolution of hardware has helped researchers to develop many powerful Deep Learning (DL) models to face numerous challenging problems. One of the most important challenges in the CV area is Medical Image Analysis in which DL models process medical images—such as magnetic resonance imaging (MRI), X-ray, computed tomography (CT), etc.—using convolutional neural networks (CNN) for diagnosis or detection of several diseases. The proper function of these models can significantly upgrade the health systems. However, recent studies have shown that CNN models are vulnerable under adversarial attacks with imperceptible perturbations. In this paper, we summarize existing methods for adversarial attacks, detections and defenses on medical imaging. Finally, we show that many attacks, which are undetectable by the human eye, can degrade the performance of the models, significantly. Nevertheless, some effective defense and attack detection methods keep the models safe to an extent. We end with a discussion on the current state-of-the-art and future challenges.

Download Full-text

Enhanced Release of Glucose into the Intraluminal Space of the Intestine Associated with Metformin Treatment as Revealed by [18F]Fluorodeoxyglucose PET-MRI

10.2337/figshare.12106923.v1 ◽

2020 ◽

Author(s):

Yasuko Morita ◽

Munenobu Nogami ◽

Kazuhiko Sakaguchi ◽

Yuko Okada ◽

Yushi Hirota ◽

...

Keyword(s):

Imaging Modality ◽

Standardized Uptake Value ◽

Intestinal Wall ◽

Control Group ◽

Metformin Treatment ◽

Visual Scale ◽

Positron Emission ◽

Metformin Group ◽

Tissue Contrast ◽

Magnetic Resonance Imaging Mri

OBJECTIVE Positron emission tomography (PET)–computed tomography has revealed that metformin promotes the intestinal accumulation of [18F]fluorodeoxyglucose (FDG), a nonmetabolizable glucose derivative. It has remained unknown, however, whether this accumulation occurs in the wall or intraluminal space of the intestine. We here addressed this question with the use of [18F]FDG PET–magnetic resonance imaging (MRI), a recently developed imaging modality with increased accuracy of registration and high soft-tissue contrast. RESEARCH DESIGN AND METHODS Among 244 individuals with type 2 diabetes who underwent PET-MRI, we extracted 24 pairs of subjects matched for age, BMI, and HbA1c level who were (metformin group) or were not (control group) receiving treatment with metformin. We evaluated accumulation of [18F]FDG in different portions of the intestine with both a visual scale and measurement of maximum standardized uptake value (SUVmax), and such accumulation within the intestinal wall or lumen was discriminated on the basis of SUVmax. RESULTS SUVmax of the jejunum, ileum, and right or left hemicolon was greater in the metformin group than in the control group. [18F]FDG accumulation in the ileum and right or left hemicolon as assessed with the visual scale was also greater in the metformin group. SUVmax for the intraluminal space of the ileum and right or left hemicolon, but not that for the intestinal wall, was greater in the metformin group than in the control group. CONCLUSIONS Metformin treatment was associated with increased accumulation of [18F]FDG in the intraluminal space of the intestine, suggesting that this drug promotes the transport of glucose from the circulation into stool.

Download Full-text

Medical Image Analysis for Image Guided Therapy

Digital Image Computing: Techniques and Applications (DICTA'05) ◽

10.1109/dicta.2005.53 ◽

2006 ◽

Author(s):

S.K. Warfield

Keyword(s):

Image Analysis ◽

Medical Image ◽

Medical Image Analysis ◽

Image Guided Therapy ◽

Image Guided ◽

Guided Therapy

Download Full-text

The role of 6-[18F]fluorodopamine positron emission tomography in the localization of adrenal pheochromocytoma associated with von Hippel–Lindau syndrome

Acta Endocrinologica ◽

10.1530/eje-06-0712 ◽

2007 ◽

Vol 156 (4) ◽

pp. 483-487 ◽

Cited By ~ 45

Author(s):

Priya Kaji ◽

Jorge A Carrasquillo ◽

W Marston Linehan ◽

Clara C Chen ◽

Graeme Eisenhofer ◽

...

Keyword(s):

Positron Emission Tomography ◽

Imaging Modality ◽

High Sensitivity ◽

Emission Tomography ◽

Mibg Scintigraphy ◽

Von Hippel Lindau ◽

Negative Results ◽

Positron Emission ◽

Adrenal Pheochromocytoma ◽

Magnetic Resonance Imaging Mri

Objective: [123/131I]metaiodobenzylguanidine (MIBG) scintigraphy is considered as the gold standard in the localization of pheochromocytoma. However, this method has less optimal sensitivity for the detection of pheochromocytoma associated with von Hippel–Lindau (VHL). Our preliminary results suggest that this is partially due to the low expression of cell membrane norepinephrine transporter system in VHL-related pheochromocytoma cells. Another probable cause may be the low affinity that [123/131I]MIBG has for these cells. Recently, 6-[18F]fluorodopamine ([18F]DA) positron emission tomography (PET) has been introduced as a novel functional imaging modality with high sensitivity for pheochromocytoma. Therefore, we investigated whether [18F]DA PET is more effective than [123/131I]MIBG scintigraphy in the diagnostic localization of VHL-related adrenal pheochromocytoma. Materials and methods: In this study, we evaluated seven VHL patients in whom adrenal pheochromocytomas were confirmed by histopathology results. Adrenal pheochromocytomas were localized using computed tomography (CT), magnetic resonance imaging (MRI), [123/131I]MIBG scintigraphy and [18F]DA PET. Results: [18F]DA PET localized pheochromocytoma in all the seven patients, as did in CT. In contrast, three out of the seven had negative results utilizing [123/131I]MIBG scintigraphy and one out of the six patients had negative MRI results. Conclusions: [18F]DA PET was found to show more promising results when compared with [123/131I]MIBG scintigraphy in the diagnostic localization of VHL-related adrenal pheochromocytoma, with a 100% rate of localization. Thus, [18F]DA PET in conjunction with CT/MRI should be considered as an effective method for the proper localization of VHL-related adrenal pheochromocytoma.

Download Full-text