Introduction: The purpose of the study was to survey orientation and mobility (O&M) instructors who are blind concerning the identification of accommodations, teaching techniques, and resources to teach students with visual impairments (i.e., blindness or low vision). Methods: The study utilized an online survey via Qualtrics (2019) with 27 closed- and open-ended items to identify accommodations, teaching techniques, and resources needed. The survey was e-mailed to membership and certification organizations requesting O&M instructors who are blind to participate for 12 weeks. The participants were 15 O&M specialists, mostly male and Caucasian. Survey data were then analyzed using descriptive statistics. Results: Forty percentage of the participants reported that there were minimal standards that they had to demonstrate prior to their admittance into an O&M program. About one-fourth of the participants mentioned their program was modified because of their visual impairment. Eleven participants (73%) reported that their nonvisual instructional strategies and techniques were predominantly gained through their university programs or other visually impaired instructors (27%, n = 4). Discussion: Aspects of this study that are similar to the current literature are smaller faculty-to-student ratios for blindfold or simulation cane courses, accommodations used by participants, and suggestions for monitoring the safety of students. The results revealed the participants’ strong belief in the importance of immersion training, the use of the Structured Discovery Cane Travel (SDCT), nonvisual skills during O&M instruction, sleep shades, and students’ problem-solving abilities. Implication for practitioners: Although the participants had received SDCT immersion training, most personnel preparation programs approved by the Association for the Education and Rehabilitation of Blind and Visually Impaired do not use this method. For this reason, it is important for faculty to identify best teaching practices from among all programs and to integrate these practices into their curricula. Sharing best practices could strengthen all programs. Moreover, students with visual impairments should be taught early about self-advocacy and the ability to have helpful knowledge about one’s skills at a university and in the workplace.

Automated segmentation and volumetry of brain magnetic resonance imaging (MRI) scans are essential for the diagnosis of Parkinson’s disease (PD) and Parkinson’s plus syndromes (P-plus). To enhance the diagnostic performance, we adopt deep learning (DL) models in brain MRI segmentation and compared their performance with the gold-standard non-DL method. We collected brain MRI scans of healthy controls ($$n=105$$ n = 105 ) and patients with PD ($$n=105$$ n = 105 ), multiple systemic atrophy ($$n=132$$ n = 132 ), and progressive supranuclear palsy ($$n=69$$ n = 69 ) at Samsung Medical Center from January 2017 to December 2020. Using the gold-standard non-DL model, FreeSurfer (FS), we segmented six brain structures: midbrain, pons, caudate, putamen, pallidum, and third ventricle, and considered them as annotated data for DL models, the representative convolutional neural network (CNN) and vision transformer (ViT)-based models. Dice scores and the area under the curve (AUC) for differentiating normal, PD, and P-plus cases were calculated to determine the measure to which FS performance can be reproduced as-is while increasing speed by the DL approaches. The segmentation times of CNN and ViT for the six brain structures per patient were 51.26 ± 2.50 and 1101.82 ± 22.31 s, respectively, being 14 to 300 times faster than FS (15,735 ± 1.07 s). Dice scores of both DL models were sufficiently high (> 0.85) so their AUCs for disease classification were not inferior to that of FS. For classification of normal vs. P-plus and PD vs. P-plus (except multiple systemic atrophy - Parkinsonian type) based on all brain parts, the DL models and FS showed AUCs above 0.8, demonstrating the clinical value of DL models in addition to FS. DL significantly reduces the analysis time without compromising the performance of brain segmentation and differential diagnosis. Our findings may contribute to the adoption of DL brain MRI segmentation in clinical settings and advance brain research.

Background: Automated segmentation and volumetry of brain magnetic resonance imaging (MRI) scans are essential for the diagnosis of Parkinson's disease (PD) and Parkinson's plus syndromes (P-plus).Objective: To enhance the diagnostic performance, we adopt deep learning (DL) models in brain segmentation and compared their performance with the gold-standard non-DL method.Methods: We collected brain MRI scans of healthy controls (n = 105) and patients with PD (n = 105), multiple systemic atrophy (n = 132), and progressive supranuclear palsy (n = 69) at Samsung Medical Center from January 2017 to December 2020. Using the gold-standard non-DL model, FreeSurfer (FS), we segmented six brain structures: midbrain, pons, caudate, putamen, pallidum, and third ventricle, and considered them as annotating data for DL models, the representative V-Net and UNETR. The Dice scores and area under the curve (AUC) for differentiating normal, PD, and P-plus cases were calculated.Results: The segmentation times of V-Net and UNETR for the six brain structures per patient were 3.48 ± 0.17 and 48.14 ± 0.97 s, respectively, being at least 300 times faster than FS (15,735 ± 1.07 s). Dice scores of both DL models were sufficiently high (>0.85), and their AUCs for disease classification were superior to that of FS. For classification of normal vs. P-plus and PD vs. multiple systemic atrophy (cerebellar type), the DL models and FS showed AUCs above 0.8.Conclusions: DL significantly reduces the analysis time without compromising the performance of brain segmentation and differential diagnosis. Our findings may contribute to the adoption of DL brain MRI segmentation in clinical settings and advance brain research.

No abstract