Integrated Segmentation and Non-linear Registration for Organ Segmentation and Motion Field Estimation in 4D CT Data

2009 ◽  
Vol 48 (04) ◽  
pp. 344-349 ◽  
Author(s):  
H. Handels ◽  
J. Ehrhardt ◽  
A. Schmidt-Richberg
Keyword(s):  
Radiation Therapy ◽  
Motion Estimation ◽  
Imaging Techniques ◽  
Image Data ◽  
Integrated Approach ◽  
Simultaneous Estimation ◽  
Motion Field ◽  
Non Linear ◽  
Induced Motion ◽  
Ct Data

Summary Objectives: The development of spatiotemporal tomographic imaging techniques allows the application of novel techniques for diagnosis and therapy in the medical routine. However, in consequence to the increasing amount of image data automatic methods for segmentation and motion estimation are required. In adaptive radiation therapy, registration techniques are used for the estimation of respiration-induced motion of pre-segmented organs. In this paper, a variational approach for the simultaneous computation of segmentations and a dense non-linear registration of the 3D images of the sequence is presented. Methods: In the presented approach, a variational region-based level set segmentation of the structures of interest is combined with a diffusive registration of the spatial images of the sequence. We integrate both parts by defining a new energy term, which allows us to incorporate mutual prior information in order to improve the segmentation as well as the registration quality. Results: The presented approach was utilized for the segmentation of the liver and the simultaneous estimation of its respiration-induced motion based on four-dimensional thoracic CT images. For the considered patients, we were able to improve the results of the segmentation and the motion estimation, compared to the conventional uncoupled methods. Conclusions: Applied in the field of radiation therapy of thoracic tumors, the presented integrated approach turns out to be useful for simultaneous segmentation and registration by improving the results compared to the application of the methods independently.

scholarly journals Multimodal Functional Imaging for Cancer/Tumor Microenvironments Based on MRI, EPRI, and PET

Molecules ◽  
2021 ◽  
Vol 26 (6) ◽  
pp. 1614
Author(s):  
Ken-ichiro Matsumoto ◽  
James B. Mitchell ◽  
Murali C. Krishna
Keyword(s):  
Radiation Therapy ◽  
Functional Imaging ◽  
Imaging Techniques ◽  
Biological Effects ◽  
Tumor Hypoxia ◽  
Redox Status ◽  
Blood Oxygen Level Dependent ◽  
Oxygen Level ◽  
Cancer Tumor

Radiation therapy is one of the main modalities to treat cancer/tumor. The response to radiation therapy, however, can be influenced by physiological and/or pathological conditions in the target tissues, especially by the low partial oxygen pressure and altered redox status in cancer/tumor tissues. Visualizing such cancer/tumor patho-physiological microenvironment would be a useful not only for planning radiotherapy but also to detect cancer/tumor in an earlier stage. Tumor hypoxia could be sensed by positron emission tomography (PET), electron paramagnetic resonance (EPR) oxygen mapping, and in vivo dynamic nuclear polarization (DNP) MRI. Tissue oxygenation could be visualized on a real-time basis by blood oxygen level dependent (BOLD) and/or tissue oxygen level dependent (TOLD) MRI signal. EPR imaging (EPRI) and/or T1-weighted MRI techniques can visualize tissue redox status non-invasively based on paramagnetic and diamagnetic conversions of nitroxyl radical contrast agent. 13C-DNP MRI can visualize glycometabolism of tumor/cancer tissues. Accurate co-registration of those multimodal images could make mechanisms of drug and/or relation of resulted biological effects clear. A multimodal instrument, such as PET-MRI, may have another possibility to link multiple functions. Functional imaging techniques individually developed to date have been converged on the concept of theranostics.

scholarly journals Current Applications, Opportunities, and Limitations of AI for 3D Imaging in Dental Research and Practice

2020 ◽  
Vol 17 (12) ◽  
pp. 4424
Author(s):  
Kuofeng Hung ◽  
Andy Wai Kan Yeung ◽  
Ray Tanaka ◽  
Michael M. Bornstein
Keyword(s):  
Treatment Planning ◽  
3D Imaging ◽  
Imaging Techniques ◽  
Current Trend ◽  
Three Dimensional ◽  
Image Data ◽  
Anatomical Landmarks ◽  
Automated Diagnosis ◽  
Dental Practitioners ◽  
Facial Scanning

The increasing use of three-dimensional (3D) imaging techniques in dental medicine has boosted the development and use of artificial intelligence (AI) systems for various clinical problems. Cone beam computed tomography (CBCT) and intraoral/facial scans are potential sources of image data to develop 3D image-based AI systems for automated diagnosis, treatment planning, and prediction of treatment outcome. This review focuses on current developments and performance of AI for 3D imaging in dentomaxillofacial radiology (DMFR) as well as intraoral and facial scanning. In DMFR, machine learning-based algorithms proposed in the literature focus on three main applications, including automated diagnosis of dental and maxillofacial diseases, localization of anatomical landmarks for orthodontic and orthognathic treatment planning, and general improvement of image quality. Automatic recognition of teeth and diagnosis of facial deformations using AI systems based on intraoral and facial scanning will very likely be a field of increased interest in the future. The review is aimed at providing dental practitioners and interested colleagues in healthcare with a comprehensive understanding of the current trend of AI developments in the field of 3D imaging in dental medicine.

scholarly journals Precipitation Nowcasting using Data-driven Reduced-order Model

2021 ◽  
Author(s):  
Divya S Vidyadharan ◽  
Aaron Xavier ◽  
Blossom Treesa Bastian ◽  
Ajay Ragh ◽  
Naveen Chittilapilly
Keyword(s):  
Radar Reflectivity ◽  
Reduced Order Model ◽  
Motion Field ◽  
L1 Norm ◽  
Order Model ◽  
Linear Dynamics ◽  
Reduced Order ◽  
Squall Lines ◽  
Short Period ◽  
Non Linear

<div>Radar-based precipitation nowcasting refers to predicting rain for a short period of time using radar reflectivity images. For dynamic nowcasting, motion fields can be extrapolated using an approximate and localized reduced-order model. Motion field estimation based on traditional Horn-Schunck (HS) algorithm suffers from over-smoothing at discontinuities in non-rigid and dissolving texture present in precipitation nowcasting products. An attempt to preserve the discontinuities using an L1 norm formulation in HS led to the use of Total Variation L1 norm (TVL1). In this paper, we propose a radar-based precipitation nowcasting model with TVL1-based estimation of motion field and Sparse Identification of Non-linear Dynamics (SINDy)-based</div><div>estimation of non-linear dynamics. TVL1 is effective in preserving the edges especially in the case of the eye of typhoons and squall lines while estimating motion vectors. SINDy captures the non-linear dynamics and generates the subsequent update values for the motion field based on a reduced-order representation. Finally, the SINDy-generated ensemble of motion field is used along with</div><div>the radar reflectivity image for generating precipitation nowcasts. We evaluated the effectiveness of TVL1 in preserving edges while capturing the motion field from non-rigid surfaces. The performance of the proposed TVL1-SINDy model in nowcasting weather events such as Typhoons and Squall lines are evaluated using performance metrics such as Mean Absolute Error (MAE), and Critical Success Index (CSI). Experimental results show that the proposed nowcasting system demonstrates better performance compared to the benchmark nowcasting models with lower MAE, higher CSI at higher lead times.</div>

scholarly journals Tracking cells in epithelial acini by light sheet microscopy reveals proximity effects in breast cancer initiation

eLife ◽  
2020 ◽  
Vol 9 ◽  
Author(s):  
Ashna Alladin ◽  
Lucas Chaible ◽  
Lucia Garcia del Valle ◽  
Reither Sabine ◽  
Monika Loeschinger ◽  
...  
Keyword(s):  
Single Cells ◽  
Image Data ◽  
Integrated Approach ◽  
Light Sheet ◽  
Mammary Epithelial ◽  
Proximity Effects ◽  
Transformed Cells ◽  
Light Sheet Microscopy ◽  
Primary Mouse ◽  
Longitudinal Imaging

Cancer clone evolution takes place within tissue ecosystem habitats. But, how exactly tumors arise from a few malignant cells within an intact epithelium is a central, yet unanswered question. This is mainly due to the inaccessibility of this process to longitudinal imaging together with a lack of systems that model the progression of a fraction of transformed cells within a tissue. Here, we developed a new methodology based on primary mouse mammary epithelial acini, where oncogenes can be switched on in single cells within an otherwise normal epithelial cell layer. We combine this stochastic breast tumor induction model with inverted light-sheet imaging to study single-cell behavior for up to four days and analyze cell fates utilizing a newly developed image-data analysis workflow. The power of this integrated approach is illustrated by us finding that small local clusters of transformed cells form tumors while isolated transformed cells do not.

scholarly journals ACTH-PRODUCING PERIPHERAL PULMONARY CARCINOID

2018 ◽  
Vol 99 (4) ◽  
pp. 211-215
Author(s):  
I. Z. Korobkova ◽  
D. A. Dremin ◽  
S. M. Kacalov ◽  
I. V. Kirsan ◽  
A. A. Ugrimov ◽  
...  
Keyword(s):  
Neuroendocrine Tumors ◽  
Adrenocorticotropic Hormone ◽  
Imaging Techniques ◽  
Diagnostic Algorithm ◽  
Integrated Approach ◽  
Hormone Production ◽  
Pulmonary Carcinoid ◽  
Topical Diagnosis ◽  
Acth Secreting ◽  
Rule Out

The paper describes a clinical example of the topical diagnosis of adrenocorticotropic hormone (ACTH)-producing typical peripheral pulmonary carcinoid. The first stage in its diagnosis was to rule out the production of ACTH by the pituitary gland. The paper presents information on the most common localization of functioning neuroendocrine tumors, as well as a diagnostic algorithm to search for an ectopic focus of the ACTH-secreting tumor that causes hypercorticism. Taking into account that bronchopulmonary neuroendocrine tumors with ectopic hormone production occur rarely (5%), a clinical example is given to demonstrate the capabilities of imaging techniques and standards for their implementation using an integrated approach.

Precipitation Nowcasting using Data-driven Reduced-order Model

2021 ◽  
Author(s):  
Divya S Vidyadharan ◽  
Aaron Xavier ◽  
Blossom Treesa Bastian ◽  
Ajay Ragh ◽  
Naveen Chittilapilly
Keyword(s):  
Radar Reflectivity ◽  
Reduced Order Model ◽  
Motion Field ◽  
L1 Norm ◽  
Order Model ◽  
Linear Dynamics ◽  
Reduced Order ◽  
Squall Lines ◽  
Short Period ◽  
Non Linear

<div>Radar-based precipitation nowcasting refers to predicting rain for a short period of time using radar reflectivity images. For dynamic nowcasting, motion fields can be extrapolated using an approximate and localized reduced-order model. Motion field estimation based on traditional Horn-Schunck (HS) algorithm suffers from over-smoothing at discontinuities in non-rigid and dissolving texture present in precipitation nowcasting products. An attempt to preserve the discontinuities using an L1 norm formulation in HS led to the use of Total Variation L1 norm (TVL1). In this paper, we propose a radar-based precipitation nowcasting model with TVL1-based estimation of motion field and Sparse Identification of Non-linear Dynamics (SINDy)-based</div><div>estimation of non-linear dynamics. TVL1 is effective in preserving the edges especially in the case of the eye of typhoons and squall lines while estimating motion vectors. SINDy captures the non-linear dynamics and generates the subsequent update values for the motion field based on a reduced-order representation. Finally, the SINDy-generated ensemble of motion field is used along with</div><div>the radar reflectivity image for generating precipitation nowcasts. We evaluated the effectiveness of TVL1 in preserving edges while capturing the motion field from non-rigid surfaces. The performance of the proposed TVL1-SINDy model in nowcasting weather events such as Typhoons and Squall lines are evaluated using performance metrics such as Mean Absolute Error (MAE), and Critical Success Index (CSI). Experimental results show that the proposed nowcasting system demonstrates better performance compared to the benchmark nowcasting models with lower MAE, higher CSI at higher lead times.</div>

Aortic valve stenosis

2015 ◽  
pp. 129-140
Author(s):  
Helmut Baumgartner ◽  
Erwan Donal ◽  
Stefan Orwat ◽  
Axel Schmermund ◽  
Raphael Rosenhek ◽  
...  
Keyword(s):  
Aortic Valve ◽  
Aortic Valve Stenosis ◽  
Continuity Equation ◽  
Imaging Techniques ◽  
Integrated Approach ◽  
Aortic Disease ◽  
Left Ventricular ◽  
Prognostic Information ◽  
And Function ◽  
Available Information

Echocardiography is the method of choice for the diagnosis, assessment of morphology, and aetiology, as well as quantification of aortic valve stenosis. It permits the additional evaluation of the consequences on left ventricular size and, function, wall thickness, mitral valve (functional regurgitation).Haemodynamic assessment can be performed by Doppler echocardiography providing transvalvular gradients and valve areas can be determined by the continuity equation. Recently, MR and CT imaging have gained importance for assessment of valve morphology, ventricular function, and associated aortic disease. In current practice their role in quantifying severity of valve stenosis, however, remains limited. It is important to be aware of the specific limitations and pitfalls of the various measurements. Final judgement should be based on an integrated approach involving all available information. Finally, imaging techniques provide important prognostic information in aortic valve stenosis and have a fundamental impact on the decision making process in clinical practice.

Sign in / Sign up

Export Citation Format

Share Document