Can computer-aided detection with double reading of screening mammograms help decrease the false-negative rate? Initial experience

Artificial intelligence in breast imaging: potentials and challenges

Breast cancer, which is the most common type of malignant tumor among humans, is a leading cause of death in females. Standard treatment strategies, including neoadjuvant chemotherapy, surgery, postoperative chemotherapy, targeted therapy, endocrine therapy, and radiotherapy, are tailored for individual patients. Such personalized therapies have tremendously reduced the threat of breast cancer in females. Furthermore, early imaging screening plays an important role in reducing the treatment cycle and improving breast cancer prognosis. The recent innovative revolution in artificial intelligence (AI) has aided radiologists in the early and accurate diagnosis of breast cancer. In this review, we introduce the necessity of incorporating AI into breast imaging and the applications of AI in mammography, ultrasonography, magnetic resonance imaging, and positron emission tomography/computed tomography based on published articles since 1994. Moreover, the challenges of AI in breast imaging are discussed.

Artificial intelligence for breast cancer detection in mammography and digital breast tomosynthesis: State of the art

Screening for breast cancer with mammography has been introduced in various countries over the last 30 years, initially using analog screen-film-based systems and, over the last 20 years, transitioning to the use of fully digital systems. With the introduction of digitization, the computer interpretation of images has been a subject of intense interest, resulting in the introduction of computer-aided detection (CADe) and diagnosis (CADx) algorithms in the early 2000's. Although they were introduced with high expectations, the potential improvement in the clinical realm failed to materialize, mostly due to the high number of false positive marks per analyzed image. In the last five years, the artificial intelligence (AI) revolution in computing, driven mostly by deep learning and convolutional neural networks, has also pervaded the field of automated breast cancer detection in digital mammography and digital breast tomosynthesis. Research in this area first involved comparison of its capabilities to that of conventional CADe/CADx methods, which quickly demonstrated the potential of this new technology. In the last couple of years, more mature and some commercial products have been developed, and studies of their performance compared to that of experienced breast radiologists are showing that these algorithms are on par with human-performance levels in retrospective data sets. Although additional studies, especially prospective evaluations performed in the real screening environment, are needed, it is becoming clear that AI will have an important role in the future breast cancer screening realm. Exactly how this new player will shape this field remains to be determined, but recent studies are already evaluating different options for implementation of this technology. The aim of this review is to provide an overview of the basic concepts and developments in the field AI for breast cancer detection in digital mammography and digital breast tomosynthesis. The pitfalls of conventional methods, and how these are, for the most part, avoided by this new technology, will be discussed. Importantly, studies that have evaluated the current capabilities of AI and proposals for how these capabilities should be leveraged in the clinical realm will be reviewed, while the questions that need to be answered before this vision becomes a reality are posed.

Stand-alone artificial intelligence - The future of breast cancer screening?

Although computers have had a role in interpretation of mammograms for at least two decades, their impact on performance has not lived up to expectations. However, in the last five years, the field of medical image analysis has undergone a revolution due to the introduction of deep learning convolutional neural networks - a form of artificial intelligence (AI). Because of their considerably higher performance compared to conventional computer aided detection methods, these AI algorithms have resulted in renewed interest in their potential for interpreting breast images in stand-alone mode. For this, first the actual capability of the algorithms, compared to breast radiologists, needs to be well understood. Although early studies have pointed to the comparable performance between AI systems and breast radiologists in interpreting mammograms, these comparisons have been performed in laboratory conditions with limited, enriched datasets. AI algorithms with performance comparable to breast radiologists could be used in a number of different ways, the most impactful being pre-selection, or triaging, of normal screening mammograms that would not need human interpretation. Initial studies evaluating this proposed use have shown very promising results, with the resulting accuracy of the complete screening process not being affected, but with a significant reduction in workload. There is a need to perform additional studies, especially prospective ones, with large screening data sets, to both gauge the actual stand-alone performance of these new algorithms, and the impact of the different implementation possibilities on screening programs.

Artificial Intelligence for Mammography and Digital Breast Tomosynthesis: Current Concepts and Future Perspectives

Although computer-aided diagnosis (CAD) is widely used in mammography, conventional CAD programs that use prompts to indicate potential cancers on the mammograms have not led to an improvement in diagnostic accuracy. Because of the advances in machine learning, especially with use of deep (multilayered) convolutional neural networks, artificial intelligence has undergone a transformation that has improved the quality of the predictions of the models. Recently, such deep learning algorithms have been applied to mammography and digital breast tomosynthesis (DBT). In this review, the authors explain how deep learning works in the context of mammography and DBT and define the important technical challenges. Subsequently, they discuss the current status and future perspectives of artificial intelligence-based clinical applications for mammography, DBT, and radiomics. Available algorithms are advanced and approach the performance of radiologists-especially for cancer detection and risk prediction at mammography. However, clinical validation is largely lacking, and it is not clear how the power of deep learning should be used to optimize practice. Further development of deep learning models is necessary for DBT, and this requires collection of larger databases. It is expected that deep learning will eventually have an important role in DBT, including the generation of synthetic images.

A new approach for detecting abnormalities in mammograms using a computer-aided windowing system based on Otsu's method

Breast cancer is the most common cancer and the leading cause of cancer deaths in women worldwide. This study aimed to provide an automatic windowing method in mammograms, based on the principles of Otsu's thresholding function, to help radiologists more easily detect abnormalities on mammograms. A total of 322 mammographic images from the Mammographic Image Analysis Society (MIAS) database were used in the present study. The image background was removed based on Otsu's method. After selecting the threshold in the computer-aided windowing (CAW) system, the pixel values were kept larger than the threshold and displayed on a grayscale. A radiologist evaluated images randomly before and after CAW. Using CAW, the radiologist correctly diagnosed all healthy images (207 images). A total of 115 mammograms were evaluated to differentiate malignancy from benign masses. All 63 benign images were accurately diagnosed after using CAW. Moreover, of 52 malignant images, all were accurately recognized as malignant except one, which was recognized as benign. Therefore, specificity and sensitivity were significantly improved to 98% and 99.6%, respectively, and the area under the receiver operating characteristic (ROC) curve was calculated to be 0.99. The study showed that the use of CAW can potentially lead to quicker image assessment and improve the diagnostic accuracy of radiologists in differentiating between benign and malignant masses on mammograms.

The frequency of missed breast cancers in women participating in a high-risk MRI screening program

Purpose

To evaluate the frequency of missed cancers on breast MRI in women participating in a high-risk screening program.

Methods

Patient files from women who participated in an increased risk mammography and MRI screening program (2003–2014) were coupled to the Dutch National Cancer Registry. For each cancer detected, we determined whether an MRI scan was available (0–24 months before cancer detection), which was reported to be negative. These negative MRI scans were in consensus re-evaluated by two dedicated breast radiologists, with knowledge of the cancer location. Cancers were scored as invisible, minimal sign, or visible. Additionally, BI-RADS scores, background parenchymal enhancement, and image quality (IQ; perfect, sufficient, bad) were determined. Results were stratified by detection mode (mammography, MRI, interval cancers, or cancers in prophylactic mastectomies) and patient characteristics (presence of BRCA mutation, age, menopausal state).

Results

Negative prior MRI scans were available for 131 breast cancers. Overall 31% of cancers were visible at the initially negative MRI scan and 34% of cancers showed a minimal sign. The presence of a BRCA mutation strongly reduced the likelihood of visible findings in the last negative MRI (19 vs. 46%, P < 0.001). Less than perfect IQ increased the likelihood of visible findings and minimal signs in the negative MRI (P = 0.021).

Conclusion

This study shows that almost one-third of cancers detected in a high-risk screening program are already visible at the last negative MRI scan, and even more in women without BRCA mutations. Regular auditing and double reading for breast MRI screening is warranted.

The importance of early detection of calcifications associated with breast cancer in screening

PURPOSE

The aim of this study was to assess how often women with undetected calcifications in prior screening mammograms are subsequently diagnosed with invasive cancer.

METHODS

From a screening cohort of 63,895 women, exams were collected from 59,690 women without any abnormalities, 744 women with a screen-detected cancer and a prior negative exam, 781 women with a false positive exam based on calcifications, and 413 women with an interval cancer. A radiologist identified cancer-related calcifications, selected by a computer-aided detection system, on mammograms taken prior to screen-detected or interval cancer diagnoses. Using this ground truth and the pathology reports, the sensitivity for calcification detection and the proportion of lesions with visible calcifications that developed into invasive cancer were determined.

RESULTS

The screening sensitivity for calcifications was 45.5%, at a specificity of 99.5%. A total of 68.4% (n = 177) of cancer-related calcifications that could have been detected earlier were associated with invasive cancer when diagnosed.

CONCLUSIONS

Screening sensitivity for detection of malignant calcifications is low. Improving the detection of these early signs of cancer is important, because the majority of lesions with detectable calcifications that are not recalled immediately but detected as interval cancer or in the next screening round are invasive at the time of diagnosis.

Recent Advances in Breast-Specific Imaging

Background

Imaging the breast is a vital component not only for breast cancer screening, but also for diagnosis, evaluation, treatment, and follow-up of patients with breast cancer.

Methods

The author reviews recent advances and also provides her personal experience in describing the status of digital mammography, computer-aided detection, dedicated magnetic resonance imaging (MRI), and positron-emission mammography for evaluating the breast.

Results

Full-field digital mammography is superior to standard mammography in women under 50 years of age and in those with dense breasts. Computer-aided detection assists inexperienced mammographers and enhances detection of microcalcifications in dense breasts. Breast MRI is useful in preoperative evaluation, clarification of indeterminate mammograms, and follow-up of BRCA mutation carriers. The specificity of MRI remains problematic, however. Positron-emission mammography promises enhanced detection of ductal carcinoma in situ (DCIS), even when not associated with microcalcifications, and should aid surgical planning.

Conclusions

These four significant advances in breast imaging have all improved the sensitivity of detecting breast abnormalities. Cost issues, however, may limit the widespread application of these advances.

Creating normograms of dural sinuses in healthy persons using computer-assisted detection for analysis and comparison of cross-section dural sinuses in the brain

Dural sinuses vary in size and shape in many pathological conditions with abnormal intracranial pressure. Size and shape normograms of dural brain sinuses are not available. The creation of such normograms may enable computer-assisted comparison to pathologic exams and facilitate diagnoses. The purpose of this study was to quantitatively evaluate normal magnetic resonance venography (MRV) studies in order to create normograms of dural sinuses using a computerized algorithm for vessel cross-sectional analysis. This was a retrospective analysis of MRV studies of 30 healthy persons. Data were analyzed using a specially developed Matlab algorithm for vessel cross-sectional analysis. The cross-sectional area and shape measurements were evaluated to create normograms. Mean cross-sectional size was 53.27±13.31 for the right transverse sinus (TS), 46.87+12.57 for the left TS (p=0.089) and 36.65+12.38 for the superior sagittal sinus. Normograms were created. The distribution of cross-sectional areas along the vessels showed distinct patterns and a parallel course for the median, 25th, 50th and 75th percentiles. In conclusion, using a novel computerized method for vessel cross-sectional analysis we were able to quantitatively characterize dural sinuses of healthy persons and create normograms.

Using a genetic-fuzzy algorithm as a computer aided diagnosis tool on Saudi Arabian breast cancer database

The computer-aided diagnosis has become one of the major research topics in medical diagnostics. In this research paper, we focus on designing an automated computer diagnosis by combining two major methodologies, namely the fuzzy base systems and the evolutionary genetic algorithms and applying them to the Saudi Arabian breast cancer diagnosis database, to be employed for assisting physicians in the early detection of breast cancers, and hence obtaining an early-computerized diagnosis complementary to that by physicians. Our hybrid algorithm, the genetic-fuzzy algorithm, has produced optimized diagnosis systems that attain high classification performance, in fact, our best three rule system obtained a 97% accuracy, with simple and well interpretive rules, and with a good degree of confidence of 91%.

Quantitative imaging biomarkers for dural sinus patterns in idiopathic intracranial hypertension

OBJECTIVE

To quantitatively characterize transverse dural sinuses (TS) on magnetic resonance venography (MRV) in patients with idiopathic intracranial hypertension (IIH), compared to healthy controls, using a computer assisted detection (CAD) method.

MATERIALS AND METHODS

We retrospectively analyzed MRV studies of 38 IIH patients and 30 controls, matched by age and gender. Data analysis was performed using a specially developed Matlab algorithm for vessel cross-sectional analysis. The cross-sectional area and shape measurements were evaluated in patients and controls.

RESULTS

Mean, minimal, and maximal cross-sectional areas as well as volumetric parameters of the right and left transverse sinuses were significantly smaller in IIH patients than in controls (p < .005 for all). Idiopathic intracranial hypertension patients showed a narrowed segment in both TS, clustering near the junction with the sigmoid sinus. In 36% (right TS) and 43% (left TS), the stenosis extended to >50% of the entire length of the TS, i.e. the TS was hypoplastic. Narrower vessels tended to have a more triangular shape than did wider vessels.

CONCLUSION

Using CAD we precisely quantified TS stenosis and its severity in IIH patients by cross-sectional and volumetric analysis. This method can be used as an exact tool for investigating mechanisms of IIH development and response to treatment.

Analysis of binary responses with outcome-specific misclassification probability in genome-wide association studies

Errors in the binary status of some response traits are frequent in human, animal, and plant applications. These error rates tend to differ between cases and controls because diagnostic and screening tests have different sensitivity and specificity. This increases the inaccuracies of classifying individuals into correct groups, giving rise to both false-positive and false-negative cases. The analysis of these noisy binary responses due to misclassification will undoubtedly reduce the statistical power of genome-wide association studies (GWAS). A threshold model that accommodates varying diagnostic errors between cases and controls was investigated. A simulation study was carried out where several binary data sets (case-control) were generated with varying effects for the most influential single nucleotide polymorphisms (SNPs) and different diagnostic error rate for cases and controls. Each simulated data set consisted of 2000 individuals. Ignoring misclassification resulted in biased estimates of true influential SNP effects and inflated estimates for true noninfluential markers. A substantial reduction in bias and increase in accuracy ranging from 12% to 32% was observed when the misclassification procedure was invoked. In fact, the majority of influential SNPs that were not identified using the noisy data were captured using the proposed method. Additionally, truly misclassified binary records were identified with high probability using the proposed method. The superiority of the proposed method was maintained across different simulation parameters (misclassification rates and odds ratios) attesting to its robustness.

Cancer active targeting by nanoparticles: a comprehensive review of literature

PURPOSE

Cancer is one of the leading causes of death, and thus, the scientific community has but great efforts to improve cancer management. Among the major challenges in cancer management is development of agents that can be used for early diagnosis and effective therapy. Conventional cancer management frequently lacks accurate tools for detection of early tumors and has an associated risk of serious side effects of chemotherapeutics. The need to optimize therapeutic ratio as the difference with which a treatment affects cancer cells versus healthy tissues lead to idea that it is needful to have a treatment that could act a the "magic bullet"-recognize cancer cells only. Nanoparticle platforms offer a variety of potentially efficient solutions for development of targeted agents that can be exploited for cancer diagnosis and treatment. There are two ways by which targeting of nanoparticles can be achieved, namely passive and active targeting. Passive targeting allows for the efficient localization of nanoparticles within the tumor microenvironment. Active targeting facilitates the active uptake of nanoparticles by the tumor cells themselves.

METHODS

Relevant English electronic databases and scientifically published original articles and reviews were systematically searched for the purpose of this review.

RESULTS

In this report, we present a comprehensive review of literatures focusing on the active targeting of nanoparticles to cancer cells, including antibody and antibody fragment-based targeting, antigen-based targeting, aptamer-based targeting, as well as ligand-based targeting.

CONCLUSION

To date, the optimum targeting strategy has not yet been announced, each has its own advantages and disadvantages even though a number of them have found their way for clinical application. Perhaps, a combination of strategies can be employed to improve the precision of drug delivery, paving the way for a more effective personalized therapy.

Who could benefit the most from using a computer-aided detection system in full-field digital mammography?

Background

The computer-aided detection (CAD) system on mammography has the potential to assist radiologists in breast cancer screening. The purpose of this study is to evaluate the diagnostic performance of the CAD system in full-field digital mammography for detecting breast cancer when used by dedicated breast radiologist (BR) and radiology resident (RR), and to reveal who could benefit the most from a CAD application.

Methods

We retrospectively chose 100 image sets from mammographies performed with CAD between June 2008 and June 2010. Thirty masses (15 benign and 15 malignant), 30 microcalcifications (15 benign and 15 malignant), and 40 normal mammography images were included. The participating radiologists consisted of 7 BRs and 13 RRs. We calculated the sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) for total, normal plus microcalcification and normal plus mass both with and without CAD use for each reader. We compared the diagnostic performance values obtained with and without CAD use for the BR and RR groups, respectively. The reading time reviewing one set of 100 images and time reduction with CAD use for the BR and RR groups were also evaluated.

Results

The diagnostic performance was generally higher in the BR group than in the RR group. Sensitivity improved with CAD use in the BR and RR groups (from 81.10 to 84.29% for BR; 75.38 to 77.95% for RR). A tendency for improvement in all diagnostic performance values was observed in the BR group, whereas in the RR group, sensitivity improved but specificity, PPV, and NPV did not. None of the diagnostic performance parameters were significantly different. The mean reading time was shortened with CAD use in both the BR and RR groups (111.6 minutes to 94.3 minutes for BR; 135.5 minutes to 109.8 minutes for RR). The mean time reduction was higher for the RR than that in the BR group.

Conclusions

CAD was helpful for dedicated BRs to improve their diagnostic performance and for RRs to improve the sensitivity in a screening setting. CAD could be essential for radiologists by decreasing reading time without decreasing diagnostic performance.

CAD May Not be Necessary for Microcalcifications in the Digital era, CAD May Benefit Radiologists for Masses

Objective:

The aim of this study was to evaluate the effectiveness of computer-aided detection (CAD) to mark the cancer on digital mammograms at the time of breast cancer diagnosis and also review retrospectively whether CAD marked the cancer if visible on any available prior mammograms, thus potentially identifying breast cancer at an earlier stage. We sought to determine why breast lesions may or may not be marked by CAD. In particular, we analyzed factors such as breast density, mammographic views, and lesion characteristics.

Materials and Methods:

Retrospective review from 2004 to 2008 revealed 3445 diagnosed breast cancers in both symptomatic and asymptomatic patients; 1293 of these were imaged with full field digital mammography (FFDM). After cancer diagnosis, in a retrospective review held by the radiologist staff, 43 of these cancers were found to be visible on prior-year mammograms (false-negative cases); these breast cancer cases are the basis of this analysis. All cases had CAD evaluation available at the time of cancer diagnosis and on prior mammography studies. Data collected included patient demographics, breast density, palpability, lesion type, mammographic size, CAD marks on current- and prior-year mammograms, needle biopsy method, pathology results (core needle and/or surgical), surgery type, and lesion size.

Results:

On retrospective review of the mammograms by the staff radiologists, 43 cancers were discovered to be visible on prior-year mammograms. All 43 cancers were masses (mass classification included mass, mass with calcification, and mass with architectural distortion); no pure microcalcifications were identified in this cohort. Mammograms with CAD applied at the time of breast cancer diagnosis were able to detect 79% (34/43) of the cases and 56% (24/43) from mammograms with CAD applied during prior year(s). In heterogeneously dense/extremely dense tissue, CAD marked 79% (27/34) on mammograms taken at the time of diagnosis and 56% (19/34) on mammograms with CAD applied during the prior year(s). At time of diagnosis, CAD marked lesions in 32% (11/34) on the craniocaudal (CC) view, 21% (7/34) on the mediolateral oblique (MLO) view. Lesion size of those marked by CAD or not marked were similar, the average being 15 and 12 mm, respectively.

Conclusion:

CAD marked cancers on mammograms at the time of diagnosis in 79% of the cases and in 56% of the cases from the mammograms with CAD applied in the prior year(s). Our review demonstrated that CAD can mark invasive breast carcinomas in even dense breast tissue. CAD marked a significant portion on the CC view only, which may be an indicator to radiologists to be especially vigilant when a lesion is marked on this view.

Is single reading with computer-aided detection (CAD) as good as double reading in mammography screening? A systematic review

BACKGROUND

In accordance with European guidelines, mammography screening comprises independent readings by two breast radiologists (double reading). CAD (computer-aided detection) has been suggested to complement or replace one of the two readers (single reading + CAD).The aim of this systematic review is to address the following question: Is the reading of mammographic x-ray images by a single breast radiologist together with CAD at least as accurate as double reading?

METHODS

The electronic literature search included the databases Pub Med, EMBASE and The Cochrane Library. Two independent reviewers assessed abstracts and full-text articles.

RESULTS

1049 abstracts were identified, of which 996 were excluded with reference to inclusion and exclusion criteria; 53 full-text articles were assessed for eligibility. Finally, four articles were included in the qualitative analysis, and one in a GRADE synthesis.

CONCLUSIONS

The scientific evidence is insufficient to determine whether the accuracy of single reading + CAD is at least equivalent to that obtained in standard practice, i.e. double reading where two breast radiologists independently read the mammographic images.

Mammography screening using independent double reading with consensus: is there a potential benefit for computer-aided detection?

BACKGROUND

Double reading improves the cancer detection rate in mammography screening. Single reading with computer-aided detection (CAD) has been considered to be an alternative to double reading. Little is known about the potential benefit of CAD in breast cancer screening with double reading.

PURPOSE

To compare prospective independent double reading of screen-film (SFM) and full-field digital (FFDM) mammography in population-based screening with retrospective standalone CAD performance on the baseline mammograms of the screen-detected cancers and subsequent cancers diagnosed during the follow-up period.

MATERIAL AND METHODS

The study had ethics committee approval. A 5-point rating scale for probability of cancer was used for 23,923 (SFM = 16,983; FFDM = 6940) screening mammograms. Of 208 evaluable cancers, 104 were screen-detected and 104 were subsequent (44 interval and 60 next screening round) cancers. Baseline mammograms of subsequent cancers were retrospectively classified in consensus without information about cancer location, histology, or CAD prompting as normal, non-specific minimal signs, significant minimal signs, and false-negatives. The baseline mammograms of the screen-detected cancers and subsequent cancers were evaluated by CAD. Significant minimal signs and false-negatives were considered 'actionable' and potentially diagnosable if correctly prompted by CAD.

RESULTS

CAD correctly marked 94% (98/104) of the baseline mammograms of the screen-detected cancers (SFM = 95% [61/64]; FFDM = 93% [37/40]), including 96% (23/24) of those with discordant interpretations. Considering only those baseline examinations of subsequent cancers prospectively interpreted as normal and retrospectively categorized as 'actionable', CAD input at baseline screening had the potential to increase the cancer detection rate from 0.43% to 0.51% (P = 0.13); and to increase cancer detection by 16% ([104 + 17]/104) and decrease interval cancers by 20% (from 44 to 35).

CONCLUSION

CAD may have the potential to increase cancer detection by up to 16%, and to reduce the number of interval cancers by up to 20% in SFM and FFDM screening programs using independent double reading with consensus review. The influence of true- and false-positive CAD marks on decision-making can, however, only be evaluated in a prospective clinical study.

CAD e mamografia: por que usar esta ferramenta?

A mamografia representa o melhor método de detecção precoce do câncer de mama, porém cerca de 10% a 30% das lesões mamárias são perdidas no rastreamento, devido a limitações próprias dos observadores humanos. A detecção auxiliada por computador (computer-aided detection - CAD) é uma tecnologia relativamente nova que tem sido implementada em alguns serviços de mamografia, com o intuito de prover uma dupla leitura. Estudos clínicos têm demonstrado que o CAD aumenta a sensibilidade de detecção do câncer da mama, por radiologistas, em até 21%. Um sistema CAD é útil em situações em que exista alta variabilidade interobservador, falta de observadores treinados, ou na impossibilidade de se realizar a dupla leitura com dois ou mais radiologistas. O objetivo desta revisão está baseado na necessidade de atualizar a comunidade médica acerca desta ferramenta, como um método auxiliar, quantitativo, não operador-dependente, e que visa a melhorar a qualidade do diagnóstico do câncer de mama.

False positive marks on unsuspicious screening mammography with computer-aided detection

The contribution of computer-aided detection (CAD) systems as an interpretive aid in screening mammography can be hampered by a high rate of false positive detections. Specificity, false positive rate, and ease of dismissing false positive marks from two CAD systems are retrospectively evaluated. One hundred screening mammographic studies with a BI-RADS assessment code of 1 or 2 and at least 2-year normal mammographic follow-up were retrospectively reviewed using two CAD systems. Breast density, CAD marks, and radiologist's ease of dismissing false positive marks were recorded. Specificities from the two CAD versions considering all marks were 23% and 15% (p value = 0.07); mass marks, 35% and 17% (p value < 0.01); and calcification marks 62% and 75% (p value = 0.01). The two CAD versions did not differ regarding mean and median marks per case for all marks (2.3, 2.0 and 2.3, 2.0, p value = 0.65) or mass marks (1.6, 1.0 and 1.8, 2.0, p value = 0.15), but differed for calcification marks (0.8, 0 and 0.5, 0, p value < 0.01). Slightly higher specificity and fewer marks per case observed in dense breasts did not reach statistical significance. The reviewing radiologist classified most marks from both CAD systems (84% and 88%) as very easy/easy to dismiss. The two CAD versions had small differences in specificity and false positive marks. Differences, although not statistically significant, in specificities and false positive rates between dense and non-dense breasts warrant further research. Most false positive marks are easily dismissed and should not affect clinical performance.

Detection of breast cancer cells using targeted magnetic nanoparticles and ultra-sensitive magnetic field sensors

INTRODUCTION

Breast cancer detection using mammography has improved clinical outcomes for many women, because mammography can detect very small (5 mm) tumors early in the course of the disease. However, mammography fails to detect 10 - 25% of tumors, and the results do not distinguish benign and malignant tumors. Reducing the false positive rate, even by a modest 10%, while improving the sensitivity, will lead to improved screening, and is a desirable and attainable goal. The emerging application of magnetic relaxometry, in particular using superconducting quantum interference device (SQUID) sensors, is fast and potentially more specific than mammography because it is designed to detect tumor-targeted iron oxide magnetic nanoparticles. Furthermore, magnetic relaxometry is theoretically more specific than MRI detection, because only target-bound nanoparticles are detected. Our group is developing antibody-conjugated magnetic nanoparticles targeted to breast cancer cells that can be detected using magnetic relaxometry.

METHODS

To accomplish this, we identified a series of breast cancer cell lines expressing varying levels of the plasma membrane-expressed human epidermal growth factor-like receptor 2 (Her2) by flow cytometry. Anti-Her2 antibody was then conjugated to superparamagnetic iron oxide nanoparticles using the carbodiimide method. Labeled nanoparticles were incubated with breast cancer cell lines and visualized by confocal microscopy, Prussian blue histochemistry, and magnetic relaxometry.

RESULTS

We demonstrated a time- and antigen concentration-dependent increase in the number of antibody-conjugated nanoparticles bound to cells. Next, anti Her2-conjugated nanoparticles injected into highly Her2-expressing tumor xenograft explants yielded a significantly higher SQUID relaxometry signal relative to unconjugated nanoparticles. Finally, labeled cells introduced into breast phantoms were measured by magnetic relaxometry, and as few as 1 million labeled cells were detected at a distance of 4.5 cm using our early prototype system.

CONCLUSIONS

These results suggest that the antibody-conjugated magnetic nanoparticles are promising reagents to apply to in vivo breast tumor cell detection, and that SQUID-detected magnetic relaxometry is a viable, rapid, and highly sensitive method for in vitro nanoparticle development and eventual in vivo tumor detection.

Missed and true interval and screen-detected breast cancers in a population based screening program

RATIONALE AND OBJECTIVES

To increase radiologic knowledge, the distribution of mammographic features on prior screening mammograms of missed interval and screen-detected cancers was compared to the distribution on diagnostic mammograms of screen-detected cancers. The same variables were compared on mammograms of discordant and concordant screen-detected cancers.

MATERIALS AND METHODS

The study was performed in Møre og Romsdal County, Norway, as a part of the quality assurance of the Norwegian Breast Cancer Screening Program. Women were screened using analog techniques and diagnosed from 2002 to 2008. Prior and diagnostic mammograms of 81 interval and 123 screen-detected breast cancers in women aged 50 to 71 years were retrospectively reviewed and classified as either missed or true by four experienced breast radiologists. Mammographic features were classified according to a modified Breast Imaging Reporting and Data System.

RESULTS

Thirty percent (24 of 81) of the interval cancers and 21% (26 of 123) of the screen-detected cancers were classified as missed. Calcifications, alone or in association with mass or asymmetry, tended to be more common on prior mammograms of missed cancers compared to diagnostic mammograms of screen-detected cancers (34% [17 of 50] vs 21% [26 of 123], P = .114), whereas an opposite trend was seen for mass (54% [27 of 50] vs 68% [84 of 123], P = .109). Similar results were seen when comparing discordant and concordant cancers.

CONCLUSIONS

Calcifications represent a challenge in the interpretation of screening mammograms. For educational purposes, the importance of reviewing both interval and screen-detected cancers is obvious. Knowledge gained from systematic reviews might reduce the number of missed cancers on mammographic screening. Performing reviews according to established guidelines would make it possible to compare results across screening programs.

Breast skin-line detection using dynamic programming

In this paper, we present a novel method to extract the breast skin-line based on dynamic programming. Skin-line extraction is an important preprocessing step in CAD systems; however, it is a challenging problem due to the presence of noise, underexposed regions, which results in a low contrast area near the skin-air interface, and artifacts such as labels. Our proposal utilizes the stroma edge to constrain searching for the border. In order to cope with noise, we consider several candidate points for the border interface which are obtained by the Laplace operator applied in pre-defined directions in the mammogram. The breast contour is obtained from the candidate points using a dynamic programming algorithm. This utilizes a criterion of optimality to obtain the optimum contour by minimization of a cost function. The method was evaluated using 82 mammograms whose contour were manually extracted by a radiologist from the mini-MIAS database. The Polyline Distance Measure was evaluated for each contour selected with the proposed method, obtaining a mean error of 2.05 pixels and a standard deviation of 0.80.

Optimal Breast Biopsy Decision-Making Based on Mammographic Features and Demographic Factors

Breast cancer is the most common non-skin cancer affecting women in the United States, where every year more than 20 million mammograms are performed. Breast biopsy is commonly performed on the suspicious findings on mammograms to confirm the presence of cancer. Currently, 700,000 biopsies are performed annually in the U.S.; 55%-85% of these biopsies ultimately are found to be benign breast lesions, resulting in unnecessary treatments, patient anxiety, and expenditures. This paper addresses the decision problem faced by radiologists: When should a woman be sent for biopsy based on her mammographic features and demographic factors? This problem is formulated as a finite-horizon discrete-time Markov decision process. The optimal policy of our model shows that the decision to biopsy should take the age of patient into account; particularly, an older patient's risk threshold for biopsy should be higher than that of a younger patient. When applied to the clinical data, our model outperforms radiologists in the biopsy decision-making problem. This study also derives structural properties of the model, including sufficiency conditions that ensure the existence of a control-limit type policy and nondecreasing control-limits with age.

Radiologists' perceptions of computer aided detection versus double reading for mammography interpretation

RATIONALE AND OBJECTIVES

The aim of this study was to examine radiologists' use and perceptions of computer-aided detection (CAD) and double reading for screening mammography interpretation.

MATERIALS AND METHODS

A mailed survey of 257 community radiologists participating in the national Breast Cancer Surveillance Consortium was used to assess perceptions and practices related to CAD and double reading. Latent class analysis was used to classify radiologists' overall perceptions of CAD and double reading on the basis of their agreement or disagreement with specific statements about CAD and double reading.

RESULTS

Most radiologists (64%) reported using CAD for more than half the screening mammograms they interpreted, but only <5% reported double reading that much. More radiologists perceived that double reading improved cancer detection rates compared to CAD (74% vs 55% reported), whereas fewer radiologists thought that double reading decreased recall rates compared to CAD (50% vs 65% reported). Radiologists with the most favorable perceptions of CAD were more likely to think that CAD improved cancer detection rates without taking too much time compared to radiologists with the most unfavorable overall perceptions. In latent class analysis, an overall favorable perception of CAD was significantly associated with the use of CAD (81%), a higher percentage of workload in screening mammography (80%), academic affiliation (71%), and fellowship training (58%). Perceptions of double reading that were most favorable were associated with academic affiliation (98%).

CONCLUSIONS

Radiologists' perceptions were more favorable toward double reading by a second clinician than by a computer, although fewer used double reading in their own practice. The majority of radiologists perceived both CAD and double reading at least somewhat favorably, although for largely different reasons.

Image analysis for classification of dysplasia in Barrett's esophagus using endoscopic optical coherence tomography

Barrett's esophagus (BE) and associated adenocarcinoma have emerged as a major health care problem. Endoscopic optical coherence tomography is a microscopic sub-surface imaging technology that has been shown to differentiate tissue layers of the gastrointestinal wall and identify dysplasia in the mucosa, and is proposed as a surveillance tool to aid in management of BE. In this work a computer-aided diagnosis (CAD) system has been demonstrated for classification of dysplasia in Barrett's esophagus using EOCT. The system is composed of four modules: region of interest segmentation, dysplasia-related image feature extraction, feature selection, and site classification and validation. Multiple feature extraction and classification methods were evaluated and the process of developing the CAD system is described in detail. Use of multiple EOCT images to classify a single site was also investigated. A total of 96 EOCT image-biopsy pairs (63 non-dysplastic, 26 low-grade and 7 high-grade dysplastic biopsy sites) from a previously described clinical study were analyzed using the CAD system, yielding an accuracy of 84% for classification of non-dysplastic vs. dysplastic BE tissue. The results motivate continued development of CAD to potentially enable EOCT surveillance of large surface areas of Barrett's mucosa to identify dysplasia.

The brain MR Image segmentation techniques and use of diagnostic packages

RATIONALE AND OBJECTIVES

This article provides a survey of segmentation methods for medical images. Usually, classification of segmentation methods is done based on the approaches adopted and the domain of application.

MATERIALS AND METHODS

This survey is conducted on the recent segmentation methods used in biomedical image processing and explores the methods useful for better segmentation. A critical appraisal of the current status of semiautomated and automated methods is made for the segmentation of anatomical medical images emphasizing the advantages and disadvantages. Computer-aided diagnosis (CAD) used by radiologists as a second opinion has become one of the major research areas in medical imaging and diagnostic radiology. A picture archiving communication system (PACS) is an integrated workflow system for managing images and related data that is designed to streamline operations throughout the whole patient care delivery process.

RESULTS

By using PACS, the medical image interpretation may be changed from conventional hard-copy images to soft-copy studies viewed on the systems workstations.

CONCLUSION

The automatic segmentations assist the doctors in making quick diagnosis. The CAD need not be comparable to that of physicians, but is surely complementary.

Dynamic multiple thresholding breast boundary detection algorithm for mammograms

PURPOSE

Automated detection of breast boundary is one of the fundamental steps for computer-aided analysis of mammograms. In this study, the authors developed a new dynamic multiple thresholding based breast boundary (MTBB) detection method for digitized mammograms.

METHODS

A large data set of 716 screen-film mammograms (442 CC view and 274 MLO view) obtained from consecutive cases of an Institutional Review Board approved project were used. An experienced breast radiologist manually traced the breast boundary on each digitized image using a graphical interface to provide a reference standard. The initial breast boundary (MTBB-Initial) was obtained by dynamically adapting the threshold to the gray level range in local regions of the breast periphery. The initial breast boundary was then refined by using gradient information from horizontal and vertical Sobel filtering to obtain the final breast boundary (MTBB-Final). The accuracy of the breast boundary detection algorithm was evaluated by comparison with the reference standard using three performance metrics: The Hausdorff distance (HDist), the average minimum Euclidean distance (AMinDist), and the area overlap measure (AOM).

RESULTS

In comparison with the authors' previously developed gradient-based breast boundary (GBB) algorithm, it was found that 68%, 85%, and 94% of images had HDist errors less than 6 pixels (4.8 mm) for GBB, MTBB-Initial, and MTBB-Final, respectively. 89%, 90%, and 96% of images had AMinDist errors less than 1.5 pixels (1.2 mm) for GBB, MTBB-Initial, and MTBB-Final, respectively. 96%, 98%, and 99% of images had AOM values larger than 0.9 for GBB, MTBB-Initial, and MTBB-Final, respectively. The improvement by the MTBB-Final method was statistically significant for all the evaluation measures by the Wilcoxon signed rank test (p < 0.0001).

CONCLUSIONS

The MTBB approach that combined dynamic multiple thresholding and gradient information provided better performance than the breast boundary detection algorithm that mainly used gradient information.

Invasive breast cancers detected by screening mammography: a detailed comparison of computer-aided detection-assisted single reading and double reading

To compare double reading plus arbitration for discordance, (currently best practice, (BP)) with computer-aided-detection (CAD)-assisted single reading (CAD-R) for detection of invasive cancers detected within BreastScreen Australia. Secondarily, to examine characteristics of cancers detected/rejected using each method. Mammograms of 157 randomly selected double-read invasive cancers were mixed 1:9 with normal cancers (total 1569), all detected in a BreastScreen service. Cancers were detected by two readers or one reader (C2 and C1 cancers, ratio 70:30%) in the program. The 1569 film-screen mammograms were read by two radiologists (reader A (RA) and reader B(RB)), with findings recorded before and after CAD. Discordant findings with BP were resolved by arbitration. We compared CAD-assisted reading (CAD-RA, CAD-RB) with BP, and CAD and arbitration contribution to findings. We correlated cancer size, sensitivity and mammographic density with detection methods. BP sensitivity 90.4% compared with CAD-RA sensitivity 86.6% (P = 0.12) and CAD-RB 94.3% (P = 0.14). CAD-RB specificity was less than BP (P = 0.01). CAD sensitivity was 93%, but readers rejected most positive CAD prompts. After CAD, reader's sensitivity increased 1.9% and specificity dropped 0.2% and 0.8%. Arbitration decreased specificity 4.7%. Receiving operator curves analysis demonstrated BP accuracy better than CAD-RA, borderline significance (P = 0.07), but not CAD-RB. Secondarily, cancer size was similar for BP and CAD-R. Cancers recalled after arbitration (P = 0.01) and CAD-R (P = 0.10) were smaller. No difference in cancer size or sensitivity between reading methods was found with increasing breast density. CAD-R and BP sensitivity and cancer detection size were not significantly different. CAD-R specificity was significantly lower for one reader.

First breast cancer mammography screening program in Mexico: initial results 2005-2006

Breast cancer is the most frequent malignant neoplasia worldwide. In emergent countries as Mexico, an increase has been shown in frequency and mortality, unfortunately, most cases in advanced loco-regional stages developed in young women. The success of breast screening in mortality reduction has been observed since 1995 in Western Europe and the United States, where as many as 40% mortality reduction has been achieved. Most countries guidelines recommends an annual or biannual mammography for all women >40 years of age. In 2005, FUCAM, a nonlucrative civil foundation in Mexico join with Mexico City government, initiated the first voluntary mammography screening program for women >40 years of age residing in Mexico City's Federal District. Mammographies were carried out with analogical mammographs in specially designed mobile units and were performed in the area of women's domiciles. This report includes data from the first 96,828 mammographies performed between March 2005 and December 2006. There were 1% of mammographies in Breast Imaging Reporting and Data System 0, 4, or 5 and 208 out of 949 women with abnormal mammographies (27.7%) had breast cancer, a rate of 2.1 per thousand, most of them in situ or stage I (29.4%) or stage II (42.2%) nevertheless 21% of those women with abnormal mammography did not present for further clinical and radiologic evaluation despite being personally notified at their home addresses. The breast cancer rate of Mexican women submitted to screening mammography is lower than in European or North American women. Family history of breast cancer, nulliparity, absence of breast feeding, and increasing age are factors that increase the risk of breast cancer. Most cancers were diagnosed in women's age below 60 years (68.5%) with a mean age of 53.55 corroborating previous data published. It is mandatory to sensitize and educate our population with regard to accepting to visit the Specialized Breast Centers.

A prospective study of variability in mammographic density during the menstrual cycle

Mammographic breast density has been proposed as a surrogate endpoint in breast cancer prevention studies, but little is known about its variability over time, particularly in relation to menstrual cycle phase. The purpose of this study was to assess variation in breast density on digital mammograms using quantitative and qualitative density measures. Menstrual cycle phase was determined by salivary estradiol and progesterone assays. 73 healthy subjects with regular menses had 1-3 mammograms with paired saliva collection during a 12-month period. The mean difference in density as a percentage of the mean density was calculated for follicular-luteal (n = 50), luteal-luteal (n = 26) and follicular-follicular (n = 23) pairs in the same woman using the same breast. Two density measures (measurement of dense area and BIRADS) were used. The mean luteal density exceeded the mean follicular density by 7.1-9.2%, but density differences between luteal pairs and follicular pairs did not exceed 5%. The intraclass correlation for measurement of dense area was greater than 85% in all phases of the menstrual cycle, but was below 50% for BIRADS for luteal-follicular and follicular-follicular pairs. Our study provides estimates of the amount of variation in mammographic density during the menstrual cycle, and that inherent in repeated density measurement in premenopausal women, and suggests that menstrual phase of mammographic evaluation should be controlled for in intervention studies where density is being used as a surrogate measure.

Computer-aided detection of breast carcinoma in standard mammographic projections with digital mammography

PURPOSE

A retrospective evaluation of the ability of computer-aided detection (CAD) ability to identify breast carcinoma in standard mammographic projections.

MATERIALS AND METHODS

Forty-five biopsy proven lesions in 44 patients imaged digitally with CAD applied at examination were reviewed. Forty-four screening BIRADS category 1 digital mammography examinations were randomly identified to serve as a comparative normal/control population. Data included patient age; BIRADS breast density; lesion type, size, and visibility; number, type, and location of CAD marks per image; CAD ability to mark lesions; needle core and surgical pathologic correlation.

RESULTS

The CAD lesion/case sensitivity of 87% (n = 39), image sensitivity of 69% (n = 31) for mediolateral oblique view and 78% (n = 35) for the craniocaudal view was found. The average false positive rate in 44 normal screening cases was 2.0 (range 1-8). The 2.0 figure is based on 88 reported false positive CAD marks in 44 normal screening exams: 98% (n = 44) lesions proceeded to excision; initial pathology upgraded at surgical excision from in situ to invasive disease in 24% (n = 9) lesions.

CONCLUSION

CAD demonstrated potential to detect mammographically visible cancers in standard projections for all lesion types.

Differentiation of common large sellar-suprasellar masses effect of artificial neural network on radiologists' diagnosis performance

RATIONALE AND OBJECTIVES

When pituitary adenoma, craniopharyngioma, and Rathke's cleft cyst grow in the sellar and suprasellar region, it is often difficult to differentiate among these three lesions on magnetic resonance (MR) images. The purpose of this study was to apply an artificial neural network (ANN) for differential diagnosis among these three lesions with MR images and retrospectively evaluate the effect of ANN output on radiologists' performance.

MATERIALS AND METHODS

Forty-three patients with sellar-suprasellar masses were studied. The ANN was designed to differentiate among pituitary adenoma, craniopharyngioma, and Rathke's cleft cyst by using patients' ages and nine MR image findings obtained by three neuroradiologists using a subjective rating scale. In the observer performance test, MR images were viewed by nine radiologists, including four neuroradiologists and five general radiologists, first without and then with ANN output. The radiologists' performance was evaluated using receiver-operating characteristic analysis with a continuous rating scale.

RESULTS

The ANN showed high performance in differentiation among the three lesions (area under the receiver-operating characteristic curve, 0.990). The average area under the curve for all radiologists for differentiation among the three lesions increased significantly from 0.910 to 0.985 (P = .0024) when they used the computer output. Areas under the curves for the general radiologists and neuroradiologists increased from 0.876 to 0.983 (P = .0083) and from 0.952 to 0.989 (P = .038), respectively.

CONCLUSION

In diagnostic performance for differentiation among pituitary macroadenoma, craniopharyngioma, and Rathke's cleft cyst with MR imaging, the ANN resulted in parity between neuroradiologists and general radiologists.

Single reading with computer-aided detection for screening mammography

BACKGROUND

The sensitivity of screening mammography for the detection of small breast cancers is higher when the mammogram is read by two readers rather than by a single reader. We conducted a trial to determine whether the performance of a single reader using a computer-aided detection system would match the performance achieved by two readers.

METHODS

The trial was designed as an equivalence trial, with matched-pair comparisons between the cancer-detection rates achieved by single reading with computer-aided detection and those achieved by double reading. We randomly assigned 31,057 women undergoing routine screening by film mammography at three centers in England to double reading, single reading with computer-aided detection, or both double reading and single reading with computer-aided detection, at a ratio of 1:1:28. The primary outcome measures were the proportion of cancers detected according to regimen and the recall rates within the group receiving both reading regimens.

RESULTS

The proportion of cancers detected was 199 of 227 (87.7%) for double reading and 198 of 227 (87.2%) for single reading with computer-aided detection (P=0.89). The overall recall rates were 3.4% for double reading and 3.9% for single reading with computer-aided detection; the difference between the rates was small but significant (P<0.001). The estimated sensitivity, specificity, and positive predictive value for single reading with computer-aided detection were 87.2%, 96.9%, and 18.0%, respectively. The corresponding values for double reading were 87.7%, 97.4%, and 21.1%. There were no significant differences between the pathological attributes of tumors detected by single reading with computer-aided detection alone and those of tumors detected by double reading alone.

CONCLUSIONS

Single reading with computer-aided detection could be an alternative to double reading and could improve the rate of detection of cancer from screening mammograms read by a single reader. (ClinicalTrials.gov number, NCT00450359.)

Advances in computer-aided diagnosis for breast cancer

PURPOSE OF REVIEW

Computer-aided diagnosis (CAD) is a technology used for the detection and characterization of cancer. Although CAD is not limited to a single type of cancer, a large number of CAD systems to date have been designed and used for breast cancer. The aim of this review is to discuss the current state of the CAD systems for breast-cancer diagnosis, their application as a second reader in clinical practice, and studies that have evaluated the effect of CAD on radiologists' performance.

RECENT FINDINGS

A large number of CAD applications are being developed for different imaging modalities. Owing to commercially available Food and Drug Administration (FDA) approved systems, the main clinical use of CAD to date is for screen-film mammography. Many studies have shown that CAD improves radiologists' performance. A large number of academic institutions have devoted a substantial research effort to developing CAD methods.

SUMMARY

CAD systems will play an increasingly important role in the clinic as a second reader. Clinical trials have shown that CAD can improve the accuracy of breast-cancer detection. Preclinical studies have demonstrated the potential of CAD to improve the classification of malignant and benign lesions. An increased number of CAD systems are being developed for different breast-imaging modalities.