Volume 11 Issue 3 | Journal of Medical Imaging

Journal of Medical Imaging

VOL. 11 · NO. 3 | May 2024

ISSUES IN PROGRESS

IN PROGRESS

SPIE publishes accepted journal articles as soon as they are approved for publication. Journal issues are considered In Progress until all articles for an issue have been published. Articles published ahead of the completed issue are fully citable.

IN THIS ISSUE

Physics of Medical Imaging (1)

Image Processing (3)

Computer-Aided Diagnosis (1)

Image-Guided Procedures, Robotic Interventions, and Modeling (1)

Image Perception, Observer Performance, and Technology Assessment (1)

Biomedical Applications in Molecular, Structural, and Functional Imaging (1)

Ultrasonic Imaging and Tomography (1)

Digital Pathology (2)

< Previous Issue | Next Issue >

Receive Email Alerts

VIEW ALL ABSTRACTS +

Physics of Medical Imaging

Maximizing microcalcification detectability in low-dose dedicated cone-beam breast CT: parallel cascades-based theoretical analysis

Thomas Larsen, Hsin Wu Tseng, Rachawadee Trinate, Zhiyang Fu, Jing-Tzyh Alan Chiang, Andrew Karellas, Srinivasan Vedantham

Journal of Medical Imaging, Vol. 11, Issue 03, 033501, (May 2024) https://doi.org/10.1117/1.JMI.11.3.033501

TOPICS: X-rays, Scintillators, Tunable filters, Modulation transfer functions, Copper, Breast, Photons, Optical filters, X-ray imaging, Imaging systems

Read Abstract +

Image Processing

Graph neural networks for automatic extraction and labeling of the coronary artery tree in CT angiography

Nils Hampe, Sanne G. M. van Velzen, Jelmer M. Wolterink, Carlos Collet, José P. S. Henriques, Nils Planken, Ivana Išgum

Journal of Medical Imaging, Vol. 11, Issue 03, 034001, (May 2024) https://doi.org/10.1117/1.JMI.11.3.034001

TOPICS: Arteries, Anatomy, Image segmentation, Education and training, Neural networks, Machine learning, Veins, Image resolution, Feature extraction, Automatic tracking

Read Abstract +

Fiberscopic pattern removal for optimal coverage in 3D bladder reconstructions of fiberscope cystoscopy videos

Rachel Eimen, Halina Krzyzanowska, Kristen R. Scarpato, Audrey K. Bowden

Journal of Medical Imaging, Vol. 11, Issue 03, 034002, (May 2024) https://doi.org/10.1117/1.JMI.11.3.034002

Read Abstract +

Transformer enhanced autoencoder rendering cleaning of noisy optical coherence tomography images

Hanya Ahmed, Qianni Zhang, Robert Donnan, Akram Alomainy

Journal of Medical Imaging, Vol. 11, Issue 03, 034008, (April 2024) https://doi.org/10.1117/1.JMI.11.3.034008

TOPICS: Denoising, Optical coherence tomography, Transformers, Speckle, Dentistry, Silver, Visualization, Education and training, Image segmentation, Data modeling

Read Abstract +

Computer-Aided Diagnosis

Computerized assessment of background parenchymal enhancement on breast dynamic contrast-enhanced-MRI including electronic lesion removal

Lindsay Douglas, Jordan Fuhrman, Qiyuan Hu, Alexandra Edwards, Deepa Sheth, Hiroyuki Abe, Maryellen Giger

Journal of Medical Imaging, Vol. 11, Issue 03, 034501, (May 2024) https://doi.org/10.1117/1.JMI.11.3.034501

TOPICS: Breast, Image segmentation, Education and training, Visualization, Magnetic resonance imaging, Tumors, Statistical analysis, Binary data, Image classification, Breast cancer

Read Abstract +

Purpose

Current clinical assessment qualitatively describes background parenchymal enhancement (BPE) as minimal, mild, moderate, or marked based on the visually perceived volume and intensity of enhancement in normal fibroglandular breast tissue in dynamic contrast-enhanced (DCE)-MRI. Tumor enhancement may be included within the visual assessment of BPE, thus inflating BPE estimation due to angiogenesis within the tumor. Using a dataset of 426 MRIs, we developed an automated method to segment breasts, electronically remove lesions, and calculate scores to estimate BPE levels.

Approach

A U-Net was trained for breast segmentation from DCE-MRI maximum intensity projection (MIP) images. Fuzzy c-means clustering was used to segment lesions; the lesion volume was removed prior to creating projections. U-Net outputs were applied to create projection images of both, affected, and unaffected breasts before and after lesion removal. BPE scores were calculated from various projection images, including MIPs or average intensity projections of first- or second postcontrast subtraction MRIs, to evaluate the effect of varying image parameters on automatic BPE assessment. Receiver operating characteristic analysis was performed to determine the predictive value of computed scores in BPE level classification tasks relative to radiologist ratings.

Results

Statistically significant trends were found between radiologist BPE ratings and calculated BPE scores for all breast regions (Kendall correlation, p<0.001). Scores from all breast regions performed significantly better than guessing (p<0.025 from the z-test). Results failed to show a statistically significant difference in performance with and without lesion removal. BPE scores of the affected breast in the second postcontrast subtraction MIP after lesion removal performed statistically greater than random guessing across various viewing projections and DCE time points.

Conclusions

Results demonstrate the potential for automatic BPE scoring to serve as a quantitative value for objective BPE level classification from breast DCE-MR without the influence of lesion enhancement.

Image-Guided Procedures, Robotic Interventions, and Modeling

Self-supervised learning for interventional image analytics: toward robust device trackers

Saahil Islam, Venkatesh N. Murthy, Dominik Neumann, Badhan Kumar Das, Puneet Sharma, Andreas Maier, Dorin Comaniciu, Florin C. Ghesu

Journal of Medical Imaging, Vol. 11, Issue 03, 035001, (May 2024) https://doi.org/10.1117/1.JMI.11.3.035001

TOPICS: Image analysis, Education and training, Analytics, X-rays, Transformers, Performance modeling, Angiography, X-ray imaging, Interpolation, Instrument modeling

Read Abstract +

Purpose

The accurate detection and tracking of devices, such as guiding catheters in live X-ray image acquisitions, are essential prerequisites for endovascular cardiac interventions. This information is leveraged for procedural guidance, e.g., directing stent placements. To ensure procedural safety and efficacy, there is a need for high robustness/no failures during tracking. To achieve this, one needs to efficiently tackle challenges, such as device obscuration by the contrast agent or other external devices or wires and changes in the field-of-view or acquisition angle, as well as the continuous movement due to cardiac and respiratory motion.

Approach

To overcome the aforementioned challenges, we propose an approach to learn spatio-temporal features from a very large data cohort of over 16 million interventional X-ray frames using self-supervision for image sequence data. Our approach is based on a masked image modeling technique that leverages frame interpolation-based reconstruction to learn fine inter-frame temporal correspondences. The features encoded in the resulting model are fine-tuned downstream in a light-weight model.

Results

Our approach achieves state-of-the-art performance, in particular for robustness, compared to ultra optimized reference solutions (that use multi-stage feature fusion or multi-task and flow regularization). The experiments show that our method achieves a 66.31% reduction in the maximum tracking error against the reference solutions (23.20% when flow regularization is used), achieving a success score of 97.95% at a 3× faster inference speed of 42 frames-per-second (on GPU). In addition, we achieve a 20% reduction in the standard deviation of errors, which indicates a much more stable tracking performance.

Conclusions

The proposed data-driven approach achieves superior performance, particularly in robustness and speed compared with the frequently used multi-modular approaches for device tracking. The results encourage the use of our approach in various other tasks within interventional image analytics that require effective understanding of spatio-temporal semantics.

Image Perception, Observer Performance, and Technology Assessment

Perceptual thresholds for differences in CT noise texture

Luuk Oostveen, Kirsten Boedeker, Daniel Shin, Craig Abbey, Ioannis Sechopoulos

Journal of Medical Imaging, Vol. 11, Issue 03, 035501, (May 2024) https://doi.org/10.1117/1.JMI.11.3.035501

TOPICS: Computed tomography, Lung, Affine motion model, Reconstruction algorithms, Medical image reconstruction, Bone, Abdomen, Manufacturing, Covariance matrices, Brain

Read Abstract +

Biomedical Applications in Molecular, Structural, and Functional Imaging

Open-source graphical user interface for the creation of synthetic skeletons for medical image analysis

Christian Herz, Nicolas Vergnet, Sijie Tian, Abdullah Aly, Matthew Jolley, Nathanael Tran, Gabriel Arenas, Andras Lasso, Nadav Schwartz, Kathleen O’Neill, Paul Yushkevich, Alison Pouch

Journal of Medical Imaging, Vol. 11, Issue 03, 036001, (May 2024) https://doi.org/10.1117/1.JMI.11.3.036001

TOPICS: Deformation, Anatomy, Modeling, Image segmentation, 3D modeling, Human-machine interfaces, Design, Medical imaging, Biomedical applications, Shape analysis

Read Abstract +

Purpose

Deformable medial modeling is an inverse skeletonization approach to representing anatomy in medical images, which can be used for statistical shape analysis and assessment of patient-specific anatomical features such as locally varying thickness. It involves deforming a pre-defined synthetic skeleton, or template, to anatomical structures of the same class. The lack of software for creating such skeletons has been a limitation to more widespread use of deformable medial modeling. Therefore, the objective of this work is to present an open-source user interface (UI) for the creation of synthetic skeletons for a range of medial modeling applications in medical imaging.

Approach

A UI for interactive design of synthetic skeletons was implemented in 3D Slicer, an open-source medical image analysis application. The steps in synthetic skeleton design include importation and skeletonization of a 3D segmentation, followed by interactive 3D point placement and triangulation of the medial surface such that the desired branching configuration of the anatomical structure’s medial axis is achieved. Synthetic skeleton design was evaluated in five clinical applications. Compatibility of the synthetic skeletons with open-source software for deformable medial modeling was tested, and representational accuracy of the deformed medial models was evaluated.

Results

Three users designed synthetic skeletons of anatomies with various topologies: the placenta, aortic root wall, mitral valve, cardiac ventricles, and the uterus. The skeletons were compatible with skeleton-first and boundary-first software for deformable medial modeling. The fitted medial models achieved good representational accuracy with respect to the 3D segmentations from which the synthetic skeletons were generated.

Conclusions

Synthetic skeleton design has been a practical challenge in leveraging deformable medial modeling for new clinical applications. This work demonstrates an open-source UI for user-friendly design of synthetic skeletons for anatomies with a wide range of topologies.

Ultrasonic Imaging and Tomography

Validation of ultrasound velocimetry and computational fluid dynamics for flow assessment in femoral artery stenotic disease

Lennart van de Velde, Majorie van Helvert, Stefan Engelhard, Ashkan Ghanbarzadeh-Dagheyan, Hadi Mirgolbabaee, Jason Voorneveld, Guillaume Lajoinie, Michel Versluis, Michel M. P. J. Reijnen, Erik Groot Jebbink

Journal of Medical Imaging, Vol. 11, Issue 03, 037001, (May 2024) https://doi.org/10.1117/1.JMI.11.3.037001

TOPICS: Ultrasonography, Velocimetry, Arteries, Computational fluid dynamics, Boundary conditions, Hemodynamics, Video, Turbulence, Particle image velocimetry, Doppler effect

Read Abstract +

Purpose

To investigate the accuracy of high-framerate echo particle image velocimetry (ePIV) and computational fluid dynamics (CFD) for determining velocity vectors in femoral bifurcation models through comparison with optical particle image velocimetry (oPIV).

Approach

Separate femoral bifurcation models were built for oPIV and ePIV measurements of a non-stenosed (control) and a 75%-area stenosed common femoral artery. A flow loop was used to create triphasic pulsatile flow. In-plane velocity vectors were measured with oPIV and ePIV. Flow was simulated with CFD using boundary conditions from ePIV and additional duplex-ultrasound (DUS) measurements. Mean differences and 95%-limits of agreement (1.96*SD) of the velocity magnitudes in space and time were compared, and the similarity of vector complexity (VC) and time-averaged wall shear stress (TAWSS) was assessed.

Results

Similar flow features were observed between modalities with velocities up to 110 and 330 cm/s in the control and the stenosed model, respectively. Relative to oPIV, ePIV and CFD-ePIV showed negligible mean differences in velocity (<3 cm/s), with limits of agreement of ±25 cm/s (control) and ±34 cm/s (stenosed). CFD-DUS overestimated velocities with limits of agreements of 13±40 and 16.1±55 cm/s for the control and stenosed model, respectively. VC showed good agreement, whereas TAWSS showed similar trends but with higher values for ePIV, CFD-DUS, and CFD-ePIV compared to oPIV.

Conclusions

EPIV and CFD-ePIV can accurately measure complex flow features in the femoral bifurcation and around a stenosis. CFD-DUS showed larger deviations in velocities making it a less robust technique for hemodynamical assessment. The applied ePIV and CFD techniques enable two- and three-dimensional assessment of local hemodynamics with high spatiotemporal resolution and thereby overcome key limitations of current clinical modalities making them an attractive and cost-effective alternative for hemodynamical assessment in clinical practice.

Digital Pathology

Multiresolution semantic segmentation of biological structures in digital histopathology

Sina Salsabili, Adrian D. Chan, Eranga Ukwatta

Journal of Medical Imaging, Vol. 11, Issue 03, 037501, (May 2024) https://doi.org/10.1117/1.JMI.11.3.037501

TOPICS: Image segmentation, Semantics, Histopathology, Education and training, Lung, Blood vessels, Spatial resolution, Image resolution, Tissues, Performance modeling

Read Abstract +

WhARIO: whole-slide-image-based survival analysis for patients treated with immunotherapy

Paul Tourniaire, Marius Ilie, Julien Mazières, Anna Vigier, François Ghiringhelli, Nicolas Piton, Jean-Christophe Sabourin, Frédéric Bibeau, Paul Hofman, Nicholas Ayache, Hervé Delingette

Journal of Medical Imaging, Vol. 11, Issue 03, 037502, (May 2024) https://doi.org/10.1117/1.JMI.11.3.037502

TOPICS: Tissues, Tumors, Education and training, Matrices, Lung cancer, Lawrencium, Feature extraction, Biological research, Cross validation, Pathology

Read Abstract +

Purpose

Immune checkpoint inhibitors (ICIs) are now one of the standards of care for patients with lung cancer and have greatly improved both progression-free and overall survival, although <20% of the patients respond to the treatment, and some face acute adverse events. Although a few predictive biomarkers have integrated the clinical workflow, they require additional modalities on top of whole-slide images and lack efficiency or robustness. In this work, we propose a biomarker of immunotherapy outcome derived solely from the analysis of histology slides.

Approach

We develop a three-step framework, combining contrastive learning and nonparametric clustering to distinguish tissue patterns within the slides, before exploiting the adjacencies of previously defined regions to derive features and train a proportional hazards model for survival analysis. We test our approach on an in-house dataset of 193 patients from 5 medical centers and compare it with the gold standard tumor proportion score (TPS) biomarker.

Results

On a fivefold cross-validation (CV) of the entire dataset, the whole-slide image-based survival analysis for patients treated with immunotherapy (WhARIO) features are able to separate a low- and a high-risk group of patients with a hazard ratio (HR) of 2.29 (CI95=1.48 to 3.56), whereas the TPS 1% reference threshold only reaches a HR of 1.81 (CI95=1.21 to 2.69). Combining the two yields a higher HR of 2.60 (CI95=1.72 to 3.94). Additional experiments on the same dataset, where one out of five centers is excluded from the CV and used as a test set, confirm these trends.

Conclusions

Our uniquely designed WhARIO features are an efficient predictor of survival for lung cancer patients who received ICI treatment. We achieve similar performance to the current gold standard biomarker, without the need to access other imaging modalities, and show that both can be used together to reach even better results.

Purpose

Approach

Results

Conclusion

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Keywords/Phrases

Search In:

Publication Years