THE DIGITAL DATABASE FOR SCREENING MAMMOGRAPHY

By Michael D. Heath, Kevin W. Bowyer, D. Kopans, Richard H. Moore. 2007

1,306 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/ff2218b349f89026ffaaccdf807228fa497c04bd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Dacheng Tao
2. Bolei Zhou
3. Yoshua Bengio
4. Quoc V. Le
5. Mohit Bansal
6. Chunhua Shen
7. Luc Van Gool
8. Yi Yang

Citations in the corpus

• AUC Maximization in the Era of Big Data and AI: A Survey (2022, methodology): “For this task, they use the DDSM+ data, which is a combination of two datasets namely DDSM and CBIS-DDSM [17, 67].”
• A Review of Deep-Learning-Based Medical Image Segmentation Methods (2021, methodology): “Digital database for screening mammography (DDSM): DDSM [108] is a resource used by the mammography image analysis research community and is widely used by researchers.”
• Deep Convolutional Neural Networks for breast cancer screening (2018, background): “DDSM [26] the Digital Database of Screening Mammography (DDSM) is publicly available and contains more than 2600 cases, sorted according to the degree of severity of the findings.”
• Controllable Medical Image Generation via Generative Adversarial Networks (2021, methodology): “We conduct our experiment on Digital Database for Screening Mammography (DDSM) [19] dataset which consists of 2,620 cases of normal, benign, and malignant cases.”
• U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications (2020, methodology): “Sample images from the DDSM dataset [283], [284].”
• Deep learning in generating radiology reports: A survey (2020, unknown): “Kisilev et al. [40] selected a subset of the DDSM database that consisted of 974 images annotated with semantic descriptors to test their multi-task-loss CNN based model.”
• Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification (2016, methodology): “We validate the proposed model on the most frequently used mammographic mass classification dataset, INbreast dataset [16], as the mammograms in other datasets, such as DDSM dataset [5] and mini-MIAS dataset [19], are of low quality.”
• Deep Learning and Structured Prediction for the Segmentation of Mass in Mammograms (2015, methodology): “1 shows the Dice index and average training (for the whole training set) and testing times (per image) of our approach with all potential functions (CNN+DBN3x3 + DBN5x5 + GMM + Prior + Pairwise) using the CRF and SSVM models on DDSM-BCRP and INbreast test sets.”
• Detecting and classifying lesions in mammograms with Deep Learning (2017, methodology): “The DDSM dataset contains 2620 digitized film-screen screening mammography exams, with pixel-level ground truth annotation of lesions.”
• Learning to Compose Domain-Specific Transformations for Data Augmentation (2017, methodology): “Mammography Tumor-Classification Dataset To demonstrate the effectiveness of our approach on real-world applications, we also considered the task of classifying benign versus malignant tumors from images in the Digital Database for Screening Mammography (DDSM) dataset [15, 4, 26], which is a class-b”
• Data Augmentation with Manifold Exploring Geometric Transformations for Increased Performance and Robustness (2019, methodology): “Therefore, models that achieve higher robustness will be characterized by a larger geodesic distance Random Affine Transformations for Dermofit [16] and DDSM [14] for a specific range of Geodesic Distances G . between classes.”
• DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification (2018, background): “One exception we noticed is their experiment on the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM) [21, 22, 23], a medical image classification task whose data is expensive to collect besides labeling.”