Item 2 — Summary of study design, methods, results, and conclusions

The abstract should present a succinct structured summary of the study’s design, methods, results, and conclusions. Include relevant details about the study population, such as data source and use of publicly available datasets, number of patients or examinations, number of studies per data source, modalities and relevant series or sequences. Provide information about data partitions and level of data splitting (e.g., patient-or image-level). Clearly state if the study is prospective or retrospective and summarize the statistical analysis that was performed. The reader should clearly understand the primary outcomes and implication of the study’s findings, including relevant clinical impact. Indicate whether the software, data, and/or resulting model are publicly available (including where to find more details, if applicable).

Explanation and Elaboration: A comprehensive abstract that includes all recommended elements facilitates efficient literature searches, enables systematic reviews, and supports evidence-based decision-making. The clear reporting of performance metrics and statistical measures helps readers evaluate the study’s significance, while information about resource availability promotes reproducibility and collaborative advancement in the field.

Examples
Results: A total of 26 722 cases (median patient age, 59.0 years [IQR, 54.0-63.0 years]) with mammograms acquired using machines from two vendors were included. Cases included 332 screen-detected, 174 interval, and 254 next-round cancers. Two of three stand-alone DL algorithms achieved noninferior sensitivity (DL-1: 64.8%, P < .001; DL-2: 56.7%, P = .03; DL-3: 58.9%, P < .001) compared with the single first reader (62.8%), and specificity was noninferior for DL-1 (92.8%; P < .001) and DL-2 (96.8%; P < .001) and superior for DL-3 (97.9%; P < .001) compared with the single first reader (96.5%). Combining the DL algorithms with human readers achieved noninferior sensitivity (67.0%, 65.6%, and 65.4% for DL-1, DL-2, and DL-3, respectively; P < .001 for all) compared with double reading (67.4%), and superior specificity (97.4%, 97.6%, and 97.6%; P < .001 for all) compared with double reading (97.1%). [Abstract (6), CC-BY 4.0]
Materials and Methods: In this retrospective study, 26 569 images were collected in 9234 women who underwent digital mammography to pretrain the algorithms. The training data included individuals who had at least 1 year of clinical and imaging history followed by biopsy-based histopathologic diagnosis from March 2013 to November 2018. A model that combined convolutional neural networks with supervised learning algorithms was independently trained to make breast lesion predictions with data from 2120 women in Israel and 1642 women in the United States. Results were reported using the area under the receiver operating characteristic curve (AUC) with the 95% DeLong approach to estimate CIs. Significance was tested with bootstrapping. [Abstract (8), CC-BY 4.0]
Purpose: To train and to validate a deep learning (DL)-based model to produce DSA-like cerebral angiograms directly from dynamic angiograms and then quantitatively and visually evaluate these angiograms for clinical usefulness. [Abstract (9), CC-BY 4.0]