Early Indicators of the Impact of Using AI in Mammography Screening for Breast Cancer.

Background Retrospective studies have suggested that using artificial intelligence (AI) may decrease the workload of radiologists while preserving mammography screening performance. Purpose To compare workload and screening performance for two cohorts of women who underwent screening before and after AI system implementation. Materials and Methods This retrospective study included 50-69-year-old women who underwent biennial mammography screening in the Capital Region of Denmark. Before AI system implementation (October 1, 2020, to November 17, 2021), all screenings involved double reading. For screenings conducted after AI system implementation (November 18, 2021, to October 17, 2022), likely normal screenings (AI examination score ≤5 before May 3, 2022, or ≤7 on or after May 3, 2022) were single read by one of 19 senior full-time breast radiologists. The remaining screenings were read by two radiologists with AI-assisted decision support. Biopsy and surgical outcomes were retrieved between October 1, 2020, and April 15, 2023, ensuring at least 180 days of follow-up. Screening metrics were compared using the χ2 test. Reading workload reduction was measured as saved screening reads. Results In total, 60 751 and 58 246 women were screened before and after AI system implementation, respectively (median age, 58 years [IQR, 54-64 years] for both cohorts), with a median screening interval before AI of 845 days (IQR, 820-878 days) and with AI of 993 days (IQR, 968-1013 days; P < .001). After AI system implementation, the recall rate decreased by 20.5% (3.09% before AI [1875 of 60 751] vs 2.46% with AI [1430 of 58 246]; P < .001), the cancer detection rate increased (0.70% [423 of 60 751] vs 0.82% [480 of 58 246]; P = .01), the false-positive rate decreased (2.39% [1452 of 60 751] vs 1.63% [950 of 58 246]; P < .001), the positive predictive value increased (22.6% [423 of 1875] vs 33.6% [480 of 1430]; P < .001), the rate of small cancers (≤1 cm) increased (36.6% [127 of 347] vs 44.9% [164 of 365]; P = .02), the rate of node-negative cancers was unchanged (76.7% [253 of 330] vs 77.8% [273 of 351]; P = .73), and the rate of invasive cancers decreased (84.9% [359 of 423] vs 79.6% [382 of 480]; P = .04). The reading workload was reduced by 33.5% (38 977 of 116 492 reads). Conclusion In a population-based mammography screening program, using AI reduced the overall workload of breast radiologists while improving screening performance. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Lee and Friedewald in this issue.

Robust cross-vendor mammographic texture models using augmentation-based domain adaptation for long-term breast cancer risk.

Purpose: Risk-stratified breast cancer screening might improve early detection and efficiency without comprising quality. However, modern mammography-based risk models do not ensure adaptation across vendor-domains and rely on cancer precursors, associated with short-term risk, which might limit long-term risk assessment. We report a cross-vendor mammographic texture model for long-term risk. Approach: The texture model was robustly trained using two systematically designed case-control datasets. Textural features, indicative of future breast cancer, were learned by excluding samples with diagnosed/potential malignancies from training. An augmentation-based domain adaption technique, based on flavorization of mammographic views, ensured generalization across vendor-domains. The model was validated in 66,607 consecutively screened Danish women with flavorized Siemens views and 25,706 Dutch women with Hologic-processed views. Performances were evaluated for interval cancers (IC) within 2 years from screening and long-term cancers (LTC) from 2 years after screening. The texture model was combined with established risk factors to flag 10% of women with the highest risk. Results: In Danish women, the texture model achieved an area under the receiver operating characteristic curve (AUC) of 0.71 and 0.65 for ICs and LTCs, respectively. In Dutch women with Hologic-processed views, the AUCs were not different from AUCs in Danish women with flavorized views. The AUC for texture combined with established risk factors increased to 0.68 for LTCs. The 10% of women flagged as high-risk accounted for 25.5% of ICs and 24.8% of LTCs. Conclusions: The texture model robustly estimated long-term breast cancer risk while adapting to an unseen processed vendor-domain and identified a clinically relevant high-risk subgroup.

Assessing Breast Cancer Risk by Combining AI for Lesion Detection and Mammographic Texture.

Background Recent mammography-based risk models can estimate short-term or long-term breast cancer risk, but whether risk assessment may improve by combining these models has not been evaluated. Purpose To determine whether breast cancer risk assessment improves when combining a diagnostic artificial intelligence (AI) system for lesion detection and a mammographic texture model. Materials and Methods This retrospective study included Danish women consecutively screened for breast cancer at mammography from November 2012 to December 2015 who had at least 5 years of follow-up data. Examinations were evaluated for short-term risk using a commercially available diagnostic AI system for lesion detection, which produced a score to indicate the probability of cancer. A mammographic texture model, trained on a separate data set, assessed textures associated with long-term cancer risk. Area under the receiver operating characteristic curve (AUC) analysis was used to evaluate both the individual and combined performance of the AI and texture models for the prediction of future cancers in women with a negative screening mammogram, including those with interval cancers diagnosed within 2 years of screening and long-term cancers diagnosed 2 years or more after screening. AUCs were compared using the DeLong test. Results The Danish screening cohort included 119 650 women (median age, 59 years [IQR, 53-64 years]), of whom 320 developed interval cancers and 1401 developed long-term cancers. The combination model achieved a higher AUC for interval and long-term cancers grouped together than either the diagnostic AI (AUC, 0.73 vs 0.70; P < .001) or the texture risk (AUC, 0.73 vs 0.66; P < .001) models. The 10% of women with the highest combined risk identified by the combination model accounted for 44.1% (141 of 320) of interval cancers and 33.7% (472 of 1401) of long-term cancers. Conclusion Combining a diagnostic AI system and mammographic texture model resulted in improved risk assessment for interval cancers and long-term cancers and enabled identification of women at high risk. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Poynton and Slanetz in this issue.

Identifying recurrent breast cancer patients in national health registries using machine learning.

BACKGROUND: More than 4500 women are diagnosed with breast cancer each year in Denmark, however, despite adequate treatment 10-30% of patients will experience a recurrence. The Danish Breast Cancer Group (DBCG) stores information on breast cancer recurrence but to improve data completeness automated identification of patients with recurrence is needed. METHODS: We included patient data from the DBCG, the National Pathology Database, and the National Patient Registry for patients with an invasive breast cancer diagnosis after 1999. In total, relevant features of 79,483 patients with a definitive surgery were extracted. A machine learning (ML) model was trained, using a simplistic encoding scheme of features, on a development sample covering 5333 patients with known recurrence and three times as many non-recurrent women. The model was validated in a validation sample consisting of 1006 patients with unknown recurrence status. RESULTS: The ML model identified patients with recurrence with AUC-ROC of 0.93 (95% CI: 0.93-0.94) in the development, and an AUC-ROC of 0.86 (95% CI: 0.83-0.88) in the validation sample. CONCLUSION: An off-the-shelf ML model, trained using the simplistic encoding scheme, could identify recurrence patients across multiple national registries. This approach might potentially enable researchers and clinicians to better and faster identify patients with recurrence and reduce manual patient data interpretation.

Breast density and risk of breast cancer.

Early studies reported a 4- to 6-fold risk of breast cancer between women with extremely dense and fatty breasts. As most early studies were case-control studies, we took advantage of a population-based screening program to study density and breast cancer incidence in a cohort design. In the Capital Region, Denmark, women aged 50 to 69 are invited to screening biennially. Women screened November 2012 to December 2017 were included, and classified by BI-RADS density code, version 4, at first screen after recruitment. Women were followed up for incident breast cancer, including ductal carcinoma in situ (DCIS), to 2020 in nationwide pathology data. Rate ratios (RRs) and 95% confidence intervals (CI) were compared across density groups using Poisson-regression. We included 189 609 women; 1 067 282 person-years; and 4110 incident breast cancers/DCIS. Thirty-three percent of women had BI-RADS density code 1; 38% code 2; 24% code 3; 4.7% code 4; and missing 0.3%. Using women with BI-RADS density code 1 as baseline; women with code 2 had RR 1.69 (95% CI 1.56-1.84); women with code 3, RR 2.06 (95% CI 1.89-2.25); and women with code 4, RR 2.37 (95% CI 1.05-2.74). Results differed between observations accumulated during screening and above screening age. Our results indicated less difference in breast cancer risk across level of breast density than normally stated. Translated into absolute risk of breast cancer after age 50, we found a 6.2% risk for the one-third of women with lowest density, and 14.7% for the 5% of women with highest density.

An Artificial Intelligence-based Mammography Screening Protocol for Breast Cancer: Outcome and Radiologist Workload.

Background Developments in artificial intelligence (AI) systems to assist radiologists in reading mammograms could improve breast cancer screening efficiency. Purpose To investigate whether an AI system could detect normal, moderate-risk, and suspicious mammograms in a screening sample to safely reduce radiologist workload and evaluate across Breast Imaging Reporting and Data System (BI-RADS) densities. Materials and Methods This retrospective simulation study analyzed mammographic examination data consecutively collected from January 2014 to December 2015 in the Danish Capital Region breast cancer screening program. All mammograms were scored from 0 to 10, representing the risk of malignancy, using an AI tool. During simulation, normal mammograms (score < 5) would be excluded from radiologist reading and suspicious mammograms (score > recall threshold [RT]) would be recalled. Two radiologists read the remaining mammograms. The RT was fitted using another independent cohort (same institution) by matching to the radiologist sensitivity. This protocol was further applied to each BI-RADS density. Screening outcomes were measured using the sensitivity, specificity, workload, and false-positive rate. The AI-based screening was tested for noninferiority sensitivity compared with radiologist screening using the Farrington-Manning test. Specificities were compared using the McNemar test. Results The study sample comprised 114 421 screenings for breast cancer in 114 421 women, resulting in 791 screen-detected, 327 interval, and 1473 long-term cancers and 2107 false-positive screenings. The mean age of the women was 59 years ± 6 (SD). The AI-based screening sensitivity was 69.7% (779 of 1118; 95% CI: 66.9, 72.4) and was noninferior (P = .02) to the radiologist screening sensitivity of 70.8% (791 of 1118; 95% CI: 68.0, 73.5). The AI-based screening specificity was 98.6% (111 725 of 113 303; 95% CI: 98.5, 98.7), which was higher (P < .001) than the radiologist specificity of 98.1% (111 196 of 113 303; 95% CI: 98.1, 98.2). The radiologist workload was reduced by 62.6% (71 585 of 114 421), and 25.1% (529 of 2107) of false-positive screenings were avoided. Screening results were consistent across BI-RADS densities, although not significantly so for sensitivity. Conclusion Artificial intelligence (AI)-based screening could detect normal, moderate-risk, and suspicious mammograms in a breast cancer screening program, which may reduce the radiologist workload. AI-based screening performed consistently across breast densities. © RSNA, 2022 Online supplemental material is available for this article.

Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients.

Patients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that machine learning (ML) models could be used to predict risks at different stages of management and thereby provide insights into drivers and prognostic markers of disease progression and death. From a cohort of approx. 2.6 million citizens in Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further analysis. SARS-CoV-2 positive cases from the United Kingdom Biobank was used for external validation. The ML models predicted the risk of death (Receiver Operation Characteristics-Area Under the Curve, ROC-AUC) of 0.906 at diagnosis, 0.818, at hospital admission and 0.721 at Intensive Care Unit (ICU) admission. Similar metrics were achieved for predicted risks of hospital and ICU admission and use of mechanical ventilation. Common risk factors, included age, body mass index and hypertension, although the top risk features shifted towards markers of shock and organ dysfunction in ICU patients. The external validation indicated fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission. ML may be used to identify drivers of progression to more severe disease and for prognostication patients in patients with COVID-19. We provide access to an online risk calculator based on these findings.

Impact of adding breast density to breast cancer risk models: A systematic review.

PURPOSE: Assessment of a woman's risk of breast cancer is essential when moving towards personalized screening. Breast density is a well-known risk factor and has the potential to improve accuracy of risk prediction models. In this study we reviewed the impact on model performance of adding breast density to clinical breast cancer risk prediction models. METHODS: We conducted a systematic review using a pre-specified search strategy for PubMed, EMBASE, Web of Science, and Cochrane Library from January 2007 until November 2019. Studies were screened using the Covidence software. Eligible studies developed or modified existing breast cancer risk prediction models applicable to the general population of women by adding breast density to the model. Improvement in discriminatory accuracy was measured as an increase in the Area Under the Curve or concordance statistics. RESULTS: Eleven eligible studies were identified by the search and one by reference check. Four studies modified the Gail model, four modified the Tyrer-Cuzick model, and five studies developed new models. Several methods were used to measure breast density, including visual, semi- and fully automated methods. Eleven studies reported discriminatory accuracy and one study reported calibration. Seven studies found a statistically significantly increased discriminatory accuracy when including density in the model. The increase in AUC ranged 0.03 to 0.14. Four studies did not report on statistical significance, but reported an increased AUC ranging from 0.01 to 0.06. CONCLUSION: Including mammographic breast density has the potential to improve breast cancer risk prediction models. However, all models demonstrated limited discrimination accuracy.

Sensitivity of screening mammography by density and texture: a cohort study from a population-based screening program in Denmark.

BACKGROUND: Screening mammography works better in fatty than in dense breast tissue. Computerized assessment of parenchymal texture is a non-subjective method to obtain a refined description of breast tissue, potentially valuable in addition to breast density scoring for the identification of women in need of supplementary imaging. We studied the sensitivity of screening mammography by a combination of radiologist-assessed Breast Imaging Reporting and Data System (BI-RADS) density score and computer-assessed parenchymal texture marker, mammography texture resemblance (MTR), in a population-based screening program. METHODS: Breast density was coded according to the fourth edition of the BI-RADS density code, and MTR marker was divided into quartiles from 1 to 4. Screening data were followed up for the identification of screen-detected and interval cancers. We calculated sensitivity and specificity with 95% confidence intervals (CI) by BI-RADS density score, MTR marker, and combination hereof. RESULTS: Density and texture were strongly correlated, but the combination led to the identification of subgroups with different sensitivity. Sensitivity was high, about 80%, in women with BI-RADS density score 1 and MTR markers 1 or 2. Sensitivity was low, 67%, in women with BI-RADS density score 2 and MTR marker 4. For women with BI-RADS density scores 3 and 4, the already low sensitivity was further decreased for women with MTR marker 4. Specificity was 97-99% in all subgroups. CONCLUSION: Our study showed that women with low density constituted a heterogenous group. Classifying women for extra imaging based on density only might be a too crude approach. Screening sensitivity was systematically high in women with fatty and homogenous breast tissue.

Change in mammographic density across birth cohorts of Dutch breast cancer screening participants.

High mammographic density is a well-known risk factor for breast cancer. This study aimed to search for a possible birth cohort effect on mammographic density, which might contribute to explain the increasing breast cancer incidence. We separately analyzed left and right breast density of Dutch women from a 13-year period (2003-2016) in the breast cancer screening programme. First, we analyzed age-specific changes in average percent dense volume (PDV) across birth cohorts. A linear regression analysis (PDV vs. year of birth) indicated a small but statistically significant increase in women of: 1) age 50 and born from 1952 to 1966 (left, slope = 0.04, p = 0.003; right, slope = 0.09, p < 0.0001); 2) age 55 and born from 1948 to 1961 (right, slope = 0.04, p = 0.01); and 3) age 70 and born from 1933 to 1946 (right, slope = 0.05, p = 0.002). A decrease of total breast volume seemed to explain the increase in PDV. Second, we compared proportion of women with dense breast in women born in 1946-1953 and 1959-1966, and observed a statistical significant increase of proportion of highly dense breast in later born women, in the 51 to 55 age-groups for the left breast (around a 20% increase in each age-group), and in the 50 to 56 age-groups for the right breast (increase ranging from 27% to 48%). The study indicated a slight increase in mammography density across birth cohorts, most pronounced for women in their early 50s, and more marked for the right than for the left breast.

Screening mammography: benefit of double reading by breast density.

PURPOSE: The currently recommended double reading of all screening mammography examinations is an economic burden for screening programs. The sensitivity of screening is higher for women with low breast density than for women with high density. One may therefore ask whether single reading could replace double reading at least for women with low density. We addressed this question using data from a screening program where the radiologists coded their readings independently. METHODS: Data include all screening mammography examinations in the Capital Region of Denmark from 1 November 2012 to 31 December 2013. Outcome of screening was assessed by linkage to the Danish Pathology Register. We calculated sensitivity, specificity, number of interval cancers, and false positive-tests per 1000 screened women by both single reader and consensus BI-RADS density code. RESULTS: In total 54,808 women were included. The overall sensitivity of double reading was 72%, specificity was 97.6%, 3 women per 1000 screened experienced an interval cancer, and 24 a false-positive test. Across all BI-RADS density codes, single reading consistently decreased sensitivity as compared with consensus reading. The same was true for specificity, apart from results across BI-RADS density codes set by reader 2. CONCLUSIONS: Single reading decreased sensitivity as compared with double reading across all BI-RADS density codes. This included results based on consensus BI-RADS density codes. This means that replacement of double with single reading would have negative consequences for the screened women, even if density could be assessed automatically calibrated to the usual consensus level.

The combined effect of mammographic texture and density on breast cancer risk: a cohort study.

BACKGROUND: Texture patterns have been shown to improve breast cancer risk segregation in addition to area-based mammographic density. The additional value of texture pattern scores on top of volumetric mammographic density measures in a large screening cohort has never been studied. METHODS: Volumetric mammographic density and texture pattern scores were assessed automatically for the first available digital mammography (DM) screening examination of 51,400 women (50-75 years of age) participating in the Dutch biennial breast cancer screening program between 2003 and 2011. The texture assessment method was developed in a previous study and validated in the current study. Breast cancer information was obtained from the screening registration system and through linkage with the Netherlands Cancer Registry. All screen-detected breast cancers diagnosed at the first available digital screening examination were excluded. During a median follow-up period of 4.2 (interquartile range (IQR) 2.0-6.2) years, 301 women were diagnosed with breast cancer. The associations between texture pattern scores, volumetric breast density measures and breast cancer risk were determined using Cox proportional hazard analyses. Discriminatory performance was assessed using c-indices. RESULTS: The median age of the women at the time of the first available digital mammography examination was 56 years (IQR 51-63). Texture pattern scores were positively associated with breast cancer risk (hazard ratio (HR) 3.16 (95% CI 2.16-4.62) (p value for trend <0.001), for quartile (Q) 4 compared to Q1). The c-index of texture was 0.61 (95% CI 0.57-0.64). Dense volume and percentage dense volume showed positive associations with breast cancer risk (HR 1.85 (95% CI 1.32-2.59) (p value for trend <0.001) and HR 2.17 (95% CI 1.51-3.12) (p value for trend <0.001), respectively, for Q4 compared to Q1). When adding texture measures to models with dense volume or percentage dense volume, c-indices increased from 0.56 (95% CI 0.53-0.59) to 0.62 (95% CI 0.58-0.65) (p < 0.001) and from 0.58 (95% CI 0.54-0.61) to 0.60 (95% CI 0.57-0.63) (p = 0.054), respectively. CONCLUSIONS: Deep-learning-based texture pattern scores, measured automatically on digital mammograms, are associated with breast cancer risk, independently of volumetric mammographic density, and augment the capacity to discriminate between future breast cancer and non-breast cancer cases.

Risk stratification of women with false-positive test results in mammography screening based on mammographic morphology and density: A case control study.

BACKGROUND: The long-term risk of breast cancer is increased in women with false-positive (FP) mammography screening results. We investigated whether mammographic morphology and/or density can be used to stratify these women according to their risk of future breast cancer METHODS: We undertook a case-control study nested in the population-based screening programme in Copenhagen, Denmark. We included 288 cases and 288 controls based on a cohort of 4743 women with at least one FP-test result in 1991-2005 who were followed up until 17 April 2008. Film-based mammograms were assessed using the Breast Imaging-Reporting and Data System (BI-RADS) density classification, the Tabár classification, and two automated techniques quantifying percentage mammographic density (PMD) and mammographic texture (MTR), respectively. The association with breast cancer was estimated using binary logistic regression calculating Odds Ratios (ORs) and the area under the receiver operating characteristic (ROC) curves (AUCs) adjusted for birth year and age and invitation round at the FP-screen RESULTS: Significantly increased ORs were seen for BI-RADS D(density)2-D4 (OR 1.94; 1.30-2.91, 2.36; 1.51-3.70 and 4.01; 1.67-9.62, respectively), Tabár's P(pattern)IV (OR 1.83; 1.16-2.89), PMD Q(quartile)2-Q4 (OR 1.71; 1.02-2.88, 1.97; 1.16-3.35 and 2.43; 1.41-4.19, respectively) and MTR Q4 (1.97; 1.12-3.46) using the lowest/fattiest category as reference CONCLUSION: All four methods, capturing either mammographic morphology or density, could segregate women with FP-screening results according to their risk of future breast cancer - using already available screening mammograms. Our findings need validation on digital mammograms, but may inform potential future risk stratification and tailored screening strategies.

Differential diagnosis of mild cognitive impairment and Alzheimer's disease using structural MRI cortical thickness, hippocampal shape, hippocampal texture, and volumetry.

This paper presents a brain T1-weighted structural magnetic resonance imaging (MRI) biomarker that combines several individual MRI biomarkers (cortical thickness measurements, volumetric measurements, hippocampal shape, and hippocampal texture). The method was developed, trained, and evaluated using two publicly available reference datasets: a standardized dataset from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the imaging arm of the Australian Imaging Biomarkers and Lifestyle flagship study of ageing (AIBL). In addition, the method was evaluated by participation in the Computer-Aided Diagnosis of Dementia (CADDementia) challenge. Cross-validation using ADNI and AIBL data resulted in a multi-class classification accuracy of 62.7% for the discrimination of healthy normal controls (NC), subjects with mild cognitive impairment (MCI), and patients with Alzheimer's disease (AD). This performance generalized to the CADDementia challenge where the method, trained using the ADNI and AIBL data, achieved a classification accuracy 63.0%. The obtained classification accuracy resulted in a first place in the challenge, and the method was significantly better (McNemar's test) than the bottom 24 methods out of the total of 29 methods contributed by 15 different teams in the challenge. The method was further investigated with learning curve and feature selection experiments using ADNI and AIBL data. The learning curve experiments suggested that neither more training data nor a more complex classifier would have improved the obtained results. The feature selection experiment showed that both common and uncommon individual MRI biomarkers contributed to the performance; hippocampal volume, ventricular volume, hippocampal texture, and parietal lobe thickness were the most important. This study highlights the need for both subtle, localized measurements and global measurements in order to discriminate NC, MCI, and AD simultaneously based on a single structural MRI scan. It is likely that additional non-structural MRI features are needed to further improve the obtained performance, especially to improve the discrimination between NC and MCI.

Mammographic density and structural features can individually and jointly contribute to breast cancer risk assessment in mammography screening: a case-control study.

BACKGROUND: Mammographic density is a well-established risk factor for breast cancer. We investigated the association between three different methods of measuring density or parenchymal pattern/texture on digitized film-based mammograms, and examined to what extent textural features independently and jointly with density can improve the ability to identify screening women at increased risk of breast cancer. METHODS: The study included 121 cases and 259 age- and time matched controls based on a cohort of 14,736 women with negative screening mammograms from a population-based screening programme in Denmark in 2007 (followed until 31 December 2010). Mammograms were assessed using the Breast Imaging-Reporting and Data System (BI-RADS) density classification, Tabár's classification on parenchymal patterns and a fully automated texture quantification technique. The individual and combined association with breast cancer was estimated using binary logistic regression to calculate Odds Ratios (ORs) and the area under the receiver operating characteristic (ROC) curves (AUCs). RESULTS: Cases showed significantly higher BI-RADS and texture scores on average than controls (p < 0.001). All three methods were individually able to segregate women into different risk groups showing significant ORs for BI-RADS D3 and D4 (OR: 2.37; 1.32-4.25 and 3.93; 1.88-8.20), Tabár's PIII and PIV (OR: 3.23; 1.20-8.75 and 4.40; 2.31-8.38), and the highest quartile of the texture score (3.04; 1.63-5.67). AUCs for BI-RADS, Tabár and the texture scores (continuous) were 0.63 (0.57-0-69), 0.65 (0.59-0-71) and 0.63 (0.57-0-69), respectively. Combining two or more methods increased model fit in all combinations, demonstrating the highest AUC of 0.69 (0.63-0.74) when all three methods were combined (a significant increase from standard BI-RADS alone). CONCLUSION: Our findings suggest that the (relative) amount of fibroglandular tissue (density) and mammographic structural features (texture/parenchymal pattern) jointly can improve risk segregation of screening women, using information already available from normal screening routine, in respect to future personalized screening strategies.

Deformation-based atrophy computation by surface propagation and its application to Alzheimer's disease.

Obtaining regional volume changes from a deformation field is more precise when using simplex counting (SC) compared with Jacobian integration (JI) due to the numerics involved in the latter. Although SC has been proposed before, numerical properties underpinning the method and a thorough evaluation of the method against JI is missing in the literature. The contributions of this paper are: (a) we propose surface propagation (SP)-a simplification to SC that significantly reduces its computational complexity; (b) we will derive the orders of approximation of SP which can also be extended to SC. In the experiments, we will begin by empirically showing that SP is indeed nearly identical to SC, and that both methods are more stable than JI in presence of moderate to large deformation noise. Since SC and SP are identical, we consider SP as a representative of both the methods for a practical evaluation against JI. In a real application on Alzheimer's disease neuroimaging initiative data, we show the following: (a) SP produces whole brain and medial temporal lobe atrophy numbers that are significantly better than JI at separating between normal controls and Alzheimer's disease patients; (b) SP produces disease group atrophy differences comparable to or better than those obtained using FreeSurfer, demonstrating the validity of the obtained clinical results. Finally, in a reproducibility study, we show that the voxel-wise application of SP yields significantly lower variance when compared to JI.

Unsupervised Deep Learning Applied to Breast Density Segmentation and Mammographic Risk Scoring.

Mammographic risk scoring has commonly been automated by extracting a set of handcrafted features from mammograms, and relating the responses directly or indirectly to breast cancer risk. We present a method that learns a feature hierarchy from unlabeled data. When the learned features are used as the input to a simple classifier, two different tasks can be addressed: i) breast density segmentation, and ii) scoring of mammographic texture. The proposed model learns features at multiple scales. To control the models capacity a novel sparsity regularizer is introduced that incorporates both lifetime and population sparsity. We evaluated our method on three different clinical datasets. Our state-of-the-art results show that the learned breast density scores have a very strong positive relationship with manual ones, and that the learned texture scores are predictive of breast cancer. The model is easy to apply and generalizes to many other segmentation and scoring problems.

Automatic segmentation of high- and low-field knee MRIs using knee image quantification with data from the osteoarthritis initiative.

Clinical studies including thousands of magnetic resonance imaging (MRI) scans offer potential for pathogenesis research in osteoarthritis. However, comprehensive quantification of all bone, cartilage, and meniscus compartments is challenging. We propose a segmentation framework for fully automatic segmentation of knee MRI. The framework combines multiatlas rigid registration with voxel classification and was trained on manual segmentations with varying configurations of bones, cartilages, and menisci. The validation included high- and low-field knee MRI cohorts from the Center for Clinical and Basic Research, the osteoarthritis initiative (QAI), and the segmentation of knee images10 (SKI10) challenge. In total, 1907 knee MRIs were segmented during the evaluation. No segmentations were excluded. Our resulting OAI cartilage volume scores are available upon request. The precision and accuracy performances matched manual reader re-segmentation well. The cartilage volume scan-rescan precision was 4.9% (RMS CV). The Dice volume overlaps in the medial/lateral tibial/femoral cartilage compartments were 0.80 to 0.87. The correlations with volumes from independent methods were between 0.90 and 0.96 on the OAI scans. Thus, the framework demonstrated precision and accuracy comparable to manual segmentations. Finally, our method placed second for cartilage segmentation in the SKI10 challenge. The comprehensive validation suggested that automatic segmentation is appropriate for cohorts with thousands of scans.

Mammographic texture resemblance generalizes as an independent risk factor for breast cancer.

INTRODUCTION: Breast density has been established as a major risk factor for breast cancer. We have previously demonstrated that mammographic texture resemblance (MTR), recognizing the local texture patterns of the mammogram, is also a risk factor for breast cancer, independent of percent breast density. We examine if these findings generalize to another population. METHODS: Texture patterns were recorded in digitalized pre-diagnosis (3.7 years) film mammograms of a nested case-control study within the Dutch screening program (S1) comprising of 245 breast cancers and 250 matched controls. The patterns were recognized in the same study using cross-validation to form resemblance scores associated with breast cancer. Texture patterns from S1 were examined in an independent nested case-control study within the Mayo Mammography Health Study cohort (S2) of 226 cases and 442 matched controls: mammograms on average 8.5 years prior to diagnosis, risk factor information and percent mammographic density (PD) estimated using Cumulus were available. MTR scores estimated from S1, S2 and S1 + S2 (the latter two as cross-validations) were evaluated in S2. MTR scores were analyzed as both quartiles and continuously for association with breast cancer using odds ratios (OR) and adjusting for known risk factors including age, body mass index (BMI), and hormone usage. RESULTS: The mean ages of S1 and S2 were 58.0 ± 5.7 years and 55.2 ± 10.5 years, respectively. The MTR scores on S1 showed significant capability to discriminate cancers from controls (area under the operator characteristics curve (AUC) = 0.63 ± 0.02, P <0.001), which persisted after adjustment for PD. S2 showed an AUC of 0.63, 0.61, and 0.60 based on PD, MTR scores trained on S2, and MTR scores trained on S1, respectively. When adjusted for PD, MTR scores of S2 trained on S1 showed an association with breast cancer for the highest quartile alone: OR in quartiles of controls as reference; 1.04 (0.59 to 1.81); 0.95 (0.52 to 1.74); 1.84 (1.10 to 3.07) respectively. The combined continuous model with both PD and MTR scores based on S1 had an AUC of 0.66 ± 0.03. CONCLUSIONS: The local texture patterns associated with breast cancer risk in S1 were also an independent risk factor in S2. Additional textures identified in S2 did not significantly improve risk segregation. Hence, the textural patterns that indicated elevated risk persisted under differences in X-ray technology, population demographics, follow-up time and geography.

Predicting knee cartilage loss using adaptive partitioning of cartilage thickness maps.

This study investigates whether measures of knee cartilage thickness can predict future loss of knee cartilage. A slow and a rapid progressor group was determined using longitudinal data, and anatomically aligned cartilage thickness maps were extracted from MRI at baseline. A novel machine learning framework was then trained using these maps. Compared to measures of mean cartilage plate thickness, group separation was increased by focusing on local cartilage differences. This result is central for clinical trials where inclusion of rapid progressors may help reduce the period needed to study effects of new disease-modifying drugs for osteoarthritis.