Estimate of false-positive breast cancer diagnoses from accuracy studies: a systematic review

Breast Cancer Diagnosis Using Extended-Wavelength-Diffuse Reflectance Spectroscopy (EW-DRS)-Proof of Concept in Ex Vivo Breast Specimens Using Machine Learning

This study aims to investigate the feasibility of using diffuse reflectance spectroscopy (DRS) to distinguish malignant breast tissue from adjacent healthy tissue, and to evaluate if an extended-wavelength range (450-1550 nm) has an advantage over the standard wavelength range (450-900 nm). Multivariate statistics and machine learning algorithms, either linear discriminant analysis (LDA) or support vector machine (SVM) are used to distinguish the two tissue types in breast specimens (total or partial mastectomy) from 23 female patients with primary breast cancer. EW-DRS has a sensitivity of 94% and specificity of 91% as compared to a sensitivity of 40% and specificity of 71% using the standard wavelength range. The results suggest that DRS can discriminate between malignant and healthy breast tissue, with improved outcomes using an extended wavelength. It is also possible to construct a simple analytical model to improve the diagnostic performance of the DRS technique.

An interpretable decision-support model for breast cancer diagnosis using histopathology images

Microscopic examination of biopsy tissue slides is perceived as the gold-standard methodology for the confirmation of presence of cancer cells. Manual analysis of an overwhelming inflow of tissue slides is highly susceptible to misreading of tissue slides by pathologists. A computerized framework for histopathology image analysis is conceived as a diagnostic tool that greatly benefits pathologists, augmenting definitive diagnosis of cancer. Convolutional Neural Network (CNN) turned out to be the most adaptable and effective technique in the detection of abnormal pathologic histology. Despite their high sensitivity and predictive power, clinical translation is constrained by a lack of intelligible insights into the prediction. A computer-aided system that can offer a definitive diagnosis and interpretability is therefore highly desirable. Conventional visual explanatory techniques, Class Activation Mapping (CAM), combined with CNN models offers interpretable decision making. The major challenge in CAM is, it cannot be optimized to create the best visualization map. CAM also decreases the performance of the CNN models. To address this challenge, we introduce a novel interpretable decision-support model using CNN with a trainable attention mechanism using response-based feed-forward visual explanation. We introduce a variant of DarkNet19 CNN model for the classification of histopathology images. In order to achieve visual interpretation as well as boost the performance of the DarkNet19 model, an attention branch is integrated with DarkNet19 network forming Attention Branch Network (ABN). The attention branch uses a convolution layer of DarkNet19 and Global Average Pooling (GAP) to model the context of the visual features and generate a heatmap to identify the region of interest. Finally, the perception branch is constituted using a fully connected layer to classify images. We trained and validated our model using more than 7000 breast cancer biopsy slide images from an openly available dataset and achieved 98.7% accuracy in the binary classification of histopathology images. The observations substantiated the enhanced clinical interpretability of the DarkNet19 CNN model, supervened by the attention branch, besides delivering a 3%-4% performance boost of the baseline model. The cancer regions highlighted by the proposed model correlate well with the findings of an expert pathologist. The coalesced approach of unifying attention branch with the CNN model capacitates pathologists with augmented diagnostic interpretability of histological images with no detriment to state-of-art performance. The model's proficiency in pinpointing the region of interest is an added bonus that can lead to accurate clinical translation of deep learning models that underscore clinical decision support.

Should low-risk DCIS lose the cancer label? An evidence review

BACKGROUND

Population mammographic screening for breast cancer has led to large increases in the diagnosis and treatment of ductal carcinoma in situ (DCIS). Active surveillance has been proposed as a management strategy for low-risk DCIS to mitigate against potential overdiagnosis and overtreatment. However, clinicians and patients remain reluctant to choose active surveillance, even within a trial setting. Re-calibration of the diagnostic threshold for low-risk DCIS and/or use of a label that does not include the word 'cancer' might encourage the uptake of active surveillance and other conservative treatment options. We aimed to identify and collate relevant epidemiological evidence to inform further discussion on these ideas.

METHODS

We searched PubMed and EMBASE databases for low-risk DCIS studies in four categories: (1) natural history; (2) subclinical cancer found at autopsy; (3) diagnostic reproducibility (two or more pathologist interpretations at a single time point); and (4) diagnostic drift (two or more pathologist interpretations at different time points). Where we identified a pre-existing systematic review, the search was restricted to studies published after the inclusion period of the review. Two authors screened records, extracted data, and performed risk of bias assessment. We undertook a narrative synthesis of the included evidence within each category.

RESULTS

Natural History (n = 11): one systematic review and nine primary studies were included, but only five provided evidence on the prognosis of women with low-risk DCIS. These studies reported that women with low-risk DCIS had comparable outcomes whether or not they had surgery. The risk of invasive breast cancer in patients with low-risk DCIS ranged from 6.5% (7.5 years) to 10.8% (10 years). The risk of dying from breast cancer in patients with low-risk DCIS ranged from 1.2 to 2.2% (10 years). Subclinical cancer at autopsy (n = 1): one systematic review of 13 studies estimated the mean prevalence of subclinical in situ breast cancer to be 8.9%. Diagnostic reproducibility (n = 13): two systematic reviews and 11 primary studies found at most moderate agreement in differentiating low-grade DCIS from other diagnoses. Diagnostic drift: no studies found.

CONCLUSION

Epidemiological evidence supports consideration of relabelling and/or recalibrating diagnostic thresholds for low-risk DCIS. Such diagnostic changes would need agreement on the definition of low-risk DCIS and improved diagnostic reproducibility.

Diagnostic Accuracy of Opportunistic Breast Cancer Screening Based on Mammography in Iran

Background: Although breast cancer is the most prevalent type of cancer among Iranian women, its screening is opportunistic in Iran. The available guidelines for breast cancer screening are based on mammography. A screening modality should have adequate diagnostic accuracy and be widely available at reasonable cost. Although mammography is highly accessible in Iran, its accuracy has not been investigated. Objectives: This study aimed to evaluate the accuracy of mammography in opportunistic screening regarding the current rate of patient attendance. Patients and Methods: A total of 491 women undergoing screening mammography were followed-up based on their medical records. They were divided into positive and negative screening groups, based on the breast imaging-reporting and data system (BI-RADS) categories and approaches. To evaluate the disease status of positive cases, pathology reports were investigated, and negative cases were followed-up for stability over time. Results: In the study sample, sensitivity was estimated at 73.08% (95% CI: 55.21 - 88.93), specificity was estimated at 94.41% (95% CI: 91.91 - 96.32), and accuracy was 93.28% (95% CI: 90.69 - 95.33). These test accuracy indices were not significantly different between the groups regarding age, family history, breast density, and history of breast interventions. Conclusion: The test’s sensitivity or ability to detect a disease was relatively low in opportunistic screening; it was found to be similar to the results of studies of first time implementation of screeninng. In both settings, a test needs to diagnose both incident and prevalent cases. The overall accuracy of mammography was acceptable, even in opportunistic screening.

Diagnostic concordance among pathologists interpreting breast core biopsies on secondary review over a 1-year period at an Australian tertiary hospital

This study provides data on the diagnostic concordance between initial and review diagnoses of all breast core biopsy cases at a single tertiary hospital in Western Australia over a 1-year period. A retrospective review of all breast core biopsy cases between January 1 and December 31, 2016, was carried out at PathWest, Fiona Stanley Hospital in Perth, Western Australia. Each biopsy is reported by a single pathologist and then reviewed within 1 week by a panel of intradepartmental subspecialist breast pathologists, who either agree with the original diagnosis, have a minor discordant diagnosis, or a major discordant diagnosis. Records for 2036 core biopsies were available between January 1 and December 31, 2016. Of these, 56.0% (n = 1141) were classified as benign, 34.3% (n = 699) as malignant, 7.2% (n = 147) as indeterminate, 2.3% (n = 46) as nondiagnostic, and 0.1% (n = 3) as suspicious for malignancy. In 99.1% (n = 2018) of cases, there was agreement between initial and review diagnoses. In total, 0.9% (n = 18) were disagreements: 0.49% (n = 10) were major discordant disagreements and 0.39% (n = 8) were minor discordant disagreements. All cases of major discordant disagreements would have resulted in significant changes to clinical management. This study demonstrates that an Australian institution is providing a high-quality pathology service with a low error rate between initial and review diagnoses of breast core biopsies. It reinforces the importance of secondary review of biopsies in a timely fashion for detecting potentially serious misdiagnoses that could lead to inappropriate management.

Performance indicators in breast cancer screening in the European Union: A comparison across countries of screen positivity and detection rates

Comparable performance indicators for breast cancer screening in the European Union (EU) have not been previously reported. We estimated adjusted breast cancer screening positivity rate (PR) and detection rates (DR) to investigate variation across EU countries. For the age 50-69 years, the adjusted EU-pooled PR for initial screening was 8.9% (cross-programme variation range 3.2-19.5%) while DR of invasive cancers was 5.3/1,000 (range 3.8-7.4/1,000) and DR of ductal carcinoma in situ (DCIS) was 1.3/1,000 (range 0.7-2.7/1,000). For subsequent screening, the adjusted EU-pooled PR was 3.6% (range 1.4-8.4%), the DR was 4.0/1,000 (range 2.2-5.8/1,000) and 0.8/1,000 (range 0.5-1.3/1,000) for invasive and DCIS, respectively. Adjusted performance indicators showed remarkable heterogeneity, likely due to different background breast cancer risk and awareness between target populations, and also different screening protocols and organisation. Periodic reporting of the screening indicators permits comparison and evaluation of the screening activities between and within countries aiming to improve the quality and the outcomes of screening programmes. Cancer Screening Registries would be a milestone in this direction and EU Screening Reports provide a fundamental contribution to building them.

Retrospective cohort study of breast cancer incidence, health service use and outcomes in Europe: a study of feasibility

Background

Comparisons of outcomes of health care in different systems can be used to inform health policy. The EuroHOPE (European Healthcare Outcomes, Performance and Efficiency) project investigated the feasibility of comparing routine data on selected conditions including breast cancer across participating European countries.

Methods

Routine data on incidence, treatment and mortality by age and clinical characteristics for breast cancer in women over 24 years of age were obtained (for a calendar year) from linked hospital discharge records, cancer and death registers from Finland, the Turin metropolitan area, Scotland and Sweden (all 2005), Hungary (2006) and Norway (2009). Age-adjusted breast cancer incidence and 1-year survival were estimated for each country/region.

Results

In total, 24 576 invasive breast cancer cases were identified from cancer registries from over 13 million women. Age-adjusted incidence ranged from 151.1 (95%CI 147.2-155.0) in Hungary to 234.7 (95%CI 227.4-242.0)/100 000 in Scotland. One-year survival ranged from 94.1% (95%CI 93.5-94.7%) in Scotland to 97.1% (95%CI 96.2-98.1%) in Italy. Scotland had the highest proportions of poor prognostic factors in terms of tumour size, nodal status and metastases. Significant variations in data completeness for prognostic factors prevented adjustment for case mix.

Conclusion

Incidence of and survival from breast cancer showed large differences between countries. Substantial improvements in the use of internationally recognised common terminology, standardised data coding and data completeness for prognostic indicators are required before international comparisons of routine data can be used to inform health policy.