Dr. Carol L. Novak Profile

Dr. Carol L. Novak

Staff Scientist at Siemens Medical Solutions USA, Inc.

SPIE Involvement:

Conference Program Committee | Conference Chair | Editor | Author

Publications (38)

SPIE Conference Volume | April 18, 2013

Medical Imaging 2013: Computer-Aided Diagnosis

PROCEEDINGS ARTICLE | March 13, 2013

Pulmonary lobe segmentation using the thin plate spline (TPS) with the help of the fissure localization areas

Proc. SPIE. 8669, Medical Imaging 2013: Image Processing

KEYWORDS: Lithium, Detection and tracking algorithms, Image segmentation, Image processing, Scanners, Ions, Lung, Computed tomography, Picosecond phenomena, Plutonium

Read Abstract

SPIE Conference Volume | April 13, 2012

Medical Imaging 2012: Computer-Aided Diagnosis

PROCEEDINGS ARTICLE | February 23, 2012

Comparison of analysis methods for airway quantification

Proc. SPIE. 8315, Medical Imaging 2012: Computer-Aided Diagnosis

KEYWORDS: Lithium, Visualization, Calibration, Image segmentation, Scanners, Arteries, Image filtering, Computed tomography, Analytical research, Chronic obstructive pulmonary disease

Read Abstract

PROCEEDINGS ARTICLE | March 9, 2010

Quantitative evaluation of bronchial enhancement: preliminary observations

Proc. SPIE. 7626, Medical Imaging 2010: Biomedical Applications in Molecular, Structural, and Functional Imaging

KEYWORDS: Visualization, Arteries, Image registration, Lung, Inflammation, Data acquisition, Iodine, Computed tomography, Dual energy imaging, Chronic obstructive pulmonary disease

Read Abstract

PROCEEDINGS ARTICLE | March 27, 2009

Automated alignment of MRI brain scan by anatomic landmarks

Proc. SPIE. 7259, Medical Imaging 2009: Image Processing

KEYWORDS: Detection and tracking algorithms, Magnetic resonance imaging, Image segmentation, Diagnostics, Bone, Head, Skull, Neuroimaging, 3D image processing, Brain

Read Abstract

PROCEEDINGS ARTICLE | February 28, 2009

Evaluation of scoring accuracy for airway wall thickness

Proc. SPIE. 7260, Medical Imaging 2009: Computer-Aided Diagnosis

KEYWORDS: Visualization, Image segmentation, Scanners, Inspection, Computing systems, Arteries, Image analysis, Optical inspection, Computed tomography, Chronic obstructive pulmonary disease

Read Abstract

Bronchial wall thickening is commonly observed in airway diseases. One method often used to quantitatively evaluate wall thickening in CT images is to estimate the ratio of the bronchial wall to the accompanying artery, or BWA ratio, and then assign a severity score based on the ratio. Assessment by visual inspection is unfortunately limited to airways perpendicular or parallel to the scanning plane. With high-resolution images from multi-detector CT scanners, it becomes possible to assess airways in any orientation. We selected CT scans from 20 patients with mild to severe COPD. A computer system automatically segmented each bronchial tree and measured the bronchial wall thicknesses. Next, neighboring arteries were detected and measured to determine BWA ratios. A score characterizing the extent and severity of wall thickening within each lobe was computed according to recommendations by Sheehan et al [1]. Two experienced radiologists independently scored wall thickening using visual assessment. Spearman's rank correlation showed a non-significant negative correlation (r=-0.1) between the computer and the reader average (p=0.4), while the correlation between readers was significant at r=0.65 (p=0.001). We subsequently identified 24 lobes with high discrepancies between visual and automated scoring. The readers re-examined those lobes and measured wall thickness using electronic calipers on perpendicular cross sections, rather than visual assessment. Using this more objective standard of wall thickness, the reader estimates of wall thickening increased to reach a significant positive correlation with automated scoring of r=0.65 (p=0.001). These results indicate that subjectivity is an important problem with visual evaluation, and that visual inspection may frequently underestimate disease extent and severity. Given that a manual evaluation of all airways is infeasible in routine clinical practice, we argue that automated methods should be developed and utilized.

PROCEEDINGS ARTICLE | February 28, 2009

Automated detection of presence of mucus foci in airway diseases: preliminary results

Proc. SPIE. 7260, Medical Imaging 2009: Computer-Aided Diagnosis

KEYWORDS: Detection and tracking algorithms, Visualization, Image segmentation, Lung, Optical inspection, Computed tomography, Reconstruction algorithms, Binary data, Cystic fibrosis, Chronic obstructive pulmonary disease

Read Abstract

PROCEEDINGS ARTICLE | March 26, 2008

Fuzzy pulmonary vessel segmentation in contrast enhanced CT data

Proc. SPIE. 6914, Medical Imaging 2008: Image Processing

KEYWORDS: Photovoltaics, Chest, Computer aided diagnosis and therapy, Visualization, Image segmentation, Arteries, Lung, Computed tomography, Binary data, Fuzzy logic

Read Abstract

PROCEEDINGS ARTICLE | March 17, 2008

An evaluation of automated broncho-arterial ratios for reliable assessment of bronchiectasis

Proc. SPIE. 6915, Medical Imaging 2008: Computer-Aided Diagnosis

KEYWORDS: Computer aided diagnosis and therapy, Image segmentation, Diagnostics, Computer simulations, Arteries, Lung, Medical imaging, Computed tomography, Solid modeling, Classification systems

Read Abstract

PROCEEDINGS ARTICLE | March 12, 2008

Active contour approach for accurate quantitative airway analysis

Proc. SPIE. 6916, Medical Imaging 2008: Physiology, Function, and Structure from Medical Images

KEYWORDS: Point spread functions, Sensors, Calibration, Image segmentation, Diagnostics, Arteries, Lung, Medical imaging, Computed tomography, Information operations

Read Abstract

PROCEEDINGS ARTICLE | May 10, 2007

Novel method and applications for labeling and identifying lymph nodes

Proc. SPIE. 6511, Medical Imaging 2007: Physiology, Function, and Structure from Medical Images

KEYWORDS: Chest, Cancer, Visualization, Image segmentation, Image processing, Lung, Biopsy, Computed tomography, Lung cancer, Lymphatic system

Read Abstract

PROCEEDINGS ARTICLE | May 10, 2007

Automated detection of mucus plugs within bronchial tree in MSCT images

Proc. SPIE. 6511, Medical Imaging 2007: Physiology, Function, and Structure from Medical Images

KEYWORDS: Optical spheres, Image segmentation, Image processing, Lung, Inflammation, Shape analysis, Computed tomography, Algorithm development, Tolerancing, Chronic obstructive pulmonary disease

Read Abstract

PROCEEDINGS ARTICLE | March 26, 2007

Solid component evaluation in mixed ground glass nodules

Proc. SPIE. 6512, Medical Imaging 2007: Image Processing

KEYWORDS: Lithium, Image segmentation, Glasses, Image processing, 3D modeling, Lung, Solids, Computed tomography, Radiology, Algorithm development

Read Abstract

PROCEEDINGS ARTICLE | March 7, 2007

Automatic corpus callosum segmentation for standardized MR brain scanning

Proc. SPIE. 6512, Medical Imaging 2007: Image Processing

KEYWORDS: 3D acquisition, Magnetic resonance imaging, Image segmentation, Magnetism, Diagnostics, 3D modeling, Medical imaging, Neuroimaging, 3D image processing, Brain

Read Abstract

PROCEEDINGS ARTICLE | March 7, 2007

Automated definition of mid-sagittal planes for MRI brain scans

Proc. SPIE. 6512, Medical Imaging 2007: Image Processing

KEYWORDS: Lithium, Visualization, Magnetic resonance imaging, Diagnostics, Image resolution, Computer science, Head, Neuroimaging, Electrical engineering, Brain

Read Abstract

PROCEEDINGS ARTICLE | March 17, 2006

A comparison of 2D and 3D evaluation methods for pulmonary embolism detection in CT images

Proc. SPIE. 6146, Medical Imaging 2006: Image Perception, Observer Performance, and Technology Assessment

KEYWORDS: Visualization, Image segmentation, Interfaces, Arteries, 3D modeling, Lung, Computed tomography, 3D vision, 3D visualizations, 3D image processing

Read Abstract

PROCEEDINGS ARTICLE | March 13, 2006

Automated airway evaluation system for multi-slice computed tomography using airway lumen diameter, airway wall thickness and broncho-arterial ratio

Proc. SPIE. 6143, Medical Imaging 2006: Physiology, Function, and Structure from Medical Images

KEYWORDS: Visualization, Image segmentation, Inspection, Computing systems, Arteries, Lung, Optical inspection, Computed tomography, 3D visualizations, Emphysema

Read Abstract

Pulmonary diseases such as bronchiectasis, asthma, and emphysema are characterized by abnormalities in airway dimensions. Multi-slice computed tomography (MSCT) has become one of the primary means to depict these abnormalities, as the availability of high-resolution near-isotropic data makes it possible to evaluate airways at oblique angles to the scanner plane. However, currently, clinical evaluation of airways is typically limited to subjective visual inspection only: systematic evaluation of the airways to take advantage of high-resolution data has not proved practical without automation. We present an automated method to quantitatively evaluate airway lumen diameter, wall thickness and broncho-arterial ratios. In addition, our method provides 3D visualization of these values, graphically illustrating the location and extent of disease. Our algorithm begins by automatic airway segmentation to extract paths to the distal airways, and to create a map of airway diameters. Normally, airway diameters decrease as paths progress distally; failure to taper indicates abnormal dilatation. Our approach monitors airway lumen diameters along each airway path in order to detect abnormal profiles, allowing even subtle degrees of pathologic dilatation to be identified. Our method also systematically computes the broncho-arterial ratio at every terminal branch of the tree model, as a ratio above 1 indicates potentially abnormal bronchial dilatation. Finally, the airway wall thickness is computed at corresponding locations. These measurements are used to highlight abnormal branches for closer inspection, and can be summed to compute a quantitative global score for the entire airway tree, allowing reproducible longitudinal assessment of disease severity. Preliminary tests on patients diagnosed with bronchiectasis demonstrated rapid identification of lack of tapering, which also was confirmed by corresponding demonstration of elevated broncho-arterial ratios.

PROCEEDINGS ARTICLE | March 13, 2006

A novel multipurpose tree and path matching algorithm with application to airway trees

Proc. SPIE. 6143, Medical Imaging 2006: Physiology, Function, and Structure from Medical Images

KEYWORDS: Veins, Chest, Detection and tracking algorithms, Image segmentation, Matrices, Arteries, Lung, Medical imaging, Computed tomography, Tolerancing

Read Abstract

PROCEEDINGS ARTICLE | March 10, 2006

Robust local intervertebral disc alignment for spinal MRI

Proc. SPIE. 6144, Medical Imaging 2006: Image Processing

KEYWORDS: Detection and tracking algorithms, Magnetic resonance imaging, Image segmentation, Scanners, Reliability, Magnetism, Diagnostics, Spine, Binary data, Automatic alignment

Read Abstract

PROCEEDINGS ARTICLE | March 10, 2006

Segmentation of hand radiographs using fast marching methods

Proc. SPIE. 6144, Medical Imaging 2006: Image Processing

KEYWORDS: Data modeling, Visualization, Image segmentation, Image processing, Radiography, Wavefronts, Image registration, Bone, Wave propagation, Binary data

Read Abstract

PROCEEDINGS ARTICLE | April 29, 2005

A computer-based method of segmenting ground glass nodules in pulmonary CT images: comparison to expert radiologists’ interpretations

Proc. SPIE. 5747, Medical Imaging 2005: Image Processing

KEYWORDS: Software, Chest, Tumor growth modeling, Data modeling, Image segmentation, Glasses, Solids, Computed tomography, Lung cancer, Magnetorheological finishing

Read Abstract

PROCEEDINGS ARTICLE | April 29, 2005

The effects of 3D region-based compression on the performance of an automatic lung nodule detection system

Proc. SPIE. 5747, Medical Imaging 2005: Image Processing

KEYWORDS: Image processing algorithms and systems, Image compression, Computer aided diagnosis and therapy, Detection and tracking algorithms, Image segmentation, JPEG2000, Lung, Medical imaging, Computed tomography, Computer aided design

Read Abstract

There is growing interest in computer aided diagnosis applications including automatic detection of lung nodules from multislice computed tomography (CT). However the increase in the number and size of CT datasets introduces high costs for data storage and transmission, and becomes an obstacle to routine clinical exam as well as hindering widespread utilization of computerized applications. We investigated the effects of 3D lossy region-based JPEG2000 standard compression on the results of an automatic lung nodule detection system. As the algorithm detects the lungs within the datasets, we used this lung segmentation to define a region of interest (ROI) where the compression should be of higher fidelity. We tested 4 methods of 3D compression: 1) default compression of the whole image, 2) default compression of segmented lungs with masking out all non-lung regions, 3) ROI-based compression as specified in the JPEG2000 standard and 4) compression where voxels in the ROI are weighted to be given emphasis in the encoding. We tested 7 compression ratios per method: 1, 4, 6, 8, 10, 20, and 30 to 1. We then evaluated our experimental CAD algorithm on 10 patients with 67 documented nodules initially identified on the decompressed data. Sensitivities and false positive rates were compared for the various compression methods and ratios. We found that region-based compression generally performs better than default compression. The sensitivity with default compression decreased from 85% at no compression to 61% at 30:1 compression, a decrease of 25%, whereas the masked compression method saw a decreased in sensitivity on only 13.5% at maximum compression. At compression levels up to 10:1, all 3 region-based compression methods had decreases in sensitivity of 7.5% or less. Detection of small nodules (< 4mm in diameter) was more affected by compression than detection of large nodules; sensitivity to calcified nodules was less affected by compression than to non-calcified nodules.

PROCEEDINGS ARTICLE | April 14, 2005

Virtual bronchoscopy of peripheral nodules using arteries as surrogate pathways

Proc. SPIE. 5746, Medical Imaging 2005: Physiology, Function, and Structure from Medical Images

KEYWORDS: Endoscopy, Visualization, Image segmentation, Scanners, Arteries, Lung, Biopsy, Optical inspection, Computed tomography, Bronchoscopy

Read Abstract

PROCEEDINGS ARTICLE | April 14, 2005

Perfusion visualization and analysis for pulmonary embolism

Proc. SPIE. 5746, Medical Imaging 2005: Physiology, Function, and Structure from Medical Images

KEYWORDS: Visual analytics, Phase modulation, Visualization, Opacity, Signal attenuation, Blood, Image segmentation, Lung, Computed tomography, 3D visualizations

Read Abstract

PROCEEDINGS ARTICLE | April 12, 2005

Cartwheel projections of segmented pulmonary vasculature for the detection of pulmonary embolism

Proc. SPIE. 5744, Medical Imaging 2005: Visualization, Image-Guided Procedures, and Display

KEYWORDS: Human-machine interfaces, Computer aided diagnosis and therapy, Detection and tracking algorithms, Visualization, Image segmentation, Scanners, Medical research, Arteries, Lung, Computed tomography

Read Abstract

PROCEEDINGS ARTICLE | May 12, 2004

Analysis of arterial subtrees affected by pulmonary emboli

Proc. SPIE. 5370, Medical Imaging 2004: Image Processing

KEYWORDS: Veins, Chest, Visualization, Image segmentation, Image resolution, Arteries, 3D modeling, Lung, Computed tomography, Analytical research

Read Abstract

PROCEEDINGS ARTICLE | May 12, 2004

Consistent interactive segmentation of pulmonary ground glass nodules identified in CT studies

Proc. SPIE. 5370, Medical Imaging 2004: Image Processing

KEYWORDS: Data modeling, Opacity, Image segmentation, Glasses, Lung, Solids, Shape analysis, Computed tomography, Magnetorheological finishing, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | May 12, 2004

System for automatic detection of lung nodules exhibiting growth

Proc. SPIE. 5370, Medical Imaging 2004: Image Processing

KEYWORDS: Chest, Computer aided diagnosis and therapy, Cancer, Detection and tracking algorithms, Tissues, Feature extraction, Lung, Solids, Computed tomography, Lung cancer

Read Abstract

PROCEEDINGS ARTICLE | May 5, 2004

A novel method for pulmonary emboli visualization from high-resolution CT images

Proc. SPIE. 5367, Medical Imaging 2004: Visualization, Image-Guided Procedures, and Display

KEYWORDS: Veins, Visualization, Blood, Image segmentation, Arteries, Lung, Angiography, Computed tomography, Algorithm development, Mathematical morphology

Read Abstract

PROCEEDINGS ARTICLE | May 22, 2003

Identification of missed pulmonary nodules on low-dose CT lung cancer screening studies using an automatic detection system

Proc. SPIE. 5034, Medical Imaging 2003: Image Perception, Observer Performance, and Technology Assessment

KEYWORDS: Computer aided diagnosis and therapy, Detection and tracking algorithms, Glasses, Scanners, Feature extraction, Lung, Solids, Computed tomography, Lung cancer, Algorithm development

Read Abstract

PROCEEDINGS ARTICLE | May 15, 2003

Method for intensity correction in CR mosaic by combined nonlinear and linear transformations

Proc. SPIE. 5032, Medical Imaging 2003: Image Processing

KEYWORDS: Visualization, Metals, X-ray sources, Radiography, Diagnostics, Image acquisition, Chromium, Bone, Image enhancement, Visibility

Read Abstract

PROCEEDINGS ARTICLE | May 9, 2002

Knowledge-based automatic detection of multitype lung nodules from multidetector CT studies

Proc. SPIE. 4684, Medical Imaging 2002: Image Processing

KEYWORDS: Chest, Detection and tracking algorithms, Opacity, Image processing, Feature extraction, Lung, Medical imaging, Computed tomography, Algorithm development, Dimension reduction

Read Abstract

PROCEEDINGS ARTICLE | April 12, 2002

Interobserver variations on interpretation of multislice CT lung cancer screening studies, and the implications for computer-aided diagnosis

Proc. SPIE. 4686, Medical Imaging 2002: Image Perception, Observer Performance, and Technology Assessment

KEYWORDS: Gold, X-ray computed tomography, Computer aided diagnosis and therapy, Detection and tracking algorithms, Visualization, Computing systems, Feature extraction, Lung, Computed tomography, Lung cancer

Read Abstract

PROCEEDINGS ARTICLE | July 3, 2001

Automatic detection of lung nodules from multislice low-dose CT images

Proc. SPIE. 4322, Medical Imaging 2001: Image Processing

KEYWORDS: Chest, X-ray computed tomography, Tissues, Image segmentation, Feature extraction, Lung, Computed tomography, Lung cancer, Binary data, 3D image processing

Read Abstract

PROCEEDINGS ARTICLE | June 1, 1991

Supervised color constancy for machine vision

Proc. SPIE. 1453, Human Vision, Visual Processing, and Digital Display II

KEYWORDS: Light sources, Visualization, Cameras, Sensors, Reflectivity, Machine vision, Neural networks, Human vision and color perception, Device simulation, RGB color model

Read Abstract

PROCEEDINGS ARTICLE | August 1, 1990

Physics-based models for early vision by machine

Proc. SPIE. 1250, Perceiving, Measuring, and Using Color

KEYWORDS: Light sources, Visual process modeling, Data modeling, Reflection, Image segmentation, Image processing, Image analysis, Machine vision, Analytical research, RGB color model

Read Abstract

PROCEEDINGS ARTICLE | August 1, 1990

Obtaining accurate color images for machine-vision research

Proc. SPIE. 1250, Perceiving, Measuring, and Using Color

KEYWORDS: Chromatic aberrations, Optical filters, Visible radiation, Imaging systems, Cameras, Sensors, Video, Machine vision, Infrared radiation, RGB color model

Read Abstract