Some methodological questions concerning receiver operating characteristic (ROC) analysis as a method for assessing image quality in radiology

Disadvantages of using the area under the receiver operating characteristic curve to assess imaging tests: a discussion and proposal for an alternative approach

OBJECTIVES

The objectives are to describe the disadvantages of the area under the receiver operating characteristic curve (ROC AUC) to measure diagnostic test performance and to propose an alternative based on net benefit.

METHODS

We use a narrative review supplemented by data from a study of computer-assisted detection for CT colonography.

RESULTS

We identified problems with ROC AUC. Confidence scoring by readers was highly non-normal, and score distribution was bimodal. Consequently, ROC curves were highly extrapolated with AUC mostly dependent on areas without patient data. AUC depended on the method used for curve fitting. ROC AUC does not account for prevalence or different misclassification costs arising from false-negative and false-positive diagnoses. Change in ROC AUC has little direct clinical meaning for clinicians. An alternative analysis based on net benefit is proposed, based on the change in sensitivity and specificity at clinically relevant thresholds. Net benefit incorporates estimates of prevalence and misclassification costs, and it is clinically interpretable since it reflects changes in correct and incorrect diagnoses when a new diagnostic test is introduced.

CONCLUSIONS

ROC AUC is most useful in the early stages of test assessment whereas methods based on net benefit are more useful to assess radiological tests where the clinical context is known. Net benefit is more useful for assessing clinical impact.

KEY POINTS

• The area under the receiver operating characteristic curve (ROC AUC) measures diagnostic accuracy. • Confidence scores used to build ROC curves may be difficult to assign. • False-positive and false-negative diagnoses have different misclassification costs. • Excessive ROC curve extrapolation is undesirable. • Net benefit methods may provide more meaningful and clinically interpretable results than ROC AUC.

Multi-reader multi-case studies using the area under the receiver operator characteristic curve as a measure of diagnostic accuracy: systematic review with a focus on quality of data reporting

INTRODUCTION

We examined the design, analysis and reporting in multi-reader multi-case (MRMC) research studies using the area under the receiver-operating curve (ROC AUC) as a measure of diagnostic performance.

METHODS

We performed a systematic literature review from 2005 to 2013 inclusive to identify a minimum 50 studies. Articles of diagnostic test accuracy in humans were identified via their citation of key methodological articles dealing with MRMC ROC AUC. Two researchers in consensus then extracted information from primary articles relating to study characteristics and design, methods for reporting study outcomes, model fitting, model assumptions, presentation of results, and interpretation of findings. Results were summarized and presented with a descriptive analysis.

RESULTS

Sixty-four full papers were retrieved from 475 identified citations and ultimately 49 articles describing 51 studies were reviewed and extracted. Radiological imaging was the index test in all. Most studies focused on lesion detection vs. characterization and used less than 10 readers. Only 6 (12%) studies trained readers in advance to use the confidence scale used to build the ROC curve. Overall, description of confidence scores, the ROC curve and its analysis was often incomplete. For example, 21 (41%) studies presented no ROC curve and only 3 (6%) described the distribution of confidence scores. Of 30 studies presenting curves, only 4 (13%) presented the data points underlying the curve, thereby allowing assessment of extrapolation. The mean change in AUC was 0.05 (-0.05 to 0.28). Non-significant change in AUC was attributed to underpowering rather than the diagnostic test failing to improve diagnostic accuracy.

CONCLUSIONS

Data reporting in MRMC studies using ROC AUC as an outcome measure is frequently incomplete, hampering understanding of methods and the reliability of results and study conclusions. Authors using this analysis should be encouraged to provide a full description of their methods and results.

Exploration of analysis methods for diagnostic imaging tests: problems with ROC AUC and confidence scores in CT colonography

BACKGROUND

Different methods of evaluating diagnostic performance when comparing diagnostic tests may lead to different results. We compared two such approaches, sensitivity and specificity with area under the Receiver Operating Characteristic Curve (ROC AUC) for the evaluation of CT colonography for the detection of polyps, either with or without computer assisted detection.

METHODS

In a multireader multicase study of 10 readers and 107 cases we compared sensitivity and specificity, using radiological reporting of the presence or absence of polyps, to ROC AUC calculated from confidence scores concerning the presence of polyps. Both methods were assessed against a reference standard. Here we focus on five readers, selected to illustrate issues in design and analysis. We compared diagnostic measures within readers, showing that differences in results are due to statistical methods.

RESULTS

Reader performance varied widely depending on whether sensitivity and specificity or ROC AUC was used. There were problems using confidence scores; in assigning scores to all cases; in use of zero scores when no polyps were identified; the bimodal non-normal distribution of scores; fitting ROC curves due to extrapolation beyond the study data; and the undue influence of a few false positive results. Variation due to use of different ROC methods exceeded differences between test results for ROC AUC.

CONCLUSIONS

The confidence scores recorded in our study violated many assumptions of ROC AUC methods, rendering these methods inappropriate. The problems we identified will apply to other detection studies using confidence scores. We found sensitivity and specificity were a more reliable and clinically appropriate method to compare diagnostic tests.

Level of diagnostic confidence, accuracy, and reasons for mistakes in teleradiology for minor injuries

The objective of this study is to determine whether eliminating uncertainty in diagnosis improves accuracy in teleradiology for remote trauma management and to assess the correlation between the probable reason for the mistake and the level of confidence. An emergency physician interpreted 2133 radiological series transmitted from a community hospital to an emergency department using videoconferencing equipment. He marked his level of confidence as 1 = sure positive; 2 = fairly sure positive; 3 = unsure; 4 = fairly sure negative; 5 = sure negative. The emergency physician also entered free-text comments, e.g., feeling tired, to enable a better understanding of what was happening. The accuracy, sensitivity, and specificity were 97.3% (98.6%), 94.48% (96.72%), and 98.63% (99.42%), respectively. Figures in brackets represent the 93.5% of cases in which the level of confidence was graded as sure. Boredom and hurry were the main reasons identified for mistakes. Reducing uncertainty in diagnosis may improve the accuracy of screen interpretation. This first series must be reproducible by others before any general use of such systems can be made for primary diagnosis. American College of Radiology standards must be met.

Digital image management and communication in medicine

With the rapid development of digital imaging modalities in medicine, there is an increasing need for an efficient management and archival of medical images in digital form. Picture Archiving and Communication Systems (PACS) are becoming an essential component of medical imaging equipment, allowing for medical images to be accessed and stored directly in digital form. This paper describes a hospital-wide PACS currently under development at the University Hospital of Geneva, based on an open architecture, regrouping equipment from different vendors in a distributed topology. The image archival is organized in multiple locations geographically distributed in the hospital. The PACS database is fully integrated with the concurrent Radiology Information System (RIS) and Hospital Information System (HIS). A standard image storage format called the PAPYRUS format was developed for the storage of medical images from a variety of imaging modalities. To provide a more uniform user interface on a variety of different workstations, a common platform for image display and manipulation called OSIRIS was developed.

From multimodality digital imaging to multimedia patient record

The constant improvement in computer power and performance nowadays offers convenient and efficient means of manipulating images, graphics, and movies on off-the-shelf workstations. With this improvement the trend toward integration of multimodality clinical documents from patient records comes naturally. Images and graphs are certainly the most important part of the complementary information that must accompany the text and numerical data. It is, however, possible to include sounds and voice messages together with all the other modalities. In medicine that could certainly help conveying hart murmur or sounds, but could also offer a convenient way of including vocal messages and comments. These new possibilities will certainly change the way physicians use workstations for direct communication. The computer industry will soon offer means of interactive communication between remote users through computer workstations. That alone will open a completely new era in cooperative computing and remote consultation scenarios in medicine. More than the technology itself, a complete change in behavior and work habits can be expected in the medical community.

Overview of some methodological problems in assessment of PACS

The purpose of technology assessment of picture archiving and communications systems (PACS) is to establish the need for the technology, provide a measure of functionality and to establish the costs and benefits associated with the introduction of the system. Given concerns about the clinical acceptability of PACS, it is unlikely that radiologists will change from existing film based systems until a clear demonstration of costs and benefits has been performed. The major need at present is to quantify the benefits which may flow from the introduction of PACS system in a standard manner which can be accepted by all parties involved.