Volume 10 Issue 4 | Journal of Medical Imaging

Journal of Medical Imaging

VOL. 10 · NO. 4 | July 2023

CONTENTS

IN THIS ISSUE

Physics of Medical Imaging (3)

Image Processing (8)

Computer-Aided Diagnosis (4)

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

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

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

Errata (1)

< Previous Issue | Next Issue >

Receive Email Alerts

VIEW ALL ABSTRACTS +

Physics of Medical Imaging

Ex vivo coronary calcium volume quantification using a high-spatial-resolution clinical photon-counting-detector computed tomography

Jeffrey F. Marsh Jr., Patrick D. VanMeter, Kishore Rajendran, Shuai Leng, Cynthia H. McCollough

Journal of Medical Imaging, Vol. 10, Issue 04, 043501, (July 2023) https://doi.org/10.1117/1.JMI.10.4.043501

TOPICS: Computed tomography, Image segmentation, Calcium, Scanners, Error analysis, Denoising, Spatial resolution, Medical image reconstruction, Collimation, Arteries

Read Abstract +

Coronary artery calcium mass measurement based on integrated intensity and volume fraction techniques

Dale Black, Xingshuo Xiao, Sabee Molloi

Journal of Medical Imaging, Vol. 10, Issue 04, 043502, (July 2023) https://doi.org/10.1117/1.JMI.10.4.043502

TOPICS: Calcium, Magnesium, Arteries, Reproducibility, Voxels, Calibration, Computed tomography, Linear regression, Optical simulations, Image segmentation

Read Abstract +

Purpose

Agatston scoring does not detect all the calcium present in computed tomography scans of the heart. A technique that removes the need for thresholding and quantifies calcium mass more accurately and reproducibly is needed.

Approach

Integrated intensity and volume fraction techniques were evaluated for accurate quantification of calcium mass. Integrated intensity calcium mass, volume fraction calcium mass, Agatston scoring, and spatially weighted calcium scoring were compared with known calcium mass in simulated and physical phantoms. The simulation was created to match a 320-slice CT scanner. Fat rings were added to the simulated phantoms, which resulted in small (30 × 20 cm²), medium (35 × 25 cm²), and large (40 × 30 cm²) phantoms. Three calcification inserts of different diameters and hydroxyapatite densities were placed within the phantoms. All the calcium mass measurements were repeated across different beam energies, patient sizes, insert sizes, and densities. Physical phantom images from a previously reported study were then used to evaluate the accuracy and reproducibility of the techniques.

Results

Both integrated intensity calcium mass and volume fraction calcium mass yielded lower root mean squared error (RMSE) and deviation (RMSD) values than Agatston scoring in all the measurements in the simulated phantoms. Specifically, integrated calcium mass (RMSE: 0.49 mg, RMSD: 0.49 mg) and volume fraction calcium mass (RMSE: 0.58 mg, RMSD: 0.57 mg) were more accurate for the low-density stationary calcium measurements than Agatston scoring (RMSE: 3.70 mg, RMSD: 2.30 mg). Similarly, integrated calcium mass (15.74%) and volume fraction calcium mass (20.37%) had fewer false-negative (CAC = 0) measurements than Agatston scoring (75.00%) and spatially weighted calcium scoring (26.85%), on the low-density stationary calcium measurements.

Conclusion

The integrated calcium mass and volume fraction calcium mass techniques can potentially improve risk stratification for patients undergoing calcium scoring and further improve risk assessment compared with Agatston scoring.

Analysis of the precision of modulation transfer function measurements with a circular edge: influence of object circularity

Sho Maruyama

Journal of Medical Imaging, Vol. 10, Issue 04, 043503, (August 2023) https://doi.org/10.1117/1.JMI.10.4.043503

TOPICS: Modulation transfer functions, Image processing, Distortion, Computed tomography, Spatial frequencies, Image quality, X-ray computed tomography, Signal processing, Shape analysis, Reconstruction algorithms

Read Abstract +

Image Processing

Single slice thigh CT muscle group segmentation with domain adaptation and self-training

Qi Yang, Xin Yu, Ho Hin Lee, Leon Cai, Kaiwen Xu, Shunxing Bao, Yuankai Huo, Ann Zenobia Moore, Sokratis Makrogiannis, Luigi Ferrucci, Bennett Landman

Journal of Medical Imaging, Vol. 10, Issue 04, 044001, (July 2023) https://doi.org/10.1117/1.JMI.10.4.044001

TOPICS: Muscles, Image segmentation, Computed tomography, Magnetic resonance imaging, Education and training, Anatomy, Bone, Gallium nitride, Data modeling, Adversarial training

Read Abstract +

Quantifying emphysema in lung screening computed tomography with robust automated lobe segmentation

Thomas Z. Li, Ho Hin Lee, Kaiwen Xu, Riqiang Gao, Benoit M. Dawant, Fabien Maldonado, Kim L. Sandler, Bennett A. Landman

Journal of Medical Imaging, Vol. 10, Issue 04, 044002, (July 2023) https://doi.org/10.1117/1.JMI.10.4.044002

TOPICS: Emphysema, Lung, Lung cancer, Computed tomography, Chronic obstructive pulmonary disease, Algorithm development, Image segmentation, Education and training, 3D modeling, Data modeling

Read Abstract +

Validation of active shape model techniques for intracochlear anatomy segmentation in computed tomography images

Rueben A. Banalagay, Robert F. Labadie, Jack H. Noble

Journal of Medical Imaging, Vol. 10, Issue 04, 044003, (July 2023) https://doi.org/10.1117/1.JMI.10.4.044003

TOPICS: Image segmentation, Computed tomography, Education and training, Cochlea, Anatomy, Error analysis, Visualization, Performance modeling, Image registration, Electrodes

Read Abstract +

Automatic classification of symmetry of hemithoraces in canine and feline radiographs

Peyman Tahghighi, Nicole Norena, Eran Ukwatta, Ryan B. Appleby, Amin Komeili

Journal of Medical Imaging, Vol. 10, Issue 04, 044004, (July 2023) https://doi.org/10.1117/1.JMI.10.4.044004

TOPICS: Radiography, Image segmentation, Spine, Education and training, Lung, Feature extraction, Contour modeling, Performance modeling, Machine learning, Histograms

Read Abstract +

Two-stage automated diagnosis framework for urogenital schistosomiasis in microscopy images from low-resource settings

Prosper Oyibo, Brice Meulah, Michel Bengtson, Lisette van Lieshout, Wellington Oyibo, Jan-Carel Diehl, Gleb Vdovine, Temitope Agbana

Journal of Medical Imaging, Vol. 10, Issue 04, 044005, (August 2023) https://doi.org/10.1117/1.JMI.10.4.044005

TOPICS: Image segmentation, Diagnostics, Semantics, Education and training, Data modeling, Evolutionary algorithms, Microscopy, Image processing algorithms and systems, Deep learning, Artificial intelligence

Read Abstract +

Purpose

Automated diagnosis of urogenital schistosomiasis using digital microscopy images of urine slides is an essential step toward the elimination of schistosomiasis as a disease of public health concern in Sub-Saharan African countries. We create a robust image dataset of urine samples obtained from field settings and develop a two-stage diagnosis framework for urogenital schistosomiasis.

Approach

Urine samples obtained from field settings were captured using the Schistoscope device, and S. haematobium eggs present in the images were manually annotated by experts to create the SH dataset. Next, we develop a two-stage diagnosis framework, which consists of semantic segmentation of S. haematobium eggs using the DeepLabv3-MobileNetV3 deep convolutional neural network and a refined segmentation step using ellipse fitting approach to approximate the eggs with an automatically determined number of ellipses. We defined two linear inequality constraints as a function of the overlap coefficient and area of a fitted ellipses. False positive diagnosis resulting from over-segmentation was further minimized using these constraints. We evaluated the performance of our framework on 7605 images from 65 independent urine samples collected from field settings in Nigeria, by deploying our algorithm on an Edge AI system consisting of Raspberry Pi + Coral USB accelerator.

Result

The SH dataset contains 12,051 images from 103 independent urine samples and the developed urogenital schistosomiasis diagnosis framework achieved clinical sensitivity, specificity, and precision of 93.8%, 93.9%, and 93.8%, respectively, using results from an experienced microscopist as reference.

Conclusion

Our detection framework is a promising tool for the diagnosis of urogenital schistosomiasis as our results meet the World Health Organization target product profile requirements for monitoring and evaluation of schistosomiasis control programs.

Performance of alternative manual and automated deep learning segmentation techniques for the prediction of benign and malignant lung nodules

Heather Selby, Pritam Mukherjee, Christopher Parham, Sachin Malik, Olivier Gevaert, Sandy Napel, Rajesh Shah

Journal of Medical Imaging, Vol. 10, Issue 04, 044006, (August 2023) https://doi.org/10.1117/1.JMI.10.4.044006

TOPICS: Frequency modulation, Fermium, Lung, Radiomics, Image segmentation, Computed tomography, Tumor growth modeling, Data modeling, Deep learning, Performance modeling

Read Abstract +

Purpose

We aim to evaluate the performance of radiomic biopsy (RB), best-fit bounding box (BB), and a deep-learning-based segmentation method called no-new-U-Net (nnU-Net), compared to the standard full manual (FM) segmentation method for predicting benign and malignant lung nodules using a computed tomography (CT) radiomic machine learning model.

Materials and Methods

A total of 188 CT scans of lung nodules from 2 institutions were used for our study. One radiologist identified and delineated all 188 lung nodules, whereas a second radiologist segmented a subset (n = 20) of these nodules. Both radiologists employed FM and RB segmentation methods. BB segmentations were generated computationally from the FM segmentations. The nnU-Net, a deep-learning-based segmentation method, performed automatic nodule detection and segmentation. The time radiologists took to perform segmentations was recorded. Radiomic features were extracted from each segmentation method, and models to predict benign and malignant lung nodules were developed. The Kruskal–Wallis and DeLong tests were used to compare segmentation times and areas under the curve (AUC), respectively.

Results

For the delineation of the FM, RB, and BB segmentations, the two radiologists required a median time (IQR) of 113 (54 to 251.5), 21 (9.25 to 38), and 16 (12 to 64.25) s, respectively (p = 0.04). In dataset 1, the mean AUC (95% CI) of the FM, RB, BB, and nnU-Net model were 0.964 (0.96 to 0.968), 0.985 (0.983 to 0.987), 0.961 (0.956 to 0.965), and 0.878 (0.869 to 0.888). In dataset 2, the mean AUC (95% CI) of the FM, RB, BB, and nnU-Net model were 0.717 (0.705 to 0.729), 0.919 (0.913 to 0.924), 0.699 (0.687 to 0.711), and 0.644 (0.632 to 0.657).

Conclusion

Radiomic biopsy-based models outperformed FM and BB models in prediction of benign and malignant lung nodules in two independent datasets while deep-learning segmentation-based models performed similarly to FM and BB. RB could be a more efficient segmentation method, but further validation is needed.

Medical volume segmentation by overfitting sparsely annotated data

Tristan Payer, Faraz Nizamani, Meinrad Beer, Michael Götz, Timo Ropinski

Journal of Medical Imaging, Vol. 10, Issue 04, 044007, (August 2023) https://doi.org/10.1117/1.JMI.10.4.044007

TOPICS: Education and training, Image segmentation, Overfitting, Interpolation, 3D modeling, Volume rendering, Medical imaging, Data modeling, Active learning, 3D applications

Read Abstract +

Self-trained deep convolutional neural network for noise reduction in CT

Zhongxing Zhou, Akitoshi Inoue, Cynthia McCollough, Lifeng Yu

Journal of Medical Imaging, Vol. 10, Issue 04, 044008, (August 2023) https://doi.org/10.1117/1.JMI.10.4.044008

TOPICS: Education and training, Data modeling, Denoising, Computed tomography, Infrared imaging, Image restoration, Performance modeling, Image quality, Deep convolutional neural networks, Quantum noise

Read Abstract +

Purpose

Supervised deep convolutional neural network (CNN)-based methods have been actively used in clinical CT to reduce image noise. The networks of these methods are typically trained using paired high- and low-quality data from a massive number of patients and/or phantom images. This training process is tedious, and the network trained under a given condition may not be generalizable to patient images acquired and reconstructed under different conditions. We propose a self-trained deep CNN (ST_CNN) method for noise reduction in CT that does not rely on pre-existing training datasets.

Approach

The ST_CNN training was accomplished using extensive data augmentation in the projection domain, and the inference was applied to the data itself. Specifically, multiple independent noise insertions were applied to the original patient projection data to generate multiple realizations of low-quality projection data. Then, rotation augmentation was adopted for both the original and low-quality projection data by applying the rotation angle directly on the projection data so that images were rotated at arbitrary angles without introducing additional bias. A large number of paired low- and high-quality images from the same patient were reconstructed and paired for training the ST_CNN model.

Results

No significant difference was found between the ST_CNN and conventional CNN models in terms of the peak signal-to-noise ratio and structural similarity index measure. The ST_CNN model outperformed the conventional CNN model in terms of noise texture and homogeneity in liver parenchyma as well as better subjective visualization of liver lesions. The ST_CNN may sacrifice the sharpness of vessels slightly compared to the conventional CNN model but without affecting the visibility of peripheral vessels or diagnosis of vascular pathology.

Conclusions

The proposed ST_CNN method trained from the data itself may achieve similar image quality in comparison with conventional deep CNN denoising methods pre-trained on external datasets.

Computer-Aided Diagnosis

Radiomic and deep learning characterization of breast parenchyma on full field digital mammograms and specimen radiographs: a pilot study of a potential cancer field effect

Natalie Baughan, Hui Li, Li Lan, Matthew Embury, Isaiah Yim, Gary J. Whitman, Randa El-Zein, Isabelle Bedrosian, Maryellen L. Giger

Journal of Medical Imaging, Vol. 10, Issue 04, 044501, (July 2023) https://doi.org/10.1117/1.JMI.10.4.044501

TOPICS: Mammography, Tumors, Radiography, Radiomics, Deep learning, Breast, Cancer, Breast cancer, Cooccurrence matrices, Histograms

Read Abstract +

Stroke-GFCN: ischemic stroke lesion prediction with a fully convolutional graph network

Ariel Iporre-Rivas, Dorothee Saur, Karl Rohr, Gerik Scheuermann, Christina Gillmann

Journal of Medical Imaging, Vol. 10, Issue 04, 044502, (July 2023) https://doi.org/10.1117/1.JMI.10.4.044502

TOPICS: Education and training, Image segmentation, Ischemic stroke, Data modeling, Deep learning, Brain, Batch normalization, Convolution, Surgery, Performance modeling

Read Abstract +

Purpose

The interpretation of image data plays a critical role during acute brain stroke diagnosis, and promptly defining the requirement of a surgical intervention will drastically impact the patient’s outcome. However, determining stroke lesions purely from images can be a daunting task. Many studies proposed automatic segmentation methods for brain stroke lesions from medical images in different modalities, though heretofore results do not satisfy the requirements to be clinically reliable. We investigate the segmentation of brain stroke lesions using a geometric deep learning model that takes advantage of the intrinsic interconnected diffusion features in a set of multi-modal inputs consisting of computer tomography (CT) perfusion parameters.

Approach

We propose a geometric deep learning model for the segmentation of ischemic stroke brain lesions that employs spline convolutions and unpooling/pooling operators on graphs to excerpt graph-structured features in a fully convolutional network architecture. In addition, we seek to understand the underlying principles governing the different components of our model. Accordingly, we structure the experiments in two parts: an evaluation of different architecture hyperparameters and a comparison with state-of-the-art methods.

Results

The ablation study shows that deeper layers obtain a higher Dice coefficient score (DCS) of up to 0.3654. Comparing different pooling and unpooling methods shows that the best performing unpooling method is the proportional approach, yet it often smooths the segmentation border. Unpooling achieves segmentation results more adapted to the lesion boundary corroborated with systematic lower values of Hausdorff distance. The model performs at the level of state-of-the-art models without optimized training methods, such as augmentation or patches, with a DCS of 0.4553 ± 0.0031.

Conclusions

We proposed and evaluated an end-to-end trainable fully convolutional graph network architecture using spline convolutional layers for the ischemic stroke lesion prediction. We propose a model that employs graph-based operations to predict acute stroke brain lesions from CT perfusion parameters. Our results prove the feasibility of using geometric deep learning to solve segmentation problems, and our model shows a better performance than other models evaluated. The proposed model achieves improved metric values for the DCS metric, ranging from 8.61% to 69.05%, compared with other models trained under the same conditions. Next, we compare different pooling and unpooling operations in relation to their segmentation results, and we show that the model can produce segmentation outputs that adapt to irregular segmentation boundaries when using simple heuristic unpooling operations.

Effect of image resolution on automated classification of chest X-rays

Md Inzamam Ul Haque, Abhishek K. Dubey, Ioana Danciu, Amy C. Justice, Olga S. Ovchinnikova, Jacob D. Hinkle

Journal of Medical Imaging, Vol. 10, Issue 04, 044503, (August 2023) https://doi.org/10.1117/1.JMI.10.4.044503

TOPICS: Image resolution, Education and training, Chest imaging, Image classification, Performance modeling, Data modeling, Lung, Medical imaging, Visualization, Feature extraction

Read Abstract +

Predicting intensive care need for COVID-19 patients using deep learning on chest radiography

Hui Li, Karen Drukker, Qiyuan Hu, Heather Whitney, Jordan Fuhrman, Maryellen Giger

Journal of Medical Imaging, Vol. 10, Issue 04, 044504, (August 2023) https://doi.org/10.1117/1.JMI.10.4.044504

TOPICS: COVID 19, Chest imaging, Data modeling, Deep learning, Education and training, Performance modeling, Radiography, Medical imaging, Machine learning, Diseases and disorders

Read Abstract +

Purpose

Image-based prediction of coronavirus disease 2019 (COVID-19) severity and resource needs can be an important means to address the COVID-19 pandemic. In this study, we propose an artificial intelligence/machine learning (AI/ML) COVID-19 prognosis method to predict patients’ needs for intensive care by analyzing chest X-ray radiography (CXR) images using deep learning.

Approach

The dataset consisted of 8357 CXR exams from 5046 COVID-19–positive patients as confirmed by reverse transcription polymerase chain reaction (RT-PCR) tests for the SARS-CoV-2 virus with a training/validation/test split of 64%/16%/20% on a by patient level. Our model involved a DenseNet121 network with a sequential transfer learning technique employed to train on a sequence of gradually more specific and complex tasks: (1) fine-tuning a model pretrained on ImageNet using a previously established CXR dataset with a broad spectrum of pathologies; (2) refining on another established dataset to detect pneumonia; and (3) fine-tuning using our in-house training/validation datasets to predict patients’ needs for intensive care within 24, 48, 72, and 96 h following the CXR exams. The classification performances were evaluated on our independent test set (CXR exams of 1048 patients) using the area under the receiver operating characteristic curve (AUC) as the figure of merit in the task of distinguishing between those COVID-19–positive patients who required intensive care following the imaging exam and those who did not.

Results

Our proposed AI/ML model achieved an AUC (95% confidence interval) of 0.78 (0.74, 0.81) when predicting the need for intensive care 24 h in advance, and at least 0.76 (0.73, 0.80) for 48 h or more in advance using predictions based on the AI prognostic marker derived from CXR images.

Conclusions

This AI/ML prediction model for patients’ needs for intensive care has the potential to support both clinical decision-making and resource management.

Image-Guided Procedures, Robotic Interventions, and Modeling

Disparity refinement framework for learning-based stereo matching methods in cross-domain setting for laparoscopic images

Zixin Yang, Richard Simon, Cristian Linte

Journal of Medical Imaging, Vol. 10, Issue 04, 045001, (July 2023) https://doi.org/10.1117/1.JMI.10.4.045001

TOPICS: Endoscopy, Education and training, Laparoscopy, Light sources and illumination, Error analysis, Equipment, Surgery, Data modeling, Natural surfaces, Interpolation

Read Abstract +

Inpainting surgical occlusion from laparoscopic video sequences for robot-assisted interventions

S. M. Kamrul Hasan, Richard A. Simon, Cristian A. Linte

Journal of Medical Imaging, Vol. 10, Issue 04, 045002, (August 2023) https://doi.org/10.1117/1.JMI.10.4.045002

TOPICS: Image segmentation, Equipment, Video, Laparoscopy, Interpolation, Visualization, Surgery, Education and training, Convolution, Endoscopy

Read Abstract +

Purpose

Medical technology for minimally invasive surgery has undergone a paradigm shift with the introduction of robot-assisted surgery. However, it is very difficult to track the position of the surgical tools in a surgical scene, so it is crucial to accurately detect and identify surgical tools. This task can be aided by deep learning-based semantic segmentation of surgical video frames. Furthermore, due to the limited working and viewing areas of these surgical instruments, there is a higher chance of complications from tissue injuries (e.g., tissue scars and tears).

Approach

With the aid of digital inpainting algorithms, we present an application that uses image segmentation to remove surgical instruments from laparoscopic/endoscopic video. We employ a modified U-Net architecture (U-NetPlus) to segment the surgical instruments. It consists of a redesigned decoder and a pre-trained VGG11 or VGG16 encoder. The decoder was modified by substituting an up-sampling operation based on nearest-neighbor interpolation for the transposed convolution operation. Furthermore, these interpolation weights do not need to be learned to perform upsampling, which eliminates the artifacts generated by the transposed convolution. In addition, we use a very fast and adaptable data augmentation technique to further enhance performance. The instrument segmentation mask is filled in (i.e., inpainted) by the tool removal algorithms using the previously acquired tool segmentation masks and either previous instrument-containing frames or instrument-free reference frames.

Results

We have shown the effectiveness of the proposed surgical tool segmentation/removal algorithms on a robotic instrument dataset from the MICCAI 2015 and 2017 EndoVis Challenge. We report a 90.20% DICE for binary segmentation, a 76.26% DICE for instrument part segmentation, and a 46.07% DICE for instrument type (i.e., all instruments) segmentation on the MICCAI 2017 challenge dataset using our U-NetPlus architecture, outperforming the results of earlier techniques used and tested on these data. In addition, we demonstrated the successful execution of the tool removal algorithm from surgical tool-free videos that contained moving surgical tools that were generated artificially.

Conclusions

Our application successfully separates and eliminates the surgical tool to reveal a view of the background tissue that was otherwise hidden by the tool, producing results that are visually similar to the actual data.

Image Perception, Observer Performance, and Technology Assessment

Serial dependence in perception across naturalistic generative adversarial network-generated mammogram

Zhihang Ren, Teresa Canas-Bajo, Cristina Ghirardo, Mauro Manassi, Stella X. Yu, David Whitney

Journal of Medical Imaging, Vol. 10, Issue 04, 045501, (July 2023) https://doi.org/10.1117/1.JMI.10.4.045501

TOPICS: Mammography, Gallium nitride, Radiography, Medical imaging, Error analysis, Interpolation, Education and training, Digital mammography, Visualization, Computer vision technology

Read Abstract +

Clinical history and incidental abnormality detection in endodontic cone beam computed tomography

Kehn E. Yapp, Ernest Ekpo

Journal of Medical Imaging, Vol. 10, Issue 04, 045502, (July 2023) https://doi.org/10.1117/1.JMI.10.4.045502

TOPICS: Cone beam computed tomography, Diagnostics, Diseases and disorders, Target detection, Design and modelling, Teeth, Dental caries, Eye tracking, Computed tomography, Target recognition

Read Abstract +

Biomedical Applications in Molecular, Structural, and Functional Imaging

Synthetic white balancing for intra-operative hyperspectral imaging

Anisha Bahl, Conor C. Horgan, Mirek Janatka, Oscar J. MacCormac, Philip Noonan, Yijing Xie, Jianrong Qiu, Nicola Cavalcanti, Philipp Fürnstahl, Michael Ebner, Mads S. Bergholt, Jonathan Shapey, Tom Vercauteren

Journal of Medical Imaging, Vol. 10, Issue 04, 046001, (July 2023) https://doi.org/10.1117/1.JMI.10.4.046001

TOPICS: Hyperspectral imaging, Vignetting, Video, Light sources, Light sources and illumination, Cameras, Reconstruction algorithms, Light emitting diodes, Spectroscopy, RGB color model

Read Abstract +

Purpose

Hyperspectral imaging shows promise for surgical applications to non-invasively provide spatially resolved, spectral information. For calibration purposes, a white reference image of a highly reflective Lambertian surface should be obtained under the same imaging conditions. Standard white references are not sterilizable and so are unsuitable for surgical environments. We demonstrate the necessity for in situ white references and address this by proposing a novel, sterile, synthetic reference construction algorithm.

Approach

The use of references obtained at different distances and lighting conditions to the subject were examined. Spectral and color reconstructions were compared with standard measurements qualitatively and quantitatively, using ΔE and normalized RMSE, respectively. The algorithm forms a composite image from a video of a standard sterile ruler, whose imperfect reflectivity is compensated for. The reference is modeled as the product of independent spatial and spectral components, and a scalar factor accounting for gain, exposure, and light intensity. Evaluation of synthetic references against ideal but non-sterile references is performed using the same metrics alongside pixel-by-pixel errors. Finally, intraoperative integration is assessed though cadaveric experiments.

Results

Improper white balancing leads to increases in all quantitative and qualitative errors. Synthetic references achieve median pixel-by-pixel errors lower than 6.5% and produce similar reconstructions and errors to an ideal reference. The algorithm integrated well into surgical workflow, achieving median pixel-by-pixel errors of 4.77% while maintaining good spectral and color reconstruction.

Conclusions

We demonstrate the importance of in situ white referencing and present a novel synthetic referencing algorithm. This algorithm is suitable for surgery while maintaining the quality of classical data reconstruction.

Errata

Erratum: Toward quantitative assessment of deformational plagiocephaly and brachycephaly at the point-of-care

Reza Seifabadi, Fereshteh Aalamifar, Seyed Hossein Hezaveh, Can Kocabalkanli, Kelly Wilburn, Marius George Linguraru

Journal of Medical Imaging, Vol. 10, Issue 04, 049801, (August 2023) https://doi.org/10.1117/1.JMI.10.4.049801

TOPICS: Point-of-care devices, Deformation, Medical imaging

Read Abstract +