Volume 12 Issue 1 | Journal of Medical Imaging

Journal of Medical Imaging

VOL. 12 · NO. 1 | January 2025

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

Editorial (1)

Physics of Medical Imaging (1)

Image Processing (3)

Computer-Aided Diagnosis (5)

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 +

Editorial

2024 List of Reviewers

Journal of Medical Imaging, Vol. 12, Issue 01, 010102, (January 2025) https://doi.org/10.1117/1.JMI.12.1.010102

TOPICS: Lithium, Mendelevium, Lutetium, Gallium nitride, Alternate lighting of surfaces

Read Abstract +

Physics of Medical Imaging

Evaluation of charge summing correction in CdTe-based photon-counting detectors for breast CT: performance metrics and image quality

Sriharsha Marupudi, Joseph Manus, Muhammad Ghani, Stephen Glick, Bahaa Ghammraoui

Journal of Medical Imaging, Vol. 12, Issue 01, 013501, (January 2025) https://doi.org/10.1117/1.JMI.12.1.013501

TOPICS: Surface plasmons, Iodine, Sensors, Modulation transfer functions, Image restoration, X-rays, Calibration, Polymethylmethacrylate, X-ray detectors, X-ray computed tomography

Read Abstract +

Purpose

We evaluate the impact of charge summing correction on a cadmium telluride (CdTe)-based photon-counting detector in breast computed tomography (CT).

Approach

We employ a custom-built laboratory benchtop system using the X-THOR FX30 0.75-mm CdTe detector (Varex Imaging, Salt Lake City, Utah, United States) with a pixel pitch of 0.1 mm, operated in both standard mode [single pixel (SP)] and charge summing correction mode [anticoincidence (AC)]. A tungsten anode source operated at 55 kVp with 2-mm aluminum external filtration and tube currents of 25, 100, and 200 mA with corresponding exposure times of 20, 5, and 2.5 ms were employed to study the effects of X-ray fluence and pulse pileup. Performance comparisons between AC and SP modes are performed in both projection and image reconstructed spaces. In the projection space, performance metrics include count rate, energy resolution, uniformity, modulation transfer function (MTF), and noise power spectrum (NPS). In the image space, performance metrics consist of contrast-to-noise ratio (CNR), uniformity, NPS, and iodine quantification accuracy. For both acquisition modes, signal-to-thickness calibration, for gain and beam hardening corrections, is used before image reconstruction. Images are reconstructed via TIGRE CT software using the standard Feldkamp, Davis, and Kress (FDK) filtered back projection algorithm with a Hann filter and reconstructed with a voxel size of 0.081 mm. Material decomposition is performed using a standard image-based method.

Results

In the detector space, the application of hardware-based charge summing correction enhances spectral resolution and improves the spatial resolution of MTF at lower energy thresholds but introduces anomalous edge enhancement effects and artifacts in the MTF at high fluence. A negative noise correlation was observed in AC mode–acquired images. As expected, the AC acquisition mode results in a decreased detector count rate. In the image space, NPS results displayed elevated noise in low-energy AC images. However, at high energy, noise was comparable between both modes. Greater uniformity was observed in SP mode–acquired images. The largest disparity was observed in the iodine quantification test, where the AC mode demonstrates a much stronger linear relationship between estimated and true iodine concentrations than the SP mode.

Conclusion

The results are specific to the studied system, reconstruction parameters, and irradiation conditions limited to 200 mA and 0.5 mAs. The AC mode generally provides better energy and MTF resolution at low energy thresholds but with increased noise and reduced uniformity. In image space, charge summing correction improved iodine quantification and CNR at high energy thresholds.

Image Processing

EAGLE: an edge-aware gradient localization enhanced loss for CT image reconstruction

Yipeng Sun, Yixing Huang, Zeyu Yang, Linda-Sophie Schneider, Mareike Thies, Mingxuan Gu, Siyuan Mei, Siming Bayer, Frank Zöllner, Andreas Maier

Journal of Medical Imaging, Vol. 12, Issue 01, 014001, (January 2025) https://doi.org/10.1117/1.JMI.12.1.014001

TOPICS: Computed tomography, CT reconstruction, Education and training, Image restoration, Image quality, Visualization, Image sharpness, Image enhancement, Medical image reconstruction, Super resolution

Read Abstract +

Purpose

We aim to enhance deep learning-based computed tomography (CT) image reconstructions. Conventional loss functions such as mean squared error (MSE) yield blurry images, and alternative methods may introduce artifacts. To address these limitations, we propose Eagle-Loss, designed to improve sharpness and edge definition without increasing computational complexity. Eagle-Loss leverages spectral analysis of localized gradient variations to enhance visual quality and quantification in CT imaging.

Approach

Eagle-Loss enhances CT reconstructions by segmenting gradient maps into patches and calculating intra-block variance to create a variance map. This map is analyzed in the frequency domain to identify critical features. We evaluate Eagle-Loss on two public datasets for low-dose CT reconstruction and field-of-view (FOV) extension and on a private photon counting CT (PCCT) dataset for super-resolution. Eagle-Loss is integrated into various deep learning models and used as a regularizer in ART, demonstrating effectiveness across reconstruction methods.

Results

Our experiments show that Eagle-Loss outperforms existing methods across all evaluated tasks, consistently improving the visual quality of reconstructed CT images. It achieves better performance compared with current top-performing loss functions when used with different network architectures while maintaining similar speed without adding extra computational costs. For low-dose CT reconstruction, Eagle-Loss achieved the highest SSIM scores of 0.958 for the TF-FBP model and 0.972 for RED-CNN. In the CT FOV task, our method reached a best SSIM of 0.966. For PCCT super-resolution, Eagle-Loss attained a top SSIM score of 0.998.

Conclusions

Eagle-Loss effectively mitigates blurring and artifacts prevalent in current CT reconstruction methods by significantly improving image sharpness and edge definition. Our evaluation confirms that Eagle-Loss can be successfully integrated into various deep learning models and reconstruction techniques without incurring additional computational costs, underscoring its robustness and model-independent nature. This significant enhancement in visual quality is important for achieving more accurate diagnoses and improved clinical outcomes.

Respiratory-gated micro-computed tomography imaging to measure radiation-induced lung injuries in mice following ultra-high dose-rate and conventional dose-rate radiation therapy

Nancy Ford, Xi Ren, Luca Egoriti, Nolan Esplen, Stephanie Radel, Brandon Humphries, Hui-Wen Koay, Thomas Planche, Cornelia Hoehr, Alexander Gottberg, Magdalena Bazalova-Carter

Journal of Medical Imaging, Vol. 12, Issue 01, 014002, (January 2025) https://doi.org/10.1117/1.JMI.12.1.014002

TOPICS: Lung, Control systems, Radiotherapy, Tissues, Tomography, Animals, Injuries, Computed tomography, Tumors, Pathology

Read Abstract +

Deep learning CT image restoration using system blur and noise models

Yijie Yuan, Grace J. Gang, J. Webster Stayman

Journal of Medical Imaging, Vol. 12, Issue 01, 014003, (February 2025) https://doi.org/10.1117/1.JMI.12.1.014003

TOPICS: Performance modeling, Deep learning, Image restoration, Computed tomography, Education and training, Imaging systems, Data modeling, Image quality, Medical imaging, Image enhancement

Read Abstract +

Computer-Aided Diagnosis

Predicting the risk of type 2 diabetes mellitus (T2DM) emergence in 5 years using mammography images: a comparison study between radiomics and deep learning algorithm

Nishta Letchumanan, Shouhei Hanaoka, Tomomi Takenaga, Yusuke Suzuki, Takahiro Nakao, Yukihiro Nomura, Takeharu Yoshikawa, Osamu Abe

Journal of Medical Imaging, Vol. 12, Issue 01, 014501, (January 2025) https://doi.org/10.1117/1.JMI.12.1.014501

TOPICS: Radiomics, Deep learning, Mammography, Cooccurrence matrices, Performance modeling, Feature extraction, Data modeling, Machine learning, Education and training, Diseases and disorders

Read Abstract +

Breast cancer classification in point-of-care ultrasound imaging—the impact of training data

Jennie Karlsson, Ida Arvidsson, Freja Sahlin, Kalle Åström, Niels Christian Overgaard, Kristina Lång, Anders Heyden

Journal of Medical Imaging, Vol. 12, Issue 01, 014502, (January 2025) https://doi.org/10.1117/1.JMI.12.1.014502

TOPICS: Education and training, Histograms, Ultrasonography, Image classification, Breast cancer, Point-of-care devices, Breast, Diagnostics, Tissues, Cancer detection

Read Abstract +

Pericoronary adipose tissue feature analysis in computed tomography calcium score images in comparison to coronary computed tomography angiography

Yingnan Song, Hao Wu, Juhwan Lee, Justin Kim, Ammar Hoori, Tao Hu, Vladislav Zimin, Mohamed Makhlouf, Sadeer Al-Kindi, Sanjay Rajagopalan, Chun-Ho Yun, Chung-Lieh Hung, David Wilson

Journal of Medical Imaging, Vol. 12, Issue 01, 014503, (January 2025) https://doi.org/10.1117/1.JMI.12.1.014503

TOPICS: Detection and tracking algorithms, Arteries, Computed tomography, Radiomics, Adipose tissue, Image segmentation, Iodine, Image registration, Feature extraction, Wavelets

Read Abstract +

Automatic detection of main pancreatic duct dilation and pancreatic parenchymal atrophy based on a shape feature in abdominal contrast-enhanced CT images

Shintaro Ambo, Ryo Hirano, Chihiro Hattori

Journal of Medical Imaging, Vol. 12, Issue 01, 014504, (January 2025) https://doi.org/10.1117/1.JMI.12.1.014504

TOPICS: Image segmentation, Computed tomography, Algorithm development, Pancreas, Pancreatic cancer, Feature extraction, Cancer detection, Deep learning, Detection and tracking algorithms, Liver

Read Abstract +

Vision transformer distillation for enhanced gastrointestinal abnormality recognition in wireless capsule endoscopy images

Yassine Oukdach, Anass Garbaz, Zakaria Kerkaou, Mohamed El Ansari, Lahcen Koutti, Nikolaos Papachrysos, Ahmed Fouad El Ouafdi, Thomas de Lange, Cosimo Distante

Journal of Medical Imaging, Vol. 12, Issue 01, 014505, (February 2025) https://doi.org/10.1117/1.JMI.12.1.014505

TOPICS: Data modeling, Performance modeling, Visual process modeling, Transformers, Education and training, Machine learning, Feature extraction, Enhanced vision, Diseases and disorders, Image classification

Read Abstract +

Image Perception, Observer Performance, and Technology Assessment

Examining the influence of digital phantom models in virtual imaging trials for tomographic breast imaging

Amar Kavuri, Mini Das

Journal of Medical Imaging, Vol. 12, Issue 01, 015501, (December 2024) https://doi.org/10.1117/1.JMI.12.1.015501

TOPICS: Breast, Digital breast tomosynthesis, Imaging systems, Breast density, Anatomy, Diagnostics, Tomography, Systems modeling, Spherical lenses, Quantum modeling

Read Abstract +

Biomedical Applications in Molecular, Structural, and Functional Imaging

Backscattering Mueller matrix polarimetry estimates microscale anisotropy and orientation in complex brain tissue structure

Rhea Carlson, Courtney Comrie, Justina Bonaventura, Kellys Morara, Noelle Daigle, Elizabeth Hutchinson, Travis Sawyer

Journal of Medical Imaging, Vol. 12, Issue 01, 016001, (December 2024) https://doi.org/10.1117/1.JMI.12.1.016001

TOPICS: Tissues, Mueller matrices, Brain tissue, Backscatter, Polarimetry, Biological samples, Anisotropy, Polarization, Brain, Magnetic resonance imaging

Read Abstract +

Ultrasonic Imaging and Tomography

Ultrasound elastic modulus reconstruction using a deep learning model trained with simulated data

Utsav Ratna Tuladhar, Richard Simon, Cristian Linte, Michael Richards

Journal of Medical Imaging, Vol. 12, Issue 01, 017001, (February 2025) https://doi.org/10.1117/1.JMI.12.1.017001

TOPICS: Data modeling, Deep learning, Education and training, Ultrasonography, Elastic modulus, Performance modeling, Tissues, Elastography, Computer simulations, Signal to noise ratio

Read Abstract +

Purpose

Ultrasound (US) elastography is a technique for non-invasive quantification of material properties, such as stiffness, from ultrasound images of deforming tissue. The material properties are calculated by solving the inverse problem on the measured displacement field from the ultrasound images. The limitations of traditional inverse problem techniques in US elastography are either slow and computationally intensive (iterative techniques) or sensitive to measurement noise and dependent on full displacement field data (direct techniques). Thus, we develop and validate a deep learning approach for solving the inverse problem in US elastography. This involves recovering the spatial modulus distribution of the elastic modulus from one component of the US-measured displacement field.

Approach

We present a U-Net-based deep learning neural network to address the inverse problem in ultrasound elastography. This approach diverges from traditional methods by focusing on a data-driven model. The neural network is trained using data generated from a forward finite element model. This simulation incorporates variations in the displacement fields that correspond to the elastic modulus distribution, allowing the network to learn without the need for extensive real-world measurement data. The inverse problem of predicting the modulus spatial distribution from ultrasound-measured displacement fields is addressed using a trained neural network. The neural network is evaluated with mean squared error (MSE) and mean absolute percentage error (MAPE) metrics. To extend our model to practical purposes, we conduct phantom experiments and also apply our model to clinical data.

Results

Our simulated results indicate that our deep learning (DL) model effectively reconstructs modulus distributions, as evidenced by low MSE and MAPE evaluation metrics. We obtain a mean MAPE of 0.32% for a hard inclusion and 0.39% for a soft inclusion. Similarly, in our phantom studies, the predicted modulus ratio aligns with the expected range, affirming the model’s accuracy. These findings, alongside evaluations using the modulus ratio and contrast-to-noise ratio, confirm our DL model’s robust generalization capabilities across diverse datasets.

Conclusions

The presented work demonstrated that provided the simulated data are sufficiently diverse and representative of a wide variability, the algorithm trained on simulated data would generalize well to both phantom, as well as real-world clinical data.

Digital Pathology

Dye amount quantification of Papanicolaou-stained cytological images by multispectral unmixing: spectral analysis of cytoplasmic mucin

Saori Takeyama, Tomoaki Watanabe, Nanxin Gong, Masahiro Yamaguchi, Takumi Urata, Fumikazu Kimura, Keiko Ishii

Journal of Medical Imaging, Vol. 12, Issue 01, 017501, (December 2024) https://doi.org/10.1117/1.JMI.12.1.017501

TOPICS: Dyes, Matrices, RGB color model, Cell biology, Statistical analysis, Absorbance, Multispectral imaging, Microscopes, Absorption, Image classification

Read Abstract +

Weakly supervised pathological differentiation of primary central nervous system lymphoma and glioblastoma on multi-site whole slide images

Liping Wang, Lin Chen, Kaixi Wei, Huiyu Zhou, Reyer Zwiggelaar, Weiwei Fu, Yingchao Liu

Journal of Medical Imaging, Vol. 12, Issue 01, 017502, (January 2025) https://doi.org/10.1117/1.JMI.12.1.017502

TOPICS: Feature extraction, Education and training, Data modeling, Tissues, Tumors, Histopathology, Nervous system, Lymphoma, Deep learning, RGB color model

Read Abstract +

Purpose

Differentiating primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM) is crucial because their prognosis and treatment differ substantially. Manual examination of their histological characteristics is considered the golden standard in clinical diagnosis. However, this process is tedious and time-consuming and might lead to misdiagnosis caused by morphological similarity between their histology and tumor heterogeneity. Existing research focuses on radiological differentiation, which mostly uses multi-parametric magnetic resonance imaging. By contrast, we investigate the pathological differentiation between the two types of tumors using whole slide images (WSIs) of postoperative formalin-fixed paraffin-embedded samples.

Approach

To learn the specific and intrinsic histological feature representations from the WSI patches, a self-supervised feature extractor is trained. Then, the patch representations are fused by feeding into a weakly supervised multiple-instance learning model for the WSI classification. We validate our approach on 134 PCNSL and 526 GBM cases collected from three hospitals. We also investigate the effect of feature extraction on the final prediction by comparing the performance of applying the feature extractors trained on the PCNSL/GBM slides from specific institutions, multi-site PCNSL/GBM slides, and large-scale histopathological images.

Results

Different feature extractors perform comparably with the overall area under the receiver operating characteristic curve value exceeding 85% for each dataset and close to 95% for the combined multi-site dataset. Using the institution-specific feature extractors generally obtains the best overall prediction with both of the PCNSL and GBM classification accuracies reaching 80% for each dataset.

Conclusions

The excellent classification performance suggests that our approach can be used as an assistant tool to reduce the pathologists’ workload by providing an accurate and objective second diagnosis. Moreover, the discriminant regions indicated by the generated attention heatmap improve the model interpretability and provide additional diagnostic information.

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

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Methods

Results

Conclusion

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Purpose

Approach

Results

Conclusions

Keywords/Phrases

Search In:

Publication Years