Insights from an autism imaging biomarker challenge: Promises and threats to biomarker discovery.

MRI has been extensively used to identify anatomical and functional differences in Autism Spectrum Disorder (ASD). Yet, many of these findings have proven difficult to replicate because studies rely on small cohorts and are built on many complex, undisclosed, analytic choices. We conducted an international challenge to predict ASD diagnosis from MRI data, where we provided preprocessed anatomical and functional MRI data from > 2,000 individuals. Evaluation of the predictions was rigorously blinded. 146 challengers submitted prediction algorithms, which were evaluated at the end of the challenge using unseen data and an additional acquisition site. On the best algorithms, we studied the importance of MRI modalities, brain regions, and sample size. We found evidence that MRI could predict ASD diagnosis: the 10 best algorithms reliably predicted diagnosis with AUC∼0.80 - far superior to what can be currently obtained using genotyping data in cohorts 20-times larger. We observed that functional MRI was more important for prediction than anatomical MRI, and that increasing sample size steadily increased prediction accuracy, providing an efficient strategy to improve biomarkers. We also observed that despite a strong incentive to generalise to unseen data, model development on a given dataset faces the risk of overfitting: performing well in cross-validation on the data at hand, but not generalising. Finally, we were able to predict ASD diagnosis on an external sample added after the end of the challenge (EU-AIMS), although with a lower prediction accuracy (AUC=0.72). This indicates that despite being based on a large multisite cohort, our challenge still produced biomarkers fragile in the face of dataset shifts.

Neuroanatomy-based matrix-guided trimming protocol for the rat brain.

Brain trimming through defined neuroanatomical landmarks is recommended to obtain consistent sections in rat toxicity studies. In this article, we describe a matrix-guided trimming protocol that uses channels to reproduce coronal levels of anatomical landmarks. Both setup phase and validation study were performed on Han Wistar male rats (Crl:WI(Han)), 10-week-old, with bodyweight of 298 ± 29 (SD) g, using a matrix (ASI-Instruments(®), Houston, TX) fitted for brains of rats with 200 to 400 g bodyweight. In the setup phase, we identified eight channels, that is, 6, 8, 10, 12, 14, 16, 19, and 21, matching the recommended landmarks midway to the optic chiasm, frontal pole, optic chiasm, infundibulum, mamillary bodies, midbrain, middle cerebellum, and posterior cerebellum, respectively. In the validation study, we trimmed the immersion-fixed brains of 60 rats using the selected channels to determine how consistently the channels reproduced anatomical landmarks. Percentage of success (i.e., presence of expected targets for each level) ranged from 89 to 100%. Where 100% success was not achieved, it was noted that the shift in brain trimming was toward the caudal pole. In conclusion, we developed and validated a trimming protocol for the rat brain that allow comparable extensiveness, homology, and relevance of coronal sections as the landmark-guided trimming with the advantage of being quickly learned by technicians.

RaVÆn: unsupervised change detection of extreme events using ML on-board satellites.

Applications such as disaster management enormously benefit from rapid availability of satellite observations. Traditionally, data analysis is performed on the ground after being transferred-downlinked-to a ground station. Constraints on the downlink capabilities, both in terms of data volume and timing, therefore heavily affect the response delay of any downstream application. In this paper, we introduce RaVÆn, a lightweight, unsupervised approach for change detection in satellite data based on Variational Auto-Encoders (VAEs), with the specific purpose of on-board deployment. RaVÆn pre-processes the sampled data directly on the satellite and flags changed areas to prioritise for downlink, shortening the response time. We verified the efficacy of our system on a dataset-which we release alongside this publication-composed of time series containing a catastrophic event, demonstrating that RaVÆn outperforms pixel-wise baselines. Finally, we tested our approach on resource-limited hardware for assessing computational and memory limitations, simulating deployment on real hardware.