Volume 11 Issue 1 | Journal of Medical Imaging

Journal of Medical Imaging

VOL. 11 · NO. 1 | January 2024

CONTENTS

IN THIS ISSUE

Editorial (2)

Physics of Medical Imaging (3)

Image Processing (8)

Computer-Aided Diagnosis (3)

Image-Guided Procedures, Robotic Interventions, and Modeling (2)

Digital Pathology (2)

< Previous Issue | Next Issue >

Receive Email Alerts

VIEW ALL ABSTRACTS +

Editorial

EIC Welcome: Embracing Innovation and Impact in Medical Imaging Research

Journal of Medical Imaging, Vol. 11, Issue 01, 010101, (January 2024) https://doi.org/10.1117/1.JMI.11.1.010101

TOPICS: Artificial intelligence, Medical imaging, Medical research, Peer review, Transparency, Image processing, Design, Scientific research, Reflection, Medicine

Read Abstract +

2023 List of Reviewers

Journal of Medical Imaging, Vol. 11, Issue 01, 010102, (January 2024) https://doi.org/10.1117/1.JMI.11.1.010102

TOPICS: Lithium, Alternate lighting of surfaces, Mendelevium, Bridges

Read Abstract +

Physics of Medical Imaging

Motion-compensation approach for quantitative digital subtraction angiography and its effect on in-vivo blood velocity measurement

Joseph Whitehead, Sarvesh Periyasamy, Paul Laeseke, Michael Speidel, Martin Wagner

Journal of Medical Imaging, Vol. 11, Issue 01, 013501, (January 2024) https://doi.org/10.1117/1.JMI.11.1.013501

TOPICS: Blood, Image segmentation, Velocity measurements, Angiography, Image registration, Arteries, Motion measurement, Motion analysis, In vivo imaging, Linear regression

Read Abstract +

Improved temporal performance and optical quantum efficiency of avalanche amorphous selenium for low dose medical imaging

Corey Orlik, Sébastien Léveillé, Salman M. Arnab, Adrian F. Howansky, Jann Stavro, Scott Dow, Safa Kasap, Kenkichi Tanioka, Amir H. Goldan, Wei Zhao

Journal of Medical Imaging, Vol. 11, Issue 01, 013502, (January 2024) https://doi.org/10.1117/1.JMI.11.1.013502

TOPICS: Tellurium, Selenium, Quantum efficiency, Quantum optics, Electrodes, Dark current, Quantum measurement, Quantum optics experiments, Prototyping, Optical testing

Read Abstract +

First experimental evaluation of a high-resolution deep silicon photon-counting sensor

Rickard Brunskog, Mats Persson, Zihui Jin, Mats Danielsson

Journal of Medical Imaging, Vol. 11, Issue 01, 013503, (February 2024) https://doi.org/10.1117/1.JMI.11.1.013503

TOPICS: Sensors, Monte Carlo methods, Electrodes, Optical simulations, Silicon, Prototyping, Photodetectors, Calibration, Image resolution, X-rays

Read Abstract +

Image Processing

Deep learning-based breast region segmentation in raw and processed digital mammograms: generalization across views and vendors

Sarah D. Verboom, Marco Caballo, Jim Peters, Jessie Gommers, Daan van den Oever, Mireille J. M. Broeders, Jonas Teuwen, Ioannis Sechopoulos

Journal of Medical Imaging, Vol. 11, Issue 01, 014001, (December 2023) https://doi.org/10.1117/1.JMI.11.1.014001

TOPICS: Image segmentation, Education and training, Muscles, Image processing, Breast, Mammography, Data modeling, Atomic force microscopy, Deep learning, Digital mammography

Read Abstract +

Analysis of DWT–DCT watermarking algorithm on digital medical imaging

Rajkumar Soundrapandiyan, Kannadasan Rajendiran, Arunkumar Gurunathan, Akila Victor, Ramani Selvanambi

Journal of Medical Imaging, Vol. 11, Issue 01, 014002, (December 2023) https://doi.org/10.1117/1.JMI.11.1.014002

TOPICS: Digital watermarking, Near infrared, Medical imaging, Discrete wavelet transforms, Image encryption, Image processing, Quantization, Error analysis, Signal to noise ratio, Analytical research

Read Abstract +

Attention-gated 3D CapsNet for robust hippocampal segmentation

Clement Poiret, Antoine Bouyeure, Sandesh Patil, Cécile Boniteau, Edouard Duchesnay, Antoine Grigis, Frederic Lemaitre, Marion Noulhiane

Journal of Medical Imaging, Vol. 11, Issue 01, 014003, (January 2024) https://doi.org/10.1117/1.JMI.11.1.014003

TOPICS: Image segmentation, 3D modeling, Magnetic resonance imaging, Education and training, Data modeling, Silver, Cross validation, Convolution, Anatomy, Voxels

Read Abstract +

Rapid automated lumen segmentation of coronary optical coherence tomography images followed by 3D reconstruction of coronary arteries

Wei Wu, Merjulah Roby, Akshat Banga, Usama Oguz, Vinay Kumar Gadamidi, Charu Hasini Vasa, Shijia Zhao, Vineeth Dasari, Anjani Kumar Thota, Sartaj Tanweer, Changkye Lee, Ghassan Kassab, Yiannis Chatzizisis

Journal of Medical Imaging, Vol. 11, Issue 01, 014004, (January 2024) https://doi.org/10.1117/1.JMI.11.1.014004

TOPICS: Image segmentation, Optical coherence tomography, 3D modeling, Optical coherence, Arteries, Image processing, 3D image processing, Tunable filters, Education and training, Shadows

Read Abstract +

Robust fiber orientation distribution function estimation using deep constrained spherical deconvolution for diffusion-weighted magnetic resonance imaging

Tianyuan Yao, Francois Rheault, Leon Y. Cai, Vishwesh Nath, Zuhayr Asad, Nancy Newlin, Can Cui, Ruining Deng, Karthik Ramadass, Andrea Shafer, Susan Resnick, Kurt Schilling, Bennett A. Landman, Yuankai Huo

Journal of Medical Imaging, Vol. 11, Issue 01, 014005, (January 2024) https://doi.org/10.1117/1.JMI.11.1.014005

TOPICS: Data modeling, Diffusion, Voxels, Education and training, Reproducibility, Modeling, 3D modeling, Brain, Silver, Performance modeling

Read Abstract +

Purpose

Diffusion-weighted magnetic resonance imaging (DW-MRI) is a critical imaging method for capturing and modeling tissue microarchitecture at a millimeter scale. A common practice to model the measured DW-MRI signal is via fiber orientation distribution function (fODF). This function is the essential first step for the downstream tractography and connectivity analyses. With recent advantages in data sharing, large-scale multisite DW-MRI datasets are being made available for multisite studies. However, measurement variabilities (e.g., inter- and intrasite variability, hardware performance, and sequence design) are inevitable during the acquisition of DW-MRI. Most existing model-based methods [e.g., constrained spherical deconvolution (CSD)] and learning-based methods (e.g., deep learning) do not explicitly consider such variabilities in fODF modeling, which consequently leads to inferior performance on multisite and/or longitudinal diffusion studies.

Approach

In this paper, we propose a data-driven deep CSD method to explicitly constrain the scan–rescan variabilities for a more reproducible and robust estimation of brain microstructure from repeated DW-MRI scans. Specifically, the proposed method introduces a three-dimensional volumetric scanner-invariant regularization scheme during the fODF estimation. We study the Human Connectome Project (HCP) young adults test–retest group as well as the MASiVar dataset (with inter- and intrasite scan/rescan data). The Baltimore Longitudinal Study of Aging dataset is employed for external validation.

Results

From the experimental results, the proposed data-driven framework outperforms the existing benchmarks in repeated fODF estimation. By introducing the contrastive loss with scan/rescan data, the proposed method achieved a higher consistency while maintaining higher angular correlation coefficients with the CSD modeling. The proposed method is assessing the downstream connectivity analysis and shows increased performance in distinguishing subjects with different biomarkers.

Conclusion

We propose a deep CSD method to explicitly reduce the scan–rescan variabilities, so as to model a more reproducible and robust brain microstructure from repeated DW-MRI scans. The plug-and-play design of the proposed approach is potentially applicable to a wider range of data harmonization problems in neuroimaging.

Deep learning segmentation of endothelial cell images using an active learning paradigm with guided label corrections

Naomi Joseph, Ian Marshall, Elizabeth Fitzpatrick, Harry J. Menegay, Jonathan H. Lass, Beth Ann M. Benetz, David L. Wilson

Journal of Medical Imaging, Vol. 11, Issue 01, 014006, (January 2024) https://doi.org/10.1117/1.JMI.11.1.014006

TOPICS: Image segmentation, Education and training, Deep learning, Active learning, Performance modeling, Data modeling, Image analysis, Image quality, Image processing, Cornea

Read Abstract +

Graph convolutional networks for automated intracranial artery labeling

Iris N. Vos, Ynte M. Ruigrok, Ishaan R. Bhat, Kimberley M. Timmins, Birgitta K. Velthuis, Hugo J. Kuijf

Journal of Medical Imaging, Vol. 11, Issue 01, 014007, (February 2024) https://doi.org/10.1117/1.JMI.11.1.014007

TOPICS: Arteries, Education and training, Calibration, Performance modeling, Independent component analysis, Spherical lenses, Feature extraction, Matrices, Image segmentation, Electrochemical etching

Read Abstract +

PS5-Net: a medical image segmentation network with multiscale resolution

Fuchen Li, Yong Liu, JianBo Qi, Yansong Du, QingYue Wang, WenBo Ma, XianChong Xu, ZhongQi Zhang

Journal of Medical Imaging, Vol. 11, Issue 01, 014008, (February 2024) https://doi.org/10.1117/1.JMI.11.1.014008

TOPICS: Image segmentation, Medical imaging, Feature extraction, Image resolution, Liver, Feature fusion, Data modeling, Convolution, Chaos, Network architectures

Read Abstract +

Purpose

In recent years, the continuous advancement of convolutional neural networks (CNNs) has led to the widespread integration of deep neural networks as a mainstream approach in clinical diagnostic support. Particularly, the utilization of CNN-based medical image segmentation has delivered favorable outcomes for aiding clinical diagnosis. Within this realm, network architectures based on the U-shaped structure and incorporating skip connections, along with their diverse derivatives, have gained extensive utilization across various medical image segmentation tasks. Nonetheless, two primary challenges persist. First, certain organs or tissues present considerable complexity, substantial morphological variations, and size discrepancies, posing significant challenges for achieving highly accurate segmentation. Second, the predominant focus of current deep neural networks on single-resolution feature extraction limits the effective extraction of feature information from complex medical images, thereby contributing to information loss via continuous pooling operations and contextual information interaction constraints within the U-shaped structure.

Approach

We proposed a five-layer pyramid segmentation network (PS5-Net), a multiscale segmentation network with diverse resolutions that is founded on the U-Net architecture. Initially, this network effectively leverages the distinct features of images at varying resolutions across different dimensions, departing from prior single-resolution feature extraction methods to adapt to intricate and variable segmentation scenarios. Subsequently, to comprehensively integrate feature information from diverse resolutions, a kernel selection module is proposed to assign weights to features across different dimensions, enhancing the fusion of feature information from various resolutions. Within the feature extraction network denoted as PS-UNet, we preserve the classical structure of the traditional U-Net while enhancing it through the incorporation of dilated convolutions.

Results

PS5-Net attains a Dice score of 0.9613 for liver segmentation on the CHLISC dataset and 0.8587 on the ISIC2018 dataset for skin lesion segmentation. Comparative analysis with diverse medical image segmentation methodologies in recent years reveals that PS5-Net has achieved the highest scores and substantial advancements.

Conclusions

PS5-Net effectively harnesses the rich semantic information available at different resolutions, facilitating a comprehensive and nuanced understanding of the input medical images. By capitalizing on global contextual connections, the network adeptly captures the intricate interplay of features and dependencies across the entire image, resulting in more accurate and robust segmentation outcomes. The experimental validation of PS5-Net underscores its superior performance in medical image segmentation tasks, offering promising prospects for enhancing diagnostic and analytical processes within clinical settings. These results highlight the potential of PS5-Net to significantly contribute to the advancement of medical imaging technologies and ultimately improve patient care through more precise and reliable image analysis.

Computer-Aided Diagnosis

Decision region analysis for generalizability of artificial intelligence models: estimating model generalizability in the case of cross-reactivity and population shift

Alexis Burgon, Berkman Sahiner, Nicholas Petrick, Gene Pennello, Kenny Cha, Ravi Samala

Journal of Medical Imaging, Vol. 11, Issue 01, 014501, (January 2024) https://doi.org/10.1117/1.JMI.11.1.014501

TOPICS: Data modeling, Statistical modeling, Artificial intelligence, Education and training, Performance modeling, Interpolation, Chest imaging, Medical imaging, Medical devices, Instrument modeling

Read Abstract +

Simulation-based feasibility study of monitoring of intracerebral hemorrhages and detection of secondary hemorrhages using electrical impedance tomography

Jussi Toivanen, Antti Paldanius, Bachir Dekdouk, Valentina Candiani, Asko Hänninen, Tuomo Savolainen, Daniel Strbian, Nina Forss, Nuutti Hyvönen, Jari Hyttinen, Ville Kolehmainen

Journal of Medical Imaging, Vol. 11, Issue 01, 014502, (January 2024) https://doi.org/10.1117/1.JMI.11.1.014502

TOPICS: Brain, Electrodes, Head, Detection and tracking algorithms, Computer simulations, Electrical conductivity, Biological imaging, Data modeling, Computed tomography, Modeling

Read Abstract +

MGMT promoter methylation prediction based on multiparametric MRI via vision graph neural network

Mingzhe Hu, Kailin Yang, Jing Wang, Richard L. J. Qiu, Justin Roper, Shannon Kahn, Hui-Kuo Shu, Xiaofeng Yang

Journal of Medical Imaging, Vol. 11, Issue 01, 014503, (February 2024) https://doi.org/10.1117/1.JMI.11.1.014503

TOPICS: Magnetic resonance imaging, Education and training, Tumors, Performance modeling, RGB color model, 3D modeling, Machine learning, Medical imaging, Image segmentation, Visualization

Read Abstract +

Image-Guided Procedures, Robotic Interventions, and Modeling

The Image-to-Physical Liver Registration Sparse Data Challenge: comparison of state-of-the-art using a common dataset

Jon Heiselman, Jarrod Collins, Morgan Ringel, T. Peter Kingham, William Jarnagin, Michael Miga

Journal of Medical Imaging, Vol. 11, Issue 01, 015001, (January 2024) https://doi.org/10.1117/1.JMI.11.1.015001

TOPICS: Image registration, Deformation, Liver, Biomechanics, Deep learning, Rigid registration, Data modeling, Detection and tracking algorithms, Natural surfaces, Boundary conditions

Read Abstract +

Purpose

Computational methods for image-to-physical registration during surgical guidance frequently rely on sparse point clouds obtained over a limited region of the organ surface. However, soft tissue deformations complicate the ability to accurately infer anatomical alignments from sparse descriptors of the organ surface. The Image-to-Physical Liver Registration Sparse Data Challenge introduced at SPIE Medical Imaging 2019 seeks to characterize the performance of sparse data registration methods on a common dataset to benchmark and identify effective tactics and limitations that will continue to inform the evolution of image-to-physical registration algorithms.

Approach

Three rigid and five deformable registration methods were contributed to the challenge. The deformable approaches consisted of two deep learning and three biomechanical boundary condition reconstruction methods. These algorithms were compared on a common dataset of 112 registration scenarios derived from a tissue-mimicking phantom with 159 subsurface validation targets. Target registration errors (TRE) were evaluated under varying conditions of data extent, target location, and measurement noise. Jacobian determinants and strain magnitudes were compared to assess displacement field consistency.

Results

Rigid registration algorithms produced significant differences in TRE ranging from 3.8±2.4 mm to 7.7±4.5 mm, depending on the choice of technique. Two biomechanical methods yielded TRE of 3.1±1.8 mm and 3.3±1.9 mm, which outperformed optimal rigid registration of targets. These methods demonstrated good performance under varying degrees of surface data coverage and across all anatomical segments of the liver. Deep learning methods exhibited TRE ranging from 4.3±3.3 mm to 7.6±5.3 mm but are likely to improve with continued development. TRE was weakly correlated among methods, with greatest agreement and field consistency observed among the biomechanical approaches.

Conclusions

The choice of registration algorithm significantly impacts registration accuracy and variability of deformation fields. Among current sparse data driven image-to-physical registration algorithms, biomechanical simulations that incorporate task-specific insight into boundary conditions seem to offer best performance.

Deep learning performance on MRI prostate gland segmentation: evaluation of two commercially available algorithms compared with an expert radiologist

Erik Thimansson, Erik Baubeta, Jonatan Engman, Anders Bjartell, Sophia Zackrisson

Journal of Medical Imaging, Vol. 11, Issue 01, 015002, (February 2024) https://doi.org/10.1117/1.JMI.11.1.015002

TOPICS: Prostate, Evolutionary algorithms, Magnetic resonance imaging, Image segmentation, Artificial intelligence, Deep learning, Biopsy, Data modeling, Education and training, Medicine

Read Abstract +

Digital Pathology

Benefits of spatial uncertainty aggregation for segmentation in digital pathology

Milda Pocevičiūtė, Gabriel Eilertsen, Claes Lundström

Journal of Medical Imaging, Vol. 11, Issue 01, 017501, (January 2024) https://doi.org/10.1117/1.JMI.11.1.017501

TOPICS: Image segmentation, Tumors, Pathology, Cancer detection, Education and training, Breast cancer, Lymph nodes, Histograms, Algorithm development, Visualization

Read Abstract +

End-to-end deep learning method for predicting hormonal treatment response in women with atypical endometrial hyperplasia or endometrial cancer

Seyed Mostafa M. Kahaki, Ian Hagemann, Kenny Cha, Christopher Trindade, Nicholas Petrick, Nicolas Kostelecky, Lindsay Borden, Doaa Atwi, Kar-Ming Fung, Weijie Chen

Journal of Medical Imaging, Vol. 11, Issue 01, 017502, (February 2024) https://doi.org/10.1117/1.JMI.11.1.017502

TOPICS: Education and training, Deep learning, Data modeling, Performance modeling, Feature extraction, Machine learning, Radiomics, RGB color model, Tumor growth modeling, Statistical modeling

Read Abstract +

Purpose

Endometrial cancer (EC) is the most common gynecologic malignancy in the United States, and atypical endometrial hyperplasia (AEH) is considered a high-risk precursor to EC. Hormone therapies and hysterectomy are practical treatment options for AEH and early-stage EC. Some patients prefer hormone therapies for reasons such as fertility preservation or being poor surgical candidates. However, accurate prediction of an individual patient’s response to hormonal treatment would allow for personalized and potentially improved recommendations for these conditions. This study aims to explore the feasibility of using deep learning models on whole slide images (WSI) of endometrial tissue samples to predict the patient’s response to hormonal treatment.

Approach

We curated a clinical WSI dataset of 112 patients from two clinical sites. An expert pathologist annotated these images by outlining AEH/EC regions. We developed an end-to-end machine learning model with mixed supervision. The model is based on image patches extracted from pathologist-annotated AEH/EC regions. Either an unsupervised deep learning architecture (Autoencoder or ResNet50), or non-deep learning (radiomics feature extraction) is used to embed the images into a low-dimensional space, followed by fully connected layers for binary prediction, which was trained with binary responder/non-responder labels established by pathologists. We used stratified sampling to partition the dataset into a development set and a test set for internal validation of the performance of our models.

Results

The autoencoder model yielded an AUROC of 0.80 with 95% CI [0.63, 0.95] on the independent test set for the task of predicting a patient with AEH/EC as a responder vs non-responder to hormonal treatment.

Conclusions

These findings demonstrate the potential of using mixed supervised machine learning models on WSIs for predicting the response to hormonal treatment in AEH/EC patients.

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusion

Purpose

Approach

Results

Conclusions

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