Growth Dynamics of Ductal Carcinoma in Situ Recapitulate Normal Breast Development.

Ductal carcinoma in situ (DCIS) and invasive breast cancer share many morphologic, proteomic, and genomic alterations. Yet in contrast to invasive cancer, many DCIS tumors do not progress and may remain indolent over decades. To better understand the heterogenous nature of this disease, we reconstructed the growth dynamics of 18 DCIS tumors based on the geo-spatial distribution of their somatic mutations. The somatic mutation topographies revealed that DCIS is multiclonal and consists of spatially discontinuous subclonal lesions. Here we show that this pattern of spread is consistent with a new 'Comet' model of DCIS tumorigenesis, whereby multiple subclones arise early and nucleate the buds of the growing tumor. The discontinuous, multiclonal growth of the Comet model is analogous to the branching morphogenesis of normal breast development that governs the rapid expansion of the mammary epithelium during puberty. The branching morphogenesis-like dynamics of the proposed Comet model diverges from the canonical model of clonal evolution, and better explains observed genomic spatial data. Importantly, the Comet model allows for the clinically relevant scenario of extensive DCIS spread, without being subjected to the selective pressures of subclone competition that promote the emergence of increasingly invasive phenotypes. As such, the normal cell movement inferred during DCIS growth provides a new explanation for the limited risk of progression in DCIS and adds biologic rationale for ongoing clinical efforts to reduce DCIS overtreatment.

Archival single-cell genomics reveals persistent subclones during DCIS progression.

Ductal carcinoma in situ (DCIS) is a common precursor of invasive breast cancer. Our understanding of its genomic progression to recurrent disease remains poor, partly due to challenges associated with the genomic profiling of formalin-fixed paraffin-embedded (FFPE) materials. Here, we developed Arc-well, a high-throughput single-cell DNA-sequencing method that is compatible with FFPE materials. We validated our method by profiling 40,330 single cells from cell lines, a frozen tissue, and 27 FFPE samples from breast, lung, and prostate tumors stored for 3-31 years. Analysis of 10 patients with matched DCIS and cancers that recurred 2-16 years later show that many primary DCIS had already undergone whole-genome doubling and clonal diversification and that they shared genomic lineages with persistent subclones in the recurrences. Evolutionary analysis suggests that most DCIS cases in our cohort underwent an evolutionary bottleneck, and further identified chromosome aberrations in the persistent subclones that were associated with recurrence.

Microcalcification crystallography as a potential marker of DCIS recurrence.

Ductal carcinoma in-situ (DCIS) accounts for 20-25% of all new breast cancer diagnoses. DCIS has an uncertain risk of progression to invasive breast cancer and a lack of predictive biomarkers may result in relatively high levels (~ 75%) of overtreatment. To identify unique prognostic biomarkers of invasive progression, crystallographic and chemical features of DCIS microcalcifications have been explored. Samples from patients with at least 5-years of follow up and no known recurrence (174 calcifications in 67 patients) or ipsilateral invasive breast cancer recurrence (179 microcalcifications in 57 patients) were studied. Significant differences were noted between the two groups including whitlockite relative mass, hydroxyapatite and whitlockite crystal maturity and, elementally, sodium to calcium ion ratio. A preliminary predictive model for DCIS to invasive cancer progression was developed from these parameters with an AUC of 0.797. These results provide insights into the differing DCIS tissue microenvironments, and how these impact microcalcification formation.

Molecular classification and biomarkers of clinical outcome in breast ductal carcinoma in situ: Analysis of TBCRC 038 and RAHBT cohorts.

Ductal carcinoma in situ (DCIS) is the most common precursor of invasive breast cancer (IBC), with variable propensity for progression. We perform multiscale, integrated molecular profiling of DCIS with clinical outcomes by analyzing 774 DCIS samples from 542 patients with 7.3 years median follow-up from the Translational Breast Cancer Research Consortium 038 study and the Resource of Archival Breast Tissue cohorts. We identify 812 genes associated with ipsilateral recurrence within 5 years from treatment and develop a classifier that predicts DCIS or IBC recurrence in both cohorts. Pathways associated with recurrence include proliferation, immune response, and metabolism. Distinct stromal expression patterns and immune cell compositions are identified. Our multiscale approach employed in situ methods to generate a spatially resolved atlas of breast precancers, where complementary modalities can be directly compared and correlated with conventional pathology findings, disease states, and clinical outcome.

Spatial interplay of tissue hypoxia and T-cell regulation in ductal carcinoma in situ.

Hypoxia promotes aggressive tumor phenotypes and mediates the recruitment of suppressive T cells in invasive breast carcinomas. We investigated the role of hypoxia in relation to T-cell regulation in ductal carcinoma in situ (DCIS). We designed a deep learning system tailored for the tissue architecture complexity of DCIS, and compared pure DCIS cases with the synchronous DCIS and invasive components within invasive ductal carcinoma cases. Single-cell classification was applied in tandem with a new method for DCIS ductal segmentation in dual-stained CA9 and FOXP3, whole-tumor section digital pathology images. Pure DCIS typically has an intermediate level of colocalization of FOXP3+ and CA9+ cells, but in invasive carcinoma cases, the FOXP3+ (T-regulatory) cells may have relocated from the DCIS and into the invasive parts of the tumor, leading to high levels of colocalization in the invasive parts but low levels in the synchronous DCIS component. This may be due to invasive, hypoxic tumors evolving to recruit T-regulatory cells in order to evade immune predation. Our data support the notion that hypoxia promotes immune tolerance through recruitment of T-regulatory cells, and furthermore indicate a spatial pattern of relocalization of T-regulatory cells from DCIS to hypoxic tumor cells. Spatial colocalization of hypoxic and T-regulatory cells may be a key event and useful marker of DCIS progression.

Genomic analysis defines clonal relationships of ductal carcinoma in situ and recurrent invasive breast cancer.

Ductal carcinoma in situ (DCIS) is the most common form of preinvasive breast cancer and, despite treatment, a small fraction (5-10%) of DCIS patients develop subsequent invasive disease. A fundamental biologic question is whether the invasive disease arises from tumor cells in the initial DCIS or represents new unrelated disease. To address this question, we performed genomic analyses on the initial DCIS lesion and paired invasive recurrent tumors in 95 patients together with single-cell DNA sequencing in a subset of cases. Our data show that in 75% of cases the invasive recurrence was clonally related to the initial DCIS, suggesting that tumor cells were not eliminated during the initial treatment. Surprisingly, however, 18% were clonally unrelated to the DCIS, representing new independent lineages and 7% of cases were ambiguous. This knowledge is essential for accurate risk evaluation of DCIS, treatment de-escalation strategies and the identification of predictive biomarkers.

A multi-modal exploration of heterogeneous physico-chemical properties of DCIS breast microcalcifications.

Ductal carcinoma in situ (DCIS) is frequently associated with breast calcification. This study combines multiple analytical techniques to investigate the heterogeneity of these calcifications at the micrometre scale. X-ray diffraction, scanning electron microscopy and Raman and Fourier-transform infrared spectroscopy were used to determine the physicochemical and crystallographic properties of type II breast calcifications located in formalin fixed paraffin embedded DCIS breast tissue samples. Multiple calcium phosphate phases were identified across the calcifications, distributed in different patterns. Hydroxyapatite was the dominant mineral, with magnesium whitlockite found at the calcification edge. Amorphous calcium phosphate and octacalcium phosphate were also identified close to the calcification edge at the apparent mineral/matrix barrier. Crystallographic features of hydroxyapatite also varied across the calcifications, with higher crystallinity centrally, and highest carbonate substitution at the calcification edge. Protein was also differentially distributed across the calcification and the surrounding soft tissue, with collagen and ß-pleated protein features present to differing extents. Combination of analytical techniques in this study was essential to understand the heterogeneity of breast calcifications and how this may link crystallographic and physicochemical properties of calcifications to the surrounding tissue microenvironment.

Improving the Quality of Neuropsychological Assessment Practice: The Development of a Self-Assessment Audit Tool.

OBJECTIVE: Strict competency frameworks exist for training in, and provision of, clinical neuropsychological assessment practice. However, as in all disciplines, daily clinical practice may drift from the gold standard practice without routine monitoring and audit. A simple-to-use, but thorough and evidence-based audit tool has been developed to facilitate the tracking, maintenance, and discussion of best practice over time. METHOD: A literature search and liaison with experienced neuropsychology colleagues did not unearth any pre-existing audit standards. Therefore, 39 new standards were generated, which were guided by best practice literature and clinical neuropsychology colleague discussions, to form the proposed self-assessment audit tool. Due to the diverse nature of services, both core and supplementary standards are proposed to enable the audit to be tailored to suit individual services' needs. RESULTS: During its development, the tool has so far been trialed in two U.K. National Health Service clinical services in different localities, on three occasions, with a total patient population of N = 78 in order to refine the standards and to generate practice recommendations. CONCLUSIONS: This audit tool is presented for services to self-assess their neuropsychological assessment practice. The authors plan to take this work forward with the British Psychological Society's Division of Neuropsychology as a policy document for self-assessment and peer review. Other potential developments include contributing to clinical neuropsychology training tools and refining audit standards for use more widely, such as in pediatric services, or internationally with diverse populations.

Prediction of Upstaging in Ductal Carcinoma in Situ Based on Mammographic Radiomic Features.

Background Improving diagnosis of ductal carcinoma in situ (DCIS) before surgery is important in choosing optimal patient management strategies. However, patients may harbor occult invasive disease not detected until definitive surgery. Purpose To assess the performance and clinical utility of mammographic radiomic features in the prediction of occult invasive cancer among women diagnosed with DCIS on the basis of core biopsy findings. Materials and Methods In this Health Insurance Portability and Accountability Act-compliant retrospective study, digital magnification mammographic images were collected from women who underwent breast core-needle biopsy for calcifications that was performed at a single institution between September 2008 and April 2017 and yielded a diagnosis of DCIS. The database query was directed at asymptomatic women with calcifications without a mass, architectural distortion, asymmetric density, or palpable disease. Logistic regression with regularization was used. Differences across training and internal test set by upstaging rate, age, lesion size, and estrogen and progesterone receptor status were assessed by using the Kruskal-Wallis or χ2 test. Results The study consisted of 700 women with DCIS (age range, 40-89 years; mean age, 59 years ± 10 [standard deviation]), including 114 with lesions (16.3%) upstaged to invasive cancer at subsequent surgery. The sample was split randomly into 400 women for the training set and 300 for the testing set (mean ages: training set, 59 years ± 10; test set, 59 years ± 10; P = .85). A total of 109 radiomic and four clinical features were extracted. The best model on the test set by using all radiomic and clinical features helped predict upstaging with an area under the receiver operating characteristic curve of 0.71 (95% CI: 0.62, 0.79). For a fixed high sensitivity (90%), the model yielded a specificity of 22%, a negative predictive value of 92%, and an odds ratio of 2.4 (95% CI: 1.8, 3.2). High specificity (90%) corresponded to a sensitivity of 37%, positive predictive value of 41%, and odds ratio of 5.0 (95% CI: 2.8, 9.0). Conclusion Machine learning models that use radiomic features applied to mammographic calcifications may help predict upstaging of ductal carcinoma in situ, which can refine clinical decision making and treatment planning. © RSNA, 2022.

Factors predicting first appointment attendance at a traumatic brain injury clinical neuropsychology outpatient clinic: a logistic regression analysis.

BACKGROUND: The purpose of our study was to investigate factors which predicted first appointment attendance within a traumatic brain injury (TBI) neuropsychology outpatient department. MATERIALS AND METHODS: A newly introduced telephone triaging system was implemented in a clinical neuropsychology service for individuals with a TBI. The effects of receiving a triage telephone call, amongst other variables, were analysed as predictors of attendance at the first face-to-face clinic appointment. The data from 161 individuals were analysed using routine patient information collected by the clinical neuropsychology service. Logistic regression analyses were performed to investigate predictors of first appointment clinic attendance. RESULTS: Logistic regression analyses identified higher age, shorter waiting times, and answering the triage call as potential predictors of attendance, highlighting where the service might focus efforts to facilitate attendance. CONCLUSIONS: Both patient and service factors were found to be significant predictors of patient attendance. Further service evaluation could explore patients' experiences of triage telephone calls, and investigate relationships between waiting times and neuropsychological outcomes.IMPLICATIONS FOR REHABILITATIONIdentifying predictors of appointment attendance can allow the service to focus on the needs of particular patient groups.Implementing a telephone triage initiative had positive effects, both on waiting times and efficient use of face-to-face clinic time.The analysis highlighted the need to think about better ways of reaching out to younger individuals and those who have waited longer to attend appointments, who are less likely to attend once invited.

Anomaly Detection of Calcifications in Mammography Based on 11,000 Negative Cases.

In mammography, calcifications are one of the most common signs of breast cancer. Detection of such lesions is an active area of research for computer-aided diagnosis and machine learning algorithms. Due to limited numbers of positive cases, many supervised detection models suffer from overfitting and fail to generalize. We present a one-class, semi-supervised framework using a deep convolutional autoencoder trained with over 50,000 images from 11,000 negative-only cases. Since the model learned from only normal breast parenchymal features, calcifications produced large signals when comparing the residuals between input and reconstruction output images. As a key advancement, a structural dissimilarity index was used to suppress non-structural noises. Our selected model achieved pixel-based AUROC of 0.959 and AUPRC of 0.676 during validation, where calcification masks were defined in a semi-automated process. Although not trained directly on any cancers, detection performance of calcification lesions on 1,883 testing images (645 malignant and 1238 negative) achieved 75% sensitivity at 2.5 false positives per image. Performance plateaued early when trained with only a fraction of the cases, and greater model complexity or a larger dataset did not improve performance. This study demonstrates the potential of this anomaly detection approach to detect mammographic calcifications in a semi-supervised manner with efficient use of a small number of labeled images, and may facilitate new clinical applications such as computer-aided triage and quality improvement.

A new method to accurately identify single nucleotide variants using small FFPE breast samples.

Most tissue collections of neoplasms are composed of formalin-fixed and paraffin-embedded (FFPE) excised tumor samples used for routine diagnostics. DNA sequencing is becoming increasingly important in cancer research and clinical management; however it is difficult to accurately sequence DNA from FFPE samples. We developed and validated a new bioinformatic pipeline to use existing variant-calling strategies to robustly identify somatic single nucleotide variants (SNVs) from whole exome sequencing using small amounts of DNA extracted from archival FFPE samples of breast cancers. We optimized this strategy using 28 pairs of technical replicates. After optimization, the mean similarity between replicates increased 5-fold, reaching 88% (range 0-100%), with a mean of 21.4 SNVs (range 1-68) per sample, representing a markedly superior performance to existing tools. We found that the SNV-identification accuracy declined when there was less than 40 ng of DNA available and that insertion-deletion variant calls are less reliable than single base substitutions. As the first application of the new algorithm, we compared samples of ductal carcinoma in situ of the breast to their adjacent invasive ductal carcinoma samples. We observed an increased number of mutations (paired-samples sign test, P < 0.05), and a higher genetic divergence in the invasive samples (paired-samples sign test, P < 0.01). Our method provides a significant improvement in detecting SNVs in FFPE samples over previous approaches.

Unmasking the immune microecology of ductal carcinoma in situ with deep learning.

Despite increasing evidence supporting the clinical relevance of tumour infiltrating lymphocytes (TILs) in invasive breast cancer, TIL spatial variability within ductal carcinoma in situ (DCIS) samples and its association with progression are not well understood. To characterise tissue spatial architecture and the microenvironment of DCIS, we designed and validated a new deep learning pipeline, UNMaSk. Following automated detection of individual DCIS ducts using a new method IM-Net, we applied spatial tessellation to create virtual boundaries for each duct. To study local TIL infiltration for each duct, DRDIN was developed for mapping the distribution of TILs. In a dataset comprising grade 2-3 pure DCIS and DCIS adjacent to invasive cancer (adjacent DCIS), we found that pure DCIS cases had more TILs compared to adjacent DCIS. However, the colocalisation of TILs with DCIS ducts was significantly lower in pure DCIS compared to adjacent DCIS, which may suggest a more inflamed tissue ecology local to DCIS ducts in adjacent DCIS cases. Our study demonstrates that technological developments in deep convolutional neural networks and digital pathology can enable an automated morphological and microenvironmental analysis of DCIS, providing a new way to study differential immune ecology for individual ducts and identify new markers of progression.

Derivation of a nuclear heterogeneity image index to grade DCIS.

Abnormalities in cell nuclear morphology are a hallmark of cancer. Histological assessment of cell nuclear morphology is frequently used by pathologists to grade ductal carcinoma in situ (DCIS). Objective methods that allow standardization and reproducibility of cell nuclear morphology assessment have potential to improve the criteria needed to predict DCIS progression and recurrence. Aggressive cancers are highly heterogeneous. We asked whether cell nuclear morphology heterogeneity could be incorporated into a metric to classify DCIS. We developed a nuclear heterogeneity image index to objectively, and quantitatively grade DCIS. A whole-tissue cell nuclear morphological analysis, that classified tumors by the worst ten percent in a duct-by-duct manner, identified nuclear size ranges associated with each DCIS grade. Digital image analysis further revealed increasing heterogeneity within ducts or between ducts in tissues of worsening DCIS grade. The findings illustrate how digital image analysis comprises a supplemental tool for pathologists to objectively classify DCIS and in the future, may provide a method to predict patient outcome through analysis of nuclear heterogeneity.

Remote Peer Learning Between US and Cambodian Lay Health Workers to Improve Outcomes for Cambodians with Type 2 Diabetes: a Pilot Study.

BACKGROUND: This paper reports a single-group, pre-post pilot of a peer-learning intervention between community health workers (CHWs) in the USA and Village Health Support Guides (Guides) in Cambodia to improve outcomes for Cambodians with type 2 diabetes (T2D). METHOD: Two US-based CHWs were trained in a culturally derived cardiometabolic education curriculum called Eat, Walk, Sleep (EWS) and they were also trained in principles of peer learning. They in turn trained five Cambodia-based Guides remotely through videoconference with a phablet in EWS. Finally, Cambodia-based Guides met with 58 patients with diabetes, face-to-face in their villages, monthly for 6 months to deliver EWS. US-based CHWs and Cambodia-based Guides responded to surveys at baseline and post-treatment. Patients responded to surveys and provided blood pressure and blood samples at baseline and post-treatment. RESULTS: For US-based CHWs, scores on all surveys of diabetes knowledge, self-evaluation, job satisfaction, and information technology improved, though no statistical tests were run due to sample size. For Cambodia-based Guides, all scores on these same measures improved except for job satisfaction. For patients, n = 60 consented, 2 withdrew, and 7 were lost to follow-up leaving n = 51 for analysis. In paired t tests, patients showed significantly decreased A1c, decreased systolic and diastolic blood pressures, improved attitudes toward medicines, and a trend for switching from all-white to part-brown rice. No changes were detected in self-reported physical activity, medication adherence, sleep quality, or frequency or amount of rice consumed. CONCLUSION: If proven effective in a controlled trial, cross-country peer learning could eventually help other diaspora communities.

Minimal barriers to invasion during human colorectal tumor growth.

Intra-tumoral heterogeneity (ITH) could represent clonal evolution where subclones with greater fitness confer more malignant phenotypes and invasion constitutes an evolutionary bottleneck. Alternatively, ITH could represent branching evolution with invasion of multiple subclones. The two models respectively predict a hierarchy of subclones arranged by phenotype, or multiple subclones with shared phenotypes. We delineate these modes of invasion by merging ancestral, topographic, and phenotypic information from 12 human colorectal tumors (11 carcinomas, 1 adenoma) obtained through saturation microdissection of 325 small tumor regions. The majority of subclones (29/46, 60%) share superficial and invasive phenotypes. Of 11 carcinomas, 9 show evidence of multiclonal invasion, and invasive and metastatic subclones arise early along the ancestral trees. Early multiclonal invasion in the majority of these tumors indicates the expansion of co-evolving subclones with similar malignant potential in absence of late bottlenecks and suggests that barriers to invasion are minimal during colorectal cancer growth.

Prediction of Upstaged Ductal Carcinoma In Situ Using Forced Labeling and Domain Adaptation.

OBJECTIVE: The goal of this study is to use adjunctive classes to improve a predictive model whose performance is limited by the common problems of small numbers of primary cases, high feature dimensionality, and poor class separability. Specifically, our clinical task is to use mammographic features to predict whether ductal carcinoma in situ (DCIS) identified at needle core biopsy will be later upstaged or shown to contain invasive breast cancer. METHODS: To improve the prediction of pure DCIS (negative) versus upstaged DCIS (positive) cases, this study considers the adjunctive roles of two related classes: atypical ductal hyperplasia (ADH), a non-cancer type of breast abnormity, and invasive ductal carcinoma (IDC), with 113 computer vision based mammographic features extracted from each case. To improve the baseline Model A's classification of pure vs. upstaged DCIS, we designed three different strategies (Models B, C, D) with different ways of embedding features or inputs. RESULTS: Based on ROC analysis, the baseline Model A performed with AUC of 0.614 (95% CI, 0.496-0.733). All three new models performed better than the baseline, with domain adaptation (Model D) performing the best with an AUC of 0.697 (95% CI, 0.595-0.797). CONCLUSION: We improved the prediction performance of DCIS upstaging by embedding two related pathology classes in different training phases. SIGNIFICANCE: The three new strategies of embedding related class data all outperformed the baseline model, thus demonstrating not only feature similarities among these different classes, but also the potential for improving classification by using other related classes.

The effects of relaxation training on depression and anxiety in people living with long-term neurological conditions.

Purpose: The present study investigated the effects of a relaxation training program on self-reported depression and anxiety in participants living with long-term neurological conditions, including acquired brain injury, stroke, Parkinson's disease, and multiple sclerosis.Materials and methods: A five-session relaxation training program, plus a follow-up session was offered to people living with a long-term neurological condition as part of routine clinical practice, and was delivered in their own homes. A self-report measure (Hospital Anxiety and Depression Scale) was administered at the pre- and post-intervention time points and at follow-up, around 5 weeks after the final session. Participants also completed an individual assessment of change questionnaire at follow-up, reporting on subjective views of observed changes.Results: Statistically significant improvements were found on measures of both anxiety and depression following completion of the relaxation program. Scores at follow-up (mean = 5 weeks) revealed the improvement was maintained for anxiety, and there was further significant improvement for depression. Reliable change analyses from pre- to post-intervention demonstrated a clinically significant decrease in anxiety scores for 47% of participants and in depression scores for 30% of participants. No clinically significant increase in depression and anxiety was identified from pre- to post-intervention, and this was generally maintained at follow-up.Conclusion: Relaxation training is proposed as a clinically effective treatment for anxiety and depression in people living with long-term neurological conditions, which could in turn lead to better functional outcomes of neurorehabilitation. The program investigated here has additional benefits of being delivered in people's own homes, which overcomes barriers to attending hospital, and is consistent with trends towards home as opposed to hospital care. This program may also be less costly to administer as it can be delivered as part of a stepped-care program by therapy assistants under supervision from qualified staff, and encourages self-management over the longer term. Design limitations may reduce the generalisability of these findings, but are clinically encouraging and should stimulate further research.Implications for RehabilitationRelaxation trainingɉۢ could be offered as an effective first-line intervention, as an alternative to medication to treat anxiety and depression to people living with Long-Term Neurological Conditionsis a self-management strategy which can be taught in people's own homes, if getting out of the house is difficultcan be delivered as a stepped-care intervention via therapy assistants, helping to reduce costs and demands on rehabilitation servicesmay help to improve the functional outcomes of wider rehabilitation interventions by addressing psychological issues which can be a barrier.

Prediction of Occult Invasive Disease in Ductal Carcinoma in Situ Using Deep Learning Features.

PURPOSE: The aim of this study was to determine whether deep features extracted from digital mammograms using a pretrained deep convolutional neural network are prognostic of occult invasive disease for patients with ductal carcinoma in situ (DCIS) on core needle biopsy. METHODS: In this retrospective study, digital mammographic magnification views were collected for 99 subjects with DCIS at biopsy, 25 of which were subsequently upstaged to invasive cancer. A deep convolutional neural network model that was pretrained on nonmedical images (eg, animals, plants, instruments) was used as the feature extractor. Through a statistical pooling strategy, deep features were extracted at different levels of convolutional layers from the lesion areas, without sacrificing the original resolution or distorting the underlying topology. A multivariate classifier was then trained to predict which tumors contain occult invasive disease. This was compared with the performance of traditional "handcrafted" computer vision (CV) features previously developed specifically to assess mammographic calcifications. The generalization performance was assessed using Monte Carlo cross-validation and receiver operating characteristic curve analysis. RESULTS: Deep features were able to distinguish DCIS with occult invasion from pure DCIS, with an area under the receiver operating characteristic curve of 0.70 (95% confidence interval, 0.68-0.73). This performance was comparable with the handcrafted CV features (area under the curve = 0.68; 95% confidence interval, 0.66-0.71) that were designed with prior domain knowledge. CONCLUSIONS: Despite being pretrained on only nonmedical images, the deep features extracted from digital mammograms demonstrated comparable performance with handcrafted CV features for the challenging task of predicting DCIS upstaging.