Dr. Andrew M. Hernandez Profile

Dr. Andrew M. Hernandez

Assistant Professor at UC Davis Health

SPIE Involvement:

Author

Publications (11)

Proceedings Article | 3 April 2024 Presentation + Paper

Harmonizing quantitative imaging feature values in CT using image quality metrics as a basis

Morgan Daly, John Hoffman, Andrew Hernandez, Ali Uneri, Jeffrey Siewerdsen, Paul Kinahan, Nicholas Bevins, Kalpana Kanal, David Zamora, Benjamin Maloney, J. Anthony Seibert, Mark Supanich, M. Mahesh, John Boone, Michael McNitt-Gray

Proceedings Volume 12927, 129271B (2024) https://doi.org/10.1117/12.3006885

KEYWORDS: Image quality, Scanners, Computed tomography, Modulation transfer functions, CT reconstruction, Quality measurement, Imaging systems, Feature extraction, Medical image reconstruction

Read Abstract +

Proceedings Article | 7 April 2023 Presentation + Paper

Impact of cone-beam CT noise correlation on self-supervised denoising strategies for low dose breast CT imaging

A. Sisniega, B. Íñigo, A. Hernandez, J. McGraw, Y. Achkire, J. Siewerdsen, J. Boone

Proceedings Volume 12463, 124630L (2023) https://doi.org/10.1117/12.2654447

KEYWORDS: Denoising, Education and training, Quantum noise, Quantum correlations, Breast, Data modeling, Systems modeling, Signal attenuation, Performance modeling, Computed tomography

Read Abstract +

Cone-beam breast CT (bCT) provides volumetric images of the uncompressed breast but present higher noise than 2D mammography. Deep Learning (DL) denoising with supervised training has shown successful CBCT noise reduction but requires matched low-dose and high-dose images. Self-supervised training removes that requirement but often assume locally independent noise. This work studies the impact of bCT noise correlation on self-supervised denoising methods. The self-supervised training strategies included two blind spot methods – Noise2Self, enforcing local similarity with independent image noise; and Noise2Sim, enforcing image similarity in presence of correlated noise – and two Noisier2Noise approaches: i) noise injection in the image domain; and, ii) noise injection in projection domain with a model of noise correlation. Self-supervised training was performed on bCT images generated from 150 voxelized models with a high-fidelity forward projector, including models of the x-ray spectrum, polychromatic attenuation, and detector signal and noise propagation. Denoised images were assessed with respect to high-dose references and supervised denoising, using RMSE, SSIM, and noise power spectrum (NPS). Noise2Sim and Noisier2Noise with noise injection in the projection domain showed good performance in presence of correlated noise, achieving RMSE of 0.21 and 0.18 (SSIM of 0.9 and 0.94), respectively, compared to RMSE of 0.17 (SSIM of 0.93) for supervised training. The independent noise assumption in Noise2Self and Noisier2Noise with image domain noise injection resulted in significantly diminished performance, yielding RMSE of 0.23 and 0.37 (SSIM of 0.86 and 0.84). The NPS measurements revealed a shift towards low frequency components for Noise2Sim, arising from blurring of tissue boundaries and residual image transfer induced by the masking of dissimilar regions in the loss function. Noisier2Noise showed a frequency distribution of noise closer to the high-dose reference. Such performance was slightly degraded for non-matched noise injection models inducing shorter correlation kernels than the nominal detector noise correlation, but models inducing longer correlation showed negligible impact in the denoising results. Self-supervised denoising in presence of correlated noise was proved feasible. Among the evaluated models, Noisier2Noise strategies with projection domain noise injection showed denoising performance comparable to supervised training and noise spectral distribution comparable to high-dose bCT.

SPIE Journal Paper | 20 July 2021

High-resolution μCT imaging for characterizing microcalcification detection performance in breast CT

Andrew Hernandez, Amy Becker, Su Hyun Lyu, Craig Abbey, John Boone

JMI, Vol. 8, Issue 05, 052107, (July 2021) https://doi.org/10.1117/12.10.1117/1.JMI.8.5.052107

KEYWORDS: Computed tomography, Calcium, Image segmentation, Breast, Imaging systems, Signal detection, Scanners, Modulation transfer functions, Carbonates, X-ray computed tomography

Read Abstract +

Purpose: To demonstrate the utility of high-resolution micro-computed tomography (μCT) for determining ground-truth size and shape properties of calcium grains for evaluation of detection performance in breast CT (bCT). Approach: Calcium carbonate grains (∼200 μm) were suspended in 1% agar solution to emulate microcalcifications (μCalcs) within a fibroglandular tissue background. Ground-truth imaging was performed on a commercial μCT scanner and was used for assessing calcium-grain size and shape, and for generating μCalc signal profiles. Calcium grains were placed within a realistic breast-shaped phantom and imaged on a prototype bCT system at 3- and 6-mGy mean glandular dose (MGD) levels, and the non-prewhitening detectability was assessed. Additionally, the μCT-derived signal profiles were used in conjunction with the bCT system characterization (MTF and NPS) to obtain predictions of bCT detectability. Results: Estimated detectability of the calcium grains on the bCT system ranged from 2.5 to 10.6 for 3 mGy and from 3.8 to 15.3 for 6 mGy with large fractions of the grains meeting the Rose criterion for visibility. Segmentation of μCT images based on morphological operations produced accurate results in terms of segmentation boundaries and segmented region size. A regression model linking bCT detectability to μCalc parameters indicated significant effects of μCalc size and vertical position within the breast phantom. Detectability using μCT-derived detection templates and bCT statistical properties (MTF and NPS) were in good correspondence with those measured directly from bCT (R2 > 0.88). Conclusions: Parameters derived from μCT ground-truth data were shown to produce useful characterizations of detectability when compared to estimates derived directly from bCT. Signal profiles derived from μCT imaging can be used in conjunction with measured or hypothesized statistical properties to evaluate the performance of a system, or system component, that may not currently be available.

SPIE Journal Paper | 29 March 2021

Computer-aided diagnosis of masses in breast computed tomography imaging: deep learning model with combined handcrafted and convolutional radiomic features

Marco Caballo, Andrew Hernandez, Su Hyun Lyu, Jonas Teuwen, Ritse Mann, Bram van Ginneken, John Boone, Ioannis Sechopoulos

JMI, Vol. 8, Issue 02, 024501, (March 2021) https://doi.org/10.1117/12.10.1117/1.JMI.8.2.024501

KEYWORDS: Computer aided diagnosis and therapy, Breast, Image segmentation, Feature extraction, Mammography, Computed tomography, Computing systems, 3D modeling, Solid modeling, 3D image processing

Read Abstract +

Proceedings Article | 22 May 2020 Paper

Advanced Monte Carlo application for in-silico clinical trials in x-ray breast imaging

A. Sarno, G. Mettivier, F. di Franco, G. Paternò, A. Taibi, P. Cardarelli, R. Tucciariello, M. E. Fantacci, K. Bliznakova, A. Hernandez, J. Boone, P. Russo

Proceedings Volume 11513, 1151315 (2020) https://doi.org/10.1117/12.2563322

KEYWORDS: Breast, Monte Carlo methods, Sensors, Tissues, Digital breast tomosynthesis, Clinical trials, X-rays, 3D image processing, X-ray imaging, Breast imaging

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

High resolution microcalcification signal profiles for dedicated breast CT

Andrew Hernandez, Amy Becker, Su Hyun Lyu, Craig Abbey, John Boone

Proceedings Volume 11312, 113120L (2020) https://doi.org/10.1117/12.2549872

KEYWORDS: Signal detection, Breast, Calcium, Signal generators, Imaging systems, Image segmentation, Image resolution, Scanners

Read Abstract +

Proceedings Article | 1 March 2019 Paper

Comparisons of 6 fps volume-rendered x-ray digital tomosynthesis TumoTrak-guided to 2D-MRI-guided radiotherapy of lung cancer

Larry Partain, Stanley Benedict, Namho Kim, Megan Daly, Austin Ely, Andrew Hernandez, Samuel Song, Micheal Weil, Vitaliy Ziskin, Kyle Foletta, John Boone, Douglas Boyd

Proceedings Volume 10948, 109483L (2019) https://doi.org/10.1117/12.2511993

KEYWORDS: Lung cancer, Radiotherapy, X-rays, Prototyping, Video, Digital imaging, Imaging systems, Cancer, 3D image processing, X-ray computed tomography

Read Abstract +

Proceedings Article | 1 March 2019 Presentation + Paper

Multi-x-ray source array for stationary tomosynthesis or multi-cone angle cone beam CT

John Boone, Amy Becker, Andrew Hernandez, James Dobbins, Paul Schwoebel

Proceedings Volume 10948, 109480U (2019) https://doi.org/10.1117/12.2512959

KEYWORDS: X-rays, X-ray computed tomography, X-ray sources, Sensors, Breast, Collimation, X-ray imaging, Prototyping, Scanners, Imaging systems

Read Abstract +

Proceedings Article | 6 July 2018 Paper

Multisource x-ray system for artifact reduction in dedicated breast CT

Amy Becker, Andrew Hernandez, Paul Schwoebel, John Boone

Proceedings Volume 10718, 107180O (2018) https://doi.org/10.1117/12.2317846

KEYWORDS: X-rays, Breast, X-ray sources, X-ray computed tomography, Scanners, Signal attenuation, Data acquisition, Cancer

Read Abstract +

Proceedings Article | 22 March 2016 Paper

kV x-ray dual digital tomosynthesis for image guided lung SBRT

Larry Partain, Douglas Boyd, Namho Kim, Andrew Hernandez, Megan Daly, John Boone

Proceedings Volume 9783, 978361 (2016) https://doi.org/10.1117/12.2216437

KEYWORDS: X-ray computed tomography, Digital imaging, Lung, X-rays, Image quality, Digital x-ray imaging, Lung cancer, Tumors, Radiotherapy, Imaging systems

Read Abstract +

Proceedings Article | 19 March 2014 Paper

Unfiltered Monte Carlo-based tungsten anode spectral model from 20 to 640 kV

A. Hernandez, John Boone

Proceedings Volume 9033, 90334P (2014) https://doi.org/10.1117/12.2042295

KEYWORDS: X-rays, Monte Carlo methods, Rhodium, Molybdenum, Spectral models, Tungsten, Mammography, X-ray imaging, Statistical modeling, Beryllium

Read Abstract +

Showing 5 of 11 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