1
|
Warren LM, Halling-Brown MD, Looney PT, Dance DR, Wallis MG, Given-Wilson RM, Wilkinson L, McAvinchey R, Young KC. Image processing can cause some malignant soft-tissue lesions to be missed in digital mammography images. Clin Radiol 2017; 72:799.e1-799.e8. [PMID: 28457521 DOI: 10.1016/j.crad.2017.03.024] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2016] [Revised: 01/24/2017] [Accepted: 03/23/2017] [Indexed: 11/19/2022]
Abstract
AIM To investigate the effect of image processing on cancer detection in mammography. METHODS AND MATERIALS An observer study was performed using 349 digital mammography images of women with normal breasts, calcification clusters, or soft-tissue lesions including 191 subtle cancers. Images underwent two types of processing: FlavourA (standard) and FlavourB (added enhancement). Six observers located features in the breast they suspected to be cancerous (4,188 observations). Data were analysed using jackknife alternative free-response receiver operating characteristic (JAFROC) analysis. Characteristics of the cancers detected with each image processing type were investigated. RESULTS For calcifications, the JAFROC figure of merit (FOM) was equal to 0.86 for both types of image processing. For soft-tissue lesions, the JAFROC FOM were better for FlavourA (0.81) than FlavourB (0.78); this difference was significant (p=0.001). Using FlavourA a greater number of cancers of all grades and sizes were detected than with FlavourB. FlavourA improved soft-tissue lesion detection in denser breasts (p=0.04 when volumetric density was over 7.5%) CONCLUSIONS: The detection of malignant soft-tissue lesions (which were primarily invasive) was significantly better with FlavourA than FlavourB image processing. This is despite FlavourB having a higher contrast appearance often preferred by radiologists. It is important that clinical choice of image processing is based on objective measures.
Collapse
Affiliation(s)
- L M Warren
- National Co-ordinating Centre for the Physics of Mammography, Royal Surrey County Hospital NHS Foundation Trust, Guildford, GU2 7XX, UK.
| | - M D Halling-Brown
- Scientific Computing, Royal Surrey County Hospital NHS Foundation Trust, Guildford, GU2 7XX, UK
| | - P T Looney
- National Co-ordinating Centre for the Physics of Mammography, Royal Surrey County Hospital NHS Foundation Trust, Guildford, GU2 7XX, UK
| | - D R Dance
- National Co-ordinating Centre for the Physics of Mammography, Royal Surrey County Hospital NHS Foundation Trust, Guildford, GU2 7XX, UK; Department of Physics, University of Surrey, Guildford, Surrey, GU2 7JP, UK
| | - M G Wallis
- Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Cambridge, CB2 0QQ, UK; NIHR Cambridge Biomedical Research Centre, Cambridge, CB2 0QQ, UK
| | - R M Given-Wilson
- Department of Radiology, St George's University Hospitals NHS Foundation Trust, Tooting, London, SW17 0QT, UK
| | - L Wilkinson
- Department of Radiology, St George's University Hospitals NHS Foundation Trust, Tooting, London, SW17 0QT, UK
| | - R McAvinchey
- Jarvis Breast Screening and Diagnostic Centre, Guildford, GU1 1LJ, UK
| | - K C Young
- National Co-ordinating Centre for the Physics of Mammography, Royal Surrey County Hospital NHS Foundation Trust, Guildford, GU2 7XX, UK; Department of Physics, University of Surrey, Guildford, Surrey, GU2 7JP, UK
| |
Collapse
|
2
|
Kim Y, Hong BW, Kim SJ, Kim JH. A population-based tissue probability map-driven level set method for fully automated mammographic density estimations. Med Phys 2015; 41:071905. [PMID: 24989383 DOI: 10.1118/1.4881525] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
Abstract
PURPOSE A major challenge when distinguishing glandular tissues on mammograms, especially for area-based estimations, lies in determining a boundary on a hazy transition zone from adipose to glandular tissues. This stems from the nature of mammography, which is a projection of superimposed tissues consisting of different structures. In this paper, the authors present a novel segmentation scheme which incorporates the learned prior knowledge of experts into a level set framework for fully automated mammographic density estimations. METHODS The authors modeled the learned knowledge as a population-based tissue probability map (PTPM) that was designed to capture the classification of experts' visual systems. The PTPM was constructed using an image database of a selected population consisting of 297 cases. Three mammogram experts extracted regions for dense and fatty tissues on digital mammograms, which was an independent subset used to create a tissue probability map for each ROI based on its local statistics. This tissue class probability was taken as a prior in the Bayesian formulation and was incorporated into a level set framework as an additional term to control the evolution and followed the energy surface designed to reflect experts' knowledge as well as the regional statistics inside and outside of the evolving contour. RESULTS A subset of 100 digital mammograms, which was not used in constructing the PTPM, was used to validate the performance. The energy was minimized when the initial contour reached the boundary of the dense and fatty tissues, as defined by experts. The correlation coefficient between mammographic density measurements made by experts and measurements by the proposed method was 0.93, while that with the conventional level set was 0.47. CONCLUSIONS The proposed method showed a marked improvement over the conventional level set method in terms of accuracy and reliability. This result suggests that the proposed method successfully incorporated the learned knowledge of the experts' visual systems and has potential to be used as an automated and quantitative tool for estimations of mammographic breast density levels.
Collapse
Affiliation(s)
- Youngwoo Kim
- Interdisciplinary Program of Radiation Applied Life Science, Seoul National University College of Medicine, Seoul, South Korea 110-744 and Center for Medical-IT Convergence Technology Research, Advanced Institutes of Convergence Technology, Suwon, South Korea 443-270
| | - Byung Woo Hong
- School of Computer Science and Engineering, Chung-Ang University, Seoul, South Korea 156-756
| | - Seung Ja Kim
- Department of Radiology, Seoul Metropolitan Government Seoul National University Boramae Medical Center, Seoul, South Korea 156-756
| | - Jong Hyo Kim
- Center for Medical-IT Convergence Technology Research, Advanced Institutes of Convergence Technology, Suwon, South Korea 443-270; Department of Radiology, Institute of Radiation Medicine, Seoul National University College of Medicine, 28, Yongon-dong, Chongno-gu, Seoul, 110-744, Korea; and Department of Transdisciplinary Studies, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea 110-744
| |
Collapse
|
3
|
Warren LM, Given-Wilson RM, Wallis MG, Cooke J, Halling-Brown MD, Mackenzie A, Chakraborty DP, Bosmans H, Dance DR, Young KC. The effect of image processing on the detection of cancers in digital mammography. AJR Am J Roentgenol 2014; 203:387-93. [PMID: 25055275 DOI: 10.2214/ajr.13.11812] [Citation(s) in RCA: 19] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/11/2024]
Abstract
OBJECTIVE. The objective of our study was to investigate the effect of image processing on the detection of cancers in digital mammography images. MATERIALS AND METHODS. Two hundred seventy pairs of breast images (both breasts, one view) were collected from eight systems using Hologic amorphous selenium detectors: 80 image pairs showed breasts containing subtle malignant masses; 30 image pairs, biopsy-proven benign lesions; 80 image pairs, simulated calcification clusters; and 80 image pairs, no cancer (normal). The 270 image pairs were processed with three types of image processing: standard (full enhancement), low contrast (intermediate enhancement), and pseudo-film-screen (no enhancement). Seven experienced observers inspected the images, locating and rating regions they suspected to be cancer for likelihood of malignancy. The results were analyzed using a jackknife-alternative free-response receiver operating characteristic (JAFROC) analysis. RESULTS. The detection of calcification clusters was significantly affected by the type of image processing: The JAFROC figure of merit (FOM) decreased from 0.65 with standard image processing to 0.63 with low-contrast image processing (p = 0.04) and from 0.65 with standard image processing to 0.61 with film-screen image processing (p = 0.0005). The detection of noncalcification cancers was not significantly different among the image-processing types investigated (p > 0.40). CONCLUSION. These results suggest that image processing has a significant impact on the detection of calcification clusters in digital mammography. For the three image-processing versions and the system investigated, standard image processing was optimal for the detection of calcification clusters. The effect on cancer detection should be considered when selecting the type of image processing in the future.
Collapse
Affiliation(s)
- Lucy M Warren
- 1 National Coordinating Centre for the Physics of Mammography, Royal Surrey County Hospital, NHS Foundation Trust, Guildford, GU2 7XX, UK
| | | | | | | | | | | | | | | | | | | |
Collapse
|
4
|
Ahn HS, Kim SM, Jang M, Yun BL, Kim B, Ko ES, Han BK, Chang JM, Yi A, Cho N, Moon WK, Choi HY. A new full-field digital mammography system with and without the use of an advanced post-processing algorithm: comparison of image quality and diagnostic performance. Korean J Radiol 2014; 15:305-12. [PMID: 24843234 PMCID: PMC4023048 DOI: 10.3348/kjr.2014.15.3.305] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2014] [Accepted: 02/21/2014] [Indexed: 11/23/2022] Open
Abstract
Objective To compare new full-field digital mammography (FFDM) with and without use of an advanced post-processing algorithm to improve image quality, lesion detection, diagnostic performance, and priority rank. Materials and Methods During a 22-month period, we prospectively enrolled 100 cases of specimen FFDM mammography (Brestige®), which was performed alone or in combination with a post-processing algorithm developed by the manufacturer: group A (SMA), specimen mammography without application of "Mammogram enhancement ver. 2.0"; group B (SMB), specimen mammography with application of "Mammogram enhancement ver. 2.0". Two sets of specimen mammographies were randomly reviewed by five experienced radiologists. Image quality, lesion detection, diagnostic performance, and priority rank with regard to image preference were evaluated. Results Three aspects of image quality (overall quality, contrast, and noise) of the SMB were significantly superior to those of SMA (p < 0.05). SMB was significantly superior to SMA for visualizing calcifications (p < 0.05). Diagnostic performance, as evaluated by cancer score, was similar between SMA and SMB. SMB was preferred to SMA by four of the five reviewers. Conclusion The post-processing algorithm may improve image quality with better image preference in FFDM than without use of the software.
Collapse
Affiliation(s)
- Hye Shin Ahn
- Department of Radiology, Seoul National University Bundang Hospital, Seongnam 463-707, Korea. ; Department of Radiology, Chung-Ang University Hospital, Seoul 156-755, Korea
| | - Sun Mi Kim
- Department of Radiology, Seoul National University Bundang Hospital, Seongnam 463-707, Korea
| | - Mijung Jang
- Department of Radiology, Seoul National University Bundang Hospital, Seongnam 463-707, Korea
| | - Bo La Yun
- Department of Radiology, Seoul National University Bundang Hospital, Seongnam 463-707, Korea
| | - Bohyoung Kim
- Department of Radiology, Seoul National University Bundang Hospital, Seongnam 463-707, Korea
| | - Eun Sook Ko
- Department of Radiology, Samsung Medical Center, Seoul 135-710, Korea
| | - Boo-Kyung Han
- Department of Radiology, Samsung Medical Center, Seoul 135-710, Korea
| | - Jung Min Chang
- Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, Seoul 110-744, Korea
| | - Ann Yi
- Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, Seoul 110-744, Korea
| | - Nariya Cho
- Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, Seoul 110-744, Korea
| | - Woo Kyung Moon
- Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, Seoul 110-744, Korea
| | - Hye Young Choi
- Department of Radiology, Gyeongsang National University Hospital, Jinju 660-702, Korea
| |
Collapse
|
5
|
Slonka J, Alrifai M, Bein G, Sachs UJ. A highly specialised self-made computer program enhances efficiency and safety of immunohaematology reports. Transfus Med 2013; 23:207-14. [DOI: 10.1111/tme.12024] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2012] [Revised: 02/04/2013] [Accepted: 02/09/2013] [Indexed: 11/28/2022]
Affiliation(s)
| | - M. Alrifai
- Haemostasis Center; University Hospital Giessen and Marburg; Marburg; Germany
| | | | | |
Collapse
|
6
|
Visser R, Veldkamp WJH, Beijerinck D, Bun PAM, Deurenberg JJM, Imhof-Tas MW, Schuur KH, Snoeren MM, den Heeten GJ, Karssemeijer N, Broeders MJM. Increase in perceived case suspiciousness due to local contrast optimisation in digital screening mammography. Eur Radiol 2011; 22:908-14. [PMID: 22071778 PMCID: PMC3297744 DOI: 10.1007/s00330-011-2320-2] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2011] [Revised: 08/31/2011] [Accepted: 09/12/2011] [Indexed: 11/27/2022]
Abstract
Objectives To determine the influence of local contrast optimisation on diagnostic accuracy and perceived suspiciousness of digital screening mammograms. Methods Data were collected from a screening region in the Netherlands and consisted of 263 digital screening cases (153 recalled,110 normal). Each case was available twice, once processed with a tissue equalisation (TE) algorithm and once with local contrast optimisation (PV). All cases had digitised previous mammograms. For both algorithms, the probability of malignancy of each finding was scored independently by six screening radiologists. Perceived case suspiciousness was defined as the highest probability of malignancy of all findings of a radiologist within a case. Differences in diagnostic accuracy of the processing algorithms were analysed by comparing the areas under the receiver operating characteristic curves (Az). Differences in perceived case suspiciousness were analysed using sign tests. Results There was no significant difference in Az (TE: 0.909, PV 0.917, P = 0.46). For all radiologists, perceived case suspiciousness using PV was higher than using TE more often than vice versa (ratio: 1.14–2.12). This was significant (P <0.0083) for four radiologists. Conclusions Optimisation of local contrast by image processing may increase perceived case suspiciousness, while diagnostic accuracy may remain similar. Key Points • Variations among different image processing algorithms for digital screening mammography are large. • Current algorithms still aim for optimal local contrast with a low dynamic range. • Although optimisation of contrast may increase sensitivity, diagnostic accuracy is probably unchanged. • Increased local contrast may render both normal and abnormal structures more conspicuous.
Collapse
Affiliation(s)
- Roelant Visser
- National Expert and Training Centre for Breast Cancer Screening, P.O. Box 6873, 6503 GJ Nijmegen, the Netherlands
| | - Wouter J. H. Veldkamp
- National Expert and Training Centre for Breast Cancer Screening, P.O. Box 6873, 6503 GJ Nijmegen, the Netherlands
- Department of Radiology, Leiden University Medical Centre, Albinusdreef 2, 2333 ZA Leiden, The Netherlands
- Department of Radiology, Leiden University Medical Centre, PO Box 9600, 2300 RC Leiden, The Netherlands
| | - David Beijerinck
- Screening Program Early detection of breast cancer in the Centre/Mid-West Part of the Netherlands, Utrecht, the Netherlands
| | - Petra A. M. Bun
- National Expert and Training Centre for Breast Cancer Screening, P.O. Box 6873, 6503 GJ Nijmegen, the Netherlands
- Department of Radiology, Leiden University Medical Centre, Albinusdreef 2, 2333 ZA Leiden, The Netherlands
| | - Jan J. M. Deurenberg
- Screening Program Early detection of breast cancer in the Centre/Mid-West Part of the Netherlands, Utrecht, the Netherlands
| | - Mechli W. Imhof-Tas
- Department of Radiology, Radboud University Nijmegen Medical Centre, Nijmegen, the Netherlands
- Screening Program Early detection of breast cancer in the Eastern Part of the Netherlands, Nijmegen, the Netherlands
| | - Klaas H. Schuur
- National Expert and Training Centre for Breast Cancer Screening, P.O. Box 6873, 6503 GJ Nijmegen, the Netherlands
| | - Miranda M. Snoeren
- Department of Radiology, Radboud University Nijmegen Medical Centre, Nijmegen, the Netherlands
- Screening Program Early detection of breast cancer in the Eastern Part of the Netherlands, Nijmegen, the Netherlands
| | - Gerard J. den Heeten
- National Expert and Training Centre for Breast Cancer Screening, P.O. Box 6873, 6503 GJ Nijmegen, the Netherlands
- Department of Radiology, Academical Medical Center Amsterdam, Amsterdam, The Netherlands
| | - Nico Karssemeijer
- Department of Radiology, Radboud University Nijmegen Medical Centre, Nijmegen, the Netherlands
| | - Mireille J. M. Broeders
- National Expert and Training Centre for Breast Cancer Screening, P.O. Box 6873, 6503 GJ Nijmegen, the Netherlands
- Department of Epidemiology, Biostatistics and HTA, Radboud University Nijmegen Medical Centre, Nijmegen, The Netherlands
| |
Collapse
|
7
|
Abstract
Current day digital mammography acquisition units have already been shown to be equal or better than screen film systems for the detection and classification of breast lesions. The optimal multimodality breast imaging diagnostic workstations and connectivity to existing picture and archiving communication systems and information systems is still a work in progress, but with more and more facilities transitioning to digital imaging it is only a matter of time until these hurdles are overcome.
Collapse
Affiliation(s)
- Margarita L Zuley
- Magee-Womens Hospital of UPMC, Breast Imaging Department, 300 Halket Street, 3rd Floor, Pittsburgh, PA 15213, USA.
| |
Collapse
|
8
|
Diagnostic digital mammography in Japan: issues to consider. Breast Cancer 2010; 17:180-2. [DOI: 10.1007/s12282-009-0196-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2009] [Accepted: 12/21/2009] [Indexed: 10/20/2022]
|