1
|
Multi-mass breast cancer classification based on hybrid descriptors and memetic meta-heuristic learning. SN APPLIED SCIENCES 2020. [DOI: 10.1007/s42452-020-3103-7] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/30/2022] Open
|
2
|
de Nazaré Silva J, de Carvalho Filho AO, Corrêa Silva A, Cardoso de Paiva A, Gattass M. Automatic Detection of Masses in Mammograms Using Quality Threshold Clustering, Correlogram Function, and SVM. J Digit Imaging 2015; 28:323-37. [PMID: 25277539 PMCID: PMC4441695 DOI: 10.1007/s10278-014-9739-3] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022] Open
Abstract
Breast cancer is the second most common type of cancer in the world. Several computer-aided detection and diagnosis systems have been used to assist health experts and to indicate suspect areas that would be difficult to perceive by the human eye; this approach has aided in the detection and diagnosis of cancer. The present work proposes a method for the automatic detection of masses in digital mammograms by using quality threshold (QT), a correlogram function, and the support vector machine (SVM). This methodology comprises the following steps: The first step is to perform preprocessing with a low-pass filter, which increases the scale of the contrast, and the next step is to use an enhancement to the wavelet transform with a linear function. After the preprocessing is segmentation using QT; then, we perform post-processing, which involves the selection of the best mass candidates. This step is performed by analyzing the shape descriptors through the SVM. For the stage that involves the extraction of texture features, we used Haralick descriptors and a correlogram function. In the classification stage, the SVM was again used for training, validation, and final test. The results were as follows: sensitivity 92.31 %, specificity 82.2 %, accuracy 83.53 %, mean rate of false positives per image 1.12, and area under the receiver operating characteristic (ROC) curve 0.8033. Breast cancer is notable for presenting the highest mortality rate in addition to one of the smallest survival rates after diagnosis. An early diagnosis means a considerable increase in the survival chance of the patients. The methodology proposed herein contributes to the early diagnosis and survival rate and, thus, proves to be a useful tool for specialists who attempt to anticipate the detection of masses.
Collapse
Affiliation(s)
- Joberth de Nazaré Silva
- />Applied Computing Group - NCA/UFMA, Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Antonio Oseas de Carvalho Filho
- />Applied Computing Group - NCA/UFMA, Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Aristófanes Corrêa Silva
- />Applied Computing Group - NCA/UFMA, Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Anselmo Cardoso de Paiva
- />Applied Computing Group - NCA/UFMA, Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Marcelo Gattass
- />Department of Computer Science, Pontifical Catholic University of Rio de Janeiro - PUC-Rio, R. Marquês de São Vicente, 225, Gávea, Rio de Janeiro, RJ 22453-900 Brazil
| |
Collapse
|
3
|
Torres-Mejía G, Smith RA, Carranza-Flores MDLL, Bogart A, Martínez-Matsushita L, Miglioretti DL, Kerlikowske K, Ortega-Olvera C, Montemayor-Varela E, Angeles-Llerenas A, Bautista-Arredondo S, Sánchez-González G, Martínez-Montañez OG, Uscanga-Sánchez SR, Lazcano-Ponce E, Hernández-Ávila M. Radiographers supporting radiologists in the interpretation of screening mammography: a viable strategy to meet the shortage in the number of radiologists. BMC Cancer 2015; 15:410. [PMID: 25975383 PMCID: PMC4436872 DOI: 10.1186/s12885-015-1399-2] [Citation(s) in RCA: 30] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2014] [Accepted: 04/29/2015] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND An alternative approach to the traditional model of radiologists interpreting screening mammography is necessary due to the shortage of radiologists to interpret screening mammograms in many countries. METHODS We evaluated the performance of 15 Mexican radiographers, also known as radiologic technologists, in the interpretation of screening mammography after a 6 months training period in a screening setting. Fifteen radiographers received 6 months standardized training with radiologists in the interpretation of screening mammography using the Breast Imaging Reporting and Data System (BI-RADS) system. A challenging test set of 110 cases developed by the Breast Cancer Surveillance Consortium was used to evaluate their performance. We estimated sensitivity, specificity, false positive rates, likelihood ratio of a positive test (LR+) and the area under the subject-specific Receiver Operating Characteristic (ROC) curve (AUC) for diagnostic accuracy. A mathematical model simulating the consequences in costs and performance of two hypothetical scenarios compared to the status quo in which a radiologist reads all screening mammograms was also performed. RESULTS Radiographer's sensitivity was comparable to the sensitivity scores achieved by U.S. radiologists who took the test but their false-positive rate was higher. Median sensitivity was 73.3 % (Interquartile range, IQR: 46.7-86.7 %) and the median false positive rate was 49.5 % (IQR: 34.7-57.9 %). The median LR+ was 1.4 (IQR: 1.3-1.7 %) and the median AUC was 0.6 (IQR: 0.6-0.7). A scenario in which a radiographer reads all mammograms first, and a radiologist reads only those that were difficult for the radiographer, was more cost-effective than a scenario in which either the radiographer or radiologist reads all mammograms. CONCLUSIONS Given the comparable sensitivity achieved by Mexican radiographers and U.S. radiologists on a test set, screening mammography interpretation by radiographers appears to be a possible adjunct to radiologists in countries with shortages of radiologists. Further studies are required to assess the effectiveness of different training programs in order to obtain acceptable screening accuracy, as well as the best approaches for the use of non-physician readers to interpret screening mammography.
Collapse
Affiliation(s)
- Gabriela Torres-Mejía
- Centro de Investigación en Salud Poblacional, Instituto Nacional de Salud Pública, Avenida Universidad No. 655, Colonia Santa María Ahuacatitlán, Cuernavaca, 62100, , Morelos, Mexico.
| | - Robert A Smith
- American Cancer Society, 250 Williams St., Atlanta, GA, 30303, USA.
| | - María de la Luz Carranza-Flores
- Centro de Diagnóstico Digital México-España, Secretaria de Salud Pública del Distrito Federal, Mariano Escobedo No. 148 col. Anáhuac, Ciudad de México D. F., 11320, Mexico.
| | - Andy Bogart
- Group Health Research Institute, Group Health Cooperative, 1730 Minor Ave #1600, Seattle, WA, 98101, USA.
| | - Louis Martínez-Matsushita
- Centro de Investigación en Salud Poblacional, Instituto Nacional de Salud Pública, Avenida Universidad No. 655, Colonia Santa María Ahuacatitlán, Cuernavaca, 62100, , Morelos, Mexico.
| | - Diana L Miglioretti
- Group Health Research Institute, Group Health Cooperative, 1730 Minor Ave #1600, Seattle, WA, 98101, USA.
- Division of Biostatistics, Department of Public Health Sciences, School of Medicine, University of California, 1 Shields Ave, Davis, CA, 95616, USA.
| | - Karla Kerlikowske
- Department of Epidemiology and Biostatistics and the General Internal Medicine Section, University of California, 4150 Clement St, San Francisco, CA, 94121, USA.
- Department of Veterans Affairs, University of California, 4150 Clement St, San Francisco, CA, 94121, USA.
| | - Carolina Ortega-Olvera
- Centro de Investigación en Salud Poblacional, Instituto Nacional de Salud Pública, Avenida Universidad No. 655, Colonia Santa María Ahuacatitlán, Cuernavaca, 62100, , Morelos, Mexico.
| | - Ernesto Montemayor-Varela
- Centro de Investigación en Salud Poblacional, Instituto Nacional de Salud Pública, Avenida Universidad No. 655, Colonia Santa María Ahuacatitlán, Cuernavaca, 62100, , Morelos, Mexico.
| | - Angélica Angeles-Llerenas
- Centro de Investigación en Salud Poblacional, Instituto Nacional de Salud Pública, Avenida Universidad No. 655, Colonia Santa María Ahuacatitlán, Cuernavaca, 62100, , Morelos, Mexico.
| | - Sergio Bautista-Arredondo
- Dirección de Economía de la Salud, Instituto Nacional de Salud Pública, Avenida Universidad No. 655, Colonia Santa María Ahuacatitlán, CP. 62100, Cuernavaca, Morelos, Mexico.
| | - Gilberto Sánchez-González
- Dirección de Economía de la Salud, Instituto Nacional de Salud Pública, Avenida Universidad No. 655, Colonia Santa María Ahuacatitlán, CP. 62100, Cuernavaca, Morelos, Mexico.
| | - Olga G Martínez-Montañez
- Hospital de Oncología, Centro Médico Siglo XXI, Instituto Mexicano del Seguro Social, Av. Cuauhtémoc 330, Cuauhtemoc Doctores, Ciudad de México, D.F. 06720, Mexico.
| | - Santos R Uscanga-Sánchez
- Federación Mexicana de Colegios de Ginecología y Obstetricia, Nueva York 38, Col. Nápoles, Benito Juárez, Ciudad de México, D.F. 03810, Mexico.
| | - Eduardo Lazcano-Ponce
- Centro de Investigación en Salud Poblacional, Instituto Nacional de Salud Pública, Avenida Universidad No. 655, Colonia Santa María Ahuacatitlán, Cuernavaca, 62100, , Morelos, Mexico.
| | - Mauricio Hernández-Ávila
- Centro de Investigación en Salud Poblacional, Instituto Nacional de Salud Pública, Avenida Universidad No. 655, Colonia Santa María Ahuacatitlán, Cuernavaca, 62100, , Morelos, Mexico.
| |
Collapse
|
4
|
Jorritsma W, Cnossen F, van Ooijen PMA. Improving the radiologist-CAD interaction: designing for appropriate trust. Clin Radiol 2014; 70:115-22. [PMID: 25459198 DOI: 10.1016/j.crad.2014.09.017] [Citation(s) in RCA: 30] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2014] [Revised: 09/17/2014] [Accepted: 09/19/2014] [Indexed: 12/25/2022]
Abstract
Computer-aided diagnosis (CAD) has great potential to improve radiologists' diagnostic performance. However, the reported performance of the radiologist-CAD team is lower than what might be expected based on the performance of the radiologist and the CAD system in isolation. This indicates that the interaction between radiologists and the CAD system is not optimal. An important factor in the interaction between humans and automated aids (such as CAD) is trust. Suboptimal performance of the human-automation team is often caused by an inappropriate level of trust in the automation. In this review, we examine the role of trust in the radiologist-CAD interaction and suggest ways to improve the output of the CAD system so that it allows radiologists to calibrate their trust in the CAD system more effectively. Observer studies of the CAD systems show that radiologists often have an inappropriate level of trust in the CAD system. They sometimes under-trust CAD, thereby reducing its potential benefits, and sometimes over-trust it, leading to diagnostic errors they would not have made without CAD. Based on the literature on trust in human-automation interaction and the results of CAD observer studies, we have identified four ways to improve the output of CAD so that it allows radiologists to form a more appropriate level of trust in CAD. Designing CAD systems for appropriate trust is important and can improve the performance of the radiologist-CAD team. Future CAD research and development should acknowledge the importance of the radiologist-CAD interaction, and specifically the role of trust therein, in order to create the perfect artificial partner for the radiologist. This review focuses on the role of trust in the radiologist-CAD interaction. The aim of the review is to encourage CAD developers to design for appropriate trust and thereby improve the performance of the radiologist-CAD team.
Collapse
Affiliation(s)
- W Jorritsma
- Department of Radiology, University of Groningen, University Medical Center Groningen, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands.
| | - F Cnossen
- Institute of Artificial Intelligence and Cognitive Engineering, University of Groningen, Nijenborgh 9, 9747 AG, Groningen, The Netherlands
| | - P M A van Ooijen
- Department of Radiology, University of Groningen, University Medical Center Groningen, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands; Center for Medical Imaging North East Netherlands, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands
| |
Collapse
|
5
|
Povyakalo AA, Alberdi E, Strigini L, Ayton P. How to discriminate between computer-aided and computer-hindered decisions: a case study in mammography. Med Decis Making 2013; 33:98-107. [PMID: 23300205 DOI: 10.1177/0272989x12465490] [Citation(s) in RCA: 31] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
BACKGROUND Computer aids can affect decisions in complex ways, potentially even making them worse; common assessment methods may miss these effects. We developed a method for estimating the quality of decisions, as well as how computer aids affect it, and applied it to computer-aided detection (CAD) of cancer, reanalyzing data from a published study where 50 professionals ("readers") interpreted 180 mammograms, both with and without computer support. METHOD We used stepwise regression to estimate how CAD affected the probability of a reader making a correct screening decision on a patient with cancer (sensitivity), thereby taking into account the effects of the difficulty of the cancer (proportion of readers who missed it) and the reader's discriminating ability (Youden's determinant). Using regression estimates, we obtained thresholds for classifying a posteriori the cases (by difficulty) and the readers (by discriminating ability). RESULTS Use of CAD was associated with a 0.016 increase in sensitivity (95% confidence interval [CI], 0.003-0.028) for the 44 least discriminating radiologists for 45 relatively easy, mostly CAD-detected cancers. However, for the 6 most discriminating radiologists, with CAD, sensitivity decreased by 0.145 (95% CI, 0.034-0.257) for the 15 relatively difficult cancers. CONCLUSIONS Our exploratory analysis method reveals unexpected effects. It indicates that, despite the original study detecting no significant average effect, CAD helped the less discriminating readers but hindered the more discriminating readers. Such differential effects, although subtle, may be clinically significant and important for improving both computer algorithms and protocols for their use. They should be assessed when evaluating CAD and similar warning systems.
Collapse
Affiliation(s)
- Andrey A Povyakalo
- Centre for Software Reliability, City University London, Northampton Square, London, UK (AAP, EA, LS)
| | - Eugenio Alberdi
- Centre for Software Reliability, City University London, Northampton Square, London, UK (AAP, EA, LS)
| | - Lorenzo Strigini
- Centre for Software Reliability, City University London, Northampton Square, London, UK (AAP, EA, LS)
| | - Peter Ayton
- Psychology Department, City University London, Northampton Square, London, UK (PA)
| |
Collapse
|
6
|
Parasuraman R, Manzey DH. Complacency and bias in human use of automation: an attentional integration. HUMAN FACTORS 2010; 52:381-410. [PMID: 21077562 DOI: 10.1177/0018720810376055] [Citation(s) in RCA: 269] [Impact Index Per Article: 19.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/21/2023]
Abstract
OBJECTIVE Our aim was to review empirical studies of complacency and bias in human interaction with automated and decision support systems and provide an integrated theoretical model for their explanation. BACKGROUND Automation-related complacency and automation bias have typically been considered separately and independently. METHODS Studies on complacency and automation bias were analyzed with respect to the cognitive processes involved. RESULTS Automation complacency occurs under conditions of multiple-task load, when manual tasks compete with the automated task for the operator's attention. Automation complacency is found in both naive and expert participants and cannot be overcome with simple practice. Automation bias results in making both omission and commission errors when decision aids are imperfect. Automation bias occurs in both naive and expert participants, cannot be prevented by training or instructions, and can affect decision making in individuals as well as in teams. While automation bias has been conceived of as a special case of decision bias, our analysis suggests that it also depends on attentional processes similar to those involved in automation-related complacency. CONCLUSION Complacency and automation bias represent different manifestations of overlapping automation-induced phenomena, with attention playing a central role. An integrated model of complacency and automation bias shows that they result from the dynamic interaction of personal, situational, and automation-related characteristics. APPLICATION The integrated model and attentional synthesis provides a heuristic framework for further research on complacency and automation bias and design options for mitigating such effects in automated and decision support systems.
Collapse
Affiliation(s)
- Raja Parasuraman
- Arch Lab, George Mason University, Fairfax, Virginia 22030, USA.
| | | |
Collapse
|
7
|
Computer-aided detection in full-field digital mammography in a clinical population: performance of radiologist and technologists. Breast Cancer Res Treat 2009; 120:499-506. [PMID: 19418215 DOI: 10.1007/s10549-009-0409-y] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2009] [Accepted: 04/21/2009] [Indexed: 01/08/2023]
Abstract
The purpose of the study was to evaluate the impact of a computer-aided detection (CAD) system on the performance of mammogram readers in interpreting digital mammograms in a clinical population. Furthermore, the ability of a CAD system to detect breast cancer in digital mammography was studied in comparison to the performance of radiologists and technologists as mammogram readers. Digital mammograms of 1,048 consecutive patients were evaluated by a radiologist and three technologists. Abnormalities were recorded and an imaging conclusion was given as a BI-RADS score before and after CAD analysis. Pathology results during 12 months follow up were used as a reference standard for breast cancer. Fifty-one malignancies were found in 50 patients. Sensitivity and specificity were computed before and after CAD analysis and provided with 95% CIs. In order to assess the detection rate of malignancies by CAD and the observers, the pathological locations of these 51 breast cancers were matched with the locations of the CAD marks and the mammographic locations that were considered to be suspicious by the observers. For all observers, the sensitivity rates did not change after application of CAD. A mean sensitivity of 92% was found for all technologists and 84% for the radiologist. For two technologists, the specificity decreased (from 84 to 83% and from 77 to 75%). For the radiologist and one technologist, the application of CAD did not have any impact on the specificity rates (95 and 83%, respectively). CAD detected 78% of all malignancies. Five malignancies were indicated by CAD without being noticed as suspicious by the observers. In conclusion, the results show that systematic application of CAD in a clinical patient population failed to improve the overall sensitivity of mammogram interpretation by the readers and was associated with an increase in false-positive results. However, CAD marked five malignancies that were missed by the different readers.
Collapse
|
8
|
Gilbert FJ, Astley SM, Boggis CR, McGee MA, Griffiths PM, Duffy SW, Agbaje OF, Gillan MG, Wilson M, Jain AK, Barr N, Beetles UM, Griffiths MA, Johnson J, Roberts RM, Deans HE, Duncan KA, Iyengar G. Variable size computer-aided detection prompts and mammography film reader decisions. Breast Cancer Res 2008; 10:R72. [PMID: 18724867 PMCID: PMC2575546 DOI: 10.1186/bcr2137] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2008] [Revised: 07/21/2008] [Accepted: 08/25/2008] [Indexed: 11/12/2022] Open
Abstract
Introduction The purpose of the present study was to investigate the effect of computer-aided detection (CAD) prompts on reader behaviour in a large sample of breast screening mammograms by analysing the relationship of the presence and size of prompts to the recall decision. Methods Local research ethics committee approval was obtained; informed consent was not required. Mammograms were obtained from women attending routine mammography at two breast screening centres in 1996. Films, previously double read, were re-read by a different reader using CAD. The study material included 315 cancer cases comprising all screen-detected cancer cases, all subsequent interval cancers and 861 normal cases randomly selected from 10,267 cases. Ground truth data were used to assess the efficacy of CAD prompting. Associations between prompt attributes and tumour features or reader recall decisions were assessed by chi-squared tests. Results There was a highly significant relationship between prompting and a decision to recall for cancer cases and for a random sample of normal cases (P < 0.001). Sixty-four per cent of all cases contained at least one CAD prompt. In cancer cases, larger prompts were more likely to be recalled (P = 0.02) for masses but there was no such association for calcifications (P = 0.9). In a random sample of 861 normal cases, larger prompts were more likely to be recalled (P = 0.02) for both mass and calcification prompts. Significant associations were observed with prompting and breast density (p = 0.009) for cancer cases but not for normal cases (P = 0.05). Conclusions For both normal cases and cancer cases, prompted mammograms were more likely to be recalled and the prompt size was also associated with a recall decision.
Collapse
Affiliation(s)
- Fiona J Gilbert
- Division of Applied Medicine, School of Medicine & Dentistry, University of Aberdeen, Lilian Sutton Building, Foresterhill, Aberdeen AB25 2ZD, UK.
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
9
|
CAD in mammography: lesion-level versus case-level analysis of the effects of prompts on human decisions. Int J Comput Assist Radiol Surg 2008. [DOI: 10.1007/s11548-008-0213-x] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
10
|
Helvie M. Improving mammographic interpretation: double reading and computer-aided diagnosis. Radiol Clin North Am 2007; 45:801-11, vi. [PMID: 17888770 DOI: 10.1016/j.rcl.2007.06.004] [Citation(s) in RCA: 18] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
Abstract
This article discusses two commonly used techniques advocated to improve screening mammography performance: double reading (DR) and computer-aided detection (CAD). Analysis of these methods is incomplete because no randomized controlled trials have been performed to assess changes in survival. Although DR and CAD have shown improvement in sensitivity, specificity often has decreased. Balancing which parameter is more important involves health care policy, costs, cultural factors, legal risk, and patient preference.
Collapse
Affiliation(s)
- Mark Helvie
- Department of Radiology, University of Michigan Health System, 1500 East Medical Center Drive, TC 2910N, Ann Arbor, MI 48109-0326, USA.
| |
Collapse
|
11
|
van den Biggelaar FJHM, Nelemans PJ, Flobbe K. Performance of radiographers in mammogram interpretation: a systematic review. Breast 2007; 17:85-90. [PMID: 17764941 DOI: 10.1016/j.breast.2007.07.035] [Citation(s) in RCA: 29] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2007] [Revised: 07/23/2007] [Accepted: 07/23/2007] [Indexed: 10/22/2022] Open
Abstract
Radiologists may be relieved from work that could be performed by radiographers. This systematic literature review focuses on the performance of radiographers (also referring to technologists and physician assistants) compared with radiologists in the interpretation of mammograms; the effect of training; and the question whether there are any studies evaluating the effects of involving radiographers in the interpretation of diagnostic mammograms in daily clinical practice on the sensitivity and specificity of cancer detection in breast imaging. Six studies met the inclusion criteria (primary aim of the study has to be the evaluation of the performance of radiographers, sensitivity and specificity have to be reported or calculable and there has to be a sufficient gold standard). The results showed that, in a screening setting, radiographers scored higher false positive rates with a similar sensitivity in the detection of malignancies, compared with radiologists. Furthermore, results suggested that training could improve their performance. No studies were reported assessing the performance of radiographers interpreting diagnostic mammograms in a consecutive patient population in a daily clinical setting. This indicates a need for a well-designed diagnostic study using an adequate gold standard, in order to evaluate the feasibility of deploying radiographers in the interpretation of diagnostic mammograms in a clinical setting.
Collapse
Affiliation(s)
- F J H M van den Biggelaar
- Department of Radiology, Maastricht University Hospital, PO Box 5800, 6202 AZ Maastricht, The Netherlands.
| | | | | |
Collapse
|
12
|
Tourassi GD, Harrawood B, Singh S, Lo JY, Floyd CE. Evaluation of information-theoretic similarity measures for content-based retrieval and detection of masses in mammograms. Med Phys 2006; 34:140-50. [PMID: 17278499 DOI: 10.1118/1.2401667] [Citation(s) in RCA: 94] [Impact Index Per Article: 5.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
Abstract
The purpose of this study was to evaluate image similarity measures employed in an information-theoretic computer-assisted detection (IT-CAD) scheme. The scheme was developed for content-based retrieval and detection of masses in screening mammograms. The study is aimed toward an interactive clinical paradigm where physicians query the proposed IT-CAD scheme on mammographic locations that are either visually suspicious or indicated as suspicious by other cuing CAD systems. The IT-CAD scheme provides an evidence-based, second opinion for query mammographic locations using a knowledge database of mass and normal cases. In this study, eight entropy-based similarity measures were compared with respect to retrieval precision and detection accuracy using a database of 1820 mammographic regions of interest. The IT-CAD scheme was then validated on a separate database for false positive reduction of progressively more challenging visual cues generated by an existing, in-house mass detection system. The study showed that the image similarity measures fall into one of two categories; one category is better suited to the retrieval of semantically similar cases while the second is more effective with knowledge-based decisions regarding the presence of a true mass in the query location. In addition, the IT-CAD scheme yielded a substantial reduction in false-positive detections while maintaining high detection rate for malignant masses.
Collapse
Affiliation(s)
- Georgia D Tourassi
- Digital Advanced Imaging Laboratories, Department of Radiology, Duke University Medical Center, Durham, North Carolina 27705, USA.
| | | | | | | | | |
Collapse
|
13
|
Houssami N, Irwig L, Ciatto S. Radiological surveillance of interval breast cancers in screening programmes. Lancet Oncol 2006; 7:259-65. [PMID: 16510335 DOI: 10.1016/s1470-2045(06)70617-9] [Citation(s) in RCA: 46] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
Abstract
Interval breast cancers-those diagnosed after a negative mammographic screen and before the next scheduled screen-are an important indicator of the potential effectiveness of population screening for breast cancer. Although the incidence of interval cancers is usually monitored, radiological surveillance is not undertaken routinely in most screening programmes. Here, we describe radiological surveillance of interval breast cancers and discuss methodological difficulties in the radiological review process and in the categorisation of interval cancers as false-negative, true, or occult. Furthermore, we identify methods that affect whether an interval cancer is classified as a false-negative (missed) or a true interval cancer. For all radiological categories of interval cancers, we outline possible changes to screening programmes that might improve cancer detection. Standardised radiological surveillance of interval cancers might allow within-programme comparisons and has the potential to guide practice and improve quality.
Collapse
Affiliation(s)
- Nehmat Houssami
- Screening and Test Evaluation Program (STEP), School of Public Health, University of Sydney, New South Wales, Australia.
| | | | | |
Collapse
|
14
|
Mello-Thoms C. How does the perception of a lesion influence visual search strategy in mammogram reading? Acad Radiol 2006; 13:275-88. [PMID: 16488839 DOI: 10.1016/j.acra.2005.11.034] [Citation(s) in RCA: 18] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2005] [Revised: 11/08/2005] [Accepted: 11/10/2005] [Indexed: 10/25/2022]
Abstract
RATIONALE AND OBJECTIVES Radiologists do not decide whether to report or to dismiss a perceived finding based solely on the conspicuity of the finding itself, but rather, they compare the finding with selected areas of the background. In this article, we examined how the perception of a malignant mass changed the background sampling strategy of experienced mammographers when searching mammograms for breast cancer. We determined whether these changes were different for correctly reported masses and for both visually inspected but unreported masses (ie, misses) and for lesion-free areas that were interpreted as containing a malignant mass (ie, false-positive decisions). MATERIALS AND METHODS Four experienced mammographers read a case set of 20 two-view mammograms on two trials. Fifteen cases contained one biopsy-proven malignant mass, and five cases were lesion-free. Each cancer case had two sets of images: 1) the ones in which the lesion was reported at mammography screening, and 2) the first prior mammogram. On each trial, for each cancer case, only one set of images was shown to the observer in a balanced mix of current and prior cases per trial. The complementary set was shown in the next trial. The lesion-free cases were shown in both trials. The observers' eye positions were recorded. Spatial frequency analysis was used to represent the observers' background sampling strategy, and analysis of variance and correlation analysis were used to evaluate whether there were significant differences in the background areas sampled before and after the observers' eyes hit for the first time the location of the lesion. RESULTS We found statistically significant differences (analysis of variance F(1,19) = 12.812, P = .0003) in the spatial frequency representation of the background areas sampled before and after the observers' eyes first hit the location of a true malignant mass. There were no statistically significant differences in the spatial frequency representation of background areas sampled before and after the observers' eyes first hit the location of a correctly reported malignant mass, but there were significant differences when either the observer did not report the mass (a miss) or the observer reported a lesion-free area as containing a mass (a false positive). CONCLUSION A true malignant mass that the observers correctly report may be perceived immediately after image onset, thus biasing background sampling from the start, whereas areas that yield both false-negative and false-positive decisions may only be perceived during visual examination of the parenchyma. For the false negatives, our data suggest that after fixating the location of the lesion, the observers actively tried to reconcile the perception of the lesion with its background, whereas for the false positives, which represent a "true" lesion for the observers, background sampling was clearly different before and after the location was fixated for the first time. Hence, the perception of a finding effectively biases any further analysis of the case.
Collapse
Affiliation(s)
- Claudia Mello-Thoms
- Department of Radiology, University of Pittsburgh, 300 Halket Street, Suite 4200, Pittsburgh, PA 15213, USA.
| |
Collapse
|
15
|
Khoo LAL, Taylor P, Given-Wilson RM. Computer-aided detection in the United Kingdom National Breast Screening Programme: prospective study. Radiology 2005; 237:444-9. [PMID: 16244252 DOI: 10.1148/radiol.2372041362] [Citation(s) in RCA: 120] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
PURPOSE To evaluate prospectively the recall and cancer detection rates with and without computer-aided detection (CAD) in the United Kingdom National Health Service Breast Screening Programme. MATERIALS AND METHODS The study had appropriate ethics committee approval. Informed consent was not required; however, patients were informed that their mammograms might be used in research efforts, and all patients agreed to participate. Mammograms obtained in 6111 women (mean age, 58.4 years) undergoing routine screening every 3 years were analyzed with a CAD system. Mammograms were independently double read. Twelve readers participated. Readers recorded an initial evaluation, viewed the CAD prompts, and recorded a final evaluation. Recall to assessment was decided after arbitration. Sensitivities were calculated for single reading, single reading with CAD, and double reading, as a proportion of the total number of cancers detected by using double reading with CAD. RESULTS A total of 62 cancers were detected in 61 women. CAD prompted 51 (84%) of 61 radiographically detected cancers. Of 12 cancers missed on single reading, nine were correctly prompted; however, seven prompts were overruled by the reader. Sensitivity of single reading was 90.2% (95% confidence interval [CI]: 83.0%, 95.0%), single reading with CAD was 91.5% (95% CI: 85.0%, 96.0%), and double reading without CAD was 98.4% (95% CI: 91.0%, 100%). Cancer detection rate was 1%. Recall to assessment rate was 6.1%, with an increase of 5.8% because of CAD. Average time required, per reader, to read a case was 25 seconds without CAD and 45 seconds with CAD. CONCLUSION CAD increases sensitivity of single reading by 1.3%, whereas double reading increases sensitivity by 8.2%.
Collapse
Affiliation(s)
- Lisanne A L Khoo
- Radiology Department, St George's Hospital, Blackshaw Rd, London SW17 0QT, England
| | | | | |
Collapse
|
16
|
Alberdi E, Povyakalo AA, Strigini L, Ayton P, Hartswood M, Procter R, Slack R. Use of computer-aided detection (CAD) tools in screening mammography: a multidisciplinary investigation. Br J Radiol 2005; 78 Spec No 1:S31-40. [PMID: 15917444 DOI: 10.1259/bjr/37646417] [Citation(s) in RCA: 26] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022] Open
Abstract
We summarise a set of analyses and studies conducted to assess the effects of the use of a computer-aided detection (CAD) tool in breast screening. We have used an interdisciplinary approach that combines: (a) statistical analyses inspired by reliability modelling in engineering; (b) experimental studies of decisions of mammography experts using the tool, interpreted in the light of human factors psychology; and (c) ethnographic observations of the use of the tool both in trial conditions and in everyday screening practice. Our investigations have shown patterns of human behaviour and effects of computer-based advice that would not have been revealed by a standard clinical trial approach. For example, we found that the negligible measured effect of CAD could be explained by a range of effects on experts' decisions, beneficial in some cases and detrimental in others. There is some evidence of the latter effects being due to the experts using the computer tool differently from the intentions of the developers. We integrate insights from the different pieces of evidence and highlight their implications for the design, evaluation and deployment of this sort of computer tool.
Collapse
Affiliation(s)
- E Alberdi
- Centre for Software Reliability and Psychology Department, City University, Northampton Square, London EC1V 0HB
| | | | | | | | | | | | | |
Collapse
|
17
|
Taylor P, Given-Wilson R, Champness J, Potts HWW, Johnston K. Assessing the impact of CAD on the sensitivity and specificity of film readers. Clin Radiol 2005; 59:1099-105. [PMID: 15556592 DOI: 10.1016/j.crad.2004.04.017] [Citation(s) in RCA: 16] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2004] [Revised: 04/14/2004] [Accepted: 04/14/2004] [Indexed: 11/21/2022]
Abstract
AIM To assess the impact of computer-aided detection (CAD) prompts on film readers' sensitivity and specificity. MATERIAL AND METHODS Thirty-five readers read 120 films, including 44 cancers, 40 of which were prompted. All readers looked at all cases with and without prompts. The sensitivity and specificity were calculated for each reader under each condition. RESULTS The sensitivity improved when CAD prompts were used (0.80 from 0.77). The difference was slightly below the threshold for statistical significance (95% CI for the difference is -0.0027-0.064). The specificity also improved (0.86 from 0.85), but not significantly. There was a significant improvement in sensitivity when readers' judgements were combined to simulate double reading, from 0.77 to 0.81. (95% CI for the difference is 0.014-0.077). CONCLUSIONS Analysis of prompted cancers that readers did and did not recall, found that cases were more likely to be correctly recalled if there were emphasized prompts, more prompts or if the case was harder. There was no statistically significant effect for type of abnormality or tumour size or for the performance, attitude or experience of the reader.
Collapse
Affiliation(s)
- P Taylor
- CHIME, Royal Free and University College Medical School, University College London, London, UK.
| | | | | | | | | |
Collapse
|
18
|
Taylor P, Given-Wilson RM. Evaluation of computer-aided detection (CAD) devices. Br J Radiol 2005; 78 Spec No 1:S26-30. [PMID: 15917442 DOI: 10.1259/bjr/84545410] [Citation(s) in RCA: 12] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022] Open
Abstract
We present a review of three major UK studies of computer-aided detection (CAD) for mammography. A short account of the motivation, methods and results is given for each of the three. A number of conclusions are drawn, particularly about the merits and difficulties of research in the field. The first two studies measured the impact of CAD on the sensitivity and specificity of film readers interpreting cases with known outcomes displayed on rollers with an artificially high frequency of cancers. In the first study 50 film readers each read 180 cases, including 60 cancers (40 screen-detected and 20 interval). In the second study 35 film readers viewed 120 cases including 44 cancers, of which 40 were selected to be difficult cases that CAD prompted correctly. The third study was carried out prospectively. 6111 films were independently double read by film readers who recorded a judgement before and after viewing CAD prompts. In addition to this, intraobserver measure of the impact of CAD, we compared the cancer detection rate in these cases with that in 1339 cases read over the same period without the benefit of CAD. None of the three studies showed a statistically significant effect attributable to CAD. There is evidence that a high proportion of missed cancers are prompted and that "emphasised" prompts, which have a greater positive predictive value, have a stronger impact on decision-making that other prompts.
Collapse
Affiliation(s)
- P Taylor
- Centre for Health Informatics and Multiprofessional Education, University College London, London
| | | |
Collapse
|
19
|
Astley SM. Evaluation of computer-aided detection (CAD) prompting techniques for mammography. Br J Radiol 2005; 78 Spec No 1:S20-5. [PMID: 15917441 DOI: 10.1259/bjr/37221979] [Citation(s) in RCA: 11] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022] Open
Abstract
Computer-aided detection (CAD) systems, in which abnormalities are automatically detected and their locations presented to the radiologist as prompts, are increasingly being used to improve reader performance. The performance of CAD systems can be evaluated in two ways: by measuring the performance of the algorithms, or by monitoring the performance of readers using the system. All aspects of evaluation need careful consideration to avoid potential bias. This paper examines a variety of different approaches to evaluation and discusses their relative strengths and weaknesses.
Collapse
Affiliation(s)
- S M Astley
- Imaging Science and Biomedical Engineering, University of Manchester, Stopford Building, Oxford Road, Manchester M13 9PT UK
| |
Collapse
|
20
|
Astley SM. Computer-based detection and prompting of mammographic abnormalities. Br J Radiol 2004; 77 Spec No 2:S194-200. [PMID: 15677361 DOI: 10.1259/bjr/30116822] [Citation(s) in RCA: 29] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022] Open
Abstract
Mammographic film reading is a highly demanding task, particularly in screening programmes where the reader must perform a detailed visual search of a large number of images for early signs of abnormality, which are often subtle or small, and which occur very infrequently. False negative cases, where signs of abnormality are missed by a film reader, are known to occur. Computer based algorithms can be used to detect abnormal patterns in images, but it is not possible to reliably detect all signs of abnormality in mammograms, so screening cannot yet be fully automated. The most successful detection algorithms are, however, incorporated in computer-aided detection (CAD) systems which indicate potentially abnormal locations to the reader in a process known as prompting. CAD systems have the capacity to reduce the frequency of false negative errors by ensuring that suspicious regions of the images are thoroughly searched and by increasing the weighting attached to subtle signs that may otherwise have been dismissed. One of the areas currently being researched is the effect of prompting on human performance. This is complex, since readers are presented with prompts generated by multiple detection algorithms, each of which has a different sensitivity and specificity. This paper reviews progress in abnormality detection, the strengths and the weaknesses of CAD, and the methodologies used to evaluate CAD in a clinical setting.
Collapse
Affiliation(s)
- S M Astley
- Imaging Science and Biomedical Engineering, Stopford Building, Oxford Road, Manchester M13 9PT, UK
| |
Collapse
|
21
|
Astley SM. Computer-aided detection for screening mammography. Acad Radiol 2004; 11:1139-43. [PMID: 15530806 DOI: 10.1016/j.acra.2004.07.009] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2004] [Revised: 05/05/2004] [Accepted: 06/30/2004] [Indexed: 11/24/2022]
Abstract
Mammographic film reading is a highly demanding task, particularly in screening programs where the reader must perform a detailed visual search of a large number of images for signs of abnormality that are often subtle or small, and which occur very infrequently. False-negative cases, in which signs of abnormality are missed by a film reader, are known to occur. Computer-aided detection (CAD) systems, which automatically detect potential abnormalities and indicate their locations to the reader, have the capacity to reduce the frequency of such errors by ensuring that all suspicious regions of the images are thoroughly searched and by increasing the weighting attached to subtle signs that may otherwise have been dismissed. CAD systems depend on suites of detection algorithms, but each algorithm has a different sensitivity and specificity and the effect of prompting errors on human performance with CAD is complex. This article is a brief review of CAD for screening mammography; it highlights both the strengths and the weaknesses of the approach, and describes some of the methodologies used to evaluate CAD in a clinical setting.
Collapse
Affiliation(s)
- Susan M Astley
- University of Manchester, Imaging Science and Biomedical Engineering, Stopford Building, Oxford Road, Manchester M13 9PT, UK.
| |
Collapse
|
22
|
Alberdi E, Povykalo A, Strigini L, Ayton P. Effects of incorrect computer-aided detection (CAD) output on human decision-making in mammography. Acad Radiol 2004; 11:909-18. [PMID: 15354301 DOI: 10.1016/j.acra.2004.05.012] [Citation(s) in RCA: 52] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
Abstract
RATIONALE AND OBJECTIVES To investigate the effects of incorrect computer output on the reliability of the decisions of human users. This work followed an independent UK clinical trial that evaluated the impact of computer-aided detection(CAD) in breast screening. The aim was to use data from this trial to feed into probabilistic models (similar to those used in "reliability engineering") which would detect and assess possible ways of improving the human-CAD interaction. Some analyses required extra data; therefore, two supplementary studies were conducted. Study 1 was designed to elucidate the effects of computer failure on human performance. Study 2 was conducted to clarify unexpected findings from Study 1. MATERIALS AND METHODS In Study 1, 20 film readers viewed 60 sets of mammograms (30 of which contained cancer) and provided "recall/no recall" decisions for each case. Computer output for each case was available to the participants. The test set was designed to contain an unusually large proportion (50%) of cancers for which CAD had generated incorrect output. In Study 2, 19 different readers viewed the same set of cases in similar conditions except that computer output was not available. RESULTS The average sensitivity of readers in Study 1 (with CAD) was significantly lower than the average sensitivity of read-ers in Study 2 (without CAD). The difference was most marked for cancers for which CAD failed to provide correct prompting. CONCLUSION Possible automation bias effects in CAD use deserve further study because they may degrade human decision-making for some categories of cases under certain conditions. This possibility should be taken into account in the assessment and design of CAD tools.
Collapse
Affiliation(s)
- Eugenio Alberdi
- Centre for Software Reliability and the Department of Psychology, City University, Northampton Square, London, UK.
| | | | | | | |
Collapse
|