Dr. Jocelyn Hoye Profile

Dr. Jocelyn Hoye

Postdoctoral Research Associate

SPIE Involvement:

Author

Publications (15)

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

An analysis of radiomics features in lung lesions in COVID-19

Anna Marie Gann, Ehsan Abadi, Jocelyn Hoye, Thomas Sauer, W. Paul Segars, Hamid Chalian, Ehsan Samei

Proceedings Volume 11595, 115953K (2021) https://doi.org/10.1117/12.2582296

KEYWORDS: Lung, Image segmentation, Computed tomography, Statistical analysis, Chest

Read Abstract +

Proceedings Article | 16 March 2020 Paper

A method to assess the performance and the relevance of segmentation in radiomic characterization

Jocelyn Hoye, Taylor Richards, Justin Solomon, Ehsan Samei

Proceedings Volume 11312, 113122O (2020) https://doi.org/10.1117/12.2549097

KEYWORDS: Image segmentation, Image quality, Image processing algorithms and systems, Algorithm development, Image resolution, Image processing, Lung, Computed tomography, Computer simulations, Feature extraction

Read Abstract +

The quantification of radiomics features is impacted by a complex interplay of image quality and segmentation performance. To understand and optimize the process, it is highly beneficial to isolate the impact of each factor quantitatively. The purpose of this study was to develop a segmentation performance index (𝑠′) to describe the segmentation performance relative to an ideal estimation, and further apply the index across several segmentation algorithms and image quality conditions in the task of characterizing lesion morphology. First, an estimator was developed with prior knowledge of the lesion and the imaging resolution properties to represent the best that an ideal segmentation operator would be expected to yield given the information content available from the image. Using three anthropomorphic lesion models of a mean contrast of 600 HU and mean radius of 5 mm, the method was applied to three segmentation operators based on (1) active contour, (2) thresholding, and (3) a commercial vendor offering (Siemens Healthineers). Images of the lesions were simulated in a uniform background for a Siemens Flash filtered back-projection (FBP) B31f reconstruction with noise magnitude ranging from 10 HU to 230 HU. Images were simulated 50 times at each noise magnitude to assess test-retest variability. The segmentation masks were used to calculate a root mean square error (RMSE) across test-retest images for morphology and size radiomics features. The ideal estimation RMSE was calculated for each feature and was divided by the segmentation RMSE resulting in the segmentation performance index (𝑠′). The 𝑠′ values were evaluated as a function of increasing noise. Traditional segmentation quality metrics including dice coefficient, volume similarity, and Hausdorff distance were also calculated for each noise magnitude to compare against the 𝑠′ index. Traditional segmentation quality metrics are not reflective of radiomics performance. The 𝑠′ values, in contrast, were found to be both feature-specific and noisespecific, useful in characterizing the performance of segmentation algorithms in measuring radiomics features. This allows for the choice of segmentation algorithms to yield optimum radiomic performance for a given imaging condition and or protocol.

SPIE Journal Paper | 12 July 2019

Systematic analysis of bias and variability of texture measurements in computed tomography

Marthony Robins, Justin Solomon, Jocelyn Hoye, Ehsan Abadi, Daniele Marin, Ehsan Samei

JMI, Vol. 6, Issue 03, 033503, (July 2019) https://doi.org/10.1117/12.10.1117/1.JMI.6.3.033503

KEYWORDS: Computed tomography, Image acquisition, Tumors, Reconstruction algorithms, Imaging systems, Scanners, Biological research, Statistical analysis, Image segmentation, Image resolution

Read Abstract +

Texture is a key radiomics measurement for quantification of disease and disease progression. The sensitivity of the measurements to image acquisition, however, is uncertain. We assessed bias and variability of computed tomography (CT) texture feature measurements across many clinical image acquisition settings and reconstruction algorithms. Diverse, anatomically informed textures (texture A, B, and C) were simulated across 1188 clinically relevant CT imaging conditions representing four in-plane pixel sizes (0.4, 0.5, 0.7, and 0.9 mm), three slice thicknesses (0.625, 1.25, and 2.5 mm), three dose levels (CTDIvol 1.90, 3.75, and 7.50 mGy), and 33 reconstruction kernels. Imaging conditions corresponded to noise and resolution properties representative of five commercial scanners (GE LightSpeed VCT, GE Discovery 750 HD, GE Revolution, Siemens Definition Flash, and Siemens Force) in filtered backprojection and iterative reconstruction. About 21 texture features were calculated and compared between the ground-truth phantom (i.e., preimaging) and its corresponding images. Each feature was measured with four unique volumes of interest (VOIs) sizes (244, 579, 1000, and 1953 mm3. To characterize the bias, the percentage relative difference [PRD(%)] in each feature was calculated between the imaged scenario and the ground truth for all VOI sizes. Feature variability was assessed in terms of (1) σPRD ( % ) indicating the variability between the ground truth and simulated image scenario based on the PRD(%), (2) COVf indicating the simulation-based variability, and (3) COVT indicating the natural variability present in the ground-truth phantom. The PRD ranged widely from −97 % to 1220%, with an underlying variability (σ) of up to 241%. Features such as gray-level nonuniformity, texture entropy, sum average, and homogeneity exhibited low susceptibility to reconstruction kernel effects (PRD < 3 % ) with relatively small σPRD ( % ) (≤5 % ) across imaging conditions. The dynamic range of results indicates that image acquisition and reconstruction conditions of in-plane pixel sizes, slice thicknesses, dose levels, and reconstruction kernels can lead to significant bias and variability in feature measurements.

SPIE Journal Paper | 21 June 2019

Design and fabrication of heterogeneous lung nodule phantoms for assessing the accuracy and variability of measured texture radiomics features in CT

Ehsan Samei, Jocelyn Hoye, Yuese Zheng, Justin Solomon, Daniele Marin

JMI, Vol. 6, Issue 02, 021606, (June 2019) https://doi.org/10.1117/12.10.1117/1.JMI.6.2.021606

KEYWORDS: 3D modeling, Lung, Computed tomography, Mahalanobis distance, Genetic algorithms, Scanners, 3D printing, Feature extraction, Databases, Chest

Read Abstract +

We aimed to design and fabricate synthetic lung nodules with patient-informed internal heterogeneity to assess the variability and accuracy of measured texture features in CT. To that end, 190 lung nodules from a publicly available database of chest CT images (Lung Image Database Consortium) were selected based on size (>3 mm) and malignancy. The texture features of the nodules were used to train a statistical texture synthesis model based on clustered lumpy background. The model parameters were ascertained based on a genetic optimization of a Mahalanobis distance objective function. The resulting texture model defined internal heterogeneity within 24 anthropomorphic lesion models which were subsequently fabricated into physical phantoms using a multimaterial three-dimensional (3-D) printer. The 3-D-printed lesions were imbedded in an anthropomorphic chest phantom and imaged with a clinical scanner using different acquisition parameters including slice thickness, dose level, and reconstruction kernel. The imaged lesions were analyzed in terms of texture features to ascertain the impact of CT imaging on lesion texture quantification. The texture modeling method produced lesion models with low and stable Mahalanobis distance between real and synthetic textures. The virtual lesions were successfully printed into 3-D phantoms. The accuracy and variability of the measured features extracted from the CT images of the phantoms showed notable influence from the imaging acquisition parameters with contrast, energy, and texture entropy exhibiting most sensitivity in terms of accuracy, and contrast, dissimilarity, and texture entropy most variability. Thinner slice thicknesses yielded more accurate and edge reconstruction kernels more stable results. We conclude that printed textured models of lesions can be developed using a method that can target and minimize the mathematical distance between real and synthetic lesions. The synthetic lesions can be used as the basis to investigate how CT imaging conditions might affect radiomics features derived from CT images.

SPIE Journal Paper | 26 March 2019

Systematic analysis of bias and variability of morphologic features for lung lesions in computed tomography

Jocelyn Hoye, Justin Solomon, Thomas Sauer, Marthony Robins, Ehsan Samei

JMI, Vol. 6, Issue 01, 013504, (March 2019) https://doi.org/10.1117/12.10.1117/1.JMI.6.1.013504

KEYWORDS: Image segmentation, Computed tomography, Lung, Image processing algorithms and systems, Scanners, Computer simulations, Imaging systems, Fuzzy logic, Image resolution, Reconstruction algorithms

Read Abstract +

We propose to characterize the bias and variability of quantitative morphology features of lung lesions across a range of computed tomography (CT) imaging conditions. A total of 15 lung lesions were simulated (five in each of three spiculation classes: low, medium, and high). For each lesion, a series of simulated CT images representing different imaging conditions were synthesized by applying three-dimensional blur and adding correlated noise based on the measured noise and resolution properties of five commercial multislice CT systems, representing three dose levels (CTDIvol of 1.90, 3.75, 7.50 mGy), three slice thicknesses (0.625, 1.25, 2.5 mm), and 33 clinical reconstruction kernels from five clinical scanners. The images were segmented using three segmentation algorithms and each algorithm was evaluated by computing a Sørensen–Dice coefficient between the ground truth and the segmentation. A series of 21 shape-based morphology features were extracted from both “ground truth” (i.e., preblur without noise) and “image rendered” lesions (i.e., postblur and with noise). For each morphology feature, the bias was quantified by comparing the percentage relative error in the morphology metric between the imaged lesions and the ground-truth lesions. The variability was characterized by calculating the average coefficient of variation averaged across repeats and imaging conditions. The active contour segmentation had the highest average Dice coefficient of 0.80 followed by 0.63 for threshold, and 0.39 for fuzzy c-means. The bias of the features was segmentation algorithm and feature-dependent, with sharper kernels being less biased and smoother kernels being more biased in general. The feature variability from simulated images ranged from 0.30% to 10% for repeats of the same condition and from 0.74% to 25.3% for different lesions in the same spiculation class. In conclusion, the bias of morphology features is dependent on the acquisition protocol in combination with the segmentation algorithm used and the variability is primarily dependent on the segmentation algorithm.

Proceedings Article | 1 March 2019 Paper

Accuracy and variability of radiomics in photon-counting CT: texture features and lung lesion morphology

Jayasai Rajagopal, Jocelyn Hoye, Marthony Robins, Elizabeth Jones, Ehsan Samei

Proceedings Volume 10948, 109484J (2019) https://doi.org/10.1117/12.2512934

KEYWORDS: Photon counting, Computed tomography, Lung, Imaging systems, X-ray computed tomography, Radiology

Read Abstract +

Proceedings Article | 1 March 2019 Paper

Quantifying truth-based change in radiomics features between CT imaging conditions

Jocelyn Hoye, Justin Solomon , Ehsan Samei

Proceedings Volume 10948, 1094834 (2019) https://doi.org/10.1117/12.2512786

KEYWORDS: Computed tomography, Lung, Scanners, Data modeling, Systems modeling, Computer simulations, Radiology

Read Abstract +

SPIE Journal Paper | 24 September 2018

Interchangeability between real and three-dimensional simulated lung tumors in computed tomography: an interalgorithm volumetry study

Marthony Robins, Justin Solomon, Jocelyn Hoye, Taylor Smith, Yuese Zheng, Lukas Ebner, Kingshuk Roy Choudhury, Ehsan Samei

JMI, Vol. 5, Issue 03, 035504, (September 2018) https://doi.org/10.1117/12.10.1117/1.JMI.5.3.035504

KEYWORDS: Tumors, Computed tomography, Image segmentation, Lung, Computer simulations, Data modeling, Environmental sensing, Medicine, Chest, 3D modeling

Read Abstract +

Using hybrid datasets consisting of patient-derived computed tomography (CT) images with digitally inserted computational tumors, we establish volumetric interchangeability between real and computational lung tumors in CT. Pathologically-confirmed malignancies from 30 thoracic patient cases from the RIDER database were modeled. Tumors were either isolated or attached to lung structures. Patient images were acquired on one of two CT scanner models (Lightspeed 16 or VCT; GE Healthcare) using standard chest protocol. Real tumors were segmented and used to inform the size and shape of simulated tumors. Simulated tumors developed in Duke Lesion Tool (Duke University) were inserted using a validated image-domain insertion program. Four readers performed volume measurements using three commercial segmentation tools. We compared the volume estimation performance of segmentation tools between real tumors in actual patient CT images and corresponding simulated tumors virtually inserted into the same patient images (i.e., hybrid datasets). Comparisons involved (1) direct assessment of measured volumes and the standard deviation between simulated and real tumors across readers and tools, respectively, (2) multivariate analysis, involving segmentation tools, readers, tumor shape, and attachment, and (3) effect of local tumor environment on volume measurement. Volume comparison showed consistent trends (9% volumetric difference) between real and simulated tumors across all segmentation tools, readers, shapes, and attachments. Across all cases, readers, and segmentation tools, an intraclass correlation coefficient = 0.99 indicates that simulated tumors correlated strongly with real tumors (p = 0.95). In addition, the impact of the local tumor environment on tumor volume measurement was found to have a segmentation tool-related influence. Strong agreement between simulated tumors modeled in this study compared to their real counterparts suggests a high degree of similarity. This indicates that, volumetrically, simulated tumors embedded into patient CT data can serve as reasonable surrogates to real patient data.

Proceedings Article | 9 March 2018 Paper

Bias and variability in morphology features of lung lesions across CT imaging conditions

Jocelyn Hoye, Justin Solomon, Thomas Sauer, Marthony Robins, Ehsan Samei

Proceedings Volume 10573, 105731Z (2018) https://doi.org/10.1117/12.2293545

KEYWORDS: Computed tomography, Lung, Imaging systems, Scanners, Image acquisition, Image segmentation, Data modeling, Reconstruction algorithms

Read Abstract +

Proceedings Article | 9 March 2018 Paper

How reliable are texture measurements?

Marthony Robins, Justin Solomon, Jocelyn Hoye, Ehsan Abadi, Daniele Marin, Ehsan Samei

Proceedings Volume 10573, 105733W (2018) https://doi.org/10.1117/12.2294591

KEYWORDS: Computed tomography, Image acquisition, Tumors, Imaging systems, Reconstruction algorithms, Computer simulations, Data modeling, Image segmentation, Image resolution

Read Abstract +

Proceedings Article | 9 March 2018 Presentation + Paper

Realistic lesion simulation: application of hyperelastic deformation to lesion-local environment in lung CT

Thomas Sauer, Ehsan Abadi, Justin Solomon, Jocelyn Hoye, Ehsan Samei

Proceedings Volume 10573, 105731U (2018) https://doi.org/10.1117/12.2294962

KEYWORDS: Tissues, Lung, Image segmentation, Computed tomography, Finite element methods, Visualization, Data modeling, Solids, Mathematical modeling, Computer simulations

Read Abstract +

SPIE Journal Paper | 1 August 2017

Organ dose variability and trends in tomosynthesis and radiography

Jocelyn Hoye, Yakun Zhang, Greeshma Agasthya, Greg Sturgeon, Anuj Kapadia, Wiliam Segars, Ehsan Samei

JMI, Vol. 4, Issue 03, 031207, (August 2017) https://doi.org/10.1117/12.10.1117/1.JMI.4.3.031207

Read Abstract +

Proceedings Article | 9 March 2017 Presentation + Paper

An atlas-based organ dose estimator for tomosynthesis and radiography

Jocelyn Hoye, Yakun Zhang, Greeshma Agasthya, Greg Sturgeon, Anuj Kapadia, W. Paul Segars, Ehsan Samei

Proceedings Volume 10132, 1013204 (2017) https://doi.org/10.1117/12.2255583

KEYWORDS: Radiography, Monte Carlo methods, Databases, X-rays, Lung, Chest, Radiation dosimetry, Spine, Bone, Heart, Liver, Esophagus

Read Abstract +

Proceedings Article | 9 March 2017 Paper

Inter-algorithm lesion volumetry comparison of real and 3D simulated lung lesions in CT

Marthony Robins, Justin Solomon, Jocelyn Hoye, Taylor Smith, Lukas Ebner, Ehsan Samei

Proceedings Volume 10132, 101321S (2017) https://doi.org/10.1117/12.2254219

KEYWORDS: Image segmentation, Lung, Medicine, Computed tomography, 3D modeling, Databases, Data modeling, Performance modeling, Chest, Imaging systems, Mathematical modeling, 3D image processing

Read Abstract +

Proceedings Article | 29 March 2016 Paper

A dual energy CT study on vascular effects of gold nanoparticles in radiation therapy

Jeffrey Ashton, Jocelyn Hoye, Katherine Deland, Melodi Whitley, Yi Qi, Everett Moding, David Kirsch, Jennifer West, Cristian Badea

Proceedings Volume 9788, 97880W (2016) https://doi.org/10.1117/12.2217012

KEYWORDS: Computed tomography, Nanoparticles, Iodine, Radiotherapy, Dual energy imaging, Gold, Cancer, Preclinical imaging, Blood vessels, Magnesium, Tumors, Image segmentation

Read Abstract +

Gold nanoparticles (AuNPs) are emerging as promising agents for both cancer therapy and CT imaging. AuNPs are delivered to tumors via the enhanced permeability and retention effect and they preferentially accumulate in close proximity to the tumor blood vessels. AuNPs produce low-energy, short-range photoelectrons during external beam radiation therapy (RT), boosting dose. This work is focused on understanding how tumor vascular permeability is influenced by AuNP-augmented radiation therapy (RT), and how this knowledge can potentially improve the delivery of additional nanoparticle-based chemotherapeutics. We use dual energy (DE) CT to detect accumulation of AuNPs and increased vascular permeability to liposomal iodine (i.e. a surrogate for chemotherapeutics with liposome encapsulation) following RT. We used sarcoma tumors generated in LSL-Kras^G12D; p53^FL/FL conditional mutant mice. A total of n=37 mice were used in this study. The treated mice were injected with 20 mg AuNP (0.1 ml/25 g mouse) 24 hours before delivery of 5 Gy RT (n=5), 10 Gy RT (n=3) or 20 Gy RT (n=6). The control mice received no AuNP injection and either no RT (n=6), 5 Gy RT (n=3), 10 Gy RT (n=3), 20 Gy RT (n=11). Twenty four hours post-RT, the mice were injected with liposomal iodine (0.3 ml/25 mouse) and imaged with DE-CT three days later. The results suggest that independent of any AuNP usage, RT levels of 10 Gy and 20 Gy increase the permeability of tumor vasculature to liposomal iodine and that the increase in permeability is dose-dependent. We found that the effect of RT on vasculature may already be at its maximum response i.e. saturated at 20 Gy, and therefore the addition of AuNPs had almost no added benefit. Similarly, at 5 Gy RT, our data suggests that there was no effect of AuNP augmentation on tumor vascular permeability. However, by using AuNPs with 10 Gy RT, we observed an increase in the vascular permeability, however this is not yet statistically significant due to the small number of mice in these groups. Such an approach can be used together with a liposomal drug delivery system to increase specific tumor delivery of chemotherapeutics. Our method has the potential to significantly improve tumor therapy and reduce the side effects from both RT and chemotherapy.

Showing 5 of 15 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years