Recommendations for Processing Head CT Data

A comparative analysis of different augmentations for brain images

Deep learning (DL) requires a large amount of training data to improve performance and prevent overfitting. To overcome these difficulties, we need to increase the size of the training dataset. This can be done by augmentation on a small dataset. The augmentation approaches must enhance the model's performance during the learning period. There are several types of transformations that can be applied to medical images. These transformations can be applied to the entire dataset or to a subset of the data, depending on the desired outcome. In this study, we categorize data augmentation methods into four groups: Absent augmentation, where no modifications are made; basic augmentation, which includes brightness and contrast adjustments; intermediate augmentation, encompassing a wider array of transformations like rotation, flipping, and shifting in addition to brightness and contrast adjustments; and advanced augmentation, where all transformation layers are employed. We plan to conduct a comprehensive analysis to determine which group performs best when applied to brain CT images. This evaluation aims to identify the augmentation group that produces the most favorable results in terms of improving model accuracy, minimizing diagnostic errors, and ensuring the robustness of the model in the context of brain CT image analysis.

A gradient mapping guided explainable deep neural network for extracapsular extension identification in 3D head and neck cancer computed tomography images

BACKGROUND

Diagnosis and treatment management for head and neck squamous cell carcinoma (HNSCC) is guided by routine diagnostic head and neck computed tomography (CT) scans to identify tumor and lymph node features. The extracapsular extension (ECE) is a strong predictor of patients' survival outcomes with HNSCC. It is essential to detect the occurrence of ECE as it changes staging and treatment planning for patients. Current clinical ECE detection relies on visual identification and pathologic confirmation conducted by clinicians. However, manual annotation of the lymph node region is a required data preprocessing step in most of the current machine learning-based ECE diagnosis studies.

PURPOSE

In this paper, we propose a Gradient Mapping Guided Explainable Network (GMGENet) framework to perform ECE identification automatically without requiring annotated lymph node region information.

METHODS

The gradient-weighted class activation mapping (Grad-CAM) technique is applied to guide the deep learning algorithm to focus on the regions that are highly related to ECE. The proposed framework includes an extractor and a classifier. In a joint training process, informative volumes of interest (VOIs) are extracted by the extractor without labeled lymph node region information, and the classifier learns the pattern to classify the extracted VOIs into ECE positive and negative.

RESULTS

In evaluation, the proposed methods are well-trained and tested using cross-validation. GMGENet achieved test accuracy and area under the curve (AUC) of 92.2% and 89.3%, respectively. GMGENetV2 achieved 90.3% accuracy and 91.7% AUC in the test. The results were compared with different existing models and further confirmed and explained by generating ECE probability heatmaps via a Grad-CAM technique. The presence or absence of ECE has been analyzed and correlated with ground truth histopathological findings.

CONCLUSIONS

The proposed deep network can learn meaningful patterns to identify ECE without providing lymph node contours. The introduced ECE heatmaps will contribute to the clinical implementations of the proposed model and reveal unknown features to radiologists. The outcome of this study is expected to promote the implementation of explainable artificial intelligence-assiste ECE detection.

Simple approach to quantify hypoxic-ischemic brain injury severity from computed tomography imaging files after cardiac arrest

BACKGROUND

Grey-white ratio (GWR) can estimate severity of cytotoxic cerebral edema secondary to hypoxic-ischemic brain injury after cardiac arrest and predict progression to death by neurologic criteria (DNC). Current approaches to calculating GWR are not standardized and have variable interrater reliability. We tested if measures of variance of brain density on early computed tomographic (CT) imaging after cardiac arrest could predict DNC.

METHODS

We performed a retrospective cohort study, identifying post-arrest patients treated between 2011 and 2020 at our single center. We extracted demographic data from our registry and Digital Imaging and Communication in Medicine (DICOM) files for each patient's first brain CT. We analyzed slices 15-20 of each DICOM, corresponding to the level of the basal ganglia while accommodating differences in patient anatomy. We extracted pixel arrays and converted the radiodensities to Hounsfield units (HU). To focus on brain tissue densities, we excluded HU > 60 and < 10. We calculated the variance of each patient's HU distribution and the difference between the means of a two-group Gaussian finite mixture model. We compared these novel metrics to existing measures of cerebral edema, then randomly divided our data into 80% training and 20% test sets and used logistic regression to predict DNC.

RESULTS

Of 1,133 included subjects, 457 (40%) were female, mean (standard deviation) age was 58 (16) years, and 115 (10%) progressed to DNC. CTs were obtained a median [interquartile range] of 4.2 [2.8-5.7] hours post-arrest. Our novel measures correlated weakly with GWR. HU variance, but not difference between mixture model means, differed significantly between subjects with and without sulcal or cistern effacement. GWR outperformed our novel measures in predicting progression to DNC with an area under the receiver operating characteristic curve (AUC) of 0.82, compared to HU variance (AUC = 0.73) and the difference between mixture model means (AUC = 0.56).

CONCLUSION

There are differences in the distribution of HU on post-arrest CT in patients with qualitative measures of cerebral edema. Current methods to quantify cerebral edema outperform simple measures of attenuation variance on early brain CT. Further analyses could investigate if these measures of variance, or other distributional characteristics of brain density, have improved predictive performance on brain CTs obtained later in the clinical course or derived from discrete regions of anatomical interest.

Concurrent Ischemic Lesion Age Estimation and Segmentation of CT Brain Using a Transformer-Based Network

The cornerstone of stroke care is expedient management that varies depending on the time since stroke onset. Consequently, clinical decision making is centered on accurate knowledge of timing and often requires a radiologist to interpret Computed Tomography (CT) of the brain to confirm the occurrence and age of an event. These tasks are particularly challenging due to the subtle expression of acute ischemic lesions and the dynamic nature of their appearance. Automation efforts have not yet applied deep learning to estimate lesion age and treated these two tasks independently, so, have overlooked their inherent complementary relationship. To leverage this, we propose a novel end-to-end multi-task transformer-based network optimized for concurrent segmentation and age estimation of cerebral ischemic lesions. By utilizing gated positional self-attention and CT-specific data augmentation, the proposed method can capture long-range spatial dependencies while maintaining its ability to be trained from scratch under low-data regimes commonly found in medical imaging. Furthermore, to better combine multiple predictions, we incorporate uncertainty by utilizing quantile loss to facilitate estimating a probability density function of lesion age. The effectiveness of our model is then extensively evaluated on a clinical dataset consisting of 776 CT images from two medical centers. Experimental results demonstrate that our method obtains promising performance, with an area under the curve (AUC) of 0.933 for classifying lesion ages ≤ 4.5 hours compared to 0.858 using a conventional approach, and outperforms task-specific state-of-the-art algorithms.

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

Purpose

Previous studies have demonstrated that three-dimensional (3D) volumetric renderings of magnetic resonance imaging (MRI) brain data can be used to identify patients using facial recognition. We have shown that facial features can be identified on simulation-computed tomography (CT) images for radiation oncology and mapped to face images from a database. We aim to determine whether CT images can be anonymized using anonymization software that was designed for T1-weighted MRI data.

Approach

Our study examines (1) the ability of off-the-shelf anonymization algorithms to anonymize CT data and (2) the ability of facial recognition algorithms to identify whether faces could be detected from a database of facial images. Our study generated 3D renderings from 57 head CT scans from The Cancer Imaging Archive database. Data were anonymized using AFNI (deface, reface, and 3Dskullstrip) and FSL's BET. Anonymized data were compared to the original renderings and passed through facial recognition algorithms (VGG-Face, FaceNet, DLib, and SFace) using a facial database (labeled faces in the wild) to determine what matches could be found.

Results

Our study found that all modules were able to process CT data and that AFNI's 3Dskullstrip and FSL's BET data consistently showed lower reidentification rates compared to the original.

Conclusions

The results from this study highlight the potential usage of anonymization algorithms as a clinical standard for deidentifying brain CT data. Our study demonstrates the importance of continued vigilance for patient privacy in publicly shared datasets and the importance of continued evaluation of anonymization methods for CT data.

Segmentation stability of human head and neck cancer medical images for radiotherapy applications under de-identification conditions: Benchmarking data sharing and artificial intelligence use-cases

Background

Demand for head and neck cancer (HNC) radiotherapy data in algorithmic development has prompted increased image dataset sharing. Medical images must comply with data protection requirements so that re-use is enabled without disclosing patient identifiers. Defacing, i.e., the removal of facial features from images, is often considered a reasonable compromise between data protection and re-usability for neuroimaging data. While defacing tools have been developed by the neuroimaging community, their acceptability for radiotherapy applications have not been explored. Therefore, this study systematically investigated the impact of available defacing algorithms on HNC organs at risk (OARs).

Methods

A publicly available dataset of magnetic resonance imaging scans for 55 HNC patients with eight segmented OARs (bilateral submandibular glands, parotid glands, level II neck lymph nodes, level III neck lymph nodes) was utilized. Eight publicly available defacing algorithms were investigated: afni_refacer, DeepDefacer, defacer, fsl_deface, mask_face, mri_deface, pydeface, and quickshear. Using a subset of scans where defacing succeeded (N=29), a 5-fold cross-validation 3D U-net based OAR auto-segmentation model was utilized to perform two main experiments: 1.) comparing original and defaced data for training when evaluated on original data; 2.) using original data for training and comparing the model evaluation on original and defaced data. Models were primarily assessed using the Dice similarity coefficient (DSC).

Results

Most defacing methods were unable to produce any usable images for evaluation, while mask_face, fsl_deface, and pydeface were unable to remove the face for 29%, 18%, and 24% of subjects, respectively. When using the original data for evaluation, the composite OAR DSC was statistically higher (p ≤ 0.05) for the model trained with the original data with a DSC of 0.760 compared to the mask_face, fsl_deface, and pydeface models with DSCs of 0.742, 0.736, and 0.449, respectively. Moreover, the model trained with original data had decreased performance (p ≤ 0.05) when evaluated on the defaced data with DSCs of 0.673, 0.693, and 0.406 for mask_face, fsl_deface, and pydeface, respectively.

Conclusion

Defacing algorithms may have a significant impact on HNC OAR auto-segmentation model training and testing. This work highlights the need for further development of HNC-specific image anonymization methods.

Development of pre-procedure virtual simulation for challenging interventional procedures: an experimental study with clinical application

Background

Most pain management techniques for challenging procedures are still performed under the guidance of the C-arm fluoroscope although it is sometimes difficult for even experienced clinicians to understand the modified three-dimensional anatomy as a two-dimensional X-ray image. To overcome these difficulties, the development of a virtual simulator may be helpful. Therefore, in this study, the authors developed a virtual simulator and presented its clinical application cases.

Methods

We developed a computer program to simulate the actual environment of the procedure. Computed tomography (CT) Digital Imaging and Communications in Medicine (DICOM) data were used for the simulations. Virtual needle placement was simulated at the most appropriate position for a successful block. Using a virtual C-arm, the authors searched for the position of the C-arm at which the needle was visualized as a point. The positional relationships between the anatomy of the patient and the needle were identified.

Results

For the simulations, the CT DICOM data of patients who visited the outpatient clinic was used. When the patients revisited the clinic, images similar to the simulated images were obtained by manipulating the C-arm. Transforaminal epidural injection, which was difficult to perform due to severe spinal deformity, and the challenging procedures of the superior hypogastric plexus block and Gasserian ganglion block, were successfully performed with the help of the simulation.

Conclusions

We created a pre-procedural virtual simulation and demonstrated its successful application in patients who are expected to undergo challenging procedures.

Mapping the association between tau-PET and Aβ-amyloid-PET using deep learning

In Alzheimer’s disease, the molecular pathogenesis of the extracellular Aβ-amyloid (Aβ) instigation of intracellular tau accumulation is poorly understood. We employed a high-resolution PET scanner, with low detection thresholds, to examine the Aβ-tau association using a convolutional neural network (CNN), and compared results to a standard voxel-wise linear analysis. The full range of Aβ Centiloid values was highly predicted by the tau topography using the CNN (training R² = 0.86, validation R² = 0.75, testing R² = 0.72). Linear models based on tau-SUVR identified widespread positive correlations between tau accumulation and Aβ burden throughout the brain. In contrast, CNN analysis identified focal clusters in the bilateral medial temporal lobes, frontal lobes, precuneus, postcentral gyrus and middle cingulate. At low Aβ levels, information from the middle cingulate, frontal lobe and precuneus regions was more predictive of Aβ burden, while at high Aβ levels, the medial temporal regions were more predictive of Aβ burden. The data-driven CNN approach revealed new associations between tau topography and Aβ burden.

Accuracy of Automated Computer-Aided Diagnosis for Stroke Imaging: A Critical Evaluation of Current Evidence

There is increasing interest in computer applications, using artificial intelligence methodologies, to perform health care tasks previously performed by humans, particularly in medical imaging for diagnosis. In stroke, there are now commercial artificial intelligence software for use with computed tomography or MR imaging to identify acute ischemic brain tissue pathology, arterial obstruction on computed tomography angiography or as hyperattenuated arteries on computed tomography, brain hemorrhage, or size of perfusion defects. A rapid, accurate diagnosis may aid treatment decisions for individual patients and could improve outcome if it leads to effective and safe treatment; or conversely, to disaster if a delayed or incorrect diagnosis results in inappropriate treatment. Despite this potential clinical impact, diagnostic tools including artificial intelligence methods are not subjected to the same clinical evaluation standards as are mandatory for drugs. Here, we provide an evidence-based review of the pros and cons of commercially available automated methods for medical imaging diagnosis, including those based on artificial intelligence, to diagnose acute brain pathology on computed tomography or magnetic resonance imaging in patients with stroke.

X-ray computed microtomography datasets for osteogenic nanofibrous coated titanium implants

Surface modifications of titanium implant influences the quality of osseointegration and are associated with favourable treatment prognosis in orthopaedic and cranio-maxillofacial cases. Hence, unlike previous works, the peri-implant region details of our novel osteogenic nanofibrous coated implants placed in rabbits (n = 6 + 1) were recorded over a 12-week period using a micro-CT imaging system. In this unique contribution, we have created a computed tomography (CT) library of rabbit’s tibiae anatomy with osteogenic nanofibrous coated/uncoated implants and are introductory useful assets for investigating the correlation between osteogenic nanofibers coated implants and its effect on improved osseointegration. Apart from using this CT dataset to conduct serial 2D image studies, three-dimensional (3D) reconstructions, assessing segmentation algorithms and developing adequate image quantitation tools, there may be positive applications of these in comparative investigations of similar or related preclinical as well as future clinical studies, further design planning, development etc. required for evolution of implants beyond the present state of art.

Measurement(s)	Bone microstructure and quality
Technology Type(s)	High-resolution imaging technology
Factor Type(s)	Osseointegration
Sample Characteristic - Organism	Oryctolagus cuniculus
Sample Characteristic - Environment	Sterile Environment
Sample Characteristic - Location	India

FeMA: Feature matching auto-encoder for predicting ischaemic stroke evolution and treatment outcome

Although, predicting ischaemic stroke evolution and treatment outcome provide important information one step towards individual treatment planning, classifying functional outcome and modelling the brain tissue evolution remains a challenge due to data complexity and visually subtle changes in the brain. We propose a novel deep learning approach, Feature Matching Auto-encoder (FeMA) that consists of two stages, predicting ischaemic stroke evolution at one week without voxel-wise annotation and predicting ischaemic stroke treatment outcome at 90 days from a baseline scan. In the first stage, we introduce feature similarity and consistency objective, and in the second stage, we show that adding stroke evolution information increase the performance of functional outcome prediction. Comparative experiments demonstrate that our proposed method is more effective to extract representative follow-up features and achieves the best results for functional outcome of stroke treatment.

A Two-Stage De-Identification Process for Privacy-Preserving Medical Image Analysis

Identification and re-identification are two major security and privacy threats to medical imaging data. De-identification in DICOM medical data is essential to preserve the privacy of patients' Personally Identifiable Information (PII) and requires a systematic approach. However, there is a lack of sufficient detail regarding the de-identification process of DICOM attributes, for example, what needs to be considered before removing a DICOM attribute. In this paper, we first highlight and review the key challenges in the medical image data de-identification process. In this paper, we develop a two-stage de-identification process for CT scan images available in DICOM file format. In the first stage of the de-identification process, the patient's PII-including name, date of birth, etc., are removed at the hospital facility using the export process available in their Picture Archiving and Communication System (PACS). The second stage employs the proposed DICOM de-identification tool for an exhaustive attribute-level investigation to further de-identify and ensure that all PII has been removed. Finally, we provide a roadmap for future considerations to build a semi-automated or automated tool for the DICOM datasets de-identification.

Feasibility of Pediatric Low-Dose Facial CT Reconstructed with Filtered Back Projection Using Adequate Kernels

Purpose

Materials and Methods

Results

Conclusion

Outcome Prediction of Patients with Intracerebral Hemorrhage by Measurement of Lesion Volume in the Corticospinal Tract on Computed Tomography

Objective:

This study investigated the potential utility of computed tomography for outcome prediction in patients with intracerebral hemorrhage.

Methods:

Patients with putaminal and/or thalamic hemorrhage for whom computed tomography images were acquired in our hospital emergency room soon after onset were retrospectively enrolled. Outcome measurements were obtained at discharge from the convalescent rehabilitation ward of our affiliated hospital. Hemiparesis was evaluated using the total score of the motor component of the Stroke Impairment Assessment Set (SIAS-motor; null to full, 0 to 25), the motor component of the Functional Independence Measure (FIM-motor; null to full, 13 to 91), and the total length of hospital stay. After registration of the computed tomography images to the standard brain, the volumes of the hematoma lesions located in the corticospinal tract were calculated. The correlation between the corticospinal tract lesion volumes and the outcome measurements was assessed using Spearman’s rank correlation test.

Results:

Thirty patients were entered into the final analytical database. Corticospinal tract lesion volumes ranged from 0.002 to 4.302 ml (median, 1.478). SIAS-motor scores ranged from 0 to 25 (median, 20), FIM-motor scores ranged from 15 to 91 (median, 80.5), and the total length of hospital stay ranged from 31 to 194 days (median, 106.5). All correlation tests were statistically significant (P <0.01). The strongest correlation was for SIAS-motor total (R=–0.710), followed by FIM-motor (R=–0.604) and LOS (R=0.493).

Conclusions:

These findings suggest that conventional computed tomography images may be useful for outcome prediction in patients with intracerebral hemorrhage.

The Stroke Neuro-Imaging Phenotype Repository: An Open Data Science Platform for Stroke Research

Stroke is one of the leading causes of death and disability worldwide. Reducing this disease burden through drug discovery and evaluation of stroke patient outcomes requires broader characterization of stroke pathophysiology, yet the underlying biologic and genetic factors contributing to outcomes are largely unknown. Remedying this critical knowledge gap requires deeper phenotyping, including large-scale integration of demographic, clinical, genomic, and imaging features. Such big data approaches will be facilitated by developing and running processing pipelines to extract stroke-related phenotypes at large scale. Millions of stroke patients undergo routine brain imaging each year, capturing a rich set of data on stroke-related injury and outcomes. The Stroke Neuroimaging Phenotype Repository (SNIPR) was developed as a multi-center centralized imaging repository of clinical computed tomography (CT) and magnetic resonance imaging (MRI) scans from stroke patients worldwide, based on the open source XNAT imaging informatics platform. The aims of this repository are to: (i) store, manage, process, and facilitate sharing of high-value stroke imaging data sets, (ii) implement containerized automated computational methods to extract image characteristics and disease-specific features from contributed images, (iii) facilitate integration of imaging, genomic, and clinical data to perform large-scale analysis of complications after stroke; and (iv) develop SNIPR as a collaborative platform aimed at both data scientists and clinical investigators. Currently, SNIPR hosts research projects encompassing ischemic and hemorrhagic stroke, with data from 2,246 subjects, and 6,149 imaging sessions from Washington University's clinical image archive as well as contributions from collaborators in different countries, including Finland, Poland, and Spain. Moreover, we have extended the XNAT data model to include relevant clinical features, including subject demographics, stroke severity (NIH Stroke Scale), stroke subtype (using TOAST classification), and outcome [modified Rankin Scale (mRS)]. Image processing pipelines are deployed on SNIPR using containerized modules, which facilitate replicability at a large scale. The first such pipeline identifies axial brain CT scans from DICOM header data and image data using a meta deep learning scan classifier, registers serial scans to an atlas, segments tissue compartments, and calculates CSF volume. The resulting volume can be used to quantify the progression of cerebral edema after ischemic stroke. SNIPR thus enables the development and validation of pipelines to automatically extract imaging phenotypes and couple them with clinical data with the overarching aim of enabling a broad understanding of stroke progression and outcomes.

Early recanalization in large-vessel occlusion stroke patients transferred for endovascular treatment

Background

We performed an exploratory analysis to identify patient and thrombus characteristics associated with early recanalization in large-vessel occlusion (LVO) stroke patients transferred for endovascular treatment (EVT) from a primary (PSC) to a comprehensive stroke center (CSC).

Methods

We included patients with an LVO stroke of the anterior circulation who were transferred to our hospital for EVT and underwent repeated imaging between January 2016 and June 2019. We compared patient characteristics, workflow time metrics, functional outcome (modified Rankin Scale at 90 days), and baseline thrombus imaging characteristics, which included: occlusion location, thrombus length, attenuation, perviousness, distance from terminus of intracranial carotid artery to the thrombus (DT), and clot burden score (CBS), between early-recanalized LVO (ER-LVO), and non-early-recanalized LVO (NER-LVO) patients.

Results

One hundred and forty-nine patients were included in the analysis. Early recanalization occurred in 32% of patients. ER-LVO patients less often had a medical history of hypertension (31% vs 49%, P=0.04), and more often had clinical improvement between PSC and CSC (ΔNIHSS −5 vs 3, P<0.01), compared with NER-LVO patients. Thrombolysis administration was similar in both groups (88% vs 78%, P=0.18). ER-LVO patients had no ICA occlusions (0% vs 27%, P<0.01), more often an M2 occlusion (35% vs 17%, P=0.01), longer DT (27 mm vs 12 mm, P<0.01), shorter thrombi (17 mm vs 27 mm, P<0.01), and higher CBS (8 vs 6, P<0.01) at baseline imaging. ER-LVO patients had lower mRS scores (1 vs 3, P=0.02).

Conclusions

Early recanalization is associated with clinical improvement between PSC and CSC admission, more distal occlusions and shorter thrombi at baseline imaging, and better functional outcome.

A simplified framework for the detection of intracranial hemorrhage in CT brain images using deep learning

BACKGROUND

The need for accurate and timely detection of Intracranial hemorrhage (ICH) is utmost important to avoid untoward incidents that may even lead to death.Hence, this presented work leverages the ability of a pretrained deep convolutional neural network (CNN) for the detection of ICH in computed tomography (CT) brain images.

METHODS

Different frameworks have been analyzed for their effectiveness for the classification of CT brain images into hemorrhage or non-hemorrhage conditions. All these frameworks were investigated on CQ500 dataset. Furthermore, an exclusive preprocessing pipeline was designed for both normal and ICH CT images. Firstly, a framework involving the pretrained deep CNN, AlexNet, has been exploited for both feature extraction and classification using the transfer learning method, secondly, a modified AlexNet-Support vector machine (SVM) classifier is explored and finally, a feature selection method, Principal Component Analysis (PCA) has been introduced in the AlexNet-SVM classifier model and its efficacy is explored.These models were trained and tested on two different sets of CT images, one containing the original images without preprocessing and another set consisting of preprocessed images.

RESULTS

The modified AlexNet-SVM classifier has shown an improved performance in comparison to the other investigated frameworks and has achieved a classification accuracy of 99.86%, sensitivity and specificity of 0.9986 for the detection of ICH in brain CT images.

CONCLUSION

This research has given an overview of a simple and efficient framework for the classification of hemorrhage and non-hemorrhage images. Also, the proposed simplified deep learning framework manifests its ability as a screening tool to assist the radiological trainees for the accurate detection of ICH.

An extensible big data software architecture managing a research resource of real-world clinical radiology data linked to other health data from the whole Scottish population

AIM

To enable a world-leading research dataset of routinely collected clinical images linked to other routinely collected data from the whole Scottish national population. This includes more than 30 million different radiological examinations from a population of 5.4 million and >2 PB of data collected since 2010.

METHODS

Scotland has a central archive of radiological data used to directly provide clinical care to patients. We have developed an architecture and platform to securely extract a copy of those data, link it to other clinical or social datasets, remove personal data to protect privacy, and make the resulting data available to researchers in a controlled Safe Haven environment.

RESULTS

An extensive software platform has been developed to host, extract, and link data from cohorts to answer research questions. The platform has been tested on 5 different test cases and is currently being further enhanced to support 3 exemplar research projects.

CONCLUSIONS

The data available are from a range of radiological modalities and scanner types and were collected under different environmental conditions. These real-world, heterogenous data are valuable for training algorithms to support clinical decision making, especially for deep learning where large data volumes are required. The resource is now available for international research access. The platform and data can support new health research using artificial intelligence and machine learning technologies, as well as enabling discovery science.

De-Identification of Radiomics Data Retaining Longitudinal Temporal Information

We propose a de-identification system which runs in a standalone mode. The system takes care of the de-identification of radiation oncology patient's clinical and annotated imaging data including RTSTRUCT, RTPLAN, and RTDOSE. The clinical data consists of diagnosis, stages, outcome, and treatment information of the patient. The imaging data could be the diagnostic, therapy planning, and verification images. Archival of the longitudinal radiation oncology verification images like cone beam CT scans along with the initial imaging and clinical data are preserved in the process. During the de-identification, the system keeps the reference of original data identity in encrypted form. These could be useful for the re-identification if necessary.

Creation of an anthropomorphic CT head phantom for verification of image segmentation

Purpose

Many methods are available to segment structural magnetic resonance (MR) images of the brain into different tissue types. These have generally been developed for research purposes but there is some clinical use in the diagnosis of neurodegenerative diseases such as dementia. The potential exists for computed tomography (CT) segmentation to be used in place of MRI segmentation, but this will require a method to verify the accuracy of CT processing, particularly if algorithms developed for MR are used, as MR has notably greater tissue contrast.

Methods

To investigate these issues we have created a three‐dimensional (3D) printed brain with realistic Hounsfield unit (HU) values based on tissue maps segmented directly from an individual T1 MRI scan of a normal subject. Several T1 MRI scans of normal subjects from the ADNI database were segmented using SPM12 and used to create stereolithography files of different tissues for 3D printing. The attenuation properties of several material blends were investigated, and three suitable formulations were used to print an object expected to have realistic geometry and attenuation properties. A skull was simulated by coating the object with plaster of Paris impregnated bandages. Using two CT scanners, the realism of the phantom was assessed by the measurement of HU values, SPM12 segmentation and comparison with the source data used to create the phantom.

Results

Realistic relative HU values were measured although a subtraction of 60 was required to obtain equivalence with the expected values (gray matter 32.9–35.8 phantom, 29.9–34.2 literature). Segmentation of images acquired at different kVps/mAs showed excellent agreement with the source data (Dice Similarity Coefficient 0.79 for gray matter). The performance of two scanners with two segmentation methods was compared, with the scanners found to have similar performance and with one segmentation method clearly superior to the other.

Conclusion

The ability to use 3D printing to create a realistic (in terms of geometry and attenuation properties) head phantom has been demonstrated and used in an initial assessment of CT segmentation accuracy using freely available software developed for MRI.