Volume 11 Issue 5 | Journal of Medical Imaging

Journal of Medical Imaging

VOL. 11 · NO. 5 | September 2024

CONTENTS

IN THIS ISSUE

Editorial (1)

Physics of Medical Imaging (2)

Image Processing (4)

Computer-Aided Diagnosis (2)

Image Perception, Observer Performance, and Technology Assessment (2)

Ultrasonic Imaging and Tomography (1)

Digital Pathology (1)

< Previous Issue | Next Issue >

Receive Email Alerts

VIEW ALL ABSTRACTS +

Editorial

ChatGP-Me?

Elias Levy, Bennett Landman

Journal of Medical Imaging, Vol. 11, Issue 05, 050101, (October 2024) https://doi.org/10.1117/1.JMI.11.5.050101

TOPICS: Artificial intelligence, Data modeling, Education and training, Data privacy, Scientific research, Medical imaging, Crystals, Clouds, Analytical research, Visualization

Read Abstract +

Physics of Medical Imaging

Deep learning architecture for scatter estimation in cone-beam computed tomography head imaging with varying field-of-measurement settings

Harshit Agrawal, Ari Hietanen, Simo Särkkä

Journal of Medical Imaging, Vol. 11, Issue 05, 053501, (October 2024) https://doi.org/10.1117/1.JMI.11.5.053501

TOPICS: Education and training, Cone beam computed tomography, Deep learning, Sensors, Computer simulations, Neural networks, Monte Carlo methods, X-rays, Windows, X-ray computed tomography

Read Abstract +

Purpose

X-ray scatter causes considerable degradation in the cone-beam computed tomography (CBCT) image quality. To estimate the scatter, deep learning–based methods have been demonstrated to be effective. Modern CBCT systems can scan a wide range of field-of-measurement (FOM) sizes. Variations in the size of FOM can cause a major shift in the scatter-to-primary ratio in CBCT. However, the scatter estimation performance of deep learning networks has not been extensively evaluated under varying FOMs. Therefore, we train the state-of-the-art scatter estimation neural networks for varying FOMs and develop a method to utilize FOM size information to improve performance.

Approach

We used FOM size information as additional features by converting it into two channels and then concatenating it to the encoder of the networks. We compared our approach for a U-Net, Spline-Net, and DSE-Net, by training them with and without the FOM information. We utilized a Monte Carlo–simulated dataset to train the networks on 18 FOM sizes and test on 30 unseen FOM sizes. In addition, we evaluated the models on the water phantoms and real clinical CBCT scans.

Results

The simulation study demonstrates that our method reduced average mean-absolute-percentage-error for U-Net by 38%, Spline-Net by 40%, and DSE-net by 33% for the scatter estimation in the 2D projection domain. Furthermore, the root-mean-square error on the 3D reconstructed volumes was improved for U-Net by 43%, Spline-Net by 30%, and DSE-Net by 23%. Furthermore, our method improved contrast and image quality on real datasets such as water phantom and clinical data.

Conclusion

Providing additional information about FOM size improves the robustness of the neural networks for scatter estimation. Our approach is not limited to utilizing only FOM size information; more variables such as tube voltage, scanning geometry, and patient size can be added to improve the robustness of a single network.

Photon-counting computed tomography versus energy-integrating computed tomography for detection of small liver lesions: comparison using a virtual framework imaging

Nicholas Felice, Benjamin Wildman-Tobriner, William Segars, Mustafa Bashir, Daniele Marin, Ehsan Samei, Ehsan Abadi

Journal of Medical Imaging, Vol. 11, Issue 05, 053502, (October 2024) https://doi.org/10.1117/1.JMI.11.5.053502

TOPICS: Liver, Computed tomography, Image quality, Scanners, Modulation transfer functions, Optical computing, Brain-machine interfaces, Image restoration, Sensors, Image sharpness

Read Abstract +

Image Processing

Predicting peritumoral glioblastoma infiltration and subsequent recurrence using deep-learning–based analysis of multi-parametric magnetic resonance imaging

Sunwoo Kwak, Hamed Akbari, Jose Garcia, Suyash Mohan, Yehuda Dicker, Chiharu Sako, Yuji Matsumoto, MacLean Nasrallah, Mahmoud Shalaby, Donald O’Rourke, Russel Shinohara, Fang Liu, Chaitra Badve, Jill Barnholtz-Sloan, Andrew Sloan, Matthew Lee, Rajan Jain, Santiago Cepeda, Arnab Chakravarti, Joshua Palmer, Adam P. Dicker, Gaurav Shukla, Adam Flanders, Wenyin Shi, Graeme Woodworth, Christos Davatzikos

Journal of Medical Imaging, Vol. 11, Issue 05, 054001, (August 2024) https://doi.org/10.1117/1.JMI.11.5.054001

TOPICS: Tumors, Education and training, Deep learning, Voxels, Magnetic resonance imaging, Data modeling, Tissues, Resection, Brain, Cross validation

Read Abstract +

Purpose

Glioblastoma (GBM) is the most common and aggressive primary adult brain tumor. The standard treatment approach is surgical resection to target the enhancing tumor mass, followed by adjuvant chemoradiotherapy. However, malignant cells often extend beyond the enhancing tumor boundaries and infiltrate the peritumoral edema. Traditional supervised machine learning techniques hold potential in predicting tumor infiltration extent but are hindered by the extensive resources needed to generate expertly delineated regions of interest (ROIs) for training models on tissue most and least likely to be infiltrated.

Approach

We developed a method combining expert knowledge and training-based data augmentation to automatically generate numerous training examples, enhancing the accuracy of our model for predicting tumor infiltration through predictive maps. Such maps can be used for targeted supra-total surgical resection and other therapies that might benefit from intensive yet well-targeted treatment of infiltrated tissue. We apply our method to preoperative multi-parametric magnetic resonance imaging (mpMRI) scans from a subset of 229 patients of a multi-institutional consortium (Radiomics Signatures for Precision Diagnostics) and test the model on subsequent scans with pathology-proven recurrence.

Results

Leave-one-site-out cross-validation was used to train and evaluate the tumor infiltration prediction model using initial pre-surgical scans, comparing the generated prediction maps with follow-up mpMRI scans confirming recurrence through post-resection tissue analysis. Performance was measured by voxel-wised odds ratios (ORs) across six institutions: University of Pennsylvania (OR: 9.97), Ohio State University (OR: 14.03), Case Western Reserve University (OR: 8.13), New York University (OR: 16.43), Thomas Jefferson University (OR: 8.22), and Rio Hortega (OR: 19.48).

Conclusions

The proposed model demonstrates that mpMRI analysis using deep learning can predict infiltration in the peri-tumoral brain region for GBM patients without needing to train a model using expert ROI drawings. Results for each institution demonstrate the model’s generalizability and reproducibility.

Automated echocardiography view classification and quality assessment with recognition of unknown views

Gino Jansen, Bob de Vos, Mitchel Molenaar, Mark Schuuring, Berto Bouma, Ivana Išgum

Journal of Medical Imaging, Vol. 11, Issue 05, 054002, (August 2024) https://doi.org/10.1117/1.JMI.11.5.054002

TOPICS: Video, Education and training, Echocardiography, Image quality, Data modeling, Neural networks, Machine learning, Image processing, Anatomy, 3D modeling

Read Abstract +

Deep network and multi-atlas segmentation fusion for delineation of thigh muscle groups in three-dimensional water–fat separated MRI

Nagasoujanya Annasamudram, Azubuike Okorie, Richard Spencer, Rita Kalyani, Qi Yang, Bennett Landman, Luigi Ferrucci, Sokratis Makrogiannis

Journal of Medical Imaging, Vol. 11, Issue 05, 054003, (September 2024) https://doi.org/10.1117/1.JMI.11.5.054003

TOPICS: Image segmentation, Muscles, Magnetic resonance imaging, Education and training, Deep learning, 3D modeling, Deformation, 3D image processing, Tissues, Anatomy

Read Abstract +

Demystifying the effect of receptive field size in U-Net models for medical image segmentation

Vincent Loos, Rohit Pardasani, Navchetan Awasthi

Journal of Medical Imaging, Vol. 11, Issue 05, 054004, (October 2024) https://doi.org/10.1117/1.JMI.11.5.054004

TOPICS: Education and training, Image segmentation, Data modeling, Medical imaging, Performance modeling, Head, Fetus, Lung, Convolution, Thyroid

Read Abstract +

Purpose

Medical image segmentation is a critical task in healthcare applications, and U-Nets have demonstrated promising results in this domain. We delve into the understudied aspect of receptive field (RF) size and its impact on the U-Net and attention U-Net architectures used for medical imaging segmentation.

Approach

We explore several critical elements including the relationship among RF size, characteristics of the region of interest, and model performance, as well as the balance between RF size and computational costs for U-Net and attention U-Net methods for different datasets. We also propose a mathematical notation for representing the theoretical receptive field (TRF) of a given layer in a network and propose two new metrics, namely, the effective receptive field (ERF) rate and the object rate, to quantify the fraction of significantly contributing pixels within the ERF against the TRF area and assessing the relative size of the segmentation object compared with the TRF size, respectively.

Results

The results demonstrate that there exists an optimal TRF size that successfully strikes a balance between capturing a wider global context and maintaining computational efficiency, thereby optimizing model performance. Interestingly, a distinct correlation is observed between the data complexity and the required TRF size; segmentation based solely on contrast achieved peak performance even with smaller TRF sizes, whereas more complex segmentation tasks necessitated larger TRFs. Attention U-Net models consistently outperformed their U-Net counterparts, highlighting the value of attention mechanisms regardless of TRF size.

Conclusions

These insights present an invaluable resource for developing more efficient U-Net-based architectures for medical imaging and pave the way for future exploration of other segmentation architectures. A tool is also developed, which calculates the TRF for a U-Net (and attention U-Net) model and also suggests an appropriate TRF size for a given model and dataset.

Computer-Aided Diagnosis

Radiomics and quantitative multi-parametric MRI for predicting uterine fibroid growth

Karen Drukker, Milica Medved, Carla Harmath, Maryellen Giger, Obianuju Madueke-Laveaux

Journal of Medical Imaging, Vol. 11, Issue 05, 054501, (September 2024) https://doi.org/10.1117/1.JMI.11.5.054501

TOPICS: Radiomics, Magnetic resonance imaging, Analog to digital converters, Principal component analysis, Cooccurrence matrices, Volume rendering, Tumors, Hazard analysis, Ultrasonography, Tissues

Read Abstract +

Significance

Uterine fibroids (UFs) can pose a serious health risk to women. UFs are benign tumors that vary in clinical presentation from asymptomatic to causing debilitating symptoms. UF management is limited by our inability to predict UF growth rate and future morbidity.

Aim

We aim to develop a predictive model to identify UFs with increased growth rates and possible resultant morbidity.

Approach

We retrospectively analyzed 44 expertly outlined UFs from 20 patients who underwent two multi-parametric MR imaging exams as part of a prospective study over an average of 16 months. We identified 44 initial features by extracting quantitative magnetic resonance imaging (MRI) features plus morphological and textural radiomics features from DCE, T2, and apparent diffusion coefficient sequences. Principal component analysis reduced dimensionality, with the smallest number of components explaining over 97.5% of the variance selected. Employing a leave-one-fibroid-out scheme, a linear discriminant analysis classifier utilized these components to output a growth risk score.

Results

The classifier incorporated the first three principal components and achieved an area under the receiver operating characteristic curve of 0.80 (95% confidence interval [0.69; 0.91]), effectively distinguishing UFs growing faster than the median growth rate of 0.93 cm3/year/fibroid from slower-growing ones within the cohort. Time-to-event analysis, dividing the cohort based on the median growth risk score, yielded a hazard ratio of 0.33 [0.15; 0.76], demonstrating potential clinical utility.

Conclusion

We developed a promising predictive model utilizing quantitative MRI features and principal component analysis to identify UFs with increased growth rates. Furthermore, the model’s discrimination ability supports its potential clinical utility in developing tailored patient and fibroid-specific management once validated on a larger cohort.

HarmonyTM: multi-center data harmonization applied to distributed learning for Parkinson’s disease classification

Raissa Souza, Emma A. Stanley, Vedant Gulve, Jasmine Moore, Chris Kang, Richard Camicioli, Oury Monchi, Zahinoor Ismail, Matthias Wilms, Nils D. Forkert

Journal of Medical Imaging, Vol. 11, Issue 05, 054502, (September 2024) https://doi.org/10.1117/1.JMI.11.5.054502

TOPICS: Scanners, Data modeling, Education and training, Machine learning, Principal component analysis, Diseases and disorders, Neuroimaging, Data acquisition, Image acquisition, Head

Read Abstract +

Image Perception, Observer Performance, and Technology Assessment

Investigating the use of signal detection information in supervised learning-based image denoising with consideration of task-shift

Kaiyan Li, Hua Li, Mark Anastasio

Journal of Medical Imaging, Vol. 11, Issue 05, 055501, (September 2024) https://doi.org/10.1117/1.JMI.11.5.055501

TOPICS: Education and training, Signal detection, Denoising, Image quality, Machine learning, Binary data, Lithium, Image denoising, Signal attenuation, Covariance matrices

Read Abstract +

Purpose

Recently, learning-based denoising methods that incorporate task-relevant information into the training procedure have been developed to enhance the utility of the denoised images. However, this line of research is relatively new and underdeveloped, and some fundamental issues remain unexplored. Our purpose is to yield insights into general issues related to these task-informed methods. This includes understanding the impact of denoising on objective measures of image quality (IQ) when the specified task at inference time is different from that employed for model training, a phenomenon we refer to as “task-shift.”

Approach

A virtual imaging test bed comprising a stylized computational model of a chest X-ray computed tomography imaging system was employed to enable a controlled and tractable study design. A canonical, fully supervised, convolutional neural network–based denoising method was purposely adopted to understand the underlying issues that may be relevant to a variety of applications and more advanced denoising or image reconstruction methods. Signal detection and signal detection-localization tasks under signal-known-statistically with background-known-statistically conditions were considered, and several distinct types of numerical observers were employed to compute estimates of the task performance. Studies were designed to reveal how a task-informed transfer-learning approach can influence the tradeoff between conventional and task-based measures of image quality within the context of the considered tasks. In addition, the impact of task-shift on these image quality measures was assessed.

Results

The results indicated that certain tradeoffs can be achieved such that the resulting AUC value was significantly improved and the degradation of physical IQ measures was statistically insignificant. It was also observed that introducing task-shift degrades the task performance as expected. The degradation was significant when a relatively simple task was considered for network training and observer performance on a more complex one was assessed at inference time.

Conclusions

The presented results indicate that the task-informed training method can improve the observer performance while providing control over the tradeoff between traditional and task-based measures of image quality. The behavior of a task-informed model fine-tuning procedure was demonstrated, and the impact of task-shift on task-based image quality measures was investigated.

Optimizing mammography interpretation education: leveraging deep learning for cohort-specific error detection to enhance radiologist training

Xuetong Tao, Warren Reed, Tong Li, Patrick Brennan, Ziba Gandomkar

Journal of Medical Imaging, Vol. 11, Issue 05, 055502, (October 2024) https://doi.org/10.1117/1.JMI.11.5.055502

TOPICS: Mammography, Machine learning, Education and training, Diagnostics, Deep learning, Performance modeling, Data modeling, Cross validation, Medical imaging, Image segmentation

Read Abstract +

Ultrasonic Imaging and Tomography

Expanding generalized contrast-to-noise ratio into a clinically relevant measure of lesion detectability by considering size and spatial resolution

Siegfried Schlunk, Brett Byram

Journal of Medical Imaging, Vol. 11, Issue 05, 057001, (October 2024) https://doi.org/10.1117/1.JMI.11.5.057001

TOPICS: Signal to noise ratio, Phased arrays, Image quality, In vivo imaging, Chromium, Speckle, Histograms, Point spread functions, Autocorrelation, Analytics

Read Abstract +

Purpose

Early image quality metrics were often designed with clinicians in mind, and ideal metrics would correlate with the subjective opinion of practitioners. Over time, adaptive beamformers and other post-processing methods have become more common, and these newer methods often violate assumptions of earlier image quality metrics, invalidating the meaning of those metrics. The result is that beamformers may “manipulate” metrics without producing more clinical information.

Approach

In this work, Smith et al.’s signal-to-noise ratio (SNR) metric for lesion detectability is considered, and a more robust version, here called generalized SNR (gSNR), is proposed that uses generalized contrast-to-noise ratio (gCNR) as a core. It is analytically shown that for Rayleigh distributed data, gCNR is a function of Smith et al.’s Cψ (and therefore can be used as a substitution). More robust methods for estimating the resolution cell size are considered. Simulated lesions are included to verify the equations and demonstrate behavior, and it is shown to apply equally well to in vivo data.

Results

gSNR is shown to be equivalent to SNR for delay-and-sum (DAS) beamformed data, as intended. However, it is shown to be more robust against transformations and report lesion detectability more accurately for non-Rayleigh distributed data. In the simulation included, the SNR of DAS was 4.4±0.8, and minimum variance (MV) was 6.4±1.9, but the gSNR of DAS was 4.5±0.9, and MV was 3.0±0.9, which agrees with the subjective assessment of the image. Likewise, the DAS2 transformation (which is clinically identical to DAS) had an incorrect SNR of 9.4±1.0 and a correct gSNR of 4.4±0.9. Similar results are shown in vivo.

Conclusions

Using gCNR as a component to estimate gSNR creates a robust measure of lesion detectability. Like SNR, gSNR can be compared with the Rose criterion and may better correlate with clinical assessments of image quality for modern beamformers.

Digital Pathology

Characterization of arteriosclerosis based on computer-aided measurements of intra-arterial thickness

Jin Zhou, Xiang Li, Dawit Demeke, Timothy A. Dinh, Yingbao Yang, Andrew Janowczyk, Jarcy Zee, Lawrence Holzman, Laura Mariani, Krishnendu Chakrabarty, Laura Barisoni, Jeffrey Hodgin, Kyle J. Lafata

Journal of Medical Imaging, Vol. 11, Issue 05, 057501, (October 2024) https://doi.org/10.1117/1.JMI.11.5.057501

TOPICS: Arteries, Image segmentation, Tissues, Pathology, Kidney, Feature extraction, Deformation, Biopsy, Tunable filters, Distortion

Read Abstract +

Purpose

Our purpose is to develop a computer vision approach to quantify intra-arterial thickness on digital pathology images of kidney biopsies as a computational biomarker of arteriosclerosis.

Approach

The severity of the arteriosclerosis was scored (0 to 3) in 753 arteries from 33 trichrome-stained whole slide images (WSIs) of kidney biopsies, and the outer contours of the media, intima, and lumen were manually delineated by a renal pathologist. We then developed a multi-class deep learning (DL) framework for segmenting the different intra-arterial compartments (training dataset: 648 arteries from 24 WSIs; testing dataset: 105 arteries from 9 WSIs). Subsequently, we employed radial sampling and made measurements of media and intima thickness as a function of spatially encoded polar coordinates throughout the artery. Pathomic features were extracted from the measurements to collectively describe the arterial wall characteristics. The technique was first validated through numerical analysis of simulated arteries, with systematic deformations applied to study their effect on arterial thickness measurements. We then compared these computationally derived measurements with the pathologists’ grading of arteriosclerosis.

Results

Numerical validation shows that our measurement technique adeptly captured the decreasing smoothness in the intima and media thickness as the deformation increases in the simulated arteries. Intra-arterial DL segmentations of media, intima, and lumen achieved Dice scores of 0.84, 0.78, and 0.86, respectively. Several significant associations were identified between arteriosclerosis grade and pathomic features using our technique (e.g., intima-media ratio average [τ=0.52, p<0.0001]) through Kendall’s tau analysis.

Conclusions

We developed a computer vision approach to computationally characterize intra-arterial morphology on digital pathology images and demonstrate its feasibility as a potential computational biomarker of arteriosclerosis.

Purpose

Approach

Results

Conclusion

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusion

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Significance

Aim

Approach

Results

Conclusion

Purpose

Approach

Results

Conclusion

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Keywords/Phrases

Search In:

Publication Years