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

Classification performance bias between training and test sets in a limited mammography dataset

OBJECTIVES

To assess the performance bias caused by sampling data into training and test sets in a mammography radiomics study.

METHODS

Mammograms from 700 women were used to study upstaging of ductal carcinoma in situ. The dataset was repeatedly shuffled and split into training (n = 400) and test cases (n = 300) forty times. For each split, cross-validation was used for training, followed by an assessment of the test set. Logistic regression with regularization and support vector machine were used as the machine learning classifiers. For each split and classifier type, multiple models were created based on radiomics and/or clinical features.

RESULTS

Area under the curve (AUC) performances varied considerably across the different data splits (e.g., radiomics regression model: train 0.58-0.70, test 0.59-0.73). Performances for regression models showed a tradeoff where better training led to worse testing and vice versa. Cross-validation over all cases reduced this variability, but required samples of 500+ cases to yield representative estimates of performance.

CONCLUSIONS

In medical imaging, clinical datasets are often limited to relatively small size. Models built from different training sets may not be representative of the whole dataset. Depending on the selected data split and model, performance bias could lead to inappropriate conclusions that might influence the clinical significance of the findings.

ADVANCES IN KNOWLEDGE

Performance bias can result from model testing when using limited datasets. Optimal strategies for test set selection should be developed to ensure study conclusions are appropriate.

Predicting Underestimation of Invasive Cancer in Patients with Core-Needle-Biopsy-Diagnosed Ductal Carcinoma In Situ Using Deep Learning Algorithms

The prediction of an occult invasive component in ductal carcinoma in situ (DCIS) before surgery is of clinical importance because the treatment strategies are different between pure DCIS without invasive component and upgraded DCIS. We demonstrated the potential of using deep learning models for differentiating between upgraded versus pure DCIS in DCIS diagnosed by core-needle biopsy. Preoperative axial dynamic contrast-enhanced magnetic resonance imaging (MRI) data from 352 lesions were used to train, validate, and test three different types of deep learning models. The highest performance was achieved by Recurrent Residual Convolutional Neural Network using Regions of Interest (ROIs) with an accuracy of 75.0% and area under the receiver operating characteristic curve (AUC) of 0.796. Our results suggest that the deep learning approach may provide an assisting tool to predict the histologic upgrade of DCIS and provide personalized treatment strategies to patients with underestimated invasive disease.

Breast Cancer Detection Using Convoluted Features and Ensemble Machine Learning Algorithm

Breast cancer is a common cause of female mortality in developing countries. Screening and early diagnosis can play an important role in the prevention and treatment of these cancers. This study proposes an ensemble learning-based voting classifier that combines the logistic regression and stochastic gradient descent classifier with deep convoluted features for the accurate detection of cancerous patients. Deep convoluted features are extracted from the microscopic features and fed to the ensemble voting classifier. This idea provides an optimized framework that accurately classifies malignant and benign tumors with improved accuracy. Results obtained using the voting classifier with convoluted features demonstrate that the highest classification accuracy of 100% is achieved. The proposed approach revealed the accuracy enhancement in comparison with the state-of-the-art approaches.

Learning to distinguish progressive and non-progressive ductal carcinoma in situ

Ductal carcinoma in situ (DCIS) is a non-invasive breast neoplasia that accounts for 25% of all screen-detected breast cancers diagnosed annually. Neoplastic cells in DCIS are confined to the ductal system of the breast, although they can escape and progress to invasive breast cancer in a subset of patients. A key concern of DCIS is overtreatment, as most patients screened for DCIS and in whom DCIS is diagnosed will not go on to exhibit symptoms or die of breast cancer, even if left untreated. However, differentiating low-risk, indolent DCIS from potentially progressive DCIS remains challenging. In this Review, we summarize our current knowledge of DCIS and explore open questions about the basic biology of DCIS, including those regarding how genomic events in neoplastic cells and the surrounding microenvironment contribute to the progression of DCIS to invasive breast cancer. Further, we discuss what information will be needed to prevent overtreatment of indolent DCIS lesions without compromising adequate treatment for high-risk patients.

Analysis of Signs and Effects of Surgical Breast Cancer Patients Based on Big Data Technology

Big data in health care has gained popularity in recent years for disease prediction. Breast cancer infections are the most common cancer in urban Indian women, as well as women internationally, and are impacted by many events across countries and regions. Breast malignant growth is a notable disease among Indian women. According to the WHO, it represents 14% of all malignant growth tumors in women. A couple of studies have been directed utilizing big data to foresee breast malignant growth. Big data is causing a transformation in healthcare, with better and more ideal results. Monstrous volumes of patient-level data are created by using EHR (Electronic Health Record) systems data because of fast mechanical upgrades. Big data applications in the healthcare business will assist with improving results. Conventional forecast models, then again, are less productive in terms of accuracy and error rate because the exact pace of a specific calculation relies upon different factors such as execution structure, datasets (little or enormous), and kinds of datasets utilized (trait-based or picture based). This audit article looks at complex information mining, AI, and profound learning models utilized for recognizing breast malignant growth. Since "early identification is the way to avoidance in any malignant growth," the motivation behind this audit article is to support the choice of fitting breast disease expectation calculations, explicitly in the big information climate, to convey powerful and productive results. This survey article analyzes the precision paces of perplexing information mining, AI, and profound learning models utilized for distinguishing breast disease on the grounds that the exactness pace of a specific calculation relies upon different factors such as execution structure, datasets (little or enormous), and dataset types (quality based or picture based). The reason for this audit article is to aid the determination of suitable breast disease expectation calculations, explicitly in the big information climate, to convey successful and productive outcomes. Thus, "Early discovery is the way to counteraction in the event of any malignant growth."

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.

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.

Domain Generalization in Biosignal Classification

OBJECTIVE

When training machine learning models, we often assume that the training data and evaluation data are sampled from the same distribution. However, this assumption is violated when the model is evaluated on another unseen but similar database, even if that database contains the same classes. This problem is caused by domain-shift and can be solved using two approaches: domain adaptation and domain generalization. Simply, domain adaptation methods can access data from unseen domains during training; whereas in domain generalization, the unseen data is not available during training. Hence, domain generalization concerns models that perform well on inaccessible, domain-shifted data.

METHOD

Our proposed domain generalization method represents an unseen domain using a set of known basis domains, afterwhich we classify the unseen domain using classifier fusion. To demonstrate our system, we employ a collection of heart sound databases that contain normal and abnormal sounds (classes).

RESULTS

Our proposed classifier fusion method achieves accuracy gains of up to 16% for four completely unseen domains.

CONCLUSION

Recognizing the complexity induced by the inherent temporal nature of biosignal data, the two-stage method proposed in this study is able to effectively simplify the whole process of domain generalization while demonstrating good results on unseen domains and the adopted basis domains.

SIGNIFICANCE

To our best knowledge, this is the first study that investigates domain generalization for biosignal data. Our proposed learning strategy can be used to effectively learn domain-relevant features while being aware of the class differences in the data.

Mixed-Methods Study to Predict Upstaging of DCIS to Invasive Disease on Mammography

BACKGROUND. The incidence of ductal carcinoma in situ (DCIS) has steadily increased, as have concerns regarding overtreatment. Active surveillance is a novel treatment strategy that avoids surgical excision, but identifying patients with occult invasive disease who should be excluded from active surveillance is challenging. Radiologists are not typically expected to predict the upstaging of DCIS to invasive disease, though they might be trained to perform this task. OBJECTIVE. The purpose of this study was to determine whether a mixed-methods two-stage observer study can improve radiologists' ability to predict upstaging of DCIS to invasive disease on mammography. METHODS. All cases of DCIS calcifications that underwent stereotactic biopsy between 2010 and 2015 were identified. Two cohorts were randomly generated, each containing 150 cases (120 pure DCIS cases and 30 DCIS cases upstaged to invasive disease at surgery). Nine breast radiologists reviewed the mammograms in the first cohort in a blinded fashion and scored the probability of upstaging to invasive disease. The radiologists then reviewed the cases and results collectively in a focus group to develop consensus criteria that could improve their ability to predict upstaging. The radiologists reviewed the mammograms from the second cohort in a blinded fashion and again scored the probability of upstaging. Statistical analysis compared the performances between rounds 1 and 2. RESULTS. The mean AUC for reader performance in predicting upstaging in round 1 was 0.623 (range, 0.514-0.684). In the focus group, radiologists agreed that upstaging was better predicted when an associated mass, asymmetry, or architectural distortion was present; when densely packed calcifications extended over a larger area; and when the most suspicious features were focused on rather than the most common features. Additionally, radiologists agreed that BI-RADS descriptors do not adequately characterize risk of invasion, and that microinvasive disease and smaller areas of DCIS will have poor prediction estimates. Reader performance significantly improved in round 2 (mean AUC, 0.765; range, 0.617-0.852; p = .045). CONCLUSION. A mixed-methods two-stage observer study identified factors that helped radiologists significantly improve their ability to predict upstaging of DCIS to invasive disease. CLINICAL IMPACT. Breast radiologists can be trained to better predict upstaging of DCIS to invasive disease, which may facilitate discussions with patients and referring providers.