KEYWORDS: Data modeling, Breast cancer, Education and training, Risk assessment, Performance modeling, Cancer, Cancer detection, Mammography, Solid modeling
This study proposes a method to use longitudinal breast cancer screening data to develop a 1- to 4-year breast cancer risk prediction model. It uses transfer learning from an open-source breast cancer detection model, an Autoencoder to perform dimensionality reduction as well as an LSTM network to incorporate the sequential data. The study utilizes a labelled dataset of 846 patients with up to five different mammography screening exams. The exams were taken on three systems from the vendor Siemens and the images are of the “FOR PRESENTATION” type. In this dataset there are 423 low risk cases and 423 high risk cases. A breast cancer detection model was used to obtain a latent representation of features extracted from the screening images. Dimensionality reduction was performed on the latent space using an Autoencoder architecture. The reduced latent space was then mapped to 1- to 4-year breast cancer risk with an LSTM model. The model achieved an AUC of 0.74 for differentiating high and low risk cases, outperforming the Tyrer-Cuzick model. At the reference specificity operating point of 85.4% from the Tyrer-Cuzick model, the longitudinal model achieves a sensitivity of 60%, outperforming a similar model trained by only seeing a single exam of a given patient. The incorporation of longitudinal data into breast cancer risk assessment models can increase the sensitivity to underlying patterns that are correlated to breast cancer and therefore improve breast cancer screening strategies.
Complementary relationship between computer-aided detection (CAD) and risk prediction has been identified. To understand the factors triggering either cancer detection or risk prediction, we previously studied the performance of the deep learning (DL)-based risk prediction model, Mirai, using a feature-centric explainable AI (XAI) approach. A total of 16 calcification features were identified from Mirai as major risk factor contributors. Several studies have revealed the existence of early detection signs on prior mammograms of screen-detected and interval cancers. Accordingly, the longitudinal behavior of calcifications may further improve the understanding of the causal relationship between Mirai calcification features and elevated risk. In this study, we hypothesize that the calcification features from Mirai have the ability to capture early suspicious signs, which may be important for the risk prediction of breast cancer development. Thus, we tracked the Mirai calcification features across two screening rounds using the breast polar coordinate system. Subsequently, we assessed the ability to predict the current Breast Imaging-Reporting and Data System (BI-RADS) assessment from prior mammograms. The results show that calcification features were able to capture early suspicious signs on prior mammograms at the same location with an average polar angle difference of 13 degrees compared to the current mammograms. In addition, the calcification features were able to classify the current BI-RADS assessment with an area under the receiver operating characteristic curve (AUC) of 0.74 using prior mammograms. In conclusion, the predictive power of calcification features in short-term risk prediction may arise from their ability to detect early suspicious signs.
KEYWORDS: Cancer, Breast, Breast cancer, Mammography, Cancer detection, Deep learning, Medical physics, Visualization, Risk assessment, Digital mammography
When developing Deep Learning models intended for clinical applications, understanding which part of the input contributed the most to the final decision is crucial. Our study brings interpretability to a Breast Cancer Risk (BCR) prediction by exploring whether the model relies on the laterality of the breast, where cancer ultimately develops, and how this reliance evolves over time. A dataset of 1210 Full-Field-Digital-Mammography exams with 0 to 7 Years To Cancer was used. MIRAI model was employed for BCR predictions. To determine which side of the breast contributed the most to the BCR prediction, the signal difference between left and right breasts was calculated for eight attribution-based interpretability techniques. AUC was calculated to investigate whether the BCR prediction is predominantly made from the breast, where the cancer ultimately develops. For 0 to 1 Years To Cancer, the model predominantly predicts BCR based on the side of the breast where the cancer is already present AUC=0.92 to 0.95. The top-performing attribution methods achieved an AUC of 0.70 for mammograms captured 1 to 3 Years To Cancer. For exams that were 3 to 5 Years To Cancer, a significant drop to AUC of 0.57 was observed. When moving to 5 to 7 Years To Cancer, focus on the breast with future cancer becomes random. All attribution methods showed that BCR predictions extending beyond three years from screen-detected cancer are most likely based on typical breast characteristics, such as density and other long-standing tissue patterns; however, for short-term BCR predictions, the model seems to detect early signs of tumor development.
Aim: This study proposes a method to bypass the requirement of large amounts of original training data to develop a 1- to 4-year breast cancer risk prediction model using transfer learning from a breast cancer detection model with digital mammography images as input. Methods: The study utilizes a labelled dataset of 423 low risk cases and 423 high risk cases, which is considered a small amount of data in terms of AI development, but from the viewpoint of a regional screening organization this represents a large number of high risk cases, given the rarity of such cases compared to the large number of low risk cases available. A breast cancer detection model was used to obtain a latent representation of features extracted from ‘FOR PRESENTATION’ screening mammography images from three systems from a single vendor (Siemens). Dimensionality reduction was performed on the latent space using an Autoencoder architecture. The reduced latent space was then mapped to 1- to 4-year breast cancer risk with a fully-connected model. Results: The resulting model achieved an AUC of 0.77 for differentiating high and low risk cases, outperforming the Tyrer-Cuzick model and achieving state-of-the-art performance. Conclusions: The use of transfer learning from breast cancer detection models can produce image-based breast cancer risk prediction models that are comparable to the state-of-the-art, while requiring only moderate amounts of data.
Purpose: Quantitative measures derived from positron emission tomography (PET) images are subject to statistical uncertainty, depending critically on system parameters, including the spatial resolution of the scanner. Predictions of statistical uncertainty of quantitative measures were compared with measurements.
Approach: Measurements were performed on the dual-ring PET prototype setup at the University of Michigan. The setup consisted of multiple detectors that, in combination, span a system resolution ranging between 1 and 5.5 mm full-width-at-half-maximum (FWHM). A Micro Jaszczak hot-spot phantom with rod diameters between 1.2 and 4.8 mm was imaged and independently reconstructed for different detector combinations. Statistical properties of quantitative measures were evaluated for different reconstructions.
Results: Measured signal-to-noise ratios (SNR) of 108 ± 14, 85 ± 11, and 40 ± 5 for high (0.92 to 0.98 mm FWHM), medium (1.3 to 1.5 mm FWHM), and low (5.5 mm FWHM) resolution detector configurations and 1 million events in general terms followed predications based on the detector resolution.
Conclusions: The unique tomograph configuration allowed for experimental comparison of the impact of spatial resolution on statistical properties of reconstructions in the same setup. An SNR advantage in systems with high resolutions was predicted and confirmed even for object features significantly larger than the detector resolution.
Aim: To develop and subsequently perform a systematic study on the impact of parameter settings on the biological reproducibility and sensitivity of extracted radiomic features from Full Field Digital Mammography (FFDM) images for the task of Breast Cancer Risk assessment. Methods: Cranio-caudal (CC) ”FOR PRESENTATION” images (88 in total, two centers: Slovenia and Belgium) were used for this study. Biological reproducibility of radiomic features was evaluated with two tests: reproducibility of extracted features between left and right breasts and by reproducibility of extracted features between the original and 4 perturbed images. The quantification was done using the intra-class correlation (ICC) coefficient between values of extracted radiomic features. To determine biological sensitivity, AUC between groups with low and high breast cancer risk was calculated. For the selection of optimal radiomic feature parameters, thresholds of 0.75 and 0.7 were defined for ICC and AUC, respectively. Results: Parameters bin Count and distances highly influenced biological reproducibility and sensitivity of specific radiomic features. Parameters weightingNorm and symmetricalGLCM had no effect. Overall, only 12/93 radiomic features passed the reproducibility and sensitivity tests in both centers. For five of these features, parameter ranges were crucial. Reproducibility varied greatly between the centers of Belgium and Slovenia. Conclusions: Rather than single radiomic parameters, parameter ranges were found to be a reasonable description for acceptable biological reproducibility and sensitivity. Overall, 12/93 radiomic features were found to be potential candidates for breast cancer risk prediction tasks, however further analysis is needed before definitive recommendations can be made.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.