Volume 10 Issue 6 | Journal of Medical Imaging

Journal of Medical Imaging

VOL. 10 · NO. 6 | November 2023

CONTENTS

IN THIS ISSUE

Editorial (1)

Special Series on Global Health, Equity, Bias, and Diversity in AI in Medical Imaging (7)

Special Section on Informatics and Imaging Data Management (4)

Physics of Medical Imaging (2)

Image Processing (4)

Computer-Aided Diagnosis (4)

Image Perception, Observer Performance, and Technology Assessment (3)

Biomedical Applications in Molecular, Structural, and Functional Imaging (4)

PACS and Imaging Informatics (1)

Digital Pathology (2)

< Previous Issue | Next Issue >

Receive Email Alerts

VIEW ALL ABSTRACTS +

Editorial

Passing the JMI Torch: Thank You to the Medical Imaging Community for our Amazing Journey

Maryellen Giger

Journal of Medical Imaging, Vol. 10, Issue 06, 060101, (December 2023) https://doi.org/10.1117/1.JMI.10.6.060101

TOPICS: Medical imaging, Artificial intelligence, Lanthanum, X-ray computed tomography, Tomography, Robotics, Reflection, Radiomics, Positron emission tomography, Pathology

Read Abstract +

Special Series on Global Health, Equity, Bias, and Diversity in AI in Medical Imaging

Special Section Guest Editorial: Global Health, Bias, and Diversity in AI in Medical Imaging

Judy W. Gichoya, Rui C. Sá, Ronald M. Summers, Heather Whitney

Journal of Medical Imaging, Vol. 10, Issue 06, 061101, (January 2024) https://doi.org/10.1117/1.JMI.10.6.061101

TOPICS: Artificial intelligence, Medical imaging, Visual process modeling, Data modeling, Evolutionary algorithms, Education and training, Deep learning, Biomedical optics, Radiology, Medicine

Read Abstract +

Homogenization of multi-institutional chest x-ray images in various data transformation schemes

Hyeongseok Kim, Seoyoung Lee, Woo Jung Shim, Min-Seong Choi, Seungryong Cho

Journal of Medical Imaging, Vol. 10, Issue 06, 061103, (April 2023) https://doi.org/10.1117/1.JMI.10.6.061103

TOPICS: Education and training, Chest imaging, Lung, Radiomics, Homogenization, Data modeling, Visualization, Image processing, Mahalanobis distance, Image segmentation

Read Abstract +

Toward fairness in artificial intelligence for medical image analysis: identification and mitigation of potential biases in the roadmap from data collection to model deployment

Karen Drukker, Weijie Chen, Judy Gichoya, Nicholas Gruszauskas, Jayashree Kalpathy-Cramer, Sanmi Koyejo, Kyle Myers, Rui Sá, Berkman Sahiner, Heather Whitney, Zi Zhang, Maryellen Giger

Journal of Medical Imaging, Vol. 10, Issue 06, 061104, (April 2023) https://doi.org/10.1117/1.JMI.10.6.061104

TOPICS: Data modeling, Education and training, Medical imaging, Artificial intelligence, Performance modeling, Data acquisition, Machine learning, Evolutionary algorithms, Diseases and disorders, COVID 19

Read Abstract +

Longitudinal assessment of demographic representativeness in the Medical Imaging and Data Resource Center open data commons

Heather M. Whitney, Natalie Baughan, Kyle J. Myers, Karen Drukker, Judy Gichoya, Brad Bower, Weijie Chen, Nicholas Gruszauskas, Jayashree Kalpathy-Cramer, Sanmi Koyejo, Rui C. Sá, Berkman Sahiner, Zi Zhang, Maryellen L. Giger

Journal of Medical Imaging, Vol. 10, Issue 06, 061105, (July 2023) https://doi.org/10.1117/1.JMI.10.6.061105

TOPICS: COVID 19, Medical imaging, Algorithm development, Diseases and disorders, Artificial intelligence, Data modeling, Gold, Medicine, Medical research, Evolutionary algorithms

Read Abstract +

Ability of artificial intelligence to identify self-reported race in chest x-ray using pixel intensity counts

John Lee Burns, Zachary Zaiman, Jack Vanschaik, Gaoxiang Luo, Le Peng, Brandon Price, Garric Mathias, Vijay Mittal, Akshay Sagane, Christopher Tignanelli, Sunandan Chakraborty, Judy Gichoya, Saptarshi Purkayastha

Journal of Medical Imaging, Vol. 10, Issue 06, 061106, (August 2023) https://doi.org/10.1117/1.JMI.10.6.061106

TOPICS: Artificial intelligence, Data modeling, Chest imaging, Binary data, X-rays, Brain-machine interfaces, Machine learning, Performance modeling, Education and training, Decision trees

Read Abstract +

Image harmonization and deep learning automated classification of plus disease in retinopathy of prematurity

Ananya Subramaniam, Faruk Orge, Michael Douglass, Basak Can, Guillermo Monteoliva, Evelin Fried, Vanina Schbib, Gabriela Saidman, Brenda Peña, Soledad Ulacia, Pedro Acevedo, Andrew M. Rollins, David L. Wilson

Journal of Medical Imaging, Vol. 10, Issue 06, 061107, (October 2023) https://doi.org/10.1117/1.JMI.10.6.061107

TOPICS: Deep learning, Image classification, Diseases and disorders, Image enhancement, Education and training, Image quality, Vascular diseases, Image processing, Retinal diseases, Diagnostics

Read Abstract +

Validating racial and ethnic non-bias of artificial intelligence decision support for diagnostic breast ultrasound evaluation

Clara Koo, Anthony Yang, Colton Welch, Vipashyana Jadav, Liana Posch, Nicholas Thoreson, Darrell Morris, Fatima Chouhdry, Janet Szabo, David Mendelson, Laurie R. Margolies

Journal of Medical Imaging, Vol. 10, Issue 06, 061108, (December 2023) https://doi.org/10.1117/1.JMI.10.6.061108

TOPICS: Artificial intelligence, Pathology, Ultrasonography, Breast, Biopsy, Breast cancer, Diagnostics, Imaging systems, Cancer detection, Mammography

Read Abstract +

Special Section on Informatics and Imaging Data Management

Malmö Breast ImaginG database: objectives and development

Victor Dahlblom, Magnus Dustler, Anetta Bolejko, Predrag R. Bakic, Henrik Granberg, Kristin Johnson, Daniel Förnvik, Kristina Lång, Anders Tingberg, Sophia Zackrisson

Journal of Medical Imaging, Vol. 10, Issue 06, 061402, (February 2023) https://doi.org/10.1117/1.JMI.10.6.061402

TOPICS: Databases, Mammography, Cancer, Breast cancer, Diagnostics, Breast, Breast imaging, Digital breast tomosynthesis, Artificial intelligence, Tumors

Read Abstract +

medigan: a Python library of pretrained generative models for medical image synthesis

Richard Osuala, Grzegorz Skorupko, Noussair Lazrak, Lidia Garrucho, Eloy García, Smriti Joshi, Socayna Jouide, Michael Rutherford, Fred Prior, Kaisar Kushibar, Oliver Díaz, Karim Lekadir

Journal of Medical Imaging, Vol. 10, Issue 06, 061403, (February 2023) https://doi.org/10.1117/1.JMI.10.6.061403

TOPICS: Data modeling, Education and training, Medical imaging, Process modeling, Statistical modeling, Mammography, Visual process modeling, Performance modeling, Systems modeling, Gallium nitride

Read Abstract +

Purpose

Deep learning has shown great promise as the backbone of clinical decision support systems. Synthetic data generated by generative models can enhance the performance and capabilities of data-hungry deep learning models. However, there is (1) limited availability of (synthetic) datasets and (2) generative models are complex to train, which hinders their adoption in research and clinical applications. To reduce this entry barrier, we explore generative model sharing to allow more researchers to access, generate, and benefit from synthetic data.

Approach

We propose medigan, a one-stop shop for pretrained generative models implemented as an open-source framework-agnostic Python library. After gathering end-user requirements, design decisions based on usability, technical feasibility, and scalability are formulated. Subsequently, we implement medigan based on modular components for generative model (i) execution, (ii) visualization, (iii) search & ranking, and (iv) contribution. We integrate pretrained models with applications across modalities such as mammography, endoscopy, x-ray, and MRI.

Results

The scalability and design of the library are demonstrated by its growing number of integrated and readily-usable pretrained generative models, which include 21 models utilizing nine different generative adversarial network architectures trained on 11 different datasets. We further analyze three medigan applications, which include (a) enabling community-wide sharing of restricted data, (b) investigating generative model evaluation metrics, and (c) improving clinical downstream tasks. In (b), we extract Fréchet inception distances (FID) demonstrating FID variability based on image normalization and radiology-specific feature extractors.

Conclusion

medigan allows researchers and developers to create, increase, and domain-adapt their training data in just a few lines of code. Capable of enriching and accelerating the development of clinical machine learning models, we show medigan’s viability as platform for generative model sharing. Our multimodel synthetic data experiments uncover standards for assessing and reporting metrics, such as FID, in image synthesis studies.

VAI-B: a multicenter platform for the external validation of artificial intelligence algorithms in breast imaging

Fernando Cossío, Haiko Schurz, Mathias Engström, Carl Barck-Holst, Apostolia Tsirikoglou, Claes Lundström, Håkan Gustafsson, Kevin Smith, Sophia Zackrisson, Fredrik Strand

Journal of Medical Imaging, Vol. 10, Issue 06, 061404, (March 2023) https://doi.org/10.1117/1.JMI.10.6.061404

TOPICS: Artificial intelligence, Databases, Evolutionary algorithms, Cancer, Breast cancer, Mammography, Data modeling, Clouds, Image processing, Imaging systems

Read Abstract +

Purpose

Multiple vendors are currently offering artificial intelligence (AI) computer-aided systems for triage detection, diagnosis, and risk prediction of breast cancer based on screening mammography. There is an imminent need to establish validation platforms that enable fair and transparent testing of these systems against external data.

Approach

We developed validation of artificial intelligence for breast imaging (VAI-B), a platform for independent validation of AI algorithms in breast imaging. The platform is a hybrid solution, with one part implemented in the cloud and another in an on-premises environment at Karolinska Institute. Cloud services provide the flexibility of scaling the computing power during inference time, while secure on-premises clinical data storage preserves their privacy. A MongoDB database and a python package were developed to store and manage the data on-premises. VAI-B requires four data components: radiological images, AI inferences, radiologist assessments, and cancer outcomes.

Results

To pilot test VAI-B, we defined a case-control population based on 8080 patients diagnosed with breast cancer and 36,339 healthy women based on the Swedish national quality registry for breast cancer. Images and radiological assessments from more than 100,000 mammography examinations were extracted from hospitals in three regions of Sweden. The images were processed by AI systems from three vendors in a virtual private cloud to produce abnormality scores related to signs of cancer in the images. A total of 105,706 examinations have been processed and stored in the database.

Conclusions

We have created a platform that will allow downstream evaluation of AI systems for breast cancer detection, which enables faster development cycles for participating vendors and safer AI adoption for participating hospitals. The platform was designed to be scalable and ready to be expanded should a new vendor want to evaluate their system or should a new hospital wish to obtain an evaluation of different AI systems on their images.

Picture archiving and communication systems: past, present, and future

Katherine P. Andriole

Journal of Medical Imaging, Vol. 10, Issue 06, 061405, (December 2023) https://doi.org/10.1117/1.JMI.10.6.061405

TOPICS: Picture Archiving and Communication System, Radiology, Medicine, Artificial intelligence, Imaging systems, Standards development, Biomedical applications, Medical imaging, Data communications, Telecommunications

Read Abstract +

Physics of Medical Imaging

Quantitative perfusion and water transport time model from multi b-value diffusion magnetic resonance imaging validated against neutron capture microspheres

Mira Liu, Niloufar Saadat, Yong Jeong, Steven Roth, Marek Niekrasz, Mihai Giurcanu, Timothy Carroll, Gregory Christoforidis

Journal of Medical Imaging, Vol. 10, Issue 06, 063501, (December 2023) https://doi.org/10.1117/1.JMI.10.6.063501

TOPICS: Microspheres, Diffusion, Capillaries, Magnetic resonance imaging, Blood, Linear regression, Tissues, Statistical analysis, Voxels, Current controlled current source

Read Abstract +

Purpose

Quantification of perfusion in ml/100 g/min, rather than comparing relative values side-to-side, is critical at the clinical and research levels for large longitudinal and multi-center trials. Intravoxel incoherent motion (IVIM) is a non-contrast magnetic resonance imaging diffusion-based scan that uses a multitude of b-values to measure various speeds of molecular perfusion and diffusion, sidestepping inaccuracy of arterial input functions or bolus kinetics. Questions remain as to the original of the signal and whether IVIM returns quantitative and accurate perfusion in a pathology setting. This study tests a novel method of IVIM perfusion quantification compared with neutron capture microspheres.

Approach

We derive an expression for the quantification of capillary blood flow in ml/100 g/min by solving the three-dimensional Gaussian probability distribution and defining water transport time (WTT) as when 50% of the original water remains in the tissue of interest. Calculations were verified in a six-subject pre-clinical canine model of normocapnia, CO₂ induced hypercapnia, and middle cerebral artery occlusion (ischemic stroke) and compared with quantitative microsphere perfusion.

Results

Linear regression analysis of IVIM and microsphere perfusion showed agreement (slope = 0.55, intercept = 52.5, R² = 0.64) with a Bland–Altman mean difference of −11.8 [ − 78,54 ] ml / 100 g / min. Linear regression between dynamic susceptibility contrast mean transit time and IVIM WTT asymmetry in infarcted tissue was excellent (slope = 0.59, intercept = 0.3, R² = 0.93). Strong linear agreement was found between IVIM and reference standard infarct volume (slope = 1.01, R² = 0.79). The simulation of cerebrospinal fluid (CSF) suppression via inversion recovery returned a blood signal reduced by 82% from combined T1 and T2 effects.

Conclusions

The accuracy and sensitivity of IVIM provides evidence that observed signal changes reflect cytotoxic edema and tissue perfusion and can be quantified with WTT. Partial volume contamination of CSF may be better removed during post-processing rather than with inversion recovery.

Coronary stenosis quantification in cardiac computed tomography angiography: multi-factorial optimization of image quality and radiation dose

Mojtaba Zarei, Ehsan Abadi, William Paul Segars, Ehsan Samei

Journal of Medical Imaging, Vol. 10, Issue 06, 063502, (December 2023) https://doi.org/10.1117/1.JMI.10.6.063502

TOPICS: Image quality, Computed tomography, Mathematical optimization, Decision trees, Physics, Data modeling, Clinical trials, Angiography, Scanners, Heart

Read Abstract +

Background

The accuracy and variability of quantification in computed tomography angiography (CTA) are affected by the interplay of imaging parameters and patient attributes. The assessment of these combined effects has been an open engineering challenge.

Purpose

In this study, we developed a framework that optimizes imaging parameters for accurate and consistent coronary stenosis quantification in cardiac CTA while accounting for patient-specific variables.

Methods

The framework utilizes a task-specific image quality index, the estimability index (e′), approximated by a surrogate estimability polynomial function (EPF) capable of finding the optimal protocol that (1) maximizes image quality with an upper bound for desired radiation dose or (2) minimizes the dose level with a lower bound of acceptable image quality. The optimization process was formulated with the decision variables being subject to a set of constraints. The methodology was verified using CTA data from a prior clinical trial (prospective multi-center imaging study for evaluation of chest pain) by assessing the concordance of its prediction with the trial results. Further, the framework was used to derive an optimum protocol for each case based on the patient attributes, gauging how much improvement would have been possible if the derived optimized protocol would have been deployed.

Results

The framework produced results consistent with imaging physics principles with approximated EPFs of 97% accuracy. The feature importance evaluation demonstrated a close match with earlier studies. The verification study found e′ scores closely predicting the cardiologist scores to within 95% in terms of the area under the receiver operating characteristic curve and predicting potential for either an average of fourfold increase in e′ within a targeted dose or a reduction in radiation dose by an average of 57% without reducing the image quality.

Conclusions

The protocol optimization framework provides means to assess and optimize CTA in terms of either image quality or radiation dose objectives with its results predicting prior clinical trial findings.

Image Processing

Reproducibility evaluation of the effects of MRI defacing on brain segmentation

Chenyu Gao, Bennett Landman, Jerry Prince, Aaron Carass

Journal of Medical Imaging, Vol. 10, Issue 06, 064001, (November 2023) https://doi.org/10.1117/1.JMI.10.6.064001

TOPICS: Image segmentation, Magnetic resonance imaging, Brain, Neuroimaging, Reproducibility, Detection and tracking algorithms, Image registration, Image processing, Image quality, Rain

Read Abstract +

Computed tomography texture analysis to discriminate fungal and non-fungal infected fluid collections

Benedikt Schnarkowski, Jakob Leonhardi, Matthias Mehdorn, Ines Gockel, Gordian Prasse, Sebastian Ebel, Timm Denecke, Hans-Jonas Meyer

Journal of Medical Imaging, Vol. 10, Issue 06, 064002, (November 2023) https://doi.org/10.1117/1.JMI.10.6.064002

TOPICS: Computed tomography, Microfluidics, Biological research, Microfluidic imaging, Diagnostics, Statistical analysis, Attenuation, Surgery, Reflection, Fungi

Read Abstract +

Deep learning based tomosynthesis denoising: a bias investigation across different breast types

Dominik Eckert, Julia Wicklein, Magdalena Herbst, Stephan Dwars, Ludwig Ritschl, Steffen Kappler, Sebastian Stober

Journal of Medical Imaging, Vol. 10, Issue 06, 064003, (December 2023) https://doi.org/10.1117/1.JMI.10.6.064003

TOPICS: Denoising, Breast, Education and training, Digital breast tomosynthesis, Tomosynthesis, Computer simulations, Deep learning, X-rays, Breast density, Photons

Read Abstract +

Image denoising in fluorescence microscopy using feature based gradient reconstruction

Suman Maji, Hussein Yahia

Journal of Medical Imaging, Vol. 10, Issue 06, 064004, (December 2023) https://doi.org/10.1117/1.JMI.10.6.064004

TOPICS: Denoising, Fluorescence microscopy, Image denoising, Image restoration, Feature extraction, Microscopy, Image resolution, Biological samples, Image processing, Wavelets

Read Abstract +

Computer-Aided Diagnosis

Sequestration of imaging studies in MIDRC: stratified sampling to balance demographic characteristics of patients in a multi-institutional data commons

Natalie Baughan, Heather Whitney, Karen Drukker, Berkman Sahiner, Tingting Hu, Hyun J. Kim, Michael McNitt-Gray, Kyle Myers, Maryellen Giger

Journal of Medical Imaging, Vol. 10, Issue 06, 064501, (November 2023) https://doi.org/10.1117/1.JMI.10.6.064501

TOPICS: Algorithm development, Medical imaging, COVID 19, Evolutionary algorithms, Histograms, Databases, Artificial intelligence, Medical research, Education and training, Data modeling

Read Abstract +

U-Net breast lesion segmentations for breast dynamic contrast-enhanced magnetic resonance imaging

Lindsay Douglas, Roma Bhattacharjee, Jordan Fuhrman, Karen Drukker, Qiyuan Hu, Alexandra Edwards, Deepa Sheth, Maryellen Giger

Journal of Medical Imaging, Vol. 10, Issue 06, 064502, (November 2023) https://doi.org/10.1117/1.JMI.10.6.064502

TOPICS: Image segmentation, Breast, 3D image processing, 3D imaging standards, Magnetic resonance imaging, Education and training, Cross validation, 3D modeling, 3D image enhancement, Artificial intelligence

Read Abstract +

Magnetic resonance imaging preprocessing and radiomic features for classification of autosomal dominant polycystic kidney disease genotype

Linnea Kremer, Arlene Chapman, Samuel Armato III

Journal of Medical Imaging, Vol. 10, Issue 06, 064503, (December 2023) https://doi.org/10.1117/1.JMI.10.6.064503

TOPICS: Kidney, Magnetic resonance imaging, Radiomics, Feature extraction, Reproducibility, Diseases and disorders, Signal intensity, Image segmentation, Cooccurrence matrices, Image classification

Read Abstract +

Purpose

Our study aims to investigate the impact of preprocessing on magnetic resonance imaging (MRI) radiomic features extracted from the noncystic kidney parenchyma of patients with autosomal dominant polycystic kidney disease (ADPKD) in the task of classifying PKD1 versus PKD2 genotypes, which differ with regard to cyst burden and disease outcome.

Approach

The effect of preprocessing on radiomic features was investigated using a single T2-weighted fat saturated (T2W-FS) MRI scan from PKD1 and PKD2 subjects (29 kidneys in total) from the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease study. Radiomic feature reproducibility using the intraclass correlation coefficient (ICC) was computed across MRI normalizations (z-score, reference-tissue, and original image), gray-level discretization, and upsampling and downsampling pixel schemes. A second dataset for genotype classification from 136 subjects T2W-FS MRI images previously enrolled in the HALT Progression of Polycystic Kidney Disease study was matched for age, gender, and Mayo imaging classification class. Genotype classification was performed using a logistic regression classifier and radiomic features extracted from (1) the noncystic kidney parenchyma and (2) the entire kidney. The area under the receiver operating characteristic curve (AUC) was used to evaluate the classification performance across preprocessing methods.

Results

Radiomic features extracted from the noncystic kidney parenchyma were sensitive to preprocessing parameters, with varying reproducibility depending on the parameter. The percentage of features with good-to-excellent ICC scores ranged from 14% to 58%. AUC values ranged between 0.47 to 0.68 and 0.56 to 0.73 for the noncystic kidney parenchyma and entire kidney, respectively.

Conclusions

Reproducibility of radiomic features extracted from the noncystic kidney parenchyma was dependent on the preprocessing parameters used, and the effect on genotype classification was sensitive to preprocessing parameters. The results suggest that texture features may be indicative of genotype expression in ADPKD.

Assessment of a deep learning model for COVID-19 classification on chest radiographs: a comparison across image acquisition techniques and clinical factors

Mena Shenouda, Isabella Flerlage, Aditi Kaveti, Maryellen L. Giger, Samuel G. Armato III

Journal of Medical Imaging, Vol. 10, Issue 06, 064504, (December 2023) https://doi.org/10.1117/1.JMI.10.6.064504

TOPICS: COVID 19, Performance modeling, Data modeling, Lung, Chest imaging, Education and training, Deep learning, Image classification, Image fusion, Image acquisition

Read Abstract +

Purpose

The purpose is to assess the performance of a pre-trained deep learning model in the task of classifying between coronavirus disease (COVID)-positive and COVID-negative patients from chest radiographs (CXRs) while considering various image acquisition parameters, clinical factors, and patient demographics.

Methods

Standard and soft-tissue CXRs of 9860 patients comprised the “original dataset,” consisting of training and test sets and were used to train a DenseNet-121 architecture model to classify COVID-19 using three classification algorithms: standard, soft tissue, and a combination of both types of images via feature fusion. A larger more-current test set of 5893 patients (the “current test set”) was used to assess the performance of the pretrained model. The current test set contained a larger span of dates, incorporated different variants of the virus and included different immunization statuses. Model performance between the original and current test sets was evaluated using area under the receiver operating characteristic curve (ROC AUC) [95% CI].

Results

The model achieved AUC values of 0.67 [0.65, 0.70] for cropped standard images, 0.65 [0.63, 0.67] for cropped soft-tissue images, and 0.67 [0.65, 0.69] for both types of cropped images. These were all significantly lower than the performance of the model on the original test set. Investigations regarding matching the acquisition dates between the test sets (i.e., controlling for virus variants), immunization status, disease severity, and age and sex distributions did not fully explain the discrepancy in performance.

Conclusions

Several relevant factors were considered to determine whether differences existed in the test sets, including time period of image acquisition, vaccination status, and disease severity. The lower performance on the current test set may have occurred due to model overfitting and a lack of generalizability.

Image Perception, Observer Performance, and Technology Assessment

Development and implementation of optimized endogenous contrast sequences for delineation in adaptive radiotherapy on a 1.5T MR-linear-accelerator: a prospective R-IDEAL stage 0-2a quantitative/qualitative evaluation of in vivo site-specific quality-assurance using a 3D T2 fat-suppressed platform for head and neck cancer

Joint Head and Neck Radiotherapy-MRI Development Cooperative, Travis Salzillo, M. Alex Dresner, Ashley Way, Kareem Wahid, Brigid McDonald, Sam Mulder, Mohamed Naser, Renjie He, Yao Ding, Alison Yoder, Sara Ahmed, Kelsey Corrigan, Gohar Manzar, Lauren Andring, Chelsea Pinnix, R. Jason Stafford, Abdallah S. Mohamed, John Christodouleas, Jihong Wang, Clifton David Fuller

Journal of Medical Imaging, Vol. 10, Issue 06, 065501, (November 2023) https://doi.org/10.1117/1.JMI.10.6.065501

TOPICS: Image segmentation, Image quality, Signal to noise ratio, Radiotherapy, Muscles, Lymph nodes, Neck, Magnetic resonance imaging, Head, Image analysis

Read Abstract +

Purpose

To improve segmentation accuracy in head and neck cancer (HNC) radiotherapy treatment planning for the 1.5T hybrid magnetic resonance imaging/linear accelerator (MR-Linac), three-dimensional (3D), T2-weighted, fat-suppressed magnetic resonance imaging sequences were developed and optimized.

Approach

After initial testing, spectral attenuated inversion recovery (SPAIR) was chosen as the fat suppression technique. Five candidate SPAIR sequences and a nonsuppressed, T2-weighted sequence were acquired for five HNC patients using a 1.5T MR-Linac. MR physicists identified persistent artifacts in two of the SPAIR sequences, so the remaining three SPAIR sequences were further analyzed. The gross primary tumor volume, metastatic lymph nodes, parotid glands, and pterygoid muscles were delineated using five segmentors. A robust image quality analysis platform was developed to objectively score the SPAIR sequences on the basis of qualitative and quantitative metrics.

Results

Sequences were analyzed for the signal-to-noise ratio and the contrast-to-noise ratio and compared with fat and muscle, conspicuity, pairwise distance metrics, and segmentor assessments. In this analysis, the nonsuppressed sequence was inferior to each of the SPAIR sequences for the primary tumor, lymph nodes, and parotid glands, but it was superior for the pterygoid muscles. The SPAIR sequence that received the highest combined score among the analysis categories was recommended to Unity MR-Linac users for HNC radiotherapy treatment planning.

Conclusions

Our study led to two developments: an optimized, 3D, T2-weighted, fat-suppressed sequence that can be disseminated to Unity MR-Linac users and a robust image quality analysis pathway that can be used to objectively score SPAIR sequences and can be customized and generalized to any image quality optimization protocol. Improved segmentation accuracy with the proposed SPAIR sequence will potentially lead to improved treatment outcomes and reduced toxicity for patients by maximizing the target coverage and minimizing the radiation exposure of organs at risk.

Local texture statistics augment the power spectrum in modeling radiographic judgments of breast density

Craig Abbey, Margarita Zuley, Jonathan Victor

Journal of Medical Imaging, Vol. 10, Issue 06, 065502, (November 2023) https://doi.org/10.1117/1.JMI.10.6.065502

TOPICS: Statistical modeling, Breast density, Mammography, Medical statistics, Image segmentation, Atomic force microscopy, Breast, Visualization, Statistical analysis, Performance modeling

Read Abstract +

Generalizations of the Jaccard index and Sørensen index for assessing agreement across multiple readers in object detection and instance segmentation in biomedical imaging

Madeleine Durkee, Kyle Lleras, Karen Drukker, Junting Ai, Thao Cao, Gabriel Casella, Deepjyoti Ghosh, Marcus Clark, Maryellen Giger

Journal of Medical Imaging, Vol. 10, Issue 06, 065503, (December 2023) https://doi.org/10.1117/1.JMI.10.6.065503

TOPICS: Image segmentation, Object detection, Matrices, Education and training, Detection and tracking algorithms, Deep convolutional neural networks, Biomedical optics, Machine learning, Image processing algorithms and systems, Biopsy

Read Abstract +

Biomedical Applications in Molecular, Structural, and Functional Imaging

Automated aortic segmentation and quantification of hemodynamic parameters from 4D flow MRI using deep learning techniques

Jenita Manokaran, Julio Garcia Flores, Eranga Ukwatta

Journal of Medical Imaging, Vol. 10, Issue 06, 066001, (November 2023) https://doi.org/10.1117/1.JMI.10.6.066001

TOPICS: Image segmentation, Aorta, Magnetic resonance imaging, 3D modeling, Hemodynamics, Electroluminescence, Blood circulation, Deep learning, Education and training, Data modeling

Read Abstract +

Purpose

To develop an automated method for aortic segmentation using deep learning techniques and further analyze the hemodynamic parameters in patients with bicuspid aortic valve (BAV). Since four-dimensional (4D) flow magnetic resonance imaging (MRI) imaging helps in analyzing and quantifying the blood flow changes that occur in aortic valve-related problems, such as BAV, 4D flow MRI images are considered.

Approach

Our dataset consisted of 91 patients who had referral indications of BAV and 30 healthy volunteers who had no known cardiovascular disease. A U-Net++ with pretrained ResNet-34 encoders was trained for aortic segmentation using manual segmentation by an expert as the ground truth. In the first stage, the model was evaluated on 21 test cohorts using overlay and distance-based metrics, such as Dice score, Hausdorff distance, and absolute volume difference. In the second stage, the hemodynamic parameters, such as wall shear stress (WSS), viscous energy loss, and vorticity, were calculated to quantify the blood flow irregularities that occur in BAV patients. The segmentation and the flow parameters generated by the algorithm were compared with those generated using the manual segmentations. Paired t-test with alpha value of 0.05 was used for statistical significance testing.

Results

As for overlap and distance-based metrics, the developed algorithm reported a Dice score coefficient of 0.90 ± 0.03, absolute volume difference of 1683 ± 1139 mm³, and Hausdorff distance of 3.2 ± 1.18 mm on test cohorts. The hemodynamic parameters calculated between automated and manual methods resulted in a mean difference of 6.62% for WSS with p-value of 0.94, 17.35% for mean viscous energy loss with p-value of 0.78, and 7.59% for vorticity with p-value of 0.97.

Conclusions

A fast and accurate segmentation tool was developed for aortic segmentation using a dataset taken at clinical and blood flow parameters that were calculated based on the segmented aorta. These results will assist the clinicians to analyze the blood flow patterns and commence distinguished treatment in BAV patients.

Characterization of anisotropy of elastic modulus with three-dimensional freehand scan shear wave elasticity imaging

Tong Wu, En-Xiang Shen, Zhi-Bin Jin, Yong Jiang, Ying Chen, Chao Tao, Jie Yuan, Yun Ge, Xiao-Jun Liu

Journal of Medical Imaging, Vol. 10, Issue 06, 066002, (November 2023) https://doi.org/10.1117/1.JMI.10.6.066002

TOPICS: Tissues, Cameras, Elastic modulus, Calibration, Anisotropy, Elasticity, Ultrasonics, Data acquisition, Imaging systems, 3D image processing

Read Abstract +

Optimizing diffuse optical imaging for breast tissues with a dual-encoder neural network to preserve small structural information and fine features

Nazish Murad, Min-Chun Pan, Ya-Fen Hsu

Journal of Medical Imaging, Vol. 10, Issue 06, 066003, (December 2023) https://doi.org/10.1117/1.JMI.10.6.066003

TOPICS: Image restoration, Optical properties, Education and training, Deep learning, Breast, Diffuse optical imaging, Tissues, Medical image reconstruction, Data modeling, Absorption

Read Abstract +

Repeatability of computed tomography liver radiomic features in a nonhuman primate model of diet-induced steatosis

Hui Wang, Jeffrey Solomon, Syed M. Reza, Hee-Jeong Yang, Winston T. Chu, Ian Crozier, Philip Sayre, Byeong Lee, Venkatesh Mani, Thomas Friedrich, David O’Connor, Gabriella Worwa, Jens Kuhn, Claudia Calcagno, Marcelo Castro

Journal of Medical Imaging, Vol. 10, Issue 06, 066004, (December 2023) https://doi.org/10.1117/1.JMI.10.6.066004

TOPICS: Radiomics, Liver, Computed tomography, Cooccurrence matrices, Attenuation, Feature extraction, Diseases and disorders, Animals, Medical image reconstruction, Spleen

Read Abstract +

PACS and Imaging Informatics

Anonymization and validation of three-dimensional volumetric renderings of computed tomography data using commercially available T1-weighted magnetic resonance imaging-based algorithms

Rahil Patel, Destie Provenzano, Murray Loew

Journal of Medical Imaging, Vol. 10, Issue 06, 066501, (November 2023) https://doi.org/10.1117/1.JMI.10.6.066501

TOPICS: Computed tomography, Detection and tracking algorithms, Facial recognition systems, Magnetic resonance imaging, 3D image processing, Head, Brain, Medical imaging, Databases, Control systems

Read Abstract +

Digital Pathology

Comparison of consecutive and restained sections for image registration in histopathology

Johannes Lotz, Nick Weiss, Jeroen van der Laak, Stefan Heldmann

Journal of Medical Imaging, Vol. 10, Issue 06, 067501, (November 2023) https://doi.org/10.1117/1.JMI.10.6.067501

TOPICS: Image registration, Deformation, Image resolution, Tissues, Distance measurement, Computation time, Histopathology, Pathology, Image restoration, Visualization

Read Abstract +

Standardized CycleGAN training for unsupervised stain adaptation in invasive carcinoma classification for breast histopathology

Nicolas Nerrienet, Rémy Peyret, Marie Sockeel, Stéphane Sockeel

Journal of Medical Imaging, Vol. 10, Issue 06, 067502, (December 2023) https://doi.org/10.1117/1.JMI.10.6.067502

TOPICS: Education and training, Tumor growth modeling, Data modeling, Histopathology, Breast, Performance modeling, Tissues, Statistical modeling, Scanners, Pathology

Read Abstract +

Purpose

Generalization is one of the main challenges of computational pathology. Slide preparation heterogeneity and the diversity of scanners lead to poor model performance when used on data from medical centers not seen during training. In order to achieve stain invariance in breast invasive carcinoma patch classification, we implement a stain translation strategy using cycleGANs for unsupervised image-to-image translation. Those models often suffer from a lack of proper metrics to monitor and stop the training at a particular point. We also introduce a method to solve this issue.

Approach

We compare three CycleGAN-based approaches to a baseline classification model obtained without any stain invariance strategy. Two of the proposed approaches use CycleGAN’s translations at inference or training to build stain-specific classification models. The last method uses them for stain data augmentation during training. This constrains the classification model to learn stain-invariant features. Regarding CycleGANs’ training monitoring, we leverage Fréchet inception distance between generated and real samples and use it as a stopping criterion. We compare CycleGANs’ models stopped using this criterion and models stopped at a fixed number of epochs.

Results

Baseline metrics are set by training and testing the baseline classification model on a reference stain. We assessed performances using three medical centers with H&E and H&E&S staining. Every approach tested in this study improves baseline metrics without needing labels on target stains. The stain augmentation-based approach produced the best results on every stain. Each method’s pros and cons are studied and discussed. Moreover, FID stopping criterion proves superiority to methods using a predefined number of training epoch and has the benefit of not requiring any visual inspection of CycleGAN results.

Conclusion

We introduce a method to attain stain invariance for breast invasive carcinoma classification by leveraging CycleGAN’s abilities to produce realistic translations between various stains. Moreover, we propose a systematical method for scheduling CycleGANs’ trainings by using FID as a stopping criterion and prove its superiority to other methods. Finally, we give an insight on the minimal amount of data required for CycleGAN training in a digital histopathology setting.