In computed tomography the Hounsfield Units (HU) are used as an indicator of the tissue type based on the linear attenuation coefficients of the tissue. HU accuracy is essential when this metric is used in any form to support diagnosis. In hybrid imaging, such as SPECT/CT and PET/CT, the information is used for attenuation correction (AC) of the emission images. This work investigates the HU accuracy of nodules of known size and HU, comparing diagnostic quality (DQ) images with images used for AC.
Ultrasound imaging of the breast is highly operator dependent. The amount of pressure applied with the transducer has a direct impact on the lesion visibility in breast ultrasound. The conspicuity index is a quantitative measure of lesion visibility, taking into account more parameters than standard measures that impact on lesion detection. This study assessed the conspicuity of lesions within a breast phantom using increased transducer compression in breast ultrasound.
Methods
A phantom was constructed of gelatine to represent adipose tissue, steel wool for glandular/blood vessels and silicone spheres to represent lesions, this meant that the lesions were also compressible, but less than the surrounding tissue. The phantom was imaged under increasing transducer compression. The conspicuity index was measured using the Conspicuity Index Software. The distance between the transducer surface and lesion surface was measured as an indication of increased compression.
Results
When moderate compression (17mm) was applied, the conspicuity index increased resulting in better visualisation of the silicone lesions. However, with increased compression the conspicuity index decreased.
New work to be presented
The conspicuity index has never been demonstrated in ultrasound imaging before. This is preliminary phantom work to demonstrate the impact of increased transducer compression on quantitative lesion visibility assessment.
Conclusion
The compression applied should be considered for optimum visualisation, as excessive pressure decreases conspicuity. However, further work needs to be conducted in order to consider other factors, such as density of the breast and lesion location, for a better understanding of the effect of compression on the visualisation of the lesion. A human study is planned.
Tube current modulation is a method employed in the use of CT in an attempt to optimize radiation dose to the patient. The acceptable noise (noise index) can be varied, based on the level of optimization required; higher accepted noise reduces the patient dose. Recent research [1] suggests that measuring the conspicuity index (C.I.) of focal lesions within an image is more reflective of a clinical reader's ability to perceive focal lesions than traditional physical measures such as contrast to noise (CNR) and signal to noise ratio (SNR). Software has been developed and validated to calculate the C.I. in DICOM images. The aim of this work is assess the impact of tube current modulation on conspicuity index and CTDIvol, to indicate the benefits and limitations of tube current modulation on lesion detectability. Method An anthropomorphic chest phantom was used “Lungman” with inserted lesions of varying size and HU (see table below) a range of Hounsfield units and sizes were used to represent the variation in lesion Hounsfield units found. This meant some lesions had negative Hounsfield unit values.
A novel software programme and associated Excel spreadsheet has been developed to provide an objective measure of the expected visual detectability of focal abnormalities within DICOM images. ROIs are drawn around the abnormality, the software then fits the lesion using a least squares method to recognize the edges of the lesion based on the full width half maximum. 180 line profiles are then plotted around the lesion, giving 360 edge profiles.
Purpose: To investigate the dose saving potential of iterative reconstruction (IR) in a computed tomography (CT) examination of the thorax.
Materials and Methods: An anthropomorphic chest phantom containing various configurations of simulated lesions (5, 8, 10 and 12mm; +100, -630 and -800 Hounsfield Units, HU) was imaged on a modern CT system over a tube current range (20, 40, 60 and 80mA). Images were reconstructed with (IR) and filtered back projection (FBP). An ATOM 701D (CIRS, Norfolk, VA) dosimetry phantom was used to measure organ dose. Effective dose was calculated. Eleven observers (15.11±8.75 years of experience) completed a free response study, localizing lesions in 544 single CT image slices. A modified jackknife alternative free-response receiver operating characteristic (JAFROC) analysis was completed to look for a significant effect of two factors: reconstruction method and tube current. Alpha was set at 0.05 to control the Type I error in this study.
Results: For modified JAFROC analysis of reconstruction method there was no statistically significant difference in lesion detection performance between FBP and IR when figures-of-merit were averaged over tube current (F(1,10)=0.08, p = 0.789). For tube current analysis, significant differences were revealed between multiple pairs of tube current settings (F(3,10) = 16.96, p<0.001) when averaged over image reconstruction method.
Conclusion: The free-response study suggests that lesion detection can be optimized at 40mA in this phantom model, a measured effective dose of 0.97mSv. In high-contrast regions the diagnostic value of IR, compared to FBP, is less clear.
Aim: To optimize automated classification of radiological errors during lung nodule detection from chest radiographs
(CxR) using a support vector machine (SVM) run on the spatial frequency features extracted from the local background
of selected regions. Background: The majority of the unreported pulmonary nodules are visually detected but not
recognized; shown by the prolonged dwell time values at false-negative regions. Similarly, overestimated nodule
locations are capturing substantial amounts of foveal attention. Spatial frequency properties of selected local
backgrounds are correlated with human observer responses either in terms of accuracy in indicating abnormality position
or in the precision of visual sampling the medical images. Methods: Seven radiologists participated in the eye tracking
experiments conducted under conditions of pulmonary nodule detection from a set of 20 postero-anterior CxR. The most
dwelled locations have been identified and subjected to spatial frequency (SF) analysis. The image-based features of
selected ROI were extracted with un-decimated Wavelet Packet Transform. An analysis of variance was run to select SF
features and a SVM schema was implemented to classify False-Negative and False-Positive from all ROI. Results: A
relative high overall accuracy was obtained for each individually developed Wavelet-SVM algorithm, with over 90%
average correct ratio for errors recognition from all prolonged dwell locations. Conclusion: The preliminary results
show that combined eye-tracking and image-based features can be used for automated detection of radiological error
with SVM. The work is still in progress and not all analytical procedures have been completed, which might have an
effect on the specificity of the algorithm.
Aim: To investigate the impact on visual sampling strategy and pulmonary nodule recognition of image-based properties
of background locations in dwelled regions where the first overt decision was made. . Background: Recent studies in
mammography show that the first overt decision (TP or FP) has an influence on further image reading including the
correctness of the following decisions. Furthermore, the correlation between the spatial frequency properties of the local
background following decision sites and the first decision correctness has been reported. Methods: Subjects with
different radiological experience were eye tracked during detection of pulmonary nodules from PA chest radiographs.
Number of outcomes and the overall quality of performance are analysed in terms of the cases where correct or incorrect
decisions were made. JAFROC methodology is applied. The spatial frequency properties of selected local backgrounds
related to a certain decisions were studied. ANOVA was used to compare the logarithmic values of energy carried by
non redundant stationary wavelet packet coefficients. Results: A strong correlation has been found between the number
of TP as a first decision and the JAFROC score (r = 0.74). The number of FP as a first decision was found negatively
correlated with JAFROC (r = -0.75). Moreover, the differential spatial frequency profiles outcomes depend on the first
choice correctness.
This study aimed to measure the sound levels in Irish x-ray departments. The study then established whether these levels
of noise have an impact on radiologists performance
Noise levels were recorded 10 times within each of 14 environments in 4 hospitals, 11 of which were locations where
radiologic images are judged. Thirty chest images were then presented to 26 senior radiologists, who were asked to
detect up to three nodular lesions within 30 posteroanterior chest x-ray images in the absence and presence of noise at
amplitude demonstrated in the clinical environment.
The results demonstrated that noise amplitudes rarely exceeded that encountered with normal conversation with the
maximum mean value for an image-viewing environment being 56.1 dB. This level of noise had no impact on the ability
of radiologists to identify chest lesions with figure of merits of 0.68, 0.69, and 0.68 with noise and 0.65, 0.68, and 0.67
without noise for chest radiologists, non-chest radiologists, and all radiologists, respectively. the difference in their
performance using the DBM MRMC method was significantly better with noise than in the absence of noise at the 90%
confidence interval (p=0.077). Further studies are required to establish whether other aspects of diagnosis are impaired
such as recall and attention and the effects of more unexpected noise on performance.
We are unsure about what information is extracted from an image to allow a decision about pathology to be made. Our
knowledge of the interplay between top down processing or bottom up, local or global perception, perceptual or
cognitive processes is uncertain. However recent research has emphasised the importance of the global or holistic look in
medical image perception in which recognition of abnormalities precedes search. Reverse Hierarchy Theory [1] is a
useful general theory that helps to explain this. It also enables us to understand what information is extracted from an
image and how this relates to expertise. Essentially the theory states that perceptual learning begins at high levels areas
and progresses down to lower level areas when better signal to noise is needed. So perceptual learning, defined as an
improvement in sensory abilities after training, stems from a gradual top down guided increase in usability of first high
then lower level task relevant information. Evaluation of the scan paths of groups of observers with different levels of
expertise when undertaking a lung nodule perception task seems to be consistent with the theory. Experts' perception is
generally immediate and holistic suggesting high level representations whereas those with an intermediate level of
expertise tend to be more variable in their scan paths. Interestingly naïve observers have eye tracking metrics that are
more similar to experts suggesting they take a common sense approach using perceptual skills we all have as they lack
experience in being able to access the low level information from the chest radiograph.
Aim: The goal of the study is to determine the spatial frequency characteristics at locations in the image of overt and covert observers' decisions and find out if there are any similarities in different observers' groups: the same radiological experience group or the same accuracy scored level. Background: The radiological task is described as a visual searching decision making procedure involving visual perception and cognitive processing. Humans perceive the world through a number of spatial frequency channels, each sensitive to visual information carried by different spatial frequency ranges and orientations. Recent studies have shown that particular physical properties of local and global image-based elements are correlated with the performance and the level of experience of human observers in breast cancer and lung nodule
detections. Neurological findings in visual perception were an inspiration for wavelet applications in vision research
because the methodology tries to mimic the brain processing algorithms. Methods: The wavelet approach to the set of
postero-anterior chest radiographs analysis has been used to characterize perceptual preferences observers with different
levels of experience in the radiological task. Psychophysical methodology has been applied to track eye movements over the image, where particular ROIs related to the observers' fixation clusters has been analysed in the spaces frame by Daubechies functions. Results: Significance differences have been found between the spatial frequency characteristics at the location of different decisions.
Purpose
Detection of low-contrast details is highly dependent on the adaptation state of the eye. It is important therefore that the
average luminance of the observer's field of view (FOV) matches those of softcopy radiological images. This study
establishes the percentage of FOV filled by workstations at various viewing distances.
Methods
Five observers stood at viewing distances of 20, 30 and 50cm from a homogenous white surface and were instructed to
continuously focus on a fixed object at a height appropriate level. A dark indicator was held at this object and then
moved steadily until the observer could no longer perceive it in his/her peripheral vision. This was performed at 0°, 90°,
180° and 270° clockwise from the median sagittal plane. Distances were recorded, radii calculated and observer and
mean FOV areas established. These values were then compared with areas of typical high and low specification
workstations.
Results
Individual and mean FOVs were 7660, 15463 and 30075cm2 at viewing distances of 20, 30 and 50cm respectively. High
and low specification monitors with respective areas of 1576.25 and 921.25cm2 contributed between 5 to 21% and 3 to
12% respectively to the total FOV depending on observer distance. Limited inter-observer variances were noted.
Conclusions
Radiology workstations typically comprise between only 3 and 21% of the observer's FOV. This demonstrates the
importance of measuring ambient light levels and surface reflection coefficients in order to maximise adaptation and
observer's perception of low contrast detail and minimise eye strain.
Aim: The study aims to help our understanding of the relationship between physical characteristics of local and global
image features and the location of visual attention by observers. Background: Neurological visual pathways are
specified at least in part by particular spatial frequency ranges at different orientations. High spatial frequencies, which
carry the information of local perturbations like edges, are assembled mainly by foveal vision, whereas peripheral vision
provides more global information coded by low frequencies. Recent visual-search studies in mammography (C Mello-Thoms et al) have shown that observers allocate visual attention to regions of the image depending on; i) spatial
frequency characteristics of regions that capture attention and ii) the level of experience of the observer. Both aspects are
considered in this study. Methods: A spatial frequency analysis of postero-anterior (PA) chest images containing
pulmonary nodules has been performed by wavelet packet transforms at different scales. This image analysis has
provided regional physical information over the whole image field on locations both with nodules present and nodules
absent. The relationship between such properties as spatial frequency, orientation, scales, contrast, and phase of localised
perturbations has been compared with eye-tracked search strategies and decision performance of observers with different
levels of expertise. Results: The work is in progress and the results of this initial stage of the project will be presented
with a critical appraisal of the methods used.
We report a study that investigated whether experienced and inexperienced radiographers benefit from knowing
where another person looked during pulmonary nodule detection. Twenty-four undergraduate radiographers (1 year
of experience) and 24 postgraduate radiographers (5+ years of experience) searched 42 chest x-rays for nodules and
rated how confident they were in their decisions. Eye movements were also recorded. Performance was compared
across three within-participant conditions: (1) free search - where radiographers could identify nodules as normal;
(2) image preview - where radiographers were first shown each chest x-ray for 20 seconds before they could then
proceed to mark the location of any nodules; and (3) eye movement preview - which was identical to image preview
except that the 20 second viewing period displayed an overlay of the real-time eye movements of another
radiographer's scanpath for that image. For this preview condition half of each group were shown where a novice
radiographer looked, and the other half were shown where an experienced radiologist looked. This was not made
known to the participants until after the experiment. Performance was assessed using JAFROC analysis. Both groups
of radiographers performed better in the eye movement preview condition compared with the image preview or free
search conditions, with inexperienced radiographers improving the most. We discuss our findings in terms of the
task-specific information interpreted from eye movement previews, task difficulty across images, and whether it
matters if radiographers are previewing the eye movements of an expert or a novice.
Traditional diagnostic modalities have been, for the most part, static two-dimensional images displayed on film
or computer screen. More recent diagnostic modalities are solely computer-based and consist of large data-sets
of multiple images. Image perception and visual search using these new modalities are complicated by the need
to interact with the computer in order to navigate through the data. This paper reports the late-breaking results
from two small studies into visual search within two types of CT Colonography (CTC) visualisations. The twelve
novice observers in the study were taking part in a week-long course in CTC and were tested at the beginning
and end of the course. A number of expert observers were also recorded. The two visualisations used in the
study were 2D axial view and 3D colon fly-through. In both cases, searching was performed by inspecting the
colon wall, but by two distinct mechanisms. The first study recorded observer eye-gaze and image navigation in
a CTC axial view. The search strategy was to follow the lumen of the colon and detect abnormalities in the colon
wall. The observer used the physical computer interface to navigate through the set of axial images to perform
this task. The 3D fly-through study recorded observer eye-gaze whilst watching a recording of a computed flight
through the colon lumen. Unlike the axial view there was no computer control, so inspection of the colon surface
was dictated by the speed of flight through the colon.
In a previously reported study we demonstrated that expert performance can decline following perceptual feedback of
eye movements in the relatively simple radiological task of wrist fracture detection. This study was carried out to
determine if the same effect could be observed using a more complicated radiological task of identifying lung nodules on
chest radiographs. Four groups (n=10 in each group) of observers with different levels of expertise were tested. The
groups were naïve observers, level 1 radiography students, level 2 radiography students and experts. Feedback was
presented to the observers in the form of their scan paths and fixations. Half the observers had feedback and half had no
perceptual feedback. JAFROC analysis was used to measure observer performance. A repeated measures ANOVA was
carried out. There was no significant effect between the pre and post "no feedback" condition. There was a significant
difference between the pre and post "feedback" condition with a significant improvement following feedback
(F(1,16)=6.6,p = 0.021). Overall the mean percentage improvement was small of 3.3%, with most of the improvement
due to the level 1 group where the percentage increase in the figure of merit (FOM) was 8.4% and this was significant
(p<0.05).
Eye tracking metrics indicate that the expert and naïve observers were less affected by feedback or a second look
whereas there were mixed results between the level 1 and level 2 students possibly reflecting the different search
strategies used. Perceptual feedback may be beneficial for those early in their training.
Clinical radiological judgments are increasingly being made on softcopy LCD monitors. These monitors are found throughout the hospital environment in radiological reading rooms, outpatient clinics and wards. This means that ambient lighting where clinical judgments from images are made can vary widely. Inappropriate ambient lighting has several deleterious effects: monitor reflections reduce contrast; veiling glare adds brightness; dynamic range and detectability of low contrast objects is limited. Radiological images displayed on LCDs are more sensitive to the impact of inappropriate ambient lighting and with these devices problems described above are often more evident.
The current work aims to provide data on optimum ambient lighting, based on lesions within chest images. The data provided may be used for the establishment of workable ambient lighting standards. Ambient lighting at 30cms from the monitor was set at 480 Lux (office lighting) 100 Lux (WHO recommendations), 40 Lux and <10 Lux. All monitors were calibrated to DICOM part 14 GSDF.
Sixty radiologists were presented with 30 chest images, 15 images having simulated nodular lesions of varying subtlety and size. Lesions were positioned in accordance with typical clinical presentation and were validated radiologically. Each image was presented for 30 seconds and viewers were asked to identify and score any visualized lesion from 1-4 to indicate confidence level of detection. At the end of the session, sensitivity and specificity were calculated. Analysis of the data suggests that visualization of chest lesions is affected by inappropriate lighting with chest radiologists demonstrating greater ambient lighting dependency. JAFROC analyses are currently being performed.
We report on the development of a novel software tool for the simulation of chest lesions. This software tool was developed for use in our study to attain optimal ambient lighting conditions for chest radiology. This study involved 61 consultant radiologists from the American Board of Radiology. Because of its success, we intend to use the same tool for future studies. The software has two main functions: the simulation of lesions and retrieval of information for ROC (Receiver Operating Characteristic) and JAFROC (Jack-Knife Free Response ROC) analysis. The simulation layer operates by randomly selecting an image from a bank of reportedly normal chest x-rays. A random location is then generated for each lesion, which is checked against a reference lung-map. If the location is within the lung fields, as derived from the lung-map, a lesion is superimposed. Lesions are also randomly selected from a bank of manually created chest lesion images. A blending algorithm determines which are the best intensity levels for the lesion to sit naturally within the chest x-ray. The same software was used to run a study for all 61 radiologists. A sequence of images is displayed in random order. Half of these images had simulated lesions, ranging from subtle to obvious, and half of the images were normal. The operator then selects locations where he/she thinks lesions exist and grades the lesion accordingly. We have found that this software was very effective in this study and intend to use the same principles for future studies.
Purpose
The aim of the work is to determine the optimum ambient lighting conditions for viewing softcopy radiological images on LCD.
Materials and Methods
The study measured the diagnostic performance of observers viewing images on liquid crystal display (LCD) monitor under different ambient lighting conditions: 480, 100, 40, 25 and 7lux. An ROC analysis was performed as a measure of diagnostic performance. A set of 30 postero-anterior wrist images was used, 15 of which had fractures present the remainder were normal. These were evaluated by 79 American Board of Radiology certified experienced Radiologists.
Results
The observers performed better at 40 and 25lux compared with 480 and 100 lux. At 7lux, the observers' performance was generally similar to that at 480 and 100lux.
Conclusion
Using the previously recommended ambient lighting levels of 100lux resulted in no improvement over typical office lighting of 480lux. Lower ambient lighting levels ranging from 40-25lux improves diagnostic performance over higher levels. Lowering ambient lighting to 7lux (almost complete darkness apart from the light emanating from the monitor) reduces diagnostic performance to a level equal to that of typical office lighting. It is clearly important to control ambient lighting to ensure that diagnostic performance is maximized.
Four observer groups with different levels of expertise were tested to determine the effect of feedback on eye movements and accuracy whilst performing a simple radiological task. The observer groups were 8 experts, 9 year 1 radiography students, 9 year 3 radiography students, and 10 naive observers (psychology students). The task was fracture detection in the wrist. A test bank of 32 films was compiled with 14 normals, 6 grade 1 fractures (subtle appearance), 6 grade 2 fractures, and 6 grade 3 fractures (obvious appearance). Eye tracking was carried out on all observers to demonstrate differences in visual activity. Observers were asked to rate their confidence in their decision on a ten point scale. Feedback was presented to the observers in the form of circles displayed on the film where fixations had occurred, the size of which was proportional to the length of fixation. Observers were asked to repeat their decision rating. Accuracy was determined by ROC analysis and the area under the curve (AUC). In two groups, the novices and first year radiography students, the feedback resulted in no significant difference in the AUC. In the other two groups, experts (p = 0.002) and second year radiography students (p = 0.031), feedback had a negative effect on performance. The eye tracking parameters were measured for all subjects and compared. This is work in progress, but initial analysis of the data suggests that in a simple radiological task such as fracture detection, where search is very limited, feedback by encouraging observers to look harder at the image can have a negative effect on image interpretation performance, however for the novice feedback is beneficial as post feedback eye-tracking parameters measured more closely matched those of the experts.
This paper describes a software framework and analysis tool to support the collection and analysis of eye movement and perceptual feedback data for a variety of diagnostic imaging modalities. The framework allows the rapid creation of experiment software that can display a collection of medical images of a particular modality, capture eye trace data, and record marks added to an image by the observer, together with their final decision. There are also a number of visualisation techniques for the display of eye trace information. The analysis tool supports the comparison of individual eye traces for a particular observer or traces from multiple observers for a particular image. Saccade and fixation data can be visualised, with user control of fixation identification functions and properties. Observer markings are displayed, and predefined regions of interest are supported. The software also supports some interactive and multi-image modalities. The analysis tool includes a novel visualisation of scan paths across multi-image modalities. Using an exploded 3D view of a stack of MRI scan sections, an observer's scan path can be shown traversing between images, in addition to inspecting them.
Twenty-four volunteer observers were divided into groups of eight radiologists, eight radiographers and eight novices to carry out a pulmonary nodule detection task on a test bank of 120 digitized PA chest radiographs. The eight radiographers were tested twice: before and after a six-month training program in interpretation of the adult chest radiograph. During each test session the observers eye movements were tracked. Data on the observers' decisions through AFROC methodology were correlated to their eye-movement and fixation patterns. False negative error-rates were recorded as 41% for the radiologists, 45% for the novices, 47% for the radiographers before training and 42% for the radiographers after training. The errors were sub-classified into search, recognition and decision errors depending on the duration of the fixation-time for each faulty response. Errors due to satisfaction of search were determined from images with multiple nodules. Differences between the groups were shown. Errors due to inefficient search were in the minority for all the observer groups and the dominant cause of unreported nodules was incorrect decision-making. True negative decisions from all observers were associated with shorter fixation times than false negative decisions. No correct negative decisions were made after fixations exceeding three seconds.
Four observer groups with different levels of expertise were tested in an investigation into the comparative nature of expert performance. The radiological task was the detection and localization of significant pulmonary nodules in postero-anterior vies of the chest in adults. Three test banks of 40 images were used. The observer groups were 6 experienced radiographers prior to a six month training program in chest image interpretation, the same radiographers after their tr4aining program, and 6 fresher undergraduate radiography students. Eye tracking was carried out on all observers to demonstrate differences in visual activity and nodule detection performance was measured with an AFROC technique. Detection performances of the four groups showed the radiologists and radiographers after training were measurably superior at the task. The eye-tracking parameters saccadic length, number of fixations visual coverage and scrutiny timer per film were measured for all subjects and compared. The missed nodules fixated and not fixated were also determined for the radiologist group. Results have shown distinct stylistic differences in the visual scanning strategies between the experienced and inexperienced observers that we believe can be generalized into a description of characteristics of expert versus non-expert performance. The findings will be used in the educational program of image interpretation for non-radiology practitioners.
KEYWORDS: Visualization, Eye, Chest, Signal to noise ratio, Lung, Signal attenuation, Optical inspection, Computer simulations, Medical imaging, Chest imaging
A test bank of verified chest radiographs was compiled for visual search experiments. The purpose was to investigate human performance in the detection of significant pulmonary nodules. Synthesized nodules supplemented native lesions. The distribution of all the lesions in the lung fields was consistent with the naturally occurring locations of these features. A measure of the physical characteristics of the lesions was derived in order to approximate the conspicuity of the synthetic to the natural nodules. The measure of conspicuity was given as (chi) =Tan(theta-1)S/N where (theta) is the maximum slope angle to the edge of the lesion profile, S is the mean pixel value of the lesion profile taken in four orientations, and N is the mean background pixel value taken in four orientations over one lesion dimension adjacent to the lesion. The variation in (chi) for each of the 81 lesions (46 natural and 35 synthetic) was plotted against SNR and edge angle. The influence of edge angle on the resulting (chi) values was more powerful than SNR for all the lesions in this experiment. Although there was an overall significant difference in (chi) values (p=0.015), observers were unable to distinguish synthetic from native lesions. Observer performance in nodule detection was measured by AFROC and supplemented with visual search recording. Correlation of AFROC scores and the (chi) values has shown no overall relationship (R2=0.0452) and this surprising result may be partly explained through inspection of the visual search recordings.
Research concerning disease prevalence has inferred that indices of observer performance become, in part, a function of predetermined prevalence. The cause of this modified performance and decision-making is not fully understood, although the alteration of the criterion level of the observer may be a feature. Novice radiography students were randomly assigned to one of three digitised test banks of 72 wrist images. Test bank A, B and C represented a fracture prevalence of 50%, 83% and 22% respectively. Half of the observers from each group were made aware of the prevalence of their respective test bank. Observers recorded their decisions on an operator rating scale. Results showed significant differences in overall Az between the 50% and 83% prevalence sets (p equals 0.04) and the 50% and 22% prevalence sets (p equals 0.005). Knowledge of the prevalence influenced both sensitivity and specificity values at the 83% prevalence level (p equals 0.03 and 0.02) but not at the lower levels. For test bank A sensitivity was 87%; specificity 53%; Az 0.80, test bank B sensitivity 81%; specificity 48%; Az 0.71 and test bank C sensitivity 85%; specificity 43%; Az 0.68. Analysis of the eye movement patterns of observers under conditions of varying prevalence is in progress.
We investigated the decision making performance of trained radiographers, novice radiographers and a neural network in the detection of fractures. Ground truth was established by the independent agreement of experienced radiologists for 740 single view digitized radiographs of the wrist. The images were categorized into negatives and positives; 520 of these were used to train the back propagation, three layer neural network in a supervised mode, and the remainder were used to create a test bank. The test was presented to 20 novice observers, 12 experienced radiographers trained in the detection of skeletal trauma and then to the trained neural network. ROC Az values for all the decision makers were not significantly different (p > 0.1) but there were significant differences in the values of True Positive and True Negative Fractions. The neural network showed a greater aptitude for distinguishing the normals. By filtering the neural net decisions through the human data we simulated the effect of assisted reporting. Results suggest that if fracture prevalence is very low in a population, a neural network demonstrating high specificity may have utility in reducing the number of images which must be reviewed by human experts.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.