Optimizing analysis, visualization, and navigation of large image data sets: one 5000-section CT scan can ruin your whole day

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

Picture archiving and communication systems (PACS) that digitally acquire, archive, transmit, and display medical images ultimately enabled the transition from an analog film-based operation to a digital workflow revolutionizing radiology. This article briefly traces early generation systems to present-day PACS, noting challenges along with key technological advances and benefits. Thoughts for future PACS evolution are discussed including the promise of integration of artificial intelligence applications.

A Patch-Based Deep Learning Approach for Detecting Rib Fractures on Frontal Radiographs in Young Children

Chest radiography is the modality of choice for the identification of rib fractures in young children and there is value for the development of computer-aided rib fracture detection in this age group. However, the automated identification of rib fractures on chest radiographs can be challenging due to the need for high spatial resolution in deep learning frameworks. A patch-based deep learning algorithm was developed to automatically detect rib fractures on frontal chest radiographs in children under 2 years old. A total of 845 chest radiographs of children 0-2 years old (median: 4 months old) were manually segmented for rib fractures by radiologists and served as the ground-truth labels. Image analysis utilized a patch-based sliding-window technique, to meet the high-resolution requirements for fracture detection. Standard transfer learning techniques used ResNet-50 and ResNet-18 architectures. Area-under-curve for precision-recall (AUC-PR) and receiver-operating-characteristic (AUC-ROC), along with patch and whole-image classification metrics, were reported. On the test patches, the ResNet-50 model showed AUC-PR and AUC-ROC of 0.25 and 0.77, respectively, and the ResNet-18 showed an AUC-PR of 0.32 and AUC-ROC of 0.76. On the whole-radiograph level, the ResNet-50 had an AUC-ROC of 0.74 with 88% sensitivity and 43% specificity in identifying rib fractures, and the ResNet-18 had an AUC-ROC of 0.75 with 75% sensitivity and 60% specificity in identifying rib fractures. This work demonstrates the utility of patch-based analysis for detection of rib fractures in children under 2 years old. Future work with large cohorts of multi-institutional data will improve the generalizability of these findings to patients with suspicion of child abuse.

Ultra-low-dose CT lung screening with artificial intelligence iterative reconstruction: evaluation via automatic nodule-detection software

AIM

To test the feasibility of ultra-low-dose (ULD) computed tomography (CT) combined with an artificial intelligence iterative reconstruction (AIIR) algorithm for screening pulmonary nodules using computer-assisted diagnosis (CAD).

MATERIALS AND METHODS

A chest phantom with artificial pulmonary nodules was first scanned using the routine protocol and the ULD protocol (3.28 versus 0.18 mSv) to compare the image quality and to test the acceptability of the ULD CT protocol. Next, 147 lung-screening patients were enrolled prospectively, undergoing an additional ULD CT immediately after their routine CT examination for clinical validation. Images were reconstructed with filtered back-projection (FBP), hybrid iterative reconstruction (HIR), the AIIR, and were imported to the CAD software for preliminary nodule detection. Subjective image quality on the phantom was scored using a five-point scale and compared using the Mann-Whitney U-test. Nodule detection using CAD was evaluated for ULD HIR and AIIR images using the routine dose image as reference.

RESULTS

Higher image quality was scored for AIIR than for FBP and HIR at ULD (p<0.001). As reported by CAD, 107 patients were presented with more than five nodules on routine dose images and were chosen to represent the challenging cases at an early stage of pulmonary disease. Among such, the performance of nodule detection by CAD on ULD HIR and AIIR images was 75.2% and 92.2% of the routine dose image, respectively.

CONCLUSION

Combined with AIIR, it was feasible to use an ULD CT protocol with 95% dose reduction for CAD-based screening of pulmonary nodules.

IoT-Based Medical Image Monitoring System Using HL7 in a Hospital Database

In recent years, the healthcare system, along with the technology that surrounds it, has become a sector in much need of development. It has already improved in a wide range of areas thanks to significant and continuous research into the practical implications of biomedical and telemedicine studies. To ensure the continuing technological improvement of hospitals, physicians now also must properly maintain and manage large volumes of patient data. Transferring large amounts of data such as images to IoT servers based on machine-to-machine communication is difficult and time consuming over MQTT and MLLP protocols, and since IoT brokers only handle a limited number of bytes of data, such protocols can only transfer patient information and other text data. It is more difficult to handle the monitoring of ultrasound, MRI, or CT image data via IoT. To address this problem, this study proposes a model in which the system displays images as well as patient data on an IoT dashboard. A Raspberry Pi processes HL7 messages received from medical devices like an ultrasound machine (ULSM) and extracts only the image data for transfer to an FTP server. The Raspberry Pi 3 (RSPI3) forwards the patient information along with a unique encrypted image data link from the FTP server to the IoT server. We have implemented an authentic and NS3-based simulation environment to monitor real-time ultrasound image data on the IoT server and have analyzed the system performance, which has been impressive. This method will enrich the telemedicine facilities both for patients and physicians by assisting with overall monitoring of data.

What eye tracking can tell us about how radiologists use automated breast ultrasound

Purpose: Automated breast ultrasound (ABUS) presents three-dimensional (3D) representations of the breast in the form of stacks of coronal and transverse plane images. ABUS is especially useful for the assessment of dense breasts. Here, we present the first eye tracking data showing how radiologists search and evaluate ABUS cases. Approach: Twelve readers evaluated single-breast cases in 20-min sessions. Positive findings were present in 56% of the evaluated cases. Eye position and the currently visible coronal and transverse slice were tracked, allowing for reconstruction of 3D "scanpaths." Results: Individual readers had consistent search strategies. Most readers had strategies that involved examination of all available images. Overall accuracy was 0.74 (sensitivity = 0.66 and specificity = 0.84). The 20 false negative errors across all readers can be classified using Kundel's (1978) taxonomy: 17 are "decision" errors (readers found the target but misclassified it as normal or benign). There was one recognition error and two "search" errors. This is an unusually high proportion of decision errors. Readers spent essentially the same proportion of time viewing coronal and transverse images, regardless of whether the case was positive or negative, correct or incorrect. Readers tended to use a "scanner" strategy when viewing coronal images and a "driller" strategy when viewing transverse images. Conclusions: These results suggest that ABUS errors are more likely to be errors of interpretation than of search. Further research could determine if readers' exploration of all images is useful or if, in some negative cases, search of transverse images is redundant following a search of coronal images.

Mandating Limits on Workload, Duty, and Speed in Radiology

Research has not yet quantified the effects of workload or duty hours on the accuracy of radiologists. With the exception of a brief reduction in imaging studies during the 2020 peak of the COVID-19 pandemic, the workload of radiologists in the United States has seen relentless growth in recent years. One concern is that this increased demand could lead to reduced accuracy. Behavioral studies in species ranging from insects to humans have shown that decision speed is inversely correlated to decision accuracy. A potential solution is to institute workload and duty limits to optimize radiologist performance and patient safety. The concern, however, is that any prescribed mandated limits would be arbitrary and thus no more advantageous than allowing radiologists to self-regulate. Specific studies have been proposed to determine whether limits reduce error, and if so, to provide a principled basis for such limits. This could determine the precise susceptibility of individual radiologists to medical error as a function of speed during image viewing, the maximum number of studies that could be read during a work shift, and the appropriate shift duration as a function of time of day. Before principled recommendations for restrictions are made, however, it is important to understand how radiologists function both optimally and at the margins of adequate performance. This study examines the relationship between interpretation speed and error rates in radiology, the potential influence of artificial intelligence on reading speed and error rates, and the possible outcomes of imposed limits on both caseload and duty hours. This review concludes that the scientific evidence needed to make meaningful rules is lacking and notes that regulating workloads without scientific principles can be more harmful than not regulating at all.

Advancing Research on Medical Image Perception by Strengthening Multidisciplinary Collaboration

Medical image interpretation is central to detecting, diagnosing, and staging cancer and many other disorders. At a time when medical imaging is being transformed by digital technologies and artificial intelligence, understanding the basic perceptual and cognitive processes underlying medical image interpretation is vital for increasing diagnosticians' accuracy and performance, improving patient outcomes, and reducing diagnostician burnout. Medical image perception remains substantially understudied. In September 2019, the National Cancer Institute convened a multidisciplinary panel of radiologists and pathologists together with researchers working in medical image perception and adjacent fields of cognition and perception for the "Cognition and Medical Image Perception Think Tank." The Think Tank's key objectives were to identify critical unsolved problems related to visual perception in pathology and radiology from the perspective of diagnosticians, discuss how these clinically relevant questions could be addressed through cognitive and perception research, identify barriers and solutions for transdisciplinary collaborations, define ways to elevate the profile of cognition and perception research within the medical image community, determine the greatest needs to advance medical image perception, and outline future goals and strategies to evaluate progress. The Think Tank emphasized diagnosticians' perspectives as the crucial starting point for medical image perception research, with diagnosticians describing their interpretation process and identifying perceptual and cognitive problems that arise. This article reports the deliberations of the Think Tank participants to address these objectives and highlight opportunities to expand research on medical image perception.

3D Modeling and Advanced Visualization of the Pediatric Brain, Neck, and Spine

The ready availability of advanced visualization tools on picture archiving and communication systems workstations or even standard laptops through server-based or cloud-based solutions has enabled greater adoption of these techniques. We describe how radiologists can tailor imaging techniques for optimal 3D reconstructions provide a brief overview of the standard and newer "on-screen" techniques. We describe the process of creating 3D printed models for surgical simulation and education, with examples from the authors' institution and the existing literature. Finally, the review highlights current uses and potential future use cases for virtual reality and augmented reality applications in a pediatric neuroimaging setting.

RiFNet: Automated rib fracture detection in postmortem computed tomography

Imaging techniques are widely used for medical diagnostics. In some cases, a lack of medical practitioners who can manually analyze the images can lead to a bottleneck. Consequently, we developed a custom-made convolutional neural network (RiFNet = Rib Fracture Network) that can detect rib fractures in postmortem computed tomography. In a retrospective cohort study, we retrieved PMCT data from 195 postmortem cases with rib fractures from July 2017 to April 2018 from our database. The computed tomography data were prepared using a plugin in the commercial imaging software Syngo.via whereby the rib cage was unfolded on a single-in-plane image reformation. Out of the 195 cases, a total of 585 images were extracted and divided into two groups labeled "with" and "without" fractures. These two groups were subsequently divided into training, validation, and test datasets to assess the performance of RiFNet. In addition, we explored the possibility of applying transfer learning techniques on our dataset by choosing two independent noncommercial off-the-shelf convolutional neural network architectures (ResNet50 V2 and Inception V3) and compared the performances of those two with RiFNet. When using pre-trained convolutional neural networks, we achieved an F₁ score of 0.64 with Inception V3 and an F₁ score of 0.61 with ResNet50 V2. We obtained an average F₁ score of 0.91 ± 0.04 with RiFNet. RiFNet is efficient in detecting rib fractures on postmortem computed tomography. Transfer learning techniques are not necessarily well adapted to make classifications in postmortem computed tomography.

Characteristics of expert search behavior in volumetric medical image interpretation

Purpose: Experienced radiologists have enhanced global processing ability relative to novices, allowing experts to rapidly detect medical abnormalities without performing an exhaustive search. However, evidence for global processing models is primarily limited to two-dimensional image interpretation, and it is unclear whether these findings generalize to volumetric images, which are widely used in clinical practice. We examined whether radiologists searching volumetric images use methods consistent with global processing models of expertise. In addition, we investigated whether search strategy (scanning/drilling) differs with experience level. Approach: Fifty radiologists with a wide range of experience evaluated chest computed-tomography scans for lung nodules while their eye movements and scrolling behaviors were tracked. Multiple linear regressions were used to determine: (1) how search behaviors differed with years of experience and the number of chest CTs evaluated per week and (2) which search behaviors predicted better performance. Results: Contrary to global processing models based on 2D images, experience was unrelated to measures of global processing (saccadic amplitude, coverage, time to first fixation, search time, and depth passes) in this task. Drilling behavior was associated with better accuracy than scanning behavior when controlling for observer experience. Greater image coverage was a strong predictor of task accuracy. Conclusions: Global processing ability may play a relatively small role in volumetric image interpretation, where global scene statistics are not available to radiologists in a single glance. Rather, in volumetric images, it may be more important to engage in search strategies that support a more thorough search of the image.

Differentiating Experience From Cue Utilization in Radiological Assessments

OBJECTIVE

This research was designed to examine the contribution of self-reported experience and cue utilization to diagnostic accuracy in the context of radiology.

BACKGROUND

Within radiology, it is unclear how task-related experience contributes to the acquisition of associations between features with events in memory, or cues, and how they contribute to diagnostic performance.

METHOD

Data were collected from 18 trainees and 41 radiologists. The participants completed a radiology edition of the established cue utilization assessment tool EXPERTise 2.0, which provides a measure of cue utilization based on performance on a number of domain-specific tasks. The participants also completed a separate image interpretation task as an independent measure of diagnostic performance.

RESULTS

Consistent with previous research, a k-means cluster analysis using the data from EXPERTise 2.0 delineated two groups, the pattern of centroids of which reflected higher and lower cue utilization. Controlling for years of experience, participants with higher cue utilization were more accurate on the image interpretation task compared to participants who demonstrated relatively lower cue utilization (p = .01).

CONCLUSION

This study provides support for the role of cue utilization in assessments of radiology images among qualified radiologists. Importantly, it also demonstrates that cue utilization and self-reported years of experience as a radiologist make independent contributions to performance on the radiological diagnostic task.

APPLICATION

Task-related experience, including training, needs to be structured to ensure that learners have the opportunity to acquire feature-event relationships and internalize these associations in the form of cues in memory.

A review of visualization techniques of post-mortem computed tomography data for forensic death investigations

Postmortem computed tomography (PMCT) is a standard image modality used in forensic death investigations. Case- and audience-specific visualizations are vital for identifying relevant findings and communicating them appropriately. Different data types and visualization methods exist in 2D and 3D, and all of these types have specific applications. 2D visualizations are more suited for the radiological assessment of PMCT data because they allow the depiction of subtle details. 3D visualizations are better suited for creating visualizations for medical laypersons, such as state attorneys, because they maintain the anatomical context. Visualizations can be refined by using additional techniques, such as annotation or layering. Specialized methods such as 3D printing and virtual and augmented reality often require data conversion. The resulting data can also be used to combine PMCT data with other 3D data such as crime scene laser scans to create crime scene reconstructions. Knowledge of these techniques is essential for the successful handling of PMCT data in a forensic setting. In this review, we present an overview of current visualization techniques for PMCT.

Security and Privacy of Cloud- and IoT-Based Medical Image Diagnosis Using Fuzzy Convolutional Neural Network

In recent times, security in cloud computing has become a significant part in healthcare services specifically in medical data storage and disease prediction. A large volume of data are produced in the healthcare environment day by day due to the development in the medical devices. Thus, cloud computing technology is utilised for storing, processing, and handling these large volumes of data in a highly secured manner from various attacks. This paper focuses on disease classification by utilising image processing with secured cloud computing environment using an extended zigzag image encryption scheme possessing a greater tolerance to different data attacks. Secondly, a fuzzy convolutional neural network (FCNN) algorithm is proposed for effective classification of images. The decrypted images are used for classification of cancer levels with different layers of training. After classification, the results are transferred to the concern doctors and patients for further treatment process. Here, the experimental process is carried out by utilising the standard dataset. The results from the experiment concluded that the proposed algorithm shows better performance than the other existing algorithms and can be effectively utilised for the medical image diagnosis.

Potential use of deep learning techniques for postmortem imaging

The use of postmortem computed tomography in forensic medicine, in addition to conventional autopsy, is now a standard procedure in several countries. However, the large number of cases, the large amount of data, and the lack of postmortem radiology experts have pushed researchers to develop solutions that are able to automate diagnosis by applying deep learning techniques to postmortem computed tomography images. While deep learning techniques require a good understanding of image analysis and mathematical optimization, the goal of this review was to provide to the community of postmortem radiology experts the key concepts needed to assess the potential of such techniques and how they could impact their work.

A phenomenological ethnography of radiology: exploring the enactive and intersubjective aspects of radiological praxis

This paper presents qualitative field research conducted at a radiology department in the USA. It examines 'the radiologist at work' and analyses the intersubjective ground for her individual diagnostic intentions and personalized strategies for enacting diagnostically-relevant experiences via imaging technology. The paper incorporates the radiologists' use of 'enactive proofs'-observations and professional memories made explicit through their interaction with medical imaging technology and other practitioners in the field. The observations strongly support the development of enactive phenomenology and provide a critique of representationalism and of the primacy of inference in cognition. The results demonstrate the crucial role of shared intentions, providing insight into expert performance in the form of concrete dealings with imaging technology, habituality, the origin of mistakes, multilayered communication, and discovering new ways for improving professional praxis. The findings have much to offer to philosophy, anthropology and radiological practice.

Temporal subtraction of low-dose and relatively thick-slice CT images with large deformation diffeomorphic metric mapping and adaptive voxel matching for detection of bone metastases: A STARD-compliant article

To evaluate the improvement of radiologist performance in detecting bone metastases at follow up low-dose computed tomography (CT) by using a temporal subtraction (TS) technique based on an advanced nonrigid image registration algorithm.Twelve patients with bone metastases (males, 5; females, 7; mean age, 64.8 ± 7.6 years; range 51-81 years) and 12 control patients without bone metastases (males, 5; females, 7; mean age, 64.8 ± 7.6 years; 51-81 years) were included, who underwent initial and follow-up CT examinations between December 2005 and July 2016. Initial CT images were registered to follow-up CT images by the algorithm, and TS images were created. Three radiologists independently assessed the bone metastases with and without the TS images. The reader averaged jackknife alternative free-response receiver operating characteristics figure of merit was used to compare the diagnostic accuracy.The reader-averaged values of the jackknife alternative free-response receiver operating characteristics figures of merit (θ) significantly improved from 0.687 for the readout without TS and 0.803 for the readout with TS (P value = .031. F statistic = 5.24). The changes in the absolute value of CT attenuations in true-positive lesions were significantly larger than those in false-negative lesions (P < .001). Using TS, segment-based sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of the readout with TS were 66.7%, 98.9%, 94.4%, 90.9%, and 94.8%, respectively.The TS images can significantly improve the radiologist's performance in the detection of bone metastases on low-dose and relatively thick-slice CT.

Reversible 3D compression of segmented medical volumes: usability analysis for teleradiology and storage

BACKGROUND

DICOM standard does not have modules that provide the possibilities of two-dimensional Presentation States to three-dimensional (3D). Once the final 3D rendering is obtained, only video/image exporting or snapshots can be used. To increase the utility of 3D Presentation States in clinical practice and teleradiology, the storing and transferring the segmentation results, obtained after tedious procedures, can be very effective.

PURPOSE

To propose a strategy for preserving interaction and mobility of visualizations for teleradiology by storing and transferring only binary segmented data, which is effectively compressed by modern adaptive and context-based reversible methods.

MATERIAL AND METHODS

A diverse set of segmented data, which include four abdominal organs (liver, spleen, right, and left kidneys) from 20 T1-DUAL and 20 T2-SPIR MRI, liver from 20 CT, and abdominal aorta with aneurysms (AAA) from 19 computed tomography-angiography datasets, are collected. Each organ is segmented manually by expert physicians, and binary volumes are created. The well-established reversible binary compression methods PNG, JPEG-LS, JPEG-XR, CCITT-G4, LZW, JBIG2, and ZIP are applied to medical datasets. Recently proposed context-based (3D-RLE) and adaptive (ABIC) algorithms are also employed. The performance assessment has been presented in terms of the compression ratio that is a universal compression metric.

RESULTS

Reversible compression of binary volumes results with substantial decreases in file size such as 254 to 2.14 MB for CT-AAA, 56.7 to 0.3 MB for CT-liver. Moreover, compared to the performance of well-established methods (i.e., mean 76.14%), CR is observed to be increased significantly for all segmented organs from both CT and MRI datasets when ABIC (95.49%) and 3D-RLE (94.98%) are utilized. The hypothesis is that morphological coherence of scanning procedure and adaptation between the segmented organs, that is, bi-level images, contributes to compression performance. Although the performance of well-established techniques is satisfactory, the sensitivity of ABIC to modality type and the advantage of 3D-RLE when the spatial coherence between the adjacent slices are high results with up to 10 times more CR performance.

CONCLUSION

Adaptive and context-based compression strategies allow effective storage and transfer of segmented binary data, which can be used to re-produce visualizations for better teleradiology practices preserving all interaction mechanisms.

A Review of Perceptual Expertise in Radiology-How it develops, How we can test it, and Why humans still matter in the era of Artificial Intelligence

As the first step in image interpretation is detection, an error in perception can prematurely end the diagnostic process leading to missed diagnoses. Because perceptual errors of this sort-"failure to detect"-are the most common interpretive error (and cause of litigation) in radiology, understanding the nature of perceptual expertise is essential in decreasing radiology's long-standing error rates. In this article, we review what constitutes a perceptual error, the existing models of radiologic image perception, the development of perceptual expertise and how it can be tested, perceptual learning methods in training radiologists, and why understanding perceptual expertise is still relevant in the era of artificial intelligence. Adding targeted interventions, such as perceptual learning, to existing teaching practices, has the potential to enhance expertise and reduce medical error.

What do we know about volumetric medical image interpretation?: a review of the basic science and medical image perception literatures

Interpretation of volumetric medical images represents a rapidly growing proportion of the workload in radiology. However, relatively little is known about the strategies that best guide search behavior when looking for abnormalities in volumetric images. Although there is extensive literature on two-dimensional medical image perception, it is an open question whether the conclusions drawn from these images can be generalized to volumetric images. Importantly, volumetric images have distinct characteristics (e.g., scrolling through depth, smooth-pursuit eye-movements, motion onset cues, etc.) that should be considered in future research. In this manuscript, we will review the literature on medical image perception and discuss relevant findings from basic science that can be used to generate predictions about expertise in volumetric image interpretation. By better understanding search through volumetric images, we may be able to identify common sources of error, characterize the optimal strategies for searching through depth, or develop new training and assessment techniques for radiology residents.

Analysis of Perceptual Expertise in Radiology - Current Knowledge and a New Perspective

Radiologists rely principally on visual inspection to detect, describe, and classify findings in medical images. As most interpretive errors in radiology are perceptual in nature, understanding the path to radiologic expertise during image analysis is essential to educate future generations of radiologists. We review the perceptual tasks and challenges in radiologic diagnosis, discuss models of radiologic image perception, consider the application of perceptual learning methods in medical training, and suggest a new approach to understanding perceptional expertise. Specific principled enhancements to educational practices in radiology promise to deepen perceptual expertise among radiologists with the goal of improving training and reducing medical error.

Development of competence in volumetric image interpretation in radiology residents

BACKGROUND

During residency, radiology residents learn to interpret volumetric radiological images. The development of their competence for volumetric image interpretation, as opposed to 2D image reading, is not completely understood. The purpose of the present study was to investigate how competence for volumetric image interpretation develops in radiology residents and how this compares with competence development for 2D image interpretation, by studying resident scores on image-based items in digital radiology tests.

METHODS

We reviewed resident scores on volumetric and 2D image-based test items in 9 consecutive semi-annual digital radiology tests that were carried out from November 2013 to April 2018. We assessed percentage-correct sum scores for all test items about volumetric images and for all test items about 2D images in each test as well as for all residents across the 9 tests (i.e. 4.5 years of test materials). We used a paired t-test to analyze whether scores differed between volumetric and 2D image-based test items in individual residents in postgraduate year (PGY) 0-5, subdivided in 10 half-year phases (PGY 0-0.5, 0.5-1.0, 1.0-1.5 et cetera).

RESULTS

The percentage-correct scores on volumetric and 2D image-based items showed a comparable trend of development, increasing in the first half of residency and flattening off in the second half. Chance-corrected scores were generally lower in volumetric than in 2D items (on average 1-5% points). In PGY 1.5-4.5, this score difference was statistically significant (p-values ranging from 0.02 to < 0.001), with the largest difference found in PGY 2.5 (mean: 5% points; 95% CI: -7.3 - -3.4). At the end of training in PGY 5, there was no statistically significant score difference between both item types.

CONCLUSIONS

The development of competence in volumetric image interpretation fits a similar curvilinear growth curve during radiology residency as 2D image interpretation competence in digital radiology tests. Although residents performed significantly lower on volumetric than 2D items in PGY 1.5-4.5, we consider the magnitude of this difference as relatively small for our educational setting and we suggest that throughout radiology training there are no relevant differences in the development of both types of competences, as investigated by digital radiology tests.

Vascular CT and MRI: a practical guide to imaging protocols

Non-invasive cross-sectional imaging techniques play a crucial role in the assessment of the varied manifestations of vascular disease. Vascular imaging encompasses a wide variety of pathology. Designing vascular imaging protocols can be challenging owing to the non-uniform velocity of blood in the aorta, differences in cardiac output between patients, and the effect of different disease states on blood flow. In this review, we provide the rationale behind—and a practical guide to—designing and implementing straightforward vascular computed tomography (CT) and magnetic resonance imaging (MRI) protocols.

Teaching Points

• There is a wide range of vascular pathologies requiring bespoke imaging protocols.

• Variations in cardiac output and non-uniform blood velocity complicate vascular imaging.

• Contrast media dose, injection rate and duration affect arterial enhancement in CTA.

• Iterative CT reconstruction can improve image quality and reduce radiation dose.

• MRA is of particular value when imaging small arteries and venous studies.

Comparing search patterns in digital breast tomosynthesis and full-field digital mammography: an eye tracking study

As a promising imaging modality, digital breast tomosynthesis (DBT) leads to better diagnostic performance than traditional full-field digital mammograms (FFDM) alone. DBT allows different planes of the breast to be visualized, reducing occlusion from overlapping tissue. Although DBT is gaining popularity, best practices for search strategies in this medium are unclear. Eye tracking allowed us to describe search patterns adopted by radiologists searching DBT and FFDM images. Eleven radiologists examined eight DBT and FFDM cases. Observers marked suspicious masses with mouse clicks. Eye position was recorded at 1000 Hz and was coregistered with slice/depth plane as the radiologist scrolled through the DBT images, allowing a 3-D representation of eye position. Hit rate for masses was higher for tomography cases than 2-D cases and DBT led to lower false positive rates. However, search duration was much longer for DBT cases than FFDM. DBT was associated with longer fixations but similar saccadic amplitude compared with FFDM. When comparing radiologists' eye movements to a previous study, which tracked eye movements as radiologists read chest CT, we found DBT viewers did not align with previously identified "driller" or "scanner" strategies, although their search strategy most closely aligns with a type of vigorous drilling strategy.

How visual search relates to visual diagnostic performance: a narrative systematic review of eye-tracking research in radiology

Eye tracking research has been conducted for decades to gain understanding of visual diagnosis such as in radiology. For educational purposes, it is important to identify visual search patterns that are related to high perceptual performance and to identify effective teaching strategies. This review of eye-tracking literature in the radiology domain aims to identify visual search patterns associated with high perceptual performance. Databases PubMed, EMBASE, ERIC, PsycINFO, Scopus and Web of Science were searched using 'visual perception' OR 'eye tracking' AND 'radiology' and synonyms. Two authors independently screened search results and included eye tracking studies concerning visual skills in radiology published between January 1, 1994 and July 31, 2015. Two authors independently assessed study quality with the Medical Education Research Study Quality Instrument, and extracted study data with respect to design, participant and task characteristics, and variables. A thematic analysis was conducted to extract and arrange study results, and a textual narrative synthesis was applied for data integration and interpretation. The search resulted in 22 relevant full-text articles. Thematic analysis resulted in six themes that informed the relation between visual search and level of expertise: (1) time on task, (2) eye movement characteristics of experts, (3) differences in visual attention, (4) visual search patterns, (5) search patterns in cross sectional stack imaging, and (6) teaching visual search strategies. Expert search was found to be characterized by a global-focal search pattern, which represents an initial global impression, followed by a detailed, focal search-to-find mode. Specific task-related search patterns, like drilling through CT scans and systematic search in chest X-rays, were found to be related to high expert levels. One study investigated teaching of visual search strategies, and did not find a significant effect on perceptual performance. Eye tracking literature in radiology indicates several search patterns are related to high levels of expertise, but teaching novices to search as an expert may not be effective. Experimental research is needed to find out which search strategies can improve image perception in learners.

Distraction in diagnostic radiology: How is search through volumetric medical images affected by interruptions?

Observational studies have shown that interruptions are a frequent occurrence in diagnostic radiology. The present study used an experimental design in order to quantify the cost of these interruptions during search through volumetric medical images. Participants searched through chest CT scans for nodules that are indicative of lung cancer. In half of the cases, search was interrupted by a series of true or false math equations. The primary cost of these interruptions was an increase in search time with no corresponding increase in accuracy or lung coverage. This time cost was not modulated by the difficulty of the interruption task or an individual's working memory capacity. Eye-tracking suggests that this time cost was driven by impaired memory for which regions of the lung were searched prior to the interruption. Potential interventions will be discussed in the context of these results.

Forensic 3D Visualization of CT Data Using Cinematic Volume Rendering: A Preliminary Study

OBJECTIVE

The 3D volume-rendering technique (VRT) is commonly used in forensic radiology. Its main function is to explain medical findings to state attorneys, judges, or police representatives. New visualization algorithms permit the generation of almost photorealistic volume renderings of CT datasets. The objective of this study is to present and compare a variety of radiologic findings to illustrate the differences between and the advantages and limitations of the current VRT and the physically based cinematic rendering technique (CRT).

MATERIALS AND METHODS

Seventy volunteers were shown VRT and CRT reconstructions of 10 different cases. They were asked to mark the findings on the images and rate them in terms of realism and understandability.

RESULTS

A total of 48 of the 70 questionnaires were returned and included in the analysis. On the basis of most of the findings presented, CRT appears to be equal or superior to VRT with respect to the realism and understandability of the visualized findings. Overall, in terms of realism, the difference between the techniques was statistically significant (p < 0.05). Most participants perceived the CRT findings to be more understandable than the VRT findings, but that difference was not statistically significant (p > 0.05).

CONCLUSION

CRT, which is similar to conventional VRT, is not primarily intended for diagnostic radiologic image analysis, and therefore it should be used primarily as a tool to deliver visual information in the form of radiologic image reports. Using CRT for forensic visualization might have advantages over using VRT if conveying a high degree of visual realism is of importance. Most of the shortcomings of CRT have to do with the software being an early prototype.

Temporal Characteristics of Radiologists' and Novices' Lesion Detection in Viewing Medical Images Presented Rapidly and Sequentially

Although viewing multiple stacks of medical images presented on a display is a relatively new but useful medical task, little is known about this task. Particularly, it is unclear how radiologists search for lesions in this type of image reading. When viewing cluttered and dynamic displays, continuous motion itself does not capture attention. Thus, it is effective for the target detection that observers' attention is captured by the onset signal of a suddenly appearing target among the continuously moving distractors (i.e., a passive viewing strategy). This can be applied to stack viewing tasks, because lesions often show up as transient signals in medical images which are sequentially presented simulating a dynamic and smoothly transforming image progression of organs. However, it is unclear whether observers can detect a target when the target appears at the beginning of a sequential presentation where the global apparent motion onset signal (i.e., signal of the initiation of the apparent motion by sequential presentation) occurs. We investigated the ability of radiologists to detect lesions during such tasks by comparing the performances of radiologists and novices. Results show that overall performance of radiologists is better than novices. Furthermore, the temporal locations of lesions in CT image sequences, i.e., when a lesion appears in an image sequence, does not affect the performance of radiologists, whereas it does affect the performance of novices. Results indicate that novices have greater difficulty in detecting a lesion appearing early than late in the image sequence. We suggest that radiologists have other mechanisms to detect lesions in medical images with little attention which novices do not have. This ability is critically important when viewing rapid sequential presentations of multiple CT images, such as stack viewing tasks.

Shuffling your way out of change blindness

Change detection is typically discussed in the literature as a 2-state phenomenon. Small differences between otherwise identical images are easy to detect when the images are superimposed in space and alternated in time ("shuffled"). However, change blindness results from any disruption that prevents the critical change from generating the sole salient transient. Here we show that different presentation strategies produce different degrees of change blindness for the same change. Specifically, shuffling the images supports faster change detection than viewing the same 2 images side by side, even when the images contain a number of distracting differences. In Experiment 1, pairs of photographs having a 50 % chance of containing a difference were viewed either in alternation, in a "Shuffle" condition, or simultaneously, in a "Side-by-Side" condition. Change detection was about 6 seconds faster when the images were viewed in the "Shuffle" mode. In Experiment 2, we presented two images that were slightly laterally shifted relative to each other (0-48 pixels). The RT benefit for the Shuffle viewing mode was very strong when the relative shift was small, to insignificant when there was a large difference between the two images. However, at large shifts, Shuffle maintained an accuracy advantage. It seems that changes are easier to detect when comparing images in a Shuffle condition rather than Side-by-Side. This has important implications for real world tasks like radiology where detection of change is critical.

Trauma in CT: The Role of Severe Injury on Satisfaction of Search Revised

PURPOSE

The satisfaction-of-search (SOS) effect occurs when an abnormality on an image is missed because another is found. The aim of this experiment was to test whether severe distracting fractures control the magnitude of SOS on other fractures when both appear in a single CT image.

METHODS

The institutional review board approved this study. The experimental (SOS) condition included 35 cervical spine CT cases, all of which contained severe cervical spine injuries. For each of these cases, a similar case was found that had no injuries. Image modification software was developed to add simulated fractures to each pair of cases, with and without a major injury. Sixteen different minor fractures were added to 16 of the 35 pairs of images. The 35 cases without native injuries constituted a control (non-SOS) condition mixed in a random order. Twenty radiologists read 35 mixed cases in each of two sessions. False-positive evaluations were collected only for cases without simulated fractures.

RESULTS

An SOS effect on the detection of simulated fractures was not observed. There was a nonsignificant (P = .07) finding of poorer detection in the presence of cases with severe injuries. However, the magnitude of the effect was no greater than has been observed for less severe distracting injuries.

CONCLUSIONS

The outcome agrees with the results of two previous experiments that failed to yield an SOS effect associated with detecting severe injuries, suggesting that the severity of a distracting injury does not determine whether a second injury is discovered.

Image Size Influences Visual Search and Perception of Hemorrhages When Reading Cranial CT: An Eye-Tracking Study

OBJECTIVE

The aim of this study was to explore reader gaze, performance, and preference during interpretation of cranial computed tomography (cCT) in stack mode at two different sizes.

BACKGROUND

Digital display of medical images allows for the manipulation of many imaging factors, like image size, by the radiologists, yet it is often not known what display parameters better suit human perception.

METHOD

Twenty-one radiologists provided informed consent to be eye tracked while reading 20 cCT cases. Half of these cases were presented at a size of 14 × 14 cm (512 × 512 pixels), half at 28 × 28 cm (1,024 × 1,024 pixels). Visual search, performance, and preference for the two image sizes were assessed.

RESULTS

When reading small images, significantly fewer, but longer, fixations were observed, and these fixations covered significantly more slices. Time to first fixation of true positive findings was faster in small images, but dwell time on true findings was longer. Readers made more false positive decisions in small images, but no overall difference in either jackknife alternative free-response receiver operating characteristic or reading time was found.

CONCLUSION

Overall performance is not affected by image size. However, small-stack-mode cCT images may better support the use of motion perception and acquiring an overview, whereas large-stack-mode cCT images seem better suited for detailed analyses.

APPLICATION

Subjective and eye-tracking data suggest that image size influences how images are searched and that different search strategies might be beneficial under different circumstances.

Lung nodule and cancer detection in computed tomography screening

Fundamental to the diagnosis of lung cancer in computed tomography (CT) scans is the detection and interpretation of lung nodules. As the capabilities of CT scanners have advanced, higher levels of spatial resolution reveal tinier lung abnormalities. Not all detected lung nodules should be reported; however, radiologists strive to detect all nodules that might have relevance to cancer diagnosis. Although medium to large lung nodules are detected consistently, interreader agreement and reader sensitivity for lung nodule detection diminish substantially as the nodule size falls below 8 to 10 mm. The difficulty in establishing an absolute reference standard presents a challenge to the reliability of studies performed to evaluate lung nodule detection. In the interest of improving detection performance, investigators are using eye tracking to analyze the effectiveness with which radiologists search CT scans relative to their ability to recognize nodules within their search path in order to determine whether strategies might exist to improve performance across readers. Beyond the viewing of transverse CT reconstructions, image processing techniques such as thin-slab maximum-intensity projections are used to substantially improve reader performance. Finally, the development of computer-aided detection has continued to evolve with the expectation that one day it will serve routinely as a tireless partner to the radiologist to enhance detection performance without significant prolongation of the interpretive process. This review provides an introduction to the current understanding of these varied issues as we enter the era of widespread lung cancer screening.

CT triage for lung malignancy: coronal multiplanar reformation versus images in three orthogonal planes

BACKGROUND

Generation of multiplanar reformation (MPR) images has become automatic on most modern computed tomography (CT) scanners, potentially increasing the workload of the reporting radiologists. It is not always clear if this increases diagnostic performance in all clinical tasks.

PURPOSE

To assess detection performance using only coronal multiplanar reformations (MPR) when triaging patients for lung malignancies with CT compared to images in three orthogonal planes, and to evaluate performance comparison of novice and experienced readers.

MATERIAL AND METHODS

Retrospective study of 63 patients with suspicion of lung cancer, scanned on 64-slice multidetector computed tomography (MDCT) with images reconstructed in three planes. Coronal images were presented to four readers, two novice and two experienced. Readers decided whether the patients were suspicious for malignant disease, and indicated their confidence on a five-point scale. Sensitivity and specificity on per-patient basis was calculated with regards to a reference standard of histological diagnosis, and compared with the original report using McNemar's test. Receiver operating characteristic (ROC) curves were plotted to compare the performance of the four readers, using the area under the curve (AUC) as figure of merit.

RESULTS

No statistically significant difference of sensitivity and specificity was found for any of the readers when compared to the original reports. ROC analysis yielded AUCs in the range of 0.92-0.93 for all readers with no significant difference. Inter-rater agreement was substantial (kappa = 0.72).

CONCLUSION

Sensitivity and specificity were comparable to diagnosis using images in three planes. No significant difference was found between experienced and novice readers.

Image toggling saves time in mammography

When two images are perfectly aligned, even subtle differences are readily detected when the images are "toggled" back and forth in the same location. However, substantial changes between two photographs can be missed if the images are misaligned ("change blindness"). Nevertheless, recent work from our lab, testing nonradiologists, suggests that toggling misaligned photographs leads to superior performance compared to side-by-side viewing (SBS). In order to determine if a benefit of toggling misaligned images may be observed in clinical mammography, we developed an image toggling technique where pairs of new and prior breast imaging exam images could be efficiently toggled back and forth. Twenty-three radiologists read 10 mammograms evenly divided in toggle and SBS modes. The toggle mode led to a 6-s benefit in reaching a decision [[Formula: see text], [Formula: see text]]. The toggle viewing mode also led to a 5% improvement in diagnostic accuracy, though in our small sample this effect was not statistically reliable. Time savings were found even though successive mammograms were not perfectly aligned. Given the ever-increasing caseload for radiologists, this simple manipulation of how the images are viewed could save valuable time in clinical practice, allowing radiologists to read more cases or spend more time on difficult cases.

Volumetric relief map for intracranial cerebrospinal fluid distribution analysis

Cerebrospinal fluid imaging plays a significant role in the clinical diagnosis of brain disorders, such as hydrocephalus and Alzheimer's disease. While three-dimensional images of cerebrospinal fluid are very detailed, the complex structures they contain can be time-consuming and laborious to interpret. This paper presents a simple technique that represents the intracranial cerebrospinal fluid distribution as a two-dimensional image in such a way that the total fluid volume is preserved. We call this a volumetric relief map, and show its effectiveness in a characterization and analysis of fluid distributions and networks in hydrocephalus patients and healthy adults.

Volumetric and two-dimensional image interpretation show different cognitive processes in learners

RATIONALE AND OBJECTIVES

In current practice, radiologists interpret digital images, including a substantial amount of volumetric images. We hypothesized that interpretation of a stack of a volumetric data set demands different skills than interpretation of two-dimensional (2D) cross-sectional images. This study aimed to investigate and compare knowledge and skills used for interpretation of volumetric versus 2D images.

MATERIALS AND METHODS

Twenty radiology clerks were asked to think out loud while reading four or five volumetric computed tomography (CT) images in stack mode and four or five 2D CT images. Cases were presented in a digital testing program allowing stack viewing of volumetric data sets and changing views and window settings. Thoughts verbalized by the participants were registered and coded by a framework of knowledge and skills concerning three components: perception, analysis, and synthesis. The components were subdivided into 16 discrete knowledge and skill elements. A within-subject analysis was performed to compare cognitive processes during volumetric image readings versus 2D cross-sectional image readings.

RESULTS

Most utterances contained knowledge and skills concerning perception (46%). A smaller part involved synthesis (31%) and analysis (23%). More utterances regarded perception in volumetric image interpretation than in 2D image interpretation (Median 48% vs 35%; z = -3.9; P < .001). Synthesis was less prominent in volumetric than in 2D image interpretation (Median 28% vs 42%; z = -3.9; P < .001). No differences were found in analysis utterances.

CONCLUSIONS

Cognitive processes in volumetric and 2D cross-sectional image interpretation differ substantially. Volumetric image interpretation draws predominantly on perceptual processes, whereas 2D image interpretation is mainly characterized by synthesis. The results encourage the use of volumetric images for teaching and testing perceptual skills.

Support for external validity of radiological anatomy tests using volumetric images

RATIONALE AND OBJECTIVES

Radiology practice has become increasingly based on volumetric images (VIs), but tests in medical education still mainly involve two-dimensional (2D) images. We created a novel, digital, VI test and hypothesized that scores on this test would better reflect radiological anatomy skills than scores on a traditional 2D image test. To evaluate external validity we correlated VI and 2D image test scores with anatomy cadaver-based test scores.

MATERIALS AND METHODS

In 2012, 246 medical students completed one of two comparable versions (A and B) of a digital radiology test, each containing 20 2D image and 20 VI questions. Thirty-three of these participants also took a human cadaver anatomy test. Mean scores and reliabilities of the 2D image and VI subtests were compared and correlated with human cadaver anatomy test scores. Participants received a questionnaire about perceived representativeness and difficulty of the radiology test.

RESULTS

Human cadaver test scores were not correlated with 2D image scores, but significantly correlated with VI scores (r = 0.44, P < .05). Cronbach's α reliability was 0.49 (A) and 0.65 (B) for the 2D image subtests and 0.65 (A) and 0.71 (B) for VI subtests. Mean VI scores (74.4%, standard deviation 2.9) were significantly lower than 2D image scores (83.8%, standard deviation 2.4) in version A (P < .001). VI questions were considered more representative of clinical practice and education than 2D image questions and less difficult (both P < .001).

CONCLUSIONS

VI tests show higher reliability, a significant correlation with human cadaver test scores, and are considered more representative for clinical practice than tests with 2D images.

Volumetric CT-images improve testing of radiological image interpretation skills

RATIONALE AND OBJECTIVES

Current radiology practice increasingly involves interpretation of volumetric data sets. In contrast, most radiology tests still contain only 2D images. We introduced a new testing tool that allows for stack viewing of volumetric images in our undergraduate radiology program. We hypothesized that tests with volumetric CT-images enhance test quality, in comparison with traditional completely 2D image-based tests, because they might better reflect required skills for clinical practice.

MATERIALS AND METHODS

Two groups of medical students (n=139; n=143), trained with 2D and volumetric CT-images, took a digital radiology test in two versions (A and B), each containing both 2D and volumetric CT-image questions. In a questionnaire, they were asked to comment on the representativeness for clinical practice, difficulty and user-friendliness of the test questions and testing program. Students' test scores and reliabilities, measured with Cronbach's alpha, of 2D and volumetric CT-image tests were compared.

RESULTS

Estimated reliabilities (Cronbach's alphas) were higher for volumetric CT-image scores (version A: .51 and version B: .54), than for 2D CT-image scores (version A: .24 and version B: .37). Participants found volumetric CT-image tests more representative of clinical practice, and considered them to be less difficult than volumetric CT-image questions. However, in one version (A), volumetric CT-image scores (M 80.9, SD 14.8) were significantly lower than 2D CT-image scores (M 88.4, SD 10.4) (p<.001). The volumetric CT-image testing program was considered user-friendly.

CONCLUSION

This study shows that volumetric image questions can be successfully integrated in students' radiology testing. Results suggests that the inclusion of volumetric CT-images might improve the quality of radiology tests by positively impacting perceived representativeness for clinical practice and increasing reliability of the test.

Interpretation of radiological images: towards a framework of knowledge and skills

The knowledge and skills that are required for radiological image interpretation are not well documented, even though medical imaging is gaining importance. This study aims to develop a comprehensive framework of knowledge and skills, required for two-dimensional and multiplanar image interpretation in radiology. A mixed-method study approach was applied. First, a literature search was performed to identify knowledge and skills that are important for image interpretation. Three databases, PubMed, PsycINFO and Embase, were searched for studies using synonyms of image interpretation skills or visual expertise combined with synonyms of radiology. Empirical or review studies concerning knowledge and skills for medical image interpretation were included and relevant knowledge and skill items were extracted. Second, a preliminary framework was built and discussed with nine selective experts in individual semi-structured interviews. The expert team consisted of four radiologists, one radiology resident, two education scientists, one cognitive psychologist and one neuropsychologist. The framework was optimised based on the experts comments. Finally, the framework was applied to empirical data, derived from verbal protocols of ten clerks interpreting two-dimensional and multiplanar radiological images. In consensus meetings adjustments were made to resolve discrepancies of the framework with the verbal protocol data. We designed a framework with three main components of image interpretation: perception, analysis and synthesis. The literature study provided four knowledge and twelve skill items. As a result of the expert interviews, one skill item was added and formulations of existing items were adjusted. The think-aloud experiment showed that all knowledge items and three of the skill items were applied within all three main components of the image interpretation process. The remaining framework items were apparent only within one of the main components. After combining two knowledge items, we finally identified three knowledge items and thirteen skills, essential for image interpretation by trainees. The framework can serve as a guideline for education and assessment of two- and three-dimensional image interpretation. Further validation of the framework in larger study groups with different levels of expertise is needed.

Predicting visual semantic descriptive terms from radiological image data: preliminary results with liver lesions in CT

We describe a framework to model visual semantics of liver lesions in CT images in order to predict the visual semantic terms (VST) reported by radiologists in describing these lesions. Computational models of VST are learned from image data using linear combinations of high-order steerable Riesz wavelets and support vector machines (SVM). In a first step, these models are used to predict the presence of each semantic term that describes liver lesions. In a second step, the distances between all VST models are calculated to establish a nonhierarchical computationally-derived ontology of VST containing inter-term synonymy and complementarity. A preliminary evaluation of the proposed framework was carried out using 74 liver lesions annotated with a set of 18 VSTs from the RadLex ontology. A leave-one-patient-out cross-validation resulted in an average area under the ROC curve of 0.853 for predicting the presence of each VST. The proposed framework is expected to foster human-computer synergies for the interpretation of radiological images while using rotation-covariant computational models of VSTs to 1) quantify their local likelihood and 2) explicitly link them with pixel-based image content in the context of a given imaging domain.

Controversies in lung cancer screening

There remains an extensive debate over lung cancer screening, with lobbying for and against screening for very compelling reasons. The National Lung Screening Trial, International Early Lung Cancer Program, and other major screening studies favor screening with low-dose CT scans and have shown a reduction in lung cancer--specific mortality. The increasing incidence of lung cancer and the dismal survival rate for advanced disease despite improved multimodality therapy have sparked an interest in the implementation of national lung cancer screening. Concerns over imaging workflow, radiation dose, management of small nodules, overdiagnosis bias, lead-time and length-time bias, emerging new technologies, and cost-effectiveness continue to be debated. The authors address each of these issues as they relate to radiologic practice.