PURPOSE: To generate and assess an algorithm combining eye tracking and speech recognition to extract brain lesion location labels automatically for deep learning (DL). MATERIALS AND METHODS: In this retrospective study, 700 two-dimensional brain tumor MRI scans from the Brain Tumor Segmentation database were clinically interpreted. For each image, a single radiologist dictated a standard phrase describing the lesion into a microphone, simulating clinical interpretation. Eye-tracking data were recorded simultaneously. Using speech recognition, gaze points corresponding to each lesion were obtained. Lesion locations were used to train a keypoint detection convolutional neural network to find new lesions. A network was trained to localize lesions for an independent test set of 85 images. The statistical measure to evaluate our method was percent accuracy. RESULTS: Eye tracking with speech recognition was 92% accurate in labeling lesion locations from the training dataset, thereby demonstrating that fully simulated interpretation can yield reliable tumor location labels. These labels became those that were used to train the DL network. The detection network trained on these labels predicted lesion location of a separate testing set with 85% accuracy. CONCLUSION: The DL network was able to locate brain tumors on the basis of training data that were labeled automatically from simulated clinical image interpretation.© RSNA, 2020.

Ewing sarcoma (ES) involves a tumor-specific chromosomal translocation that produces the EWS-FLI1 protein, which is required for the growth of ES cells both in vitro and in vivo. However, an EWS-FLI1-driven transgenic mouse model is not currently available. Here, we present data from six independent laboratories seeking an alternative approach to express EWS-FLI1 in different murine tissues. We used the Runx2, Col1a2.3, Col1a3.6, Prx1, CAG, Nse, NEFL, Dermo1, P0, Sox9 and Osterix promoters to target EWS-FLI1 or Cre expression. Additional approaches included the induction of an endogenous chromosomal translocation, in utero knock-in, and the injection of Cre-expressing adenovirus to induce EWS-FLI1 expression locally in multiple lineages. Most models resulted in embryonic lethality or developmental defects. EWS-FLI1-induced apoptosis, promoter leakiness, the lack of potential cofactors, and the difficulty of expressing EWS-FLI1 in specific sites were considered the primary reasons for the failed attempts to create a transgenic mouse model of ES.