Sentinel lymph nodes (SLN) are more likely to contain metastatic breast carcinoma than non-SLNs. The limited number of SLNs compared with an axillary dissection has prompted more comprehensive lymph ...node analysis increasing detection of micrometastases. National data show that many women previously classified node negative are now classified minimally node positive. As a result, our nodal classification and cancer staging have evolved to recognize the continuum of nodal tumor burden rather than a simplistic dichotomous stratification. It is quite clear that the more sections we evaluate from SLNs the more metastases we identify; however, it is impractical to expect the practicing pathologist to mount, stain, and microscopically examine every section through the SLN paraffin blocks. Despite recommendations from the College of American Pathologists and the American Society of Clinical Oncology, heterogeneity in the approach to SLN evaluation exists. What is needed is adherence to a standardized evaluation protocol. The most important aspect of the sentinel node examination is careful attention to slicing the SLN no thicker than 2.0 mm and correct embedding of the slices to assure we identify all macrometastases larger than 2.0 mm. A single section from blocks prepared in this manner will identify all macrometastases present but smaller metastases will be missed. The prognostic significance of these missed micrometastases is still being evaluated as we await SLN outcome studies. In the context of the new molecular classification of breast cancer, subgroups may be identified where detection of micrometastases has clinical significance. It is critical that both clinicians and pathologists understand there is a random component to micrometastasis distribution within the three-dimensional paraffin tissue blocks. If we ultimately adopt more comprehensive microscopic evaluation of SLNs, the candidate sampling strategies need to be carefully considered in the context of statistically valid sampling strategies.
•Commonly studied scenario considers only binary cancer vs. no cancer classification.•Our system classifies whole slide breast biopsies into five diagnostic categories.•Pipeline of fully ...convolutional networks localizes diagnostically relevant regions.•Convolutional neural network classifies detected regions of interest in whole slides.•Experiments show that our method is compatible with predictions of 45 pathologists.
Generalizability of algorithms for binary cancer vs. no cancer classification is unknown for clinically more significant multi-class scenarios where intermediate categories have different risk factors and treatment strategies. We present a system that classifies whole slide images (WSI) of breast biopsies into five diagnostic categories. First, a saliency detector that uses a pipeline of four fully convolutional networks, trained with samples from records of pathologists’ screenings, performs multi-scale localization of diagnostically relevant regions of interest in WSI. Then, a convolutional network, trained from consensus-derived reference samples, classifies image patches as non-proliferative or proliferative changes, atypical ductal hyperplasia, ductal carcinoma in situ, and invasive carcinoma. Finally, the saliency and classification maps are fused for pixel-wise labeling and slide-level categorization. Experiments using 240 WSI showed that both saliency detector and classifier networks performed better than competing algorithms, and the five-class slide-level accuracy of 55% was not statistically different from the predictions of 45 pathologists. We also present example visualizations of the learned representations for breast cancer diagnosis.
Digital pathology has entered a new era with the availability of whole slide scanners that create the high-resolution images of full biopsy slides. Consequently, the uncertainty regarding the ...correspondence between the image areas and the diagnostic labels assigned by pathologists at the slide level, and the need for identifying regions that belong to multiple classes with different clinical significances have emerged as two new challenges. However, generalizability of the state-of-the-art algorithms, whose accuracies were reported on carefully selected regions of interest (ROIs) for the binary benign versus cancer classification, to these multi-class learning and localization problems is currently unknown. This paper presents our potential solutions to these challenges by exploiting the viewing records of pathologists and their slide-level annotations in weakly supervised learning scenarios. First, we extract candidate ROIs from the logs of pathologists' image screenings based on different behaviors, such as zooming, panning, and fixation. Then, we model each slide with a bag of instances represented by the candidate ROIs and a set of class labels extracted from the pathology forms. Finally, we use four different multi-instance multi-label learning algorithms for both slide-level and ROI-level predictions of diagnostic categories in whole slide breast histopathology images. Slide-level evaluation using 5-class and 14-class settings showed average precision values up to 81% and 69%, respectively, under different weakly labeled learning scenarios. ROI-level predictions showed that the classifier could successfully perform multi-class localization and classification within whole slide images that were selected to include the full range of challenging diagnostic categories.
The tumor microenvironment is a complex mixture of cell types that bi-directionally interact and influence tumor initiation, progression, recurrence, and patient survival. Mesenchymal stromal cells ...(MSCs) of the tumor microenvironment engage in crosstalk with cancer cells to mediate epigenetic control of gene expression. We identified CD90+ MSCs residing in the tumor microenvironment of patients with invasive breast cancer that exhibit a unique gene expression signature. Single-cell transcriptional analysis of these MSCs in tumor-associated stroma identified a distinct subpopulation characterized by increased expression of genes functionally related to extracellular matrix signaling. Blocking the TGFβ pathway reveals that these cells directly contribute to cancer cell proliferation. Our findings provide novel insight into communication between breast cancer cells and MSCs that are consistent with an epithelial to mesenchymal transition and acquisition of competency for compromised control of proliferation, mobility, motility, and phenotype.
As agenda-setting theory moves toward its 50th anniversary, its productivity in the past and at present augurs a highly promising future. In this essay, the original theorists trace the development ...of agenda setting and identify seven distinct facets. They explore three of the seven facets-need for orientation, network agenda setting, and agendamelding-in greater detail because those are particularly active arenas of contemporary research. Grounded in more than 40 years of productive collaboration among the authors, this inaugural Deutschmann Scholars Essay offers numerous new ideas about recent trends in and future directions for agenda-setting theory and research. The three authors are all recipients of AEJMC's Paul J. Deutschmann Award for Excellence in Research recognizing a career of scholarly achievement. The Deutschmann scholars observed that this may well be the most original article they have ever written together.
Adaptive gain theory proposes that the dynamic shifts between exploration and exploitation control states are modulated by the locus coeruleus-norepinephrine system and reflected in tonic and phasic ...pupil diameter. This study tested predictions of this theory in the context of a societally important visual search task: the review and interpretation of digital whole slide images of breast biopsies by physicians (pathologists). As these medical images are searched, pathologists encounter difficult visual features and intermittently zoom in to examine features of interest. We propose that tonic and phasic pupil diameter changes during image review may correspond to perceived difficulty and dynamic shifts between exploration and exploitation control states. To examine this possibility, we monitored visual search behavior and tonic and phasic pupil diameter while pathologists (N = 89) interpreted 14 digital images of breast biopsy tissue (1,246 total images reviewed). After viewing the images, pathologists provided a diagnosis and rated the level of difficulty of the image. Analyses of tonic pupil diameter examined whether pupil dilation was associated with pathologists' difficulty ratings, diagnostic accuracy, and experience level. To examine phasic pupil diameter, we parsed continuous visual search data into discrete zoom-in and zoom-out events, including shifts from low to high magnification (e.g., 1× to 10×) and the reverse. Analyses examined whether zoom-in and zoom-out events were associated with phasic pupil diameter change. Results demonstrated that tonic pupil diameter was associated with image difficulty ratings and zoom level, and phasic pupil diameter showed constriction upon zoom-in events, and dilation immediately preceding a zoom-out event. Results are interpreted in the context of adaptive gain theory, information gain theory, and the monitoring and assessment of physicians' diagnostic interpretive processes.
A breast pathology diagnosis provides the basis for clinical treatment and management decisions; however, its accuracy is inadequately understood.
To quantify the magnitude of diagnostic disagreement ...among pathologists compared with a consensus panel reference diagnosis and to evaluate associated patient and pathologist characteristics.
Study of pathologists who interpret breast biopsies in clinical practices in 8 US states.
Participants independently interpreted slides between November 2011 and May 2014 from test sets of 60 breast biopsies (240 total cases, 1 slide per case), including 23 cases of invasive breast cancer, 73 ductal carcinoma in situ (DCIS), 72 with atypical hyperplasia (atypia), and 72 benign cases without atypia. Participants were blinded to the interpretations of other study pathologists and consensus panel members. Among the 3 consensus panel members, unanimous agreement of their independent diagnoses was 75%, and concordance with the consensus-derived reference diagnoses was 90.3%.
The proportions of diagnoses overinterpreted and underinterpreted relative to the consensus-derived reference diagnoses were assessed.
Sixty-five percent of invited, responding pathologists were eligible and consented to participate. Of these, 91% (N = 115) completed the study, providing 6900 individual case diagnoses. Compared with the consensus-derived reference diagnosis, the overall concordance rate of diagnostic interpretations of participating pathologists was 75.3% (95% CI, 73.4%-77.0%; 5194 of 6900 interpretations). Among invasive carcinoma cases (663 interpretations), 96% (95% CI, 94%-97%) were concordant, and 4% (95% CI, 3%-6%) were underinterpreted; among DCIS cases (2097 interpretations), 84% (95% CI, 82%-86%) were concordant, 3% (95% CI, 2%-4%) were overinterpreted, and 13% (95% CI, 12%-15%) were underinterpreted; among atypia cases (2070 interpretations), 48% (95% CI, 44%-52%) were concordant, 17% (95% CI, 15%-21%) were overinterpreted, and 35% (95% CI, 31%-39%) were underinterpreted; and among benign cases without atypia (2070 interpretations), 87% (95% CI, 85%-89%) were concordant and 13% (95% CI, 11%-15%) were overinterpreted. Disagreement with the reference diagnosis was statistically significantly higher among biopsies from women with higher (n = 122) vs lower (n = 118) breast density on prior mammograms (overall concordance rate, 73% 95% CI, 71%-75% for higher vs 77% 95% CI, 75%-80% for lower, P < .001), and among pathologists who interpreted lower weekly case volumes (P < .001) or worked in smaller practices (P = .034) or nonacademic settings (P = .007).
In this study of pathologists, in which diagnostic interpretation was based on a single breast biopsy slide, overall agreement between the individual pathologists' interpretations and the expert consensus-derived reference diagnoses was 75.3%, with the highest level of concordance for invasive carcinoma and lower levels of concordance for DCIS and atypia. Further research is needed to understand the relationship of these findings with patient management.
The vast majority of women diagnosed with ductal carcinoma in situ (DCIS) undergo treatment. Therefore, the risks of invasive progression and competing death in the absence of locoregional therapy ...are uncertain.
We performed survival analyses of patient-level data from DCIS patients who did not receive definitive surgery or radiation therapy as recorded in the US National Cancer Institute's Surveillance, Epidemiology, and End Results program (1992-2014). Kaplan-Meier curves were used to estimate the net risk of subsequent ipsilateral invasive cancer. The cumulative incidences of ipsilateral invasive cancer, contralateral breast cancer, and death were estimated using competing risk methods.
A total of 1286 DCIS patients who did not undergo locoregional therapy were identified. Median age at diagnosis was 60 years (inter-quartile range = 51-74 years), with median follow-up of 5.5 years (inter-quartile range = 2.3-10.6 years). Among patients with tumor grade I/II (n = 547), the 10-year net risk of ipsilateral invasive breast cancer was 12.2% (95% confidence interval CI = 8.6% to 17.1%) compared with 17.6% (95% CI = 12.1% to 25.2%) among patients with tumor grade III (n = 244) and 10.1% (95% CI = 7.4% to 13.8%) among patients with unknown grade (n = 495). Among all patients, the 10-year cumulative incidences of ipsilateral invasive cancer, contralateral breast cancer, and all-cause mortality were 10.5% (95% CI = 8.5% to 12.4%), 3.9% (95% CI = 2.6% to 5.2%), and 24.1% (95% CI = 21.2% to 26.9%), respectively.
Despite limited data, our findings suggest that DCIS patients without locoregional treatment have a limited risk of invasive progression. Although the cohort is not representative of the general population of patients diagnosed with DCIS, the findings suggest that there may be overtreatment, especially among older patients and patients with elevated comorbidities.
The breast stromal microenvironment is a pivotal factor in breast cancer development, growth and metastases. Although pathologists often detect morphologic changes in stroma by light microscopy, ...visual classification of such changes is subjective and non-quantitative, limiting its diagnostic utility. To gain insights into stromal changes associated with breast cancer, we applied automated machine learning techniques to digital images of 2387 hematoxylin and eosin stained tissue sections of benign and malignant image-guided breast biopsies performed to investigate mammographic abnormalities among 882 patients, ages 40–65 years, that were enrolled in the Breast Radiology Evaluation and Study of Tissues (BREAST) Stamp Project. Using deep convolutional neural networks, we trained an algorithm to discriminate between stroma surrounding invasive cancer and stroma from benign biopsies. In test sets (928 whole-slide images from 330 patients), this algorithm could distinguish biopsies diagnosed as invasive cancer from benign biopsies solely based on the stromal characteristics (area under the receiver operator characteristics curve = 0.962). Furthermore, without being trained specifically using ductal carcinoma in situ as an outcome, the algorithm detected tumor-associated stroma in greater amounts and at larger distances from grade 3 versus grade 1 ductal carcinoma in situ. Collectively, these results suggest that algorithms based on deep convolutional neural networks that evaluate only stroma may prove useful to classify breast biopsies and aid in understanding and evaluating the biology of breast lesions.