Machine Learning Techniques for the Assessment of AAA Rupture Risk

2011 ◽  
Author(s):  
Judy Shum ◽  
Elena S. Di Martino ◽  
Satish C. Muluk ◽  
Ender A. Finol
Keyword(s):  
Wall Thickness ◽  
Three Dimensional ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Transverse Diameter ◽  
Data Sets ◽  
Rupture Risk ◽  
Elective Repair ◽  
Three Dimensional Models ◽  
Enhanced Computed Tomography

Recent clinical studies have shown that the maximum transverse diameter of an abdominal aortic aneurysm (AAA) alone, or in combination with its expansion rate are not entirely reliable indicators of rupture potential. We hypothesize that AAA shape, size, and wall thickness may be related to rupture risk and can be deciding factors in the clinical management of the disease. A non-invasive, image-based evaluation of AAA size and geometry was implemented using an in-house code (AAAVASC v1.0, Carnegie Mellon University) on a retrospective study of 88 subjects. The contrast enhanced, computed tomography (CT) scans of 44 patients who suffered AAA rupture within 1 month of the scan were compared to those of 44 patients who received elective repair. The images were segmented and three-dimensional models were generated. Twenty-eight geometry-based indices were calculated to characterize the size and shape of each AAA and estimate regional variations in wall thickness. A multivariate analysis of variance was performed for all indices comparing the ruptured and non-ruptured data sets to determine which indices were statistically significant. A classification model was created using a J48 decision tree algorithm and its performance was assessed using 10-fold cross validation. The model correctly classified eighty-six data sets and had an average prediction accuracy of 74% (κ = 0.69). Such a decision model can be used in a clinical setting to assess the risk of AAA rupture with minimal user intervention.

Geometry Quantification of Abdominal Aortic Aneurysms

2010 ◽  
Author(s):  
Judy Shum ◽  
Elena Di Martino ◽  
Satish Muluk ◽  
Ender A. Finol
Keyword(s):  
Wall Thickness ◽  
Three Dimensional ◽  
Roc Curves ◽  
Aortic Aneurysms ◽  
Maximum Diameter ◽  
Transverse Diameter ◽  
Rupture Risk ◽  
Abdominal Aortic ◽  
Elective Repair ◽  
Segmented Images

Recent studies have shown that the maximum transverse diameter of an abdominal aortic aneurysm (AAA) and expansion rate are not entirely reliable indicators of rupture potential. We hypothesize that aneurysm morphology and wall thickness can be quantified in a systematic approach leading to accurate differentiation of the geometric characteristics of aneurysm population subsets. A non-invasive, image-based evaluation of AAA shape was implemented on a retrospective study of sixty-six subjects who underwent elective repair and twenty-eight subjects who suffered AAA rupture within 1 month of their last pre-operative follow-up. The contrast-enhanced computed tomography (CT) scans of these patients were used to generate three-dimensional models from the segmented images. Twenty-eight geometry-based indices were calculated to characterize the size and shape of the AAA sac, and regional variations in wall thickness were estimated based on a novel segmentation algorithm. A multivariate analysis of variance using a maximum AAA diameter of 5.5 cm as a factor was performed for all indices as dependent variables, for the electively repaired group. Box and Whisker plots and ROC curves were generated to determine the indices’ potential as predictors of rupture risk. Listed from highest to lowest area under the ROC curve (AUC), the following six indices were found statistically significant (p < 0.05): volume (V, p < 0.0001), surface area (S, p < 0.0001), intraluminal thrombus volume (VILT, p < 0.0001), diameter-to-diameter ratio (DDr, p < 0.0001), diameter-to-height ratio (DHr, p = 0.015), and centroid distance of the maximum diameter (dc, p = 0.008). Given that individual AAAs have complex, tortuous and asymmetric shapes with local changes in surface curvature and wall thickness, the assessment of AAA rupture risk should require the accurate characterization of aneurysmal sac shape.

Quantitative Assessment of Abdominal Aortic Aneurysm Geometry and Rupture Potential

2009 ◽  
Author(s):  
Judy Shum ◽  
Giampaolo Martufi ◽  
Elena S. DiMartino ◽  
Ender A. Finol
Keyword(s):  
Abdominal Aortic Aneurysm ◽  
Aortic Aneurysm ◽  
Wall Thickness ◽  
Three Dimensional ◽  
Maximum Diameter ◽  
Transverse Diameter ◽  
Geometrical Shape ◽  
Rupture Risk ◽  
Abdominal Aortic ◽  
Elective Repair

Recent biomechanics studies have shown that the maximum transverse diameter of an abdominal aortic aneurysm (AAA) and its expansion rate are not reliable indicators of rupture potential. We hypothesize that geometrical shape and size, as well as wall thickness may be related to rupture risk and can therefore be deciding factors in the clinical management of the disease. A non-invasive, image-based evaluation of AAA size and geometry was implemented on a retrospective study of twenty subjects. The contrast enhanced, computed tomography (CT) scans of 10 patients who suffered AAA rupture within 1 month of the scan were compared to those of 10 patients who received elective repair. The images were segmented and three-dimensional models were generated. Twenty-eight geometry-based indices were calculated to characterize the size and shape of each AAA and regional variations in wall thickness were estimated. A multivariate analysis of variance was performed for all indices comparing the ruptured and non-ruptured data sets to determine which indices are statistically significant. Receiving Operating Characteristic (ROC) curves were generated to determine the indices’ potential as predictors of rupture risk. In addition to maximum diameter, five other geometry-based indices were found to be statistically significant, with the minimum wall thickness being the best discriminator between ruptures and non-ruptured AAAs.

Three-Dimensional Geometrical Characterization of Abdominal Aortic Aneurysms: Image-Based Wall Thickness Distribution

2009 ◽  
Vol 131 (6) ◽  
Author(s):  
Giampaolo Martufi ◽  
Elena S. Di Martino ◽  
Cristina H. Amon ◽  
Satish C. Muluk ◽  
Ender A. Finol
Keyword(s):  
Wall Thickness ◽  
Three Dimensional ◽  
Aortic Aneurysms ◽  
Maximum Diameter ◽  
Patient Specific ◽  
Future Research ◽  
Geometrical Shape ◽  
Rupture Risk ◽  
Abdominal Aortic ◽  
Elective Repair

The clinical assessment of abdominal aortic aneurysm (AAA) rupture risk is based on the quantification of AAA size by measuring its maximum diameter from computed tomography (CT) images and estimating the expansion rate of the aneurysm sac over time. Recent findings have shown that geometrical shape and size, as well as local wall thickness may be related to this risk; thus, reliable noninvasive image-based methods to evaluate AAA geometry have a potential to become valuable clinical tools. Utilizing existing CT data, the three-dimensional geometry of nine unruptured human AAAs was reconstructed and characterized quantitatively. We propose and evaluate a series of 1D size, 2D shape, 3D size, 3D shape, and second-order curvature-based indices to quantify AAA geometry, as well as the geometry of a size-matched idealized fusiform aneurysm and a patient-specific normal abdominal aorta used as controls. The wall thickness estimation algorithm, validated in our previous work, is tested against discrete point measurements taken from a cadaver tissue model, yielding an average relative difference in AAA wall thickness of 7.8%. It is unlikely that any one of the proposed geometrical indices alone would be a reliable index of rupture risk or a threshold for elective repair. Rather, the complete geometry and a positive correlation of a set of indices should be considered to assess the potential for rupture. With this quantitative parameter assessment, future research can be directed toward statistical analyses correlating the numerical values of these parameters with the risk of aneurysm rupture or intervention (surgical or endovascular). While this work does not provide direct insight into the possible clinical use of the geometric parameters, we believe it provides the foundation necessary for future efforts in that direction.

scholarly journals MulTiNet: Multimodal Neural Networks for Glaucoma Based on Transfer Learning

2021 ◽  
Author(s):  
Yi Li ◽  
YuJie Han ◽  
XueSi Zhao ◽  
ZiHan Li ◽  
ZhiFen Guo
Keyword(s):  
Transfer Learning ◽  
Medical Images ◽  
Open Angle Glaucoma ◽  
Three Dimensional ◽  
Classification Model ◽  
Angle Closure ◽  
Data Sets ◽  
Data Set ◽  
Primary Angle Closure ◽  
Glaucoma Diagnosis

Abstract Background: Being one of the most serious causes of irreversible blindness, glaucoma has many subtypes and complex symptoms. In clinic, doctors usually need to use a variety of medical images for diagnosis. Optical Coherence Tomography (OCT), Visual Field (VF) , Fundus Photosexams (FP) and Ultrasonic BioMicroscope (UBM) are widely-used and complementary techniques for diagnosing glaucoma.Methods: At present, the field of intelligent diagnosis of glaucoma is limited by two major problems. One is the small number of data sets, and the other is the low diagnostic accuracy of Single-Modal Modal. In order to solve the above two problems, we have done the following work. First, we construct DualSY glaucoma multimodal data set. The four most important subtypes of glaucoma are discussed in this article which are Primary Open Angle Glaucoma (POAG), Primary Angle Closure Glaucoma (PACG), Primary Angle Closure Suspect (PACS) and Primary Angle Closure (PAC). Each patient in the DualSY data set contains more than five medical images, as shown in the figure 4.And DualSY are labeled with image-level multi-labels. Second, We propose a new Multi-Modal classification network for glaucoma, which is a multiclass classification model with various medical images of glaucoma patients and text information as input. The network structure consists of three main branches to deal with patient metadata, domain-based glaucoma features and medical images. Transfer learning method is introduced into this paper due to the small number of medical image data sets. The flowchart is shown in Figure 5.Result: Our method on glaucoma diagnosis outperforms state-of-the-art methods. A promising average result of overall accuracy (ACC) of 94.7% is obtained. Our data set outperformed most data sets in glaucoma diagnosis with an accuracy of 87.8%.Conclusions: The results suggest that medical images such as Heidelberg OCT and three-dimensional fundus photos used in this paper can better express the high-level information of glaucoma and our modal greatly improve the accuracy of glaucoma diagnosis. At the same time, this data set has great potential, and we continue to study this data.

Computer-aided methods for 3-D visualization of serial sections and thick biological specimens

1992 ◽  
Vol 50 (2) ◽  
pp. 1060-1061
Author(s):  
Mark Ellisman ◽  
Maryann Martone ◽  
Gabriel Soto ◽  
Eleizer Masliah ◽  
David Hessler ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Three Dimensional ◽  
Neuritic Plaque ◽  
Dimensional Structure ◽  
Data Sets ◽  
Molecular Physiology ◽  
Research Activities ◽  
Computer Aided ◽  
Dimensional Reconstruction

Structurally-oriented biologists examine cells, tissues, organelles and macromolecules in order to gain insight into cellular and molecular physiology by relating structure to function. The understanding of these structures can be greatly enhanced by the use of techniques for the visualization and quantitative analysis of three-dimensional structure. Three projects from current research activities will be presented in order to illustrate both the present capabilities of computer aided techniques as well as their limitations and future possibilities.The first project concerns the three-dimensional reconstruction of the neuritic plaques found in the brains of patients with Alzheimer's disease. We have developed a software package “Synu” for investigation of 3D data sets which has been used in conjunction with laser confocal light microscopy to study the structure of the neuritic plaque. Tissue sections of autopsy samples from patients with Alzheimer's disease were double-labeled for tau, a cytoskeletal marker for abnormal neurites, and synaptophysin, a marker of presynaptic terminals.

Plastic replicas as three-dimensional models of pulps

1975 ◽  
Vol 39 (8) ◽  
pp. 544-546
Author(s):  
HL Wakkerman ◽  
GS The ◽  
AJ Spanauf
Keyword(s):  
Three Dimensional ◽  
Dimensional Models ◽  
Three Dimensional Models

Validation of a Belt Model for Prediction of Hub Forces from a Rolling Tire4

2009 ◽  
Vol 37 (2) ◽  
pp. 62-102 ◽  
Author(s):  
C. Lecomte ◽  
W. R. Graham ◽  
D. J. O’Boy
Keyword(s):  
Internal Pressure ◽  
Equations Of Motion ◽  
Three Dimensional ◽  
Prediction Method ◽  
Analytical Models ◽  
Beam Model ◽  
Impedance Boundary ◽  
Bending Waves ◽  
Tire Rotation ◽  
Three Dimensional Models

Abstract An integrated model is under development which will be able to predict the interior noise due to the vibrations of a rolling tire structurally transmitted to the hub of a vehicle. Here, the tire belt model used as part of this prediction method is first briefly presented and discussed, and it is then compared to other models available in the literature. This component will be linked to the tread blocks through normal and tangential forces and to the sidewalls through impedance boundary conditions. The tire belt is modeled as an orthotropic cylindrical ring of negligible thickness with rotational effects, internal pressure, and prestresses included. The associated equations of motion are derived by a variational approach and are investigated for both unforced and forced motions. The model supports extensional and bending waves, which are believed to be the important features to correctly predict the hub forces in the midfrequency (50–500 Hz) range of interest. The predicted waves and forced responses of a benchmark structure are compared to the predictions of several alternative analytical models: two three dimensional models that can support multiple isotropic layers, one of these models include curvature and the other one is flat; a one-dimensional beam model which does not consider axial variations; and several shell models. Finally, the effects of internal pressure, prestress, curvature, and tire rotation on free waves are discussed.

Sign in / Sign up

Export Citation Format

Share Document