Volume 10 Issue S2 | Journal of Medical Imaging

Journal of Medical Imaging

VOL. 10 · NO. S2 | February 2023

CONTENTS

IN THIS ISSUE

Special Issue on Advances in Breast Imaging (10)

< Previous Issue | Next Issue >

Receive Email Alerts

VIEW ALL ABSTRACTS +

Special Issue on Advances in Breast Imaging

Introduction to the JMI Special Issue on Advances in Breast Imaging

Hilde Bosmans, Robert Marti, Nicholas Marshall, Martin Tornai, Reyer Zwiggelaer, Alistair Mackenzie

Journal of Medical Imaging, Vol. 10, Issue S2, S22401, (September 2023) https://doi.org/10.1117/1.JMI.10.S2.S22401

TOPICS: Digital breast tomosynthesis, Breast imaging, Breast, Cancer detection, Breast cancer, Artificial intelligence, Animal model studies, Mammography, Ultrasonography, Evolutionary algorithms

Read Abstract +

Phosphotungstic acid-enhanced microcomputed tomography for quantitative visualization of mouse mammary gland morphology

Anthi Kolokotroni, Evi Gkikopoulou, Vagelis Rinotas, Eleni Douni

Journal of Medical Imaging, Vol. 10, Issue S2, S22402, (February 2023) https://doi.org/10.1117/1.JMI.10.S2.S22402

TOPICS: Mammary gland, 3D image processing, Stereoscopy, Microcomputed tomography, Tissues, Breast density, 3D modeling, Visualization, Bone, Adipose tissue

Read Abstract +

4D digital anthropomorphic breast phantom for iodinated contrast-enhanced imaging

Dan Li, Andrey Makeev, Stephen Glick

Journal of Medical Imaging, Vol. 10, Issue S2, S22403, (March 2023) https://doi.org/10.1117/1.JMI.10.S2.S22403

TOPICS: Breast, Tissues, Mammography, Contrast agents, 3D modeling, Arteries, Voxels, Iodine, Diffusion, Breast imaging

Read Abstract +

Purpose

Differentiating between benign and malignant masses is one of the biggest challenges in breast imaging. The challenge is ingrained in the similarity of the attenuation coefficients between different types of lesion tissues and fibroglandular tissues. Contrast-enhanced imaging techniques can take advantage of the differing metabolism in different tissues, therefore, potentially allowing better differentiation of malignant and benign lesions. To facilitate the development and optimization of such technologies, we propose a fully digital 4D phantom that features time-varying enhancement patterns for different tissue types.

Approach

The 4D model is based on a static, anthropomorphic 3D digital breast phantom. Masses inserted into the 3D phantom are based on a previously published model. Physiological parameters that capture the key characteristics of masses, e.g., wash-in and wash-out rates indicating metabolic level, are employed in the model to simulate fundamental features for categorizing mass types. The two-compartmental model, a well-known model in the field of pharmacokinetics, is used to depict the diffusion process of the contrast agent. Two methods are proposed to allow for the simulations of lesions with necrotic cores of varying shapes and sizes.

Results

The fourth dimension of the phantom models different time-varying enhancement patterns for different materials including fibroglandular tissue and lesion tissue. Metabolic characteristics of mass models can be adjusted to provide different enhancement patterns. The parameters of the 4D phantom can also be adjusted to fit different scenarios. The usage of the phantom is demonstrated by simulating mammograms at different time frames.

Conclusion

A 4D digital anthropomorphic breast phantom that models different time-varying contrast enhancement patterns is presented. This phantom could be an integral tool for use in in silico trials to assess image quality of iodinated contrast-enhanced mammography, digital breast tomosynthesis, and breast computed tomography systems.

Deep-learning convolutional neural network-based scatter correction for contrast enhanced digital breast tomosynthesis in both cranio-caudal and mediolateral-oblique views

Xiaoyu Duan, Pranjal Sahu, Hailiang Huang, Wei Zhao

Journal of Medical Imaging, Vol. 10, Issue S2, S22404, (March 2023) https://doi.org/10.1117/1.JMI.10.S2.S22404

TOPICS: Breast, Monte Carlo methods, Education and training, Muscles, Polymethylmethacrylate, Lead, Convolutional neural networks, Chest, Digital breast tomosynthesis, Picosecond phenomena

Read Abstract +

Implications for downstream workload based on calibrating an artificial intelligence detection algorithm by standalone-reader or combined-reader sensitivity matching

Karin Dembrower M.D., Mattie Salim, Martin Eklund, Peter Lindholm, Fredrik Strand

Journal of Medical Imaging, Vol. 10, Issue S2, S22405, (April 2023) https://doi.org/10.1117/1.JMI.10.S2.S22405

TOPICS: Artificial intelligence, Mammography, Evolutionary algorithms, Cancer, Calibration, Breast cancer, Cancer detection, Breast density, Detection and tracking algorithms, Statistical analysis

Read Abstract +

Purpose

In double-reading of screening mammograms, artificial intelligence (AI) algorithms hold promise as a potential replacement for one of the two readers. The choice of operating point, or abnormality threshold, for the AI algorithm will affect cancer detection and workload. In our retrospective study, the baseline approach was based on matching stand-alone reader sensitivity, while the alternative approach was based on matching the combined-reader sensitivity of two humans and of AI plus human.

Approach

Full-field digital screening mammograms within the Stockholm County area between February 1, 2012, and December 30, 2015, acquired on Philips equipment, were collected. All exams of women with breast cancer within 23 months of screening and a random selection of healthy controls were included. An exam-level continuous AI abnormality score was generated (Insight MMG from Lunit Inc). Sensitivity and abnormal interpretation rates were estimated for operating points defined by the standalone-reader approach and the combined-reader approach.

Results

The study population included 1684 exams of women with breast cancer and 5024 exams of healthy women. Observations of healthy women were up-sampled to attain a realistic proportion of cancer. The observed sensitivity for reader 1, 2 and 1+2 was 69.7%, 75.6%, and 78.6%, respectively, at an abnormal interpretation rate of 4.4%, 4.6%, and 6.1%, respectively. For the combination of reader 1 + AI we estimated a sensitivity of 82.4% for standalone-reader matching and 78.6% for combined-reader matching, at an abnormal interpretation rate of 12.6% and 7.0%, respectively.

Conclusions

Setting the operating point by matching stand-alone AI stand-alone with a radiologist will nearly double the downstream workload compared to a modest increase of 15% for the alternative method of matching sensitivity between the combination of AI and a radiologist with two radiologists.

Theoretical comparison and optimization of cadmium telluride and gallium arsenide photon-counting detectors for contrast-enhanced spectral mammography

Colin Schaeffer, Bahaa Ghammraoui, Katsuyuki Taguchi, Stephen J. Glick

Journal of Medical Imaging, Vol. 10, Issue S2, S22406, (April 2023) https://doi.org/10.1117/1.JMI.10.S2.S22406

TOPICS: Gallium arsenide, Iodine, Mammography, Aluminum, X-rays, Cadmium telluride, Simulations, Breast, Photodetectors, X-ray imaging

Read Abstract +

Comparison of lesion detection and conspicuity between narrow-angle and wide-angle digital breast tomosynthesis for dense and non-dense breasts

Hailiang Huang, David Scaduto, Anastasia Plaunova, Kim Rinaldi, Paul R. Fisher, Wei Zhao

Journal of Medical Imaging, Vol. 10, Issue S2, S22407, (May 2023) https://doi.org/10.1117/1.JMI.10.S2.S22407

TOPICS: Digital breast tomosynthesis, Breast, Autoregressive models, Imaging systems, Quantum reading, Diagnostics, Breast density, Quantum noise, Tissues, Cancer detection

Read Abstract +

Personalized breast cancer screening with selective addition of digital breast tomosynthesis through artificial intelligence

Victor Dahlblom, Anders Tingberg, Sophia Zackrisson, Magnus Dustler

Journal of Medical Imaging, Vol. 10, Issue S2, S22408, (June 2023) https://doi.org/10.1117/1.JMI.10.S2.S22408

TOPICS: Digital breast tomosynthesis, Cancer, Cancer detection, Artificial intelligence, Breast cancer, Breast, Medicine, Breast density, Tumor growth modeling, Mammography

Read Abstract +

Breast cancer detection with upstream data fusion, machine learning, and automated registration: initial results

Lisa Mullen, William Walton, Michael Williams, Keith Peyton, David Porter

Journal of Medical Imaging, Vol. 10, Issue S2, S22409, (June 2023) https://doi.org/10.1117/1.JMI.10.S2.S22409

TOPICS: Cancer detection, Digital breast tomosynthesis, Data fusion, Breast cancer, Image fusion, Image registration, Education and training, Image processing, Breast, Mammography

Read Abstract +

Texture quantified from ultrasound Nakagami parametric images is diagnostically relevant for breast tumor characterization

Sabiq Muhtadi, Rezwana R. Razzaque, Ahmad Chowdhury, Brian S. Garra, S. Kaisar Alam

Journal of Medical Imaging, Vol. 10, Issue S2, S22410, (June 2023) https://doi.org/10.1117/1.JMI.10.S2.S22410

TOPICS: Tumors, Windows, Ultrasonography, Breast, Image classification, Feature extraction, Cooccurrence matrices, Spatial resolution, Tissues, MATLAB

Read Abstract +

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusion

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusion

Purpose

Approach

Results

Conclusion

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Keywords/Phrases

Search In:

Publication Years