Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Computer-aided detection and novel mammography imaging techniques
KTH, School of Engineering Sciences (SCI), Physics.
2006 (English)Doctoral thesis, comprehensive summary (Other scientific)
Abstract [en]

This thesis presents techniques constructed to aid the radiologists in detecting breast cancer, the second largest cause of cancer deaths for western women. In the first part of the thesis, a computer-aided detection (CAD) system constructed for the detection of stellate lesions is presented. Different segmentation methods and an attempt to incorporate contra-lateral information are evaluated.

In the second part, a new method for evaluating such CAD systems is presented based on constructing credible regions for the number of false positive marks per image at a certain desired target sensitivity. This method shows that the resulting regions are rather wide and this explains some of the difficulties encountered by other researchers when trying to compare CAD algorithms on different data sets. In this part an attempt to model the clinical use of CAD as a second look is also made and it shows that applying CAD in sequence to the radiologist in a routine manner, without duly altering the decision criterion of the radiologist, might very well result in suboptimal operating points.

Finally, in the third part two dual-energy imaging methods optimized for contrast-enhanced imaging of breast tumors are presented. The first is based on applying an electronic threshold to a photon-counting digital detector to discriminate between high- and low-energy photons. This allows simultaneous acquisition of the high- and low-energy images. The second method is based on the geometry of a scanned multi-slit system and also allows single-shot contrast-enhanced dual-energy mammography by filtering the x-ray beam that reaches different detector lines differently.

Place, publisher, year, edition, pages
Stockholm: KTH , 2006.
Series
Trita-FYS, ISSN 0280-316X ; 2006:06
Keyword [en]
computer-aided detection, FROC, mammography, optimal operating points, single-shot dual-energy imaging
National Category
Radiology, Nuclear Medicine and Medical Imaging
Identifiers
URN: urn:nbn:se:kth:diva-3861ISBN: 91-7178-274-5 (print)OAI: oai:DiVA.org:kth-3861DiVA: diva2:9754
Public defence
2006-03-10, Sal F3, Lindstedtsvägen 26, Stockholm, 10:00
Opponent
Supervisors
Note
QC 20100819Available from: 2006-03-03 Created: 2006-03-03 Last updated: 2010-08-19Bibliographically approved
List of papers
1. Implications of unchanged detection criteria with CAD as second reader of mammograms
Open this publication in new window or tab >>Implications of unchanged detection criteria with CAD as second reader of mammograms
2006 (English)In: Medical physics (Lancaster), ISSN 0094-2405, Vol. 33, no 4, 922-929 p.Article in journal (Refereed) Published
Abstract [en]

In this paper we address the use of computer-aided detection (CAD) systems as second readers in mammography. The approach is based on Bayesian decision theory and its implication for the choice of optimal operating points. The choice of a certain operating point along an ROC curve corresponds to a particular tradeoff between false positives and missed cancers. By minimizing a total risk function given this tradeoff, we determine optimal decision thresholds for the radiologist and CAD system when CAD is used as a second reader. We show that under very general circumstances, the performance of the sequential system is improved if the decision threshold of the latent human decision variable is increased compared to what it would have been in the absence of the CAD system. This means that an initial stricter decision criterion should be applied by the radiologist when CAD is used as a second reader than otherwise. First and foremost, the results in this paper should be interpreted qualitatively, but an attempt is made at quantifying the effect by tuning the model to a prospective study evaluating the use of CAD as a second reader. By making some necessary and plausible assumptions, we are able to estimate the effect of the resulting suboptimal operating point. In this study of 12 860 women, we estimate that a 15% reduction in callbacks for masses could have been achieved with only about a 1.5% relative decrease in sensitivity compared to that without using a stricter initial criterion by the radiologist. For microcalcifications the corresponding values are 7% and 0.2%. (c) 2006 American Association of Physicists in Medicine.

Keyword
CAD; mammography; second reader; decision theory; optimal operating points
National Category
Natural Sciences
Identifiers
urn:nbn:se:kth:diva-5395 (URN)10.1118/1.2179148 (DOI)000237038300013 ()2-s2.0-33645510446 (Scopus ID)
Note
QC 20100819Available from: 2006-03-03 Created: 2006-03-03 Last updated: 2017-11-21Bibliographically approved
2. Estimation and Comparison of CAD System Performance in Clinical Settings
Open this publication in new window or tab >>Estimation and Comparison of CAD System Performance in Clinical Settings
2005 (English)In: Academic Radiology, ISSN 1076-6332, E-ISSN 1878-4046, Vol. 12, no 6, 687-694 p.Article in journal (Refereed) Published
Abstract [en]

Rationale and Objectives. Computer-aided detection (CAD) systems are frequently compared using free-response receiver operating characteristic (FROC) curves. While there are ample statistical methods for comparing FROC curves, when one is interested in comparing the outcomes of 2 CAD systems applied in a typical clinical setting, there is the additional matter of correctly determining the system operating point. This article shows how the effect of the sampling error on determining the correct CAD operating point can be captured. By incorporating this uncertainty, a method is presented that allows estimation of the probability with which a particular CAD system performs better than another on unseen data in a clinical setting.

Materials and Methods. The distribution of possible clinical outcomes from 2 artificial CAD systems with different FROC curves is examined. The sampling error is captured by the distribution of possible system thresholds of the classifying machine that yields a specified sensitivity. After introducing a measure of superiority, the probability of one system being superior to the other can be determined.

Results. It is shown that for 2 typical mammography CAD systems, each trained on independent representative datasets of 100 cases, the FROC curves must be separated by 0.20 false positives per image in order to conclude that there is a 90% probability that one is better than the other in a clinical setting. Also, there is no apparent gain in increasing the size of the training set beyond 100 cases.

Discussion. CAD systems for mammography are modeled for illustrative purposes, but the method presented is applicable to any computer-aided detection system evaluated with FROC curves. The presented method is designed to construct confidence intervals around possible clinical outcomes and to assess the importance of training set size and separation between FROC curves of systems trained on different datasets.

Keyword
CAD; performance evaluation; sampling error; confidence interval; mammography; operating point estimation
National Category
Natural Sciences
Identifiers
urn:nbn:se:kth:diva-5394 (URN)10.1016/j.acra.2005.02.005 (DOI)000229717100004 ()2-s2.0-20344405978 (Scopus ID)
Note
QC 20100819Available from: 2006-03-03 Created: 2006-03-03 Last updated: 2017-11-21Bibliographically approved
3. Use of Quadrature Filters for Detection of Stellate Lesions in Mammograms
Open this publication in new window or tab >>Use of Quadrature Filters for Detection of Stellate Lesions in Mammograms
2005 (English)In: IMAGE ANALYSIS, PROCEEDINGS / [ed] Kalviainen, H; Parkkinen, J; Kaarna, A, 2005, Vol. 3540, 649-658 p.Conference paper, Published paper (Refereed)
Abstract [en]

We propose a method for finding stellate lesions in digitized mammograms based on the use of both local phase and local orientation information extracted from quadrature filter outputs. The local phase information allows efficient and fast separation between edges and lines and the local orientation estimates are used to find areas circumscribed by edges and with radiating lines. The method is incorporated in a computer-aided detection system and evaluation by FROG-curve analysis on a data set of 90 mammograms (45 pairs) yields a false positive rate of 0.3 per image at 90% sensitivity.

Series
LECTURE NOTES IN COMPUTER SCIENCE, ISSN 0302-9743 ; 3540
National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-5392 (URN)000230372500066 ()2-s2.0-26444606889 (Scopus ID)3-540-26320-9 (ISBN)
Conference
14th Scandinavian Conference on Image Analysis Location: Joensuu, FINLAND Date: JUN 19-22, 2005
Note
QC 20100818Available from: 2006-03-03 Created: 2006-03-03 Last updated: 2011-10-14Bibliographically approved
4. On the comparison of FROC curves in mammography CAD systems
Open this publication in new window or tab >>On the comparison of FROC curves in mammography CAD systems
2005 (English)In: Medical physics (Lancaster), ISSN 0094-2405, Vol. 32, no 2, 412-417 p.Article in journal (Refereed) Published
Abstract [en]

We present a novel method for assessing the performance of computer-aided detection systems on unseen cases at a given sensitivity level. The sampling error introduced when training the system on a limited data set is captured as the uncertainty in determining the system threshold that would yield a certain predetermined sensitivity on unseen data sets. By estimating the distribution of system thresholds, we construct a confidence interval for the expected number of false positive markings per image at a given sensitivity. We present two alternative procedures for estimating the probability density functions needed for the construction of the confidence interval. The first is based on the common assumption of Poisson distributed number of false positive markings per image. This procedure also relies on the assumption of independence between false positives and sensitivity, an assumption that can be relaxed with the second procedure, which is nonparametric. The second procedure uses the bootstrap applied to the data generated in the leave-one-out construction of the FROC curve, and is a fast and robust way of obtaining the desired confidence interval. Standard FROC curve analysis does not account for the uncertainty in setting the system threshold, so this method should allow for a more fair comparison of different systems. The resulting confidence intervals are surprisingly wide. For our system a conventional FROC curve analysis yields 0.47 false positive markings per image at 90% sensitivity. The 90% confidence interval for the number of false positive markings per image is (0.28, 1.02) with the parametric procedure and (0.27, 1.04) with the nonparametric bootstrap. Due to its computational simplicity and its allowing more fair comparisons between systems, we propose this method as a complement to the traditionally presented FROC curves. (C) 2005 American Association of Physicists in Medicine.

Keyword
FROC; confidence interval; mammography; CAD; bootstrap; sampling error; system threshold estimation
National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-5393 (URN)10.1118/1.1844433 (DOI)000227420800015 ()2-s2.0-14644427741 (Scopus ID)
Note
QC 20100818Available from: 2006-03-03 Created: 2006-03-03 Last updated: 2017-11-21Bibliographically approved
5. Contrast-enhanced dual-energy mammography using a scanned multi-slit system: valuation of a differential beam filtering technique
Open this publication in new window or tab >>Contrast-enhanced dual-energy mammography using a scanned multi-slit system: valuation of a differential beam filtering technique
2007 (English)In: Journal of Electronic Imaging (JEI), ISSN 1017-9909, E-ISSN 1560-229X, Vol. 16, no 2, 023006- p.Article in journal (Refereed) Published
Abstract [en]

This paper describes a method for single-exposure, contrast-enhanced dual-energy imaging of tumors utilizing a scanned multislit system for digital mammography. This photon-counting system employs an array of silicon strip detectors mounted in an edge-on geometry. The line detectors and pre- and post-collimator slits are carefully aligned, and the multislit setup allows differential filtering of the x-ray beam in the pre-collimator slits. A high-energy image is constructed from those lines where the filter material has been chosen to harden the x-ray beam and the low-energy image from the lines with a filter producing softer beams. Both images are obtained in the same scan, eliminating the need to change tube voltages and anode materials and minimizing the risk of motion artifacts. The method is illustrated on a purpose-built phantom, and logarithmic subtraction of the images produces images essentially free of anatomical clutter with the contrast-enhanced targets clearly visible.

National Category
Physical Sciences
Identifiers
urn:nbn:se:kth:diva-5396 (URN)10.1117/1.2727497 (DOI)000250739700007 ()2-s2.0-34548062288 (Scopus ID)
Note
Conference on Medical Imaging - Physics of Medical Imaging Location: San Diego, CA Date: FEB, 2006 Available from: 2006-03-03 Created: 2006-03-03 Last updated: 2017-11-21Bibliographically approved
6. Improved dual-energy imaging with electronic spectrum splitting
Open this publication in new window or tab >>Improved dual-energy imaging with electronic spectrum splitting
(English)In: Medical physics (Lancaster), ISSN 0094-2405Article in journal (Refereed) Submitted
National Category
Natural Sciences
Identifiers
urn:nbn:se:kth:diva-5397 (URN)
Note
QC 20100819Available from: 2006-03-03 Created: 2006-03-03 Last updated: 2017-11-21Bibliographically approved

Open Access in DiVA

fulltext(2217 kB)1264 downloads
File information
File name FULLTEXT01.pdfFile size 2217 kBChecksum MD5
d125337b527da926ab6dc08f6807e83f6c1132967e8b030a4b3a59988311a2e18374877c
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Bornefalk, Hans
By organisation
Physics
Radiology, Nuclear Medicine and Medical Imaging

Search outside of DiVA

GoogleGoogle Scholar
Total: 1264 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 1109 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf