The Use of Machine Learning in Eye Tracking Studies in Medical Imaging: A Review

Machine learning (ML) has revolutionized medical image-based diagnostics. In this review, we cover a rapidly emerging field that can be potentially significantly impacted by ML - eye tracking in medical imaging. The review investigates the clinical, algorithmic, and hardware properties of the existing studies. In particular, it evaluates 1) the type of eye-tracking equipment used and how the equipment aligns with study aims; 2) the software required to record and process eye-tracking data, which often requires user interface development, and controller command and voice recording; 3) the ML methodology utilized depending on the anatomy of interest, gaze data representation, and target clinical application. The review concludes with a summary of recommendations for future studies, and confirms that the inclusion of gaze data broadens the ML applicability in Radiology from computer-aided diagnosis (CAD) to gaze-based image annotation, physicians' error detection, fatigue recognition, and other areas of potentially high research and clinical impact.

Clinical applications of artificial intelligence in radiology

The rapid growth of medical imaging has placed increasing demands on radiologists. In this scenario, artificial intelligence (AI) has become an attractive partner, one that may complement case interpretation and may aid in various non-interpretive aspects of the work in the radiological clinic. In this review, we discuss interpretative and non-interpretative uses of AI in the clinical practice, as well as report on the barriers to AI's adoption in the clinic. We show that AI currently has a modest to moderate penetration in the clinical practice, with many radiologists still being unconvinced of its value and the return on its investment. Moreover, we discuss the radiologists' liabilities regarding the AI decisions, and explain how we currently do not have regulation to guide the implementation of explainable AI or of self-learning algorithms.

Special Section Editorial: Artificial Intelligence for Medical Imaging in Clinical Practice

The editorial introduces the JMI Special Section on Artificial Intelligence for Medical Imaging in Clinical Practice.

Assessing satisfaction of search in virtual mammograms for experienced and novice searchers

Purpose

Satisfaction of search (SOS) is a phenomenon where searchers are more likely to miss a lesion/target after detecting a first lesion/target. Here, we investigated SOS for masses and calcifications in virtual mammograms with experienced and novice searchers to determine the extent to which: (1) SOS affects breast lesion detection, (2) similarity between lesions impacts detection, and (3) experience impacts SOS rates.

Approach

The open virtual clinical trials framework was used to simulate the breast anatomy of patients, and up to two simulated masses and/or single-calcifications were inserted into the breast models. Experienced searchers (residents, fellows, and radiologists with breast imaging experience) and novice searchers (undergraduates who had no breast imaging experience) were instructed to search for up to two lesions (masses and calcifications) per image.

Results

2 × 2 mixed factors analysis of variances (ANOVAs) were run with: (1) single versus second lesion hit rates, (2) similar versus dissimilar second-lesion hit rates, and (3) similar versus dissimilar second-lesion response times as within-subject factors and experience as the between subject's factor. The ANOVAs demonstrated that: (1) experienced and novice searchers made a significant amount of SOS errors, (2) similarity had little impact on experienced searchers, but novice searchers were more likely to miss a dissimilar second lesion compared to when it was similar to a detected first lesion, (3) experienced and novice searchers were faster at finding similar compared to dissimilar second lesions.

Conclusions

We demonstrated that SOS is a significant cause of lesion misses in virtual mammograms and that reader experience impacts detection rates for similar compared to dissimilar abnormalities. These results suggest that experience may impact strategy and/or recognition with theoretical implications for determining why SOS occurs.

Fifty years of SPIE Medical Imaging proceedings papers

Purpose: To commemorate the 50th anniversary of the first SPIE Medical Imaging meeting, we highlight some of the important publications published in the conference proceedings. Approach: We determined the top cited and downloaded papers. We also asked members of the editorial board of the Journal of Medical Imaging to select their favorite papers. Results: There was very little overlap between the three methods of highlighting papers. The downloads were mostly recent papers, whereas the favorite papers were mostly older papers. Conclusions: The three different methods combined provide an overview of the highlights of the papers published in the SPIE Medical Imaging conference proceedings over the last 50 years.

Special Section Guest Editorial: Conclusion to the Special Series on 2D and 3D Imaging: Perspectives in Human and Model Observer Performance

Guest editors Claudia Mello-Thoms, Craig K. Abbey, and Elizabeth A. Krupinski conclude the JMI Special Series on 2D and 3D Imaging, with commentary on the contributions.

Introducing the Special Series on 2D and 3D Imaging: Perspectives in Human and Model Observer Performance

Guest editors Claudia Mello-Thoms, Craig Abbey, and Elizabeth A. Krupinski introduce the Special Series on 2D and 3D Imaging: Perspectives in Human and Model Observer Performance.

Can a Machine Learn from Radiologists' Visual Search Behaviour and Their Interpretation of Mammograms-a Deep-Learning Study

Visual search behaviour and the interpretation of mammograms have been studied for errors in breast cancer detection. We aim to ascertain whether machine-learning models can learn about radiologists' attentional level and the interpretation of mammograms. We seek to determine whether these models are practical and feasible for use in training and teaching programmes. Eight radiologists of varying experience levels in reading mammograms reviewed 120 two-view digital mammography cases (59 cancers). Their search behaviour and decisions were captured using a head-mounted eye-tracking device and software allowing them to record their decisions. This information from radiologists was used to build an ensembled machine-learning model using top-down hierarchical deep convolution neural network. Separately, a model to determine type of missed cancer (search, perception or decision-making) was also built. Analysis and comparison of variants of these models using different convolution networks with and without transfer learning were also performed. Our ensembled deep-learning network architecture can be trained to learn about radiologists' attentional level and decisions. High accuracy (95%, p value ≅ 0 [better than dumb/random model]) and high agreement between true and predicted values (kappa = 0.83) in such modelling can be achieved. Transfer learning techniques improve by < 10% with the performance of this model. We also show that spatial convolution neural networks are insufficient in determining the type of missed cancers. Ensembled hierarchical deep convolution machine-learning models are plausible in modelling radiologists' attentional level and their interpretation of mammograms. However, deep convolution networks fail to characterise the type of false-negative decisions.

Computer-Assisted Nuclear Atypia Scoring of Breast Cancer: a Preliminary Study

Inter-pathologist agreement for nuclear atypia scoring of breast cancer is poor. To address this problem, previous studies suggested some criteria for describing the variations appearance of tumor cells relative to normal cells. However, these criteria were still assessed subjectively by pathologists. Previous studies used quantitative computer-extracted features for scoring. However, application of these tools is limited as further improvement in their accuracy is required. This study proposes COMPASS (COMputer-assisted analysis combined with Pathologist's ASSessment) for reproducible nuclear atypia scoring. COMPASS relies on both cytological criteria assessed subjectively by pathologists as well as computer-extracted textural features. Using machine learning, COMPASS combines these two sets of features and output nuclear atypia score. COMPASS's performance was evaluated using 300 images for which expert-consensus derived reference nuclear pleomorphism scores were available, and they were scanned by two scanners from different vendors. A personalized model was built for three pathologists who gave scores to six atypia-related criteria for each image. Leave-one-out cross validation (LOOCV) was used. COMPASS was trained and tested for each pathologist separately. Percentage agreement between COMPASS and the reference nuclear scores was 93.8%, 92.9%, and 93.1% for three pathologists. COMPASS's performance in nuclear grading was almost identical for both scanners, with Cohen's kappa ranging from 0.80 to 0.86 for different pathologists and different scanners. Independently, the images were also assessed by two experienced senior pathologists. Cohen's kappa of COMPASS was comparable to the Cohen's kappa for two senior pathologists (0.79 and 0.68).

Visual search in breast imaging

Breast cancer is the most common cancer among females worldwide and large volumes of breast images are produced and interpreted annually. As long as radiologists interpret these images, the diagnostic accuracy will be limited by human factors and both false-positive and false-negative errors might occur. By understanding visual search in breast images, we may be able to identify causes of diagnostic errors, find ways to reduce them, and also provide a better education to radiology residents. Many visual search studies in breast radiology have been devoted to mammography. These studies showed that 70% of missed lesions on mammograms attract radiologists' visual attention and that a plethora of different reasons, such as satisfaction of search, incorrect background sampling, and incorrect first impression can cause diagnostic errors in the interpretation of mammograms. Recently, highly accurate tools, which rely on both eye-tracking data and the content of the mammogram, have been proposed to provide feedback to the radiologists. Improving these tools and determining the optimal pathway to integrate them in the radiology workflow could be a possible line of future research. Moreover, in the past few years deep learning has led to improving diagnostic accuracy of computerized diagnostic tools and visual search studies will be required to understand how radiologists interact with the prompts from these tools, and to identify the best way to utilize them. Visual search in other breast imaging modalities, such as breast ultrasound and digital breast tomosynthesis, have so far received less attention, probably due to associated complexities of eye-tracking monitoring and analysing the data. For example, in digital breast tomosynthesis, scrolling through the image results in longer trials, adds a new factor to the study's complexity and makes calculation of gaze parameters more difficult. However, considering the wide utilization of three-dimensional imaging modalities, more visual search studies involving reading stack-view examinations are required in the future. To conclude, in the past few decades visual search studies provided extensive understanding about underlying reasons for diagnostic errors in breast radiology and characterized differences between experts' and novices' visual search patterns. Further visual search studies are required to investigate radiologists' interaction with relatively newer imaging modalities and artificial intelligence tools.

Benefits of Independent Double Reading in Digital Mammography: A Theoretical Evaluation of All Possible Pairing Methodologies

RATIONALE AND OBJECTIVES

To establish the efficacy of pairing readers randomly and evaluate the merits of developing optimal pairing methodologies.

MATERIALS AND METHODS

Sensitivity, specificity, and proportion correct were computed for three different case sets that were independently read by 16 radiologists. Performance of radiologists as single readers was compared to expected double reading performance. We theoretically evaluated all possible pairing methodologies. Bootstrap resampling methods were used for statistical analyses.

RESULTS

Significant improvements in expected performance for double versus single reading (ie, delta performance) were shown for all performance measures and case-sets (p ≤ .003), with overall delta performance across all theoretically possible pairing schemes (n = 10,395) ranging between .05 and .08. Delta performance for the 20 best pairing schemes was significant (p < .001) and ranged between .07 and .10. Delta performance for 20 random pairing schemes was also significant (p ≤ .003) and ranged between .05 and .08. Delta performance for the 20 worst pairing schemes ranged between .03 and .06, reaching significance in delta proportion correct (p ≤ .021) for all three case-sets and in delta specificity for two case-sets (p ≤ .033) but not for a third case-set (p = .131), and not reaching significance in delta sensitivity for any of the three case-sets (.098 ≥ p ≥ .067).

CONCLUSION

Significant benefits accrue from double reading, and while random reader pairing achieves most double reading benefits, a strategic pairing approach may maximize the benefits of double reading.

Radiologists’ Performance at Reduced Recall Rates in Mammography: A Laboratory Study

Rationale and objectives:

Target recall rates are often used as a performance indicator in mammography screening programs with the intention of reducing false positive decisions, over diagnosis and anxiety for participants. However, the relationship between target recall rates and cancer detection is unclear, especially when readers are directed to adhere to a predetermined rate. The purpose of this study was to explore the effect of setting different recall rates on radiologist’s performance.

Materials and Methods:

Institutional ethics approval was granted and informed consent was obtained from each participating radiologist. Five experienced breast imaging radiologists read a single test set of 200 mammographic cases (20 abnormal and 180 normal). The radiologists were asked to identify each case that they required to be recalled in three different recall conditions; free recall, 15% and 10% and mark the location of any suspicious lesions.

Results:

Wide variability in recall rates was observed when reading at free recall, ranging from 18.5% to 34.0%. Readers demonstrated significantly reduced performance when reading at prescribed recall rates, with lower sensitivity (H=12.891, P=0.002), case location sensitivity (H=12.512, P=0.002) and ROC AUC (H=11.601, P=0.003) albeit with an increased specificity (H=12.704, P=0.002). However, no significant changes were evident in lesion location sensitivity (H=1.982, P=0.371) and JAFROC FOM (H=1.820, P=0.403).

Conclusion:

In this laboratory study, reducing the number of recalled cases to 10% significantly reduced radiologists’ performance with lower detection sensitivity, although a significant improvement in specificity was observed.

Observer Variability in Breast Cancer Diagnosis between Countries with and without Breast Screening

RATIONAL AND OBJECTIVES

Image reporting is a vital component of patient management depending on individual radiologists' performance. Our objective was to explore mammographic diagnostic efficacy in a country where breast cancer screening does not exist.

MATERIALS AND METHODS

Two mammographic test sets were used: a typical screening (TS) and high-difficulty (HD) test set. Nonscreening (NS) radiologists (n = 11) read both test sets, while 52 and 49 screening radiologists read the TS and HD test sets, respectively. The screening radiologists were classified into two groups: a less experienced (LE) group with ≤5 years' experience and a more experienced (ME) group with ≥5 years' experience. A Kruskal-Wallis and Tukey-Kramer post hoc test were used to compare reading performance among reader groups, and the Wilcoxon matched pairs tests was used to compare TS and ND test sets for the NS radiologists.

RESULTS

Across the three reader groups, there were significant differences in case sensitivity (χ² [2] = 9.4, P = .008), specificity (χ² [2] = 10.3, P = .006), location sensitivity (χ² [2] = 19.8, P < .001), receiver operating characteristics, area under the curve (χ² [2] = 19.7, P < .001) and jack-knife free-response receiver operating characteristics (JAFROCs) (χ² [2] = 18.1, P < .001). NS performance for all measured scores was significantly lower than those for the ME readers (P < .006), while only location sensitivity was lower (χ² [2] = 17.5, P = .026) for the NS compared to the LE group. No other significant differences were observed.

CONCLUSION

Large variations in mammographic performance exist between radiologists from screening and nonscreening countries.

A review of factors influencing radiologists' visual search behaviour

This narrative literature review aims to identify the various factors that have significant impact on radiologists' visual search patterns. Identifying the factors that influences readers' visual search behaviour helps to understand their perception and interpretation of medical images, which in turn could lead to the development and implementation of effective strategies that could aid in improving the ability to detect abnormalities. Databases including PubMed, MedLine, Web of Science and ScienceDirect were searched using terms 'visual search', 'eye-tracking', 'radiology OR radiography', 'mammogram OR mammography' published since the early 1960s until June 30, 2016. Some of the factors that have been identified to significantly influence radiologists' visual search patterns were (i) readers' expertise, (ii) Satisfaction of Search, (iii) readers' visual fatigue, (iv) readers' confidence in reporting abnormalities, (v) training received and (vi) readers' prior knowledge. Readers' level of expertise was the factor that has been identified to have the most significant impact on their visual search pattern. Eye-tracking studies have shown the differences in visual search patterns of readers with different levels of experience and not so surprisingly, more experienced readers have shown effective visual search strategies. Readers' expertise has also been found to have significant impact in their confidence in reporting abnormalities and their ability to discriminate lesions from background structures in medical images.

Can eye-tracking metrics be used to better pair radiologists in a mammogram reading task?

PURPOSE

To propose a framework for optimal pairing of radiologists when reading mammograms based on their search patterns.

MATERIALS AND METHODS

Four experienced and four less-experienced radiologists were asked to assess 120 cases (59 with cancers) while their eye positions were tracked. Fourteen eye-tracking metrics were extracted to quantify the differences among radiologists' visual search pattern. For each radiologist and metric, less-experienced radiologists and expert readers were ranked based on the level of similarities in gaze patterns (from the most different to the most similar). Less-experienced readers and experts were also ranked based on the values of area under the receiver operating characteristic curve (AUC) after pairing (the best possible way of ranking). Using the Kendall's tau distance, rankings based on different metrics were compared with the best possible ranking. Using paired Wilcoxon signed-rank test, the AUC values when pairing in the best way were compared with pairing based on different metrics. Finally, we investigated the robustness of pairing strategies against the small sample size.

RESULTS

For ranking the experienced radiologists, results from eight metrics were as good as the best possible ranking. For the less-experienced ones, only one metric resulted in a ranking comparable to the best possible way of ranking. The AUC values of pairings based on these metrics did not differ significantly from the best pairing scenario. Compared to the pairings based on the cognitive metrics, the ranking based on AUC values varied more greatly with the sample size, suggesting that it is less robust against the small sample size compared to the cognitive metrics.

CONCLUSION

Different pairings may have different effects on performance; some are detrimental while some improve the performance of the pair. Using the suggested cognitive metrics, we can optimize the pairings even with a small dataset.

Modeling visual search behavior of breast radiologists using a deep convolution neural network

Visual search, the process of detecting and identifying objects using eye movements (saccades) and foveal vision, has been studied for identification of root causes of errors in the interpretation of mammograms. The aim of this study is to model visual search behavior of radiologists and their interpretation of mammograms using deep machine learning approaches. Our model is based on a deep convolutional neural network, a biologically inspired multilayer perceptron that simulates the visual cortex and is reinforced with transfer learning techniques. Eye-tracking data were obtained from eight radiologists (of varying experience levels in reading mammograms) reviewing 120 two-view digital mammography cases (59 cancers), and it has been used to train the model, which was pretrained with the ImageNet dataset for transfer learning. Areas of the mammogram that received direct (foveally fixated), indirect (peripherally fixated), or no (never fixated) visual attention were extracted from radiologists' visual search maps (obtained by a head mounted eye-tracking device). These areas along with the radiologists' assessment (including confidence in the assessment) of the presence of suspected malignancy were used to model: (1) radiologists' decision, (2) radiologists' confidence in such decisions, and (3) the attentional level (i.e., foveal, peripheral, or none) in an area of the mammogram. Our results indicate high accuracy and low misclassification in modeling such behaviors.

Mammographic detection of breast cancer in a non-screening country

OBJECTIVE:

To compare the diagnostic accuracy between radiologists' from a country with and without breast cancer screening.

METHODS:

All participating radiologists gave informed consent. A test-set involving 60 mammographic cases (20 cancer and 40 non-cancer) were read by 11 radiologists from a non-screening (NS) country during a workshop in July 2016. 52 radiologists from a screening country read the same test-set at the Royal Australian and New Zealand College of Radiologists' meetings in July 2015. The screening radiologists were classified into two groups: those with less than or equal to 5 years of experience; those with more than 5 years of experience, and each group was compared to the group of NS radiologists. A Kruskal-Wallis test followed by post-hoc multiple comparisons test were used to compare measures of diagnostic accuracy among the reader groups.

RESULTS:

The diagnostic accuracy of the NS radiologists was significantly lower in terms of sensitivity [mean = 54.0; 95% confidence interval (CI) (40.0-67.0)], location sensitivity [mean = 26.0; 95% CI (16.0-37.0)], receive roperating characteristic area under curve [mean = 73.0; 95% CI (66.5-81.0)] and Jackknifefree-response receiver operating characteristics figure-of-merit [mean = 45.0; 95% CI (40.0-50.0)] when compared with the less and more experienced screening radiologists, whilst no difference in specificity [mean = 75.0; 95% CI (70.0- 81.0)] was found. No significant differences in all measured diagnostic accuracy were found between the two groups of screening radiologists.

CONCLUSION:

The mammographic performance of a group of radiologists from a country without screening program was suboptimal compared with radiologists from Australia.

ADVANCES IN KNOWLEDGE:

Identifying mammographic performance in developing countries is required to optimize breast cancer diagnosis.

Recurrence quantification analysis of radiologists' scanpaths when interpreting mammograms

PURPOSE

The purpose of this study was to Propose a classifier based on recurrence quantification analysis (RQA) metrics for distinguishing experts' scanpaths from those of less-experienced readers and to explore the association of spatiotemporal dynamics of the mammographic scanpaths with the characteristics of cases and radiologists using RQA metrics.

MATERIALS AND METHODS

Eye movements were recorded from eight radiologists (two cohorts: four experienced and four less-experienced) while reading 120 mammograms (59 cancer, 61 normal). Ten RQA measures were extracted for each recorded scanpath. The measures described the temporal distribution of recurrent fixations as well as laminar and deterministic eye movements. Recurrent fixations are fixations that are located close to a previously fixated point in a scanpath. Deterministic eye movements represent looking back and forth between two locations, while laminar eye movements indicate detailed scanning of an area with consecutive fixations. The RQA metrics along with six conventional eye-tracking parameters were used to construct a classifier for distinguishing experts' scanpaths from those of less-experienced readers. Leave-one-out cross validation was used for evaluating the classifier. For each reader cohort, the ANOVA analysis was done to study the relationship of RQA measures with breast density, case pathology, readers' expertise, and readers' decisions on the case. The proportions of laminar and deterministic movements involved fixations in the location of lesions were also compared for two reader cohorts using two proportion z-tests.

RESULTS

All RQA measures differed significantly between scanpaths of experienced readers and those of less-experienced readers. The classifier achieved an area under the receiver operating characteristic curve of 0.89 (0.87-0.91) for detecting experts' scanpaths. Proportionately more refixations and laminar and deterministic sequences were in the location of the lesion for the experienced cohort compared to the less-experienced cohort (all P-values < 0.001). Eight and four RQA measures differed between normal and cancer cases for the experienced and less experienced readers, respectively. None of metrics differed between fatty and dense breasts for the less experienced readers, while two measures resulted into a significant difference for the experienced readers. For experts, six measures differed significantly between true negatives and false positives and nine were significantly different between true positives and false negatives. For the less-experienced cohort, the corresponding figures were seven and one measures, respectively.

CONCLUSION

The RQA measures can quantify the differences among experienced and less experienced radiologists. They also capture differences among experts' scanpaths related to case pathology and radiologists' decisions on the case.

MuDeRN: Multi-category classification of breast histopathological image using deep residual networks

MOTIVATION

Identifying carcinoma subtype can help to select appropriate treatment options and determining the subtype of benign lesions can be beneficial to estimate the patients' risk of developing cancer in the future. Pathologists' assessment of lesion subtypes is considered as the gold standard, however, sometimes strong disagreements among pathologists for distinction among lesion subtypes have been previously reported in the literature.

OBJECTIVE

To propose a framework for classifying hematoxylin-eosin stained breast digital slides either as benign or cancer, and then categorizing cancer and benign cases into four different subtypes each.

MATERIALS AND METHODS

We used data from a publicly available database (BreakHis) of 81 patients where each patient had images at four magnification factors (×40, ×100, ×200, and ×400) available, for a total of 7786 images. The proposed framework, called MuDeRN (MUlti-category classification of breast histopathological image using DEep Residual Networks) consisted of two stages. In the first stage, for each magnification factor, a deep residual network (ResNet) with 152 layers has been trained for classifying patches from the images as benign or malignant. In the next stage, the images classified as malignant were subdivided into four cancer subcategories and those categorized as benign were classified into four subtypes. Finally, the diagnosis for each patient was made by combining outputs of ResNets' processed images in different magnification factors using a meta-decision tree.

RESULTS

For the malignant/benign classification of images, MuDeRN's first stage achieved correct classification rates (CCR) of 98.52%, 97.90%, 98.33%, and 97.66% in ×40, ×100, ×200, and ×400 magnification factors respectively. For eight-class categorization of images based on the output of MuDeRN's both stages, CCRs in four magnification factors were 95.40%, 94.90%, 95.70%, and 94.60%. Finally, for making patient-level diagnosis, MuDeRN achieved a CCR of 96.25% for eight-class categorization.

CONCLUSIONS

MuDeRN can be helpful in the categorization of breast lesions.

Mammographic Appearances in Mongolia: Causal Factors for Varying Densities

Objective: Mammographic density (MD) is a significant risk factor for breast cancer and an important determinant for establishing efficiency of any screening program. Currently, the distribution and influential factors of MD is unknown among Mongolian women. This work aims to characterize MD of Mongolian women. Methods: The ethical approval was obtained from Research Ethics Board of the University of Sydney (2014/973) and National Ethic Committee from Ministry of Mongolia (2015/04). We recruited 1985 women aged 16-83 from the National Cancer Center in Mongolia for whom MD and age of each woman was known. From this total group, 983 women also had additional available details on height, weight, body mass index (BMI) and area of residency. We investigated the association of each of these variables with breast density, which was assessed by using the Breast Imaging Reporting and Data System (BIRADS) lexicon. Univariate and multivariate regression analyses were conducted to explore the importance of these variables as predictors of MD. Results: Category B (33%) was the most common type of MD, whereas 25%, 18% and 24% of women belonged to the category A, C and D respectively. The univariate analysis demonstrated that, younger women had more dens breasts than their older counterparts (OR=6.8). Also, increased MD was significantly (p<0.05) associated with decreased weight (OR=4.5), increased height (OR=0.4) and lower BMI (OR=13.2). Urban women had significantly higher MD compared with rural counterparts (OR=2.2). In the multivariate analysis, 75% of variation in MD was explained by age (OR=4.5) and BMI (OR=7.3). Conclusion: A high proportion of Mongolian women have very high density breasts and age and body size are key factors determining MD among these women.

Determining Image Processing Features Describing the Appearance of Challenging Mitotic Figures and Miscounted Nonmitotic Objects

Context:

Previous studies showed that the agreement among pathologists in recognition of mitoses in breast slides is fairly modest.

Aims:

Determining the significantly different quantitative features among easily identifiable mitoses, challenging mitoses, and miscounted nonmitoses within breast slides and identifying which color spaces capture the difference among groups better than others.

Materials and Methods:

The dataset contained 453 mitoses and 265 miscounted objects in breast slides. The mitoses were grouped into three categories based on the confidence degree of three pathologists who annotated them. The mitoses annotated as “probably a mitosis” by the majority of pathologists were considered as the challenging category. The miscounted objects were recognized as a mitosis or probably a mitosis by only one of the pathologists. The mitoses were segmented using k-means clustering, followed by morphological operations. Morphological, intensity-based, and textural features were extracted from the segmented area and also the image patch of 63 × 63 pixels in different channels of eight color spaces. Holistic features describing the mitoses' surrounding cells of each image were also extracted.

Statistical Analysis Used:

The Kruskal–Wallis H-test followed by the Tukey-Kramer test was used to identify significantly different features.

Results:

The results indicated that challenging mitoses were smaller and rounder compared to other mitoses. Among different features, the Gabor textural features differed more than others between challenging mitoses and the easily identifiable ones. Sizes of the non-mitoses were similar to easily identifiable mitoses, but nonmitoses were rounder. The intensity-based features from chromatin channels were the most discriminative features between the easily identifiable mitoses and the miscounted objects.

Conclusions:

Quantitative features can be used to describe the characteristics of challenging mitoses and miscounted nonmitotic objects.

An investigation into the mammographic appearances of missed breast cancers when recall rates are reduced

OBJECTIVE

This study investigated whether certain mammographic appearances of breast cancer are missed when radiologists read at lower recall rates.

METHODS

5 radiologists read 1 identical test set of 200 mammographic (180 normal cases and 20 abnormal cases) 3 times and were requested to adhere to 3 different recall rate conditions: free recall, 15% and 10%. The radiologists were asked to mark the locations of suspicious lesions and provide a confidence rating for each decision. An independent expert radiologist identified the various types of cancers in the test set, including the presence of calcifications and the lesion location, including specific mammographic density.

RESULTS

Radiologists demonstrated lower sensitivity and receiver operating characteristic area under the curve for non-specific density/asymmetric density (H = 6.27, p = 0.04 and H = 7.35, p = 0.03, respectively) and mixed features (H = 9.97, p = 0.01 and H = 6.50, p = 0.04, respectively) when reading at 15% and 10% recall rates. No significant change was observed on cancer characterized with stellate masses (H = 3.43, p = 0.18 and H = 1.23, p = 0.54, respectively) and architectural distortion (H = 0.00, p = 1.00 and H = 2.00, p = 0.37, respectively). Across all recall conditions, stellate masses were likely to be recalled (90.0%), whereas non-specific densities were likely to be missed (45.6%).

CONCLUSION

Cancers with a stellate mass were more easily detected and were more likely to continue to be recalled, even at lower recall rates. Cancers with non-specific density and mixed features were most likely to be missed at reduced recall rates. Advances in knowledge: Internationally, recall rates vary within screening mammography programs considerably, with a range between 1% and 15%, and very little is known about the type of breast cancer appearances found when radiologists interpret screening mammograms at these various recall rates. Therefore, understanding the lesion types and the mammographic appearances of breast cancers that are affected by readers' recall decisions should be investigated.

iCAP: An Individualized Model Combining Gaze Parameters and Image-Based Features to Predict Radiologists' Decisions While Reading Mammograms

This study introduces an individualized tool for identifying mammogram interpretation errors, called eye-Computer Assisted Perception (iCAP). iCAP consists of two modules, one which processes areas marked by radiologists as suspicious for cancer and classifies these as False Positive (FP) or True Positive (TP) decisions, while the second module classifies fixated but not marked locations as False Negative (FN) or True-Negative (TN) decisions. iCAP relies on both radiologists' gaze-related parameters, extracted from eye tracking data, and image-based features. In order to evaluate iCAP, eye tracking data from eight breast radiologists reading 120 two-view digital mammograms were collected. Fifty-nine cases had biopsy proven cancer. For each radiologist, a user-specific support vector machine model was built to classify the radiologist' s reported areas as TPs or FPs and fixated locations as TNs or FNs. The performances of the classifiers were evaluated by utilizing leave-one-out cross validation. iCAP was tested retrospectively in a simulated scenario in which it was assumed that the radiologists would accept all iCAP decisions. Using iCAP led to an average increase of 12%±6% in the number of correctly localized cancer and an average decrease of 44.5%±22.7% in the number of FPs per image.

CONTEMPORARY AUSTRALIAN DOSE AREA PRODUCT LEVELS IN THE FLUOROSCOPIC INVESTIGATION OF PAEDIATRIC CONGENITAL HEART DISEASE

This study examines radiation dose levels delivered to children from birth to 15 y of age in the investigation of congenital heart disease (CHD) at a major Sydney children's hospital. The aims are to compare values with those derived from similar studies, to provide a template for more consistent dose reporting, to establish local and national diagnostic reference levels and to contribute to the worldwide paediatric dosimetry database. A retrospective review of 1007 paediatric procedural records was undertaken. The cohort consisted of 795 patients over a period from January 2007 to December 2012 who have undergone cardiac catheterisation for the investigation of CHD. The age range included was from the day of birth to 15 y. Archived dose area product (DAP) and fluoroscopy time (FT) readings were retrieved and analysed. The mean, median, 25th and 75th percentile DAP levels were calculated for six specific age groupings. The 75th percentile DAP values for the specific age categories were as follows: 0-30 d-1.9 Gy cm2, 1-12 months-2.9 Gy cm2, 1-3 y-5.3 Gy cm2, 3-5 y-6.2 Gy cm2, 5-10 y-7.5 Gy cm2 and 10-15 y-17.3 Gy cm2. These levels were found to be lower than the values reported in comparable overseas studies. Individual year-specific levels were determined, and it is proposed that these are more useful than the common grouping method. The age-specific 75th percentile DAP levels outlined in this study can be used as baseline local diagnostic reference levels. The needs for the standardisation of DAP reporting and for a greater range of age-specific diagnostic reference levels have been highlighted. For the first time, Australian dose values for paediatric cardiac catheterisation are presented.

RELATIONSHIP BETWEEN RADIATION DOSE AND IMAGE QUALITY IN DIGITAL BREAST TOMOSYNTHESIS

This phantom-based study aimed to examine radiation dose from digital breast tomosynthesis (DBT) and digital mammography (DM) and to assess the potential for dose reductions for each modality. Images were acquired at 10-60 mm thicknesses and four dose levels and mean glandular dose was determined using a solid-state dosemeter. Eleven readers assessed image quality and compared simulated lesions with those on a reference image, and the data produced was analysed with the Friedman and Wilcoxon signed-rank tests. For a phantom thickness of 50 mm (typical breast thickness), DBT dose was 13 % higher than DM, but this differential is highly dependent on thickness. Visibility of masses was equal to a reference image (produced at 100 % dose) when dose was reduced by 75 and 50 % for DBT and DM. For microcalcifications, visibility was comparable with the reference image for both modalities at 50 % dose. This study highlighted the potential for reducing dose with DBT.

Fixated and Not Fixated Regions of Mammograms: A Higher-Order Statistical Analysis of Visual Search Behavior

RATIONALE AND OBJECTIVES

Visual search is an inhomogeneous yet efficient sampling process accomplished by the saccades and the central (foveal) vision. Areas that attract the central vision have been studied for errors in interpretation of medical imaging. In this study, we extend existing visual search studies to understand what characterizes areas that receive direct visual attention and elicit a mark by the radiologist (True and False Positive decisions) from those that elicit a mark but were captured by the peripheral vision. We also investigate if there are any differences between these areas and those that are never fixated by radiologists.

MATERIALS AND METHODS

Eight radiologists participated in this fully crossed multi-reader multi-case visual search study of digital mammography (DM) involving 120 two-view cases (59 cancers). From these DM images, 3 types of areas, namely Fixated Clusters (FC), Marked Peripherally Fixated Clusters (MPFC) and Never Fixated Clusters (NFC), were extracted and analysed using statistical information theory (in the form of third and fourth-order cumulants and polyspectrum [specifically bispectrum and trispectrum]) in addition to traditional second-order statistics (in the form of power spectrum) and other nonspectral features to characterize these types of areas.

RESULTS

Our results suggest that energy profiles of FC, MPFC, and NFC areas are distinct. We found evidence that energy profiles and dwell time of these areas influence radiologists' decisions (and confidence in such decisions). We also noted that foveated areas are selected on the basis of being most informative.

CONCLUSION

We show that properties of these areas influence radiologists' decisions and their confidence in the decisions made.

Risk Factors of Female Breast Cancer in Vietnam: A Case-Control Study

Purpose

Rates of women with breast cancer have increased rapidly in recent years in Vietnam, with over 10,000 new patients contracting the disease every year. This study was conducted to identify demographic, reproductive and lifestyle risk factors for breast cancer in Vietnam.

Materials and Methods

Breast density, demographic, reproductive and lifestyle data of 269 women with breast cancer and 519 age-matched controls were collected in the two largest oncology hospitals in Vietnam (one in the north and one in the south). Baseline differences between cases and controls in all women, premenopausal and postmenopausal women were assessed using chi-squared tests and independent t tests. Conditional logistic regression was used to derive odds ratios (OR) for factors that had statistically significant associations with breast cancer.

Results

Vietnamese women with breast cancer were significantly more likely to have a breast density > 75% (OR, 1.7), be younger than 14 years at first menstrual period (OR, 2.2), be postmenopausal (OR, 2.0), have less than three pregnancies (OR, 2.1), and have less than two babies (OR, 1.7). High breast density (OR, 1.6), early age at first menstrual period (OR, 2.6), low number of pregnancies (OR, 2.3), hormone use (OR, 1.8), and no physical activities (OR, 2.2) were significantly associated with breast cancer among premenopausal women, while breast density (OR, 2.0), age at first menstrual period (OR, 1.8), number of pregnancies (OR, 2.3), and number of live births (OR, 2.4) were the risk factors for postmenopausal women.

Conclusion

Breast density, age at first menarche, menopause status, number of pregnancies, number of babies born, hormone use and physical activities were significantly associated with breast cancer in Vietnamese women.

Breast cancer in Mongolia: an increasingly important health policy issue

Breast cancer is a leading cause of cancer-related death for women in both developed and developing countries. The incidence and mortality of breast cancer in Mongolia, while low compared with other counties, has been increasing on an annual basis. In addition, in Mongolia, approximately 90% of the patients are diagnosed at a late stage, resulting in high mortality, with the majority of individuals diagnosed with breast cancer dying within 5 years of diagnosis. Breast cancer screening plays an important role in reducing mortality in Western countries and has been adopted by a number of Asian countries; however, no such approach exists in Mongolia. In a country of limited resources, implementation of expensive health strategies such as screening requires effective allocations of resources and the identification of the most effective imaging methods. This requirement relies on recent accurate data; however, at this time, there is a paucity of information around breast cancer in Mongolia. Until data around features of the disease are available, effective strategies to diagnose breast cancer that recognize the economic climate in Mongolia cannot be implemented and the impact of breast cancer is likely to increase.

Inconsistencies of Breast Cancer Risk Factors between the Northern and Southern Regions of Vietnam

Background: In recent decades the amount of new breast cancer cases in the southern region has been reported to increase more rapidly than in the northernVietnam. The aim of this study is to compare breast cancer risk factors between the two regions and establish if westernized influences have an impact on any reported differences. Method: Data was collected from the two largest oncology hospitals in the north and the south of Vietnam in 2015. Breast density, demographic, reproductive and lifestyle data of 127 cases and 269 controls were collected in the north and 141 cases and 250 controls were gathered from the south. Baseline differences in factors between cases and age-matched controls in each region were assessed using chi-square tests and independent t-tests. Odds ratios (OR) for independent risk factors for breast cancer were obtained from conditional logistic regression. Results: In northern Vietnam significantly increased risks in developing breast cancer were observed for women with age at first menstrual period less than 14 years old (OR=2.1; P<0.05), post-menopausal status (OR=2.6; P<0.0001), having less than 2 babies (OR=2.1; P<0.05). Southern Vietnamese women having a breast density of more than 75% (OR=2.1; P<0.01), experiencing post-menopause (OR=1.6; P<0.05), having a history of less than 3 pregnancies (OR=2.6; P<0.0001) and drinking more than a cup of coffee per day (OR=1.9; P<0.05) were more likely to be diagnosed with breast cancer. Conclusion: We found that women living in the south had some breast cancer associations, such as increased mammographic density and coffee consumption, which are closer to the risks in westernized populations than women in the north.

Computer-based image analysis in breast pathology

Whole slide imaging (WSI) has the potential to be utilized in telepathology, teleconsultation, quality assurance, clinical education, and digital image analysis to aid pathologists. In this paper, the potential added benefits of computer-assisted image analysis in breast pathology are reviewed and discussed. One of the major advantages of WSI systems is the possibility of doing computer-based image analysis on the digital slides. The purpose of computer-assisted analysis of breast virtual slides can be (i) segmentation of desired regions or objects such as diagnostically relevant areas, epithelial nuclei, lymphocyte cells, tubules, and mitotic figures, (ii) classification of breast slides based on breast cancer (BCa) grades, the invasive potential of tumors, or cancer subtypes, (iii) prognosis of BCa, or (iv) immunohistochemical quantification. While encouraging results have been achieved in this area, further progress is still required to make computer-based image analysis of breast virtual slides acceptable for clinical practice.

Does Expectation of Abnormality Affect the Search Pattern of Radiologists When Looking for Pulmonary Nodules?

This experiment investigated whether there might be an effect on the visual search strategy of radiologists during image interpretation of the same adult chest radiographs when given different clinical information. Each of 17 experienced radiologists was asked to interpret a set of 57 (10 abnormal) posteroanterior chest images to identify the presence of pulmonary lesions using differing clinical information (leading to unknown, low and high expectations of prevalence). Eye position metrics (search time, dwell time and time to first fixation) were compared for normal and abnormal images, as well as between conditions. For all images, there was a significantly longer search time at high prevalence expectation compared to low prevalence expectation (W = 75.19, P = <0.0001). Mann-Whitney analysis of the abnormal images demonstrated that the dwell time on correctly identified lesions was significantly shorter at low prevalence expectation compared to both unknown (U = 364.5, P = 0.02) and high prevalence expectation (U = 397.0, P = 0.0002). Visual search patterns of radiologists appear to be affected by changing a priori information where such information fosters an expectation of abnormality.

Descriptive epidemiology of breast cancer in China: incidence, mortality, survival and prevalence

Breast cancer is the most common neoplasm diagnosed amongst women worldwide and is the leading cause of female cancer death. However, breast cancer in China is not comprehensively understood compared with Westernised countries, although the 5-year prevalence statistics indicate that approximately 11 % of worldwide breast cancer occurs in China and that the incidence has increased rapidly in recent decades. This paper reviews the descriptive epidemiology of Chinese breast cancer in terms of incidence, mortality, survival and prevalence, and explores relevant factors such as age of manifestation and geographic locations. The statistics are compared with data from the Westernised world with particular emphasis on the United States and Australia. Potential causal agents responsible for differences in breast cancer epidemiology between Chinese and other populations are also explored. The need to minimise variability and discrepancies in methods of data acquisition, analysis and presentation is highlighted.

Outcomes Knowledge May Bias Radiological Decision-making

RATIONALE AND OBJECTIVES

This research investigates whether an expectation of abnormality and prior knowledge might potentially influence the decision-making of radiologists, and discusses the implications for radiological expert witness testimony.

MATERIALS AND METHODS

This study was a web-based perception experiment. A total of 12 board-certified radiologists were asked to interpret 40 adult chest images (20 abnormal) twice and decide if pulmonary lesions were present. Before the first viewing, a general clinical history was given for all images: cough for 3+ weeks. This was called the "defendants read." Two weeks later, the radiologists were asked to view the same dataset (unaware that the dataset was unchanged). For this reading, the radiologists were given the following information for all images: "These images were reported normal but all of these patients have a lung tumour diagnosed on a subsequent radiograph 6 months later." They were also given the lobar location of the newly diagnosed tumor. This was called the "expert witness read."

RESULTS

There was a significant difference in location-based sensitivity (W = -45, P = 0.02) between the two conditions with nodule detection increasing under the second condition. Specificity increased outside the lobe of interest (W = 727, P = < 0.0001) and decreased within the lobe of interest (W = -237, P = 0.03) significantly in the "expert witness" read. Case-based sensitivity and case-based specificity were unaffected.

CONCLUSIONS

This study showed evidence that increased clinical information affects the performance of radiologists. This effect may bias expert witnesses in radiological malpractice litigation.

Relationship Between Breast Density and Selective Estrogen-Receptor Modulators, Aromatase Inhibitors, Physical Activity, and Diet: A Systematic Review

Background Lower breast density (BD) is associated with lower risk of breast cancer and may serve as a biomarker for the efficacy of chemopreventive strategies. This review explores parameters that are thought to be associated with lower BD. We conducted a systematic review of articles published to date using the PRISMA strategy. Articles that assessed change in BD with estrogen-receptor modulators (tamoxifene [TAM], raloxifene [RLX], and tibolone) and aromatase inhibitors (AIs), as well as cross-sectional and longitudinal studies (LSs) that assessed association between BD and physical activity (PA) or diet were reviewed. Results Ten studies assessed change in BD with TAM; all reported TAM-mediated BD decreases. Change in BD with RLX was assessed by 11 studies; 3 reported a reduction in BD. Effect of tibolone was assessed by 5 RCTs; only 1 reported change in BD. AI-mediated BD reduction was reported by 3 out of 10 studies. The association between PA and BD was assessed by 21 studies; 4 reported an inverse association. The relationship between diet and BD was assessed in 34 studies. All studies on calcium and vitamin D as well as vegetable intake reported an inverse association with BD in premenopausal women. Two RCTs demonstrated BD reduction with a low-fat, high-carbohydrate intervention. Conclusion TAM induces BD reduction; however, the effect of RLX, tibolone, and AIs on BD is unclear. Although data on association between diet and BD in adulthood are contradictory, intake of vegetables, vitamin D, and calcium appear to be associated with lower BD in premenopausal women.

Inter-observer variability in mammographic density assessment using Royal Australian and New Zealand College of Radiologists (RANZCR) synoptic scales

INTRODUCTION

The aim of this study was to evaluate observer variability in mammographic density assessment as measured using the Royal Australian and New Zealand College of Radiologists (RANZCR) synoptic scales. Visual assessment of mammographic density by radiologists is commonly used in clinical practice; however, these assessments have been shown to be more subjective than quantitative methods.

METHODS

The study included 40 cases of left cranial-caudal (CC) and mediolateral oblique (MLO) radiographs from 20 women. RANZCR-registered radiologists (n = 26) estimated mammographic breast density of the same images according to RANZCR synoptic scales 1-4. All images had their volumetric density classified using Volpara Density Grade (VDG) and Average Volumetric Breast Density percentage (AvBD%).

RESULTS

The results showed that the radiologists sampled had specialized for 17.18 years (sd 12.03) and read 2072 (sd 2441) mammograms per year on average. Inter-observer agreement using RANZCR synoptic scales had an average Kappa of 0.360; (95% CI = 0.308-0.412) and a range of 0.078-0.499. Radiologists estimated percentage density was lower by 0.37 than VDG, with their mean being 2.18 and the mean VDG was 2.55 (Z = -3.873; P < 0.001). VDG and RANZCR showed a positive strong correlation (ρ = 0.898; P < 0.001). AvBD% and RANZCR also showed a positive strong correlation (ρ = 0.904; P < 0.001).

CONCLUSION

The inter-observer agreement with RANZCR synoptic scales was fair. Wide inter-observer variability was observed. Continued research on appropriate assessment methods for mammographic density assessment is required to avoid unnecessary variations.

Increasing Prevalence Expectation in Thoracic Radiology Leads to Overcall

RATIONALE AND OBJECTIVES

The aim of this study was to measure the effect of prevalence expectation as determined by clinical history on the diagnostic performance of radiologists during pulmonary nodule detection on adult chest radiographs.

MATERIALS AND METHODS

A multi-observer, counter-balanced study (having half the readers in each group read a different condition initially) was performed to assess the effect of abnormality expectation on experienced radiologists' performance. A total of 33 board-certified radiologists were divided into three groups and searched for evidence of malignancy on a single set of 47 postero-anterior (PA) chest radiographs, 10 of which contained a single pulmonary nodule. The radiologists were unaware of disease prevalence. Before each viewing of the same dataset, the radiologists were allocated to two of three conditions based on the differing clinical information (previous cancer, no history, visa applicant). Location sensitivity, specificity, and jack-knife free-response receiver operator characteristics figure of merit were used to compare radiologist performance between conditions.

RESULTS

A significant reduction in specificity was shown for the cancer compared to that for the visa condition (W = -41 P = 0.02). No other significant findings were demonstrated for this or the other condition comparisons. No significant difference in the performance of radiologists was noted when viewing images under the same conditions.

CONCLUSIONS

This study suggested that there is a reduction in specificity with high compared to low prevalence expectation following specific radiological contexts. A reduction in specificity can have important clinical consequences leading to unnecessary interventions. The results and their implications emphasize the caution that should be placed on providing accurate referral criteria.

Quantra™ should be considered a tool for two-grade scale mammographic breast density classification

OBJECTIVE

To assess the agreement between Quantra™ (Hologic Inc., Bedford, MA) and Breast Imaging Reporting and Data Systems (BI-RADS(®)) and the performance of Quantra at reproducing BI-RADS mammographic breast density (MBD) assessment.

METHODS

MBD assessment was performed using Quantra and BI-RADS. BI-RADS assessment was performed in two phases (1314 and 292 cases, respectively). Kappa was used to assess the interreader agreement and the agreement between Quantra and BI-RADS, and receiver-operating characteristics analysis was used to assess the performance of Quantra at reproducing BI-RADS rating.

RESULTS

Agreement (weighted kappa) between BI-RADS and Quantra in Phase 1 was 0.75 [95% confidence interval (CI): 0.73-0.78] and 0.85 (95% CI: 0.80-0.90) on four- and two-grade scales, respectively. The corresponding agreement in Phase 2 was 0.79 (95% CI: 0.75-0.84) and 0.84 (95% CI: 0.79-0.87) using the majority report. In Phase 1, Quantra demonstrated 93.2% sensitivity and 86.1% specificity for BI-RADS on a two-grade scale (1-2 vs 3-4). In Phase 2, it demonstrated 91.3% sensitivity and 83.6% specificity on a two-grade scale.

CONCLUSION

Quantra is limited in reproducing BI-RADS rating on a four-grade scale; however, it highly reproduces BI-RADS assessment on a two-grade scale.

ADVANCES IN KNOWLEDGE

Quantra (v. 2.0) is a poor predictor of BI-RADS assessment on a four-grade scale, but well reproduces BI-RADS rating on a two-grade scale. Therefore, it should be considered a tool for two-grade scale MBD classification.

Reporting instructions significantly impact false positive rates when reading chest radiographs

OBJECTIVES

To determine the impact of specific reporting tasks on the performance of radiologists when reading chest radiographs.

METHODS

Ten experienced radiologists read a set of 40 postero-anterior (PA) chest radiographs: 21 nodule free and 19 with a proven solitary nodule. There were two reporting conditions: an unframed task (UFT) to report any abnormality and a framed task (FT) reporting only lung nodule/s. Jackknife free-response operating characteristic (JAFROC) figure of merit (FOM), specificity, location sensitivity and number of true positive (TP), false positive (FP), true negative (TN) and false negative (FN) decisions were used for analysis.

RESULTS

JAFROC FOM for tasks showed a significant reduction in performance for framed tasks (P = 0.006) and an associated decrease in specificity (P = 0.011) but no alteration to the location sensitivity score. There was a significant increase in number of FP decisions made during framed versus unframed tasks for nodule-containing (P = 0.005) and nodule-free (P = 0.011) chest radiographs. No significant differences in TP were recorded.

CONCLUSIONS

Radiologists report more FP decisions when given specific reporting instructions to search for nodules on chest radiographs. The relevance of clinical history supplied to radiologists is called into question and may induce a negative effect.

KEY POINTS

• Framed reporting tasks increases false positive rates when searching for pulmonary nodules • False positive results were observed in both nodule-containing and nodule-free cases • Radiologist's decision-making may be influenced by clinical history in thoracic imaging.

Mammographic Breast Density Assessment Using Automated Volumetric Software and Breast Imaging Reporting and Data System (BIRADS) Categorization by Expert Radiologists

RATIONALE AND OBJECTIVES

To investigate agreement on mammographic breast density (MD) assessment between automated volumetric software and Breast Imaging Reporting and Data System (BIRADS) categorization by expert radiologists.

MATERIALS AND METHODS

Forty cases of left craniocaudal and mediolateral oblique mammograms from 20 women were used. All images had their volumetric density classified using Volpara density grade (VDG) and average volumetric breast density percentage. The same images were then classified into BIRADS categories (I-IV) by 20 American Board of Radiology examiners.

RESULTS

The results demonstrated a moderate agreement (κ = 0.537; 95% CI = 0.234-0.699) between VDG classification and radiologists' BIRADS density assessment. Interreader agreement using BIRADS also demonstrated moderate agreement (κ = 0.565; 95% CI = 0.519-0.610) ranging from 0.328 to 0.669. Radiologists' average BIRADS was lower than average VDG scores by 0.33, with their mean being 2.13, whereas the mean VDG was 2.48 (U = -3.742; P < 0.001). VDG and BIRADS showed a very strong positive correlation (ρ = 0.91; P < 0.001) as did BIRADS and average volumetric breast density percentage (ρ = 0.94; P < 0.001).

CONCLUSIONS

Automated volumetric breast density assessment shows moderate agreement and very strong correlation with BIRADS; interreader variations still exist within BIRADS. Because of the increasing importance of MD measurement in clinical management of patients, widely accepted, reproducible, and accurate measures of MD are required.