Artificial intelligence (AI) is showing promise in improving clinical diagnosis. In breast cancer screening, several recent studies show that AI has the potential to improve radiologists' accuracy, subsequently helping in early cancer diagnosis and reducing unnecessary workup. As the number of proposed models and their complexity grows, it is becoming increasingly difficult to re-implement them in order to reproduce the results and to compare different approaches. To enable reproducibility of research in this application area and to enable comparison between different methods, we release a meta-repository containing deep learning models for classification of screening mammograms. This meta-repository creates a framework that enables the evaluation of machine learning models on any private or public screening mammography data set. At its inception, our meta-repository contains five state-of-the-art models with open-source implementations and cross-platform compatibility. We compare their performance on five international data sets: two private New York University breast cancer screening data sets as well as three public (DDSM, INbreast and Chinese Mammography Database) data sets. Our framework has a flexible design that can be generalized to other medical image analysis tasks. The meta-repository is available at https://www.github.com/nyukat/mammography_metarepository.

ImportanceAn accurate and robust artificial intelligence (AI) algorithm for detecting cancer in digital breast tomosynthesis (DBT) could significantly improve detection accuracy and reduce health care costs worldwide.ObjectivesTo make training and evaluation data for the development of AI algorithms for DBT analysis available, to develop well-defined benchmarks, and to create publicly available code for existing methods.Design, Setting, and ParticipantsThis diagnostic study is based on a multi-institutional international grand challenge in which research teams developed algorithms to detect lesions in DBT. A data set of 22 032 reconstructed DBT volumes was made available to research teams. Phase 1, in which teams were provided 700 scans from the training set, 120 from the validation set, and 180 from the test set, took place from December 2020 to January 2021, and phase 2, in which teams were given the full data set, took place from May to July 2021.Main Outcomes and MeasuresThe overall performance was evaluated by mean sensitivity for biopsied lesions using only DBT volumes with biopsied lesions; ties were broken by including all DBT volumes.ResultsA total of 8 teams participated in the challenge. The team with the highest mean sensitivity for biopsied lesions was the NYU B-Team, with 0.957 (95% CI, 0.924-0.984), and the second-place team, ZeDuS, had a mean sensitivity of 0.926 (95% CI, 0.881-0.964). When the results were aggregated, the mean sensitivity for all submitted algorithms was 0.879; for only those who participated in phase 2, it was 0.926.Conclusions and RelevanceIn this diagnostic study, an international competition produced algorithms with high sensitivity for using AI to detect lesions on DBT images. A standardized performance benchmark for the detection task using publicly available clinical imaging data was released, with detailed descriptions and analyses of submitted algorithms accompanied by a public release of their predictions and code for selected methods. These resources will serve as a foundation for future research on computer-assisted diagnosis methods for DBT, significantly lowering the barrier of entry for new researchers.

This paper investigates various Transformer architectures on the WikiReading Information Extraction and Machine Reading Comprehension dataset. The proposed dual-source model outperforms the current state-of-theart by a large margin.Next, we introduce WikiReading Recycled-a newly developed public dataset, and the task of multipleproperty extraction. It uses the same data as WikiReading but does not inherit its predecessor's identified disadvantages. In addition, we provide a human-annotated test set with diagnostic subsets for a detailed analysis of model performance.

No abstract