- Browse by Author
Browsing by Author "Hillis, Argye E."
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Automatic comprehensive radiological reports for clinical acute stroke MRIs(Springer Nature, 2023-07-10) Liu, Chin-Fu; Zhao, Yi; Yedavalli, Vivek; Leigh, Richard; Falcao, Vito; STIR and VISTA Imaging investigators; Miller, Michael I.; Hillis, Argye E.; Faria, Andreia V.; Biostatistics and Health Data Science, School of MedicineBackground: Although artificial intelligence systems that diagnosis among different conditions from medical images are long term aims, specific goals for automation of human-labor, time-consuming tasks are not only feasible but equally important. Acute conditions that require quantitative metrics, such as acute ischemic strokes, can greatly benefit by the consistency, objectiveness, and accessibility of automated radiological reports. Methods: We used 1,878 annotated brain MRIs to generate a fully automated system that outputs radiological reports in addition to the infarct volume, 3D digital infarct mask, and the feature vector of anatomical regions affected by the acute infarct. This system is associated to a deep-learning algorithm for segmentation of the ischemic core and to parcellation schemes defining arterial territories and classically-identified anatomical brain structures. Results: Here we show that the performance of our system to generate radiological reports was comparable to that of an expert evaluator. The weight of the components of the feature vectors that supported the prediction of the reports, as well as the prediction probabilities are outputted, making the pre-trained models behind our system interpretable. The system is publicly available, runs in real time, in local computers, with minimal computational requirements, and it is readily useful for non-expert users. It supports large-scale processing of new and legacy data, enabling clinical and translational research. Conclusion: The generation of reports indicates that our fully automated system is able to extract quantitative, objective, structured, and personalized information from stroke MRIs.Item Brain volumes as predictors of tDCS effects in primary progressive aphasia(Elsevier, 2020-01) de Aguiar, Vânia; Zhao, Yi; Faria, Andreia; Ficek, Bronte; Webster, Kimberly T.; Wendt, Haley; Wang, Zeyi; Hillis, Argye E.; Onyike, Chiadi U.; Frangakis, Constantine; Caffo, Brian; Tsapkini, Kyrana; Biostatistics, School of Public HealthThe current study aims to determine the brain areas critical for response to anodal transcranial direct current stimulation (tDCS) in PPA. Anodal tDCS and sham were administered over the left inferior frontal gyrus (IFG), combined with written naming/spelling therapy. Thirty people with PPA were included in this study, and assessed immediately, 2 weeks, and 2 months post-therapy. We identified anatomical areas whose volumes significantly predicted the additional tDCS effects. For trained words, the volumes of the left Angular Gyrus and left Posterior Cingulate Cortex predicted the additional tDCS gain. For untrained words, the volumes of the left Middle Frontal Gyrus, left Supramarginal Gyrus, and right Posterior Cingulate Cortex predicted the additional tDCS gain. These findings show that areas involved in language, attention and working memory contribute to the maintenance and generalization of stimulation effects. The findings highlight that tDCS possibly affects areas anatomically or functionally connected to stimulation targets.Item Sex differences in effects of tDCS and language treatments on brain functional connectivity in primary progressive aphasia(Elsevier, 2023) Licata, Abigail E.; Zhao, Yi; Herrmann, Olivia; Hillis, Argye E.; Desmond, John; Onyike, Chiadi; Tsapkini, Kyrana; Biostatistics, School of Public HealthPrimary Progressive Aphasia (PPA) is a neurodegenerative disorder primarily affecting language functions. Neuromodulatory techniques (e.g., transcranial direct current stimulation, active-tDCS) and behavioral (speech-language) therapy have shown promising results in treating speech and language deficits in PPA patients. One mechanism of active-tDCS efficacy is through modulation of network functional connectivity (FC). It remains unknown how biological sex influences FC and active-tDCS or language treatment(s). In the current study, we compared sex differences, induced by active-tDCS and language therapy alone, in the default mode and language networks, acquired during resting-state fMRI in 36 PPA patients. Using a novel statistical method, the covariate-assisted-principal-regression (CAPs) technique, we found sex and age differences in FC changes following active-tDCS. In the default mode network (DMN): (1) men (in both conditions) showed greater FC in DMN than women. (2) men who received active-tDCS showed greater FC in the DMN than men who received language-treatment only. In the language network: (1) women who received active-tDCS showed significantly greater FC across the language network than women who received sham-tDCS. As age increases, regardless of sex and treatment condition, FC in language regions decreases. The current findings suggest active-tDCS treatment in PPA alters network-specific FC in a sex-dependent manner.