Utilizing connectome fingerprinting functional MRI models for motor activity prediction in presurgical planning: A feasibility study.

Presurgical planning prior to brain tumor resection is critical for the preservation of neurologic function post-operatively. Neurosurgeons increasingly use advanced brain mapping techniques pre- and intra-operatively to delineate brain regions which are "eloquent" and should be spared during resection. Functional MRI (fMRI) has emerged as a commonly used non-invasive modality for individual patient mapping of critical cortical regions such as motor, language, and visual cortices. To map motor function, patients are scanned using fMRI while they perform various motor tasks to identify brain networks critical for motor performance, but it may be difficult for some patients to perform tasks in the scanner due to pre-existing deficits. Connectome fingerprinting (CF) is a machine-learning approach that learns associations between resting-state functional networks of a brain region and the activations in the region for specific tasks; once a CF model is constructed, individualized predictions of task activation can be generated from resting-state data. Here we utilized CF to train models on high-quality data from 208 subjects in the Human Connectome Project (HCP) and used this to predict task activations in our cohort of healthy control subjects (n = 15) and presurgical patients (n = 16) using resting-state fMRI (rs-fMRI) data. The prediction quality was validated with task fMRI data in the healthy controls and patients. We found that the task predictions for motor areas are on par with actual task activations in most healthy subjects (model accuracy around 90%-100% of task stability) and some patients suggesting the CF models can be reliably substituted where task data is either not possible to collect or hard for subjects to perform. We were also able to make robust predictions in cases in which there were no task-related activations elicited. The findings demonstrate the utility of the CF approach for predicting activations in out-of-sample subjects, across sites and scanners, and in patient populations. This work supports the feasibility of the application of CF models to presurgical planning, while also revealing challenges to be addressed in future developments. PRACTITIONER POINTS: Precision motor network prediction using connectome fingerprinting. Carefully trained models' performance limited by stability of task-fMRI data. Successful cross-scanner predictions and motor network mapping in patients with tumor.

DynAMoS: The Dynamic Affective Movie Clip Database for Subjectivity Analysis.

In this paper, we describe the design, collection, and validation of a new video database that includes holistic and dynamic emotion ratings from 83 participants watching 22 affective movie clips. In contrast to previous work in Affective Computing, which pursued a single "ground truth" label for the affective content of each moment of each video (e.g., by averaging the ratings of 2 to 7 trained participants), we embrace the subjectivity inherent to emotional experiences and provide the full distribution of all participants' ratings (with an average of 76.7 raters per video). We argue that this choice represents a paradigm shift with the potential to unlock new research directions, generate new hypotheses, and inspire novel methods in the Affective Computing community. We also describe several interdisciplinary use cases for the database: to provide dynamic norms for emotion elicitation studies (e.g., in psychology, medicine, and neuroscience), to train and test affective content analysis algorithms (e.g., for dynamic emotion recognition, video summarization, and movie recommendation), and to study subjectivity in emotional reactions (e.g., to identify moments of emotional ambiguity or ambivalence within movies, identify predictors of subjectivity, and develop personalized affective content analysis algorithms). The database is made freely available to researchers for noncommercial use at https://dynamos.mgb.org.