Prompting in Mammography: How Good Must Prompt Generators Be?

Astley, Susan M.; Zwiggelaar, Reyer; Wolstenholme, Chris; Davies, Karen; Parr, Tim C.; Taylor, Christopher J.

doi:10.1007/978-94-011-5318-8_56

Cited by 10 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[8]. This study could lead to a development of a new evaluation metric which could be used to estimate the degree of certainty of the system, hence provides positive potential impacts of CAD systems [8,17]. This study indicates that using A and AU C in conjunction with confidence measure to provide a more transparent representation of the actual reliability of CAD systems which is similar to our previous study [18].…”

supporting

confidence: 77%

Confidence Analysis for Breast Mass Image Classification

Rampun

Wang

Scotney

et al. 2018

2018 25th IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Computer-aided diagnosis (CAD) has great potential in providing real benefits to doctors and patients. Recent studies have, however, found lack of trust in CAD by radiologists in clinical diagnostic decision making. One of the main reasons is the lack of an appropriate confidence measure. This paper presents the first-ever study of classification confidence in the context of breast mass classification. We evaluated 11 state-of-the-art classification algorithms on breast mass image data using their confidence of classification metric, in addition to other standard evaluation metrics including accuracy and area under the curve (ROC). Experimental results show that although most classifiers produced very similar results with less than 2% difference in terms of accuracy and ROC, their performances are significantly different in terms of confidence levels. We suggest that the confidence measure should be used in conjunction with the existing performance metrics such as accuracy and ROC.

show abstract

supporting

confidence: 77%

Confidence Analysis for Breast Mass Image Classification

Rampun

Wang

Scotney

et al. 2018

2018 25th IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, when prompts are used to direct attention to areas of interest, lesions may still be missed. This may be due to the CAD algorithm missing areas of abnormality, or the distraction to the reader, caused by high levels of false prompts (Astley et al, 1998), or even human reader error. In order to investigate why lesions are missed when using CAD, studies have been carried out to examine the visual search patterns of radiologists using CAD systems.…”

Section: Introductionmentioning

confidence: 95%

The effect of novel prompts upon radiologists" visual search of mammograms

et al. 2004

View full text Add to dashboard Cite

Prompting is utilised in CAD systems to draw attention to regions of potential abnormality within screening mammograms. The benefit of such systems is under debate. Our previous research found that radiologists' visual search patterns were significantly altered when mammographic prompts were displayed. Visual attention concentrated upon prompted areas, with significantly less attention to unprompted regions. Additionally, prompts caused a reduction in the amount of bi-lateral visual comparisons between the two breasts. Current CAD systems use a variety of prompts (e.g. circle and triangle) that appear incongruous to the mammogram and may inadvertently detract attention from unprompted regions. The aim of this experiment was to determine whether attentional focus would continue when using subtle prompts, without resulting in the insufficient search of unprompted areas.A series of paired medio lateral-oblique view mammographic cases were presented to participants on a monitor. Images were presented as 'unprompted' and 'prompted'-using various methods to highlight potentially abnormal areas. These included typical prompt shapes and also more novel prompts (e.g. altered brightness and colour). Participants were instructed to scan the images as they normally would when screening for abnormalities and to indicate their confidence that an abnormality was present, using a five-point scale. Eye movements were also recorded during the task.Results demonstrated that visual attention was drawn to the prompted regions. However, the potentially negative influence of prompts upon normal visual search patterns within mammograms was found to be less pronounced in conditions containing novel prompts. By comparing differing prompts during screening it was possible to establish their consequent impact upon visual search patterns. This research contributes to the establishment of optimal prompt displays in soft copy systems.

show abstract

“…As a result, computer-based systems cannot be used to identify films that are unequivocally normal, and a skilled human interpreter must make the final decision on every film. Prompting, in which the areas detected by the computer are used to draw the radiologist's attention to the corresponding regions in the original films, has the potential to improve an individual's detection performance, provided that the prompts are sufficiently accurate [5]. It allows radiologists to exploit some of the benefits of computer-based analysis such as reproducibility and objectivity, without making unrealistic demands on algorithm performance, because it neither requires a complete suite of algorithms nor perfectly sensitive prompts.…”

Section: Full Textmentioning

confidence: 99%

“…In particular, studies have shown that the number and distribution of false prompts are critical to the success of the process [5,7]. In most commercial systems, in which sensitivity to abnormalities is seen as an important selling point, false prompts are the price one has to pay.…”

Section: Full Textmentioning

confidence: 99%

Computer-assisted mammographic imaging

Boggis¹,

Astley²

2000

Breast Cancer Res

View full text Add to dashboard Cite

Computer-assisted mammography imaging comprises computer-based analysis of digitized images resulting in prompts aiding mammographic interpretation and computerized stereotactic localization devices which improve location accuracy. The commercial prompting systems available are designed to draw attention to mammographic abnormalities detected by algorithms based on symptomatic practise in North America. High sensitivity rates are important commercially but result in increased false prompt rates, which are known to distract radiologists. A national shortage of breast radiologists in the UK necessitates evaluation of such systems in a population breast screening programme to determine effectiveness in increasing cancer detection and feasibility of implementation.

show abstract

Prompting in Mammography: How Good Must Prompt Generators Be?

Cited by 10 publications

References 5 publications

Confidence Analysis for Breast Mass Image Classification

Confidence Analysis for Breast Mass Image Classification

The effect of novel prompts upon radiologists" visual search of mammograms

Computer-assisted mammographic imaging

Contact Info

Product

Resources

About