Effects of an AAC feature on decoding and encoding skills of adults with Down syndrome.

Literacy skills can assist in the navigation and enjoyment of adult life. For individuals who have reached adulthood without strong literacy skills, opportunities for continued literacy learning are few. Redesigning AAC technologies to support literacy skill development could extend literacy learning opportunities for adults with developmental disabilities who have limited speech. The current preliminary study evaluated an AAC technology feature designed to support literacy development. The study used a multiple probe across participants design. Three adults with Down syndrome who had limited speech and only basic decoding skills participated. Results suggest the participants made modest gains in decoding accuracy after interacting using the AAC app with the literacy supportive feature, though performance was highly variable. Results also offer emerging evidence that, for two participants, some generalization to encoding performance may have also been achieved. Results showed that, for all the participants, interacting using the literacy supportive feature increased their reading confidence. Altogether, the study's results show preliminary evidence that the feature can support adults with Down syndrome in their ongoing literacy learning, though access to formal instruction is still critical. Future research is needed to continue to explore this and other AAC technology redesigns to increase learning opportunities for the people who use the technology every day to communicate.

Core vocabulary lists for young children and considerations for early language development: a narrative review.

For early symbolic communicators, acquisition of an initial vocabulary is a critically important achievement that sets the stage for future language development. Children who require augmentative and alternative communication (AAC) rely on others to select and provide these important first words for them. One resource to help guide this process includes published lists of words that may contribute to a core vocabulary for individuals who require AAC. Although some clinicians report that they consider or prioritize core words during the vocabulary selection process, it is not known whether an emphasis on core words will best meet the expressive vocabulary needs of early symbolic communicators. The purposes of this narrative review were to (a) review studies that have developed word lists to inform selection of a core vocabulary for young children who require AAC, (b) compare the words on these lists to the early words used by children with typical development, and (c) consider the implications for vocabulary selection and language development for early symbolic communicators who require AAC. Results suggest that core word lists may under-emphasize many of the types of words that predominate in early expressive vocabulary; these lists may not be the most appropriate resources to guide AAC system design and instruction for early symbolic communicators.

Effect of an application with video visual scene displays on communication during play: pilot study of a child with autism spectrum disorder and a peer.

Children with autism spectrum disorder (ASD) and limited speech are at risk for exclusion from pretend play with their peers due in part to communication difficulties. The purpose of this pilot study was to examine the effect of an intervention package, consisting of tablet-based augmentative and alternative communication technology with video visual scene displays (video VSDs) and instruction, on communication between a child with ASD and a peer with typical development across three play activities. One dyad, consisting of the child with ASD and the peer, participated in this study. A multiple probe design across three play activities was used to evaluate the effect of the intervention on the number of symbolic communicative turns taken by the participant with ASD. At baseline, this participant demonstrated minimal symbolic communication related to play activities. Following the intervention, he demonstrated an increase in symbolic communicative turns across all three play activities, with a large overall effect size. The results of this study provide preliminary support for use of a video VSD intervention to support communication for children with ASD and limited speech during pretend play with their peers.

The Effect of Naturalistic Developmental Behavioral Interventions and Aided AAC on the Language Development of Children on the Autism Spectrum with Minimal Speech: A Systematic Review and Meta-analysis.

Both naturalistic developmental behavioral interventions (NDBIs) and augmentative and alternative communication (AAC) have been shown to support the language development of children with a diagnosis of autism spectrum disorder and minimal speech. However, little research has addressed the impact of incorporating AAC systems within NDBIs. This systematic review was conducted to assess the relative impact of NDBI procedures with and without AAC on the language development of children on the autism spectrum with minimal speech. Relevant studies were located through systematic database searching, targeted review of relevant journals, and ancestral search of references from identified and associated papers. Relevant study characteristics were coded for all included studies, as well as determining certainty of evidence and calculating effect sizes for language variables. All procedures followed the systematic review guidelines set by the Cochrane Collaboration. A total of 29 relevant studies were included within this review, covering both single-case and group design research. Three studies were identified that directly compared NDBI and AAC interventions. NDBIs had a strong impact on language across study types (i.e., with and without AAC), though both aggregate and comparative effect sizes were notably larger when AAC was included within NDBI procedures, as compared to NDBIs without AAC. Results suggest that combining AAC with NDBI procedures may lead to better language outcomes than NDBIs alone for children on the autism spectrum with minimal speech.

"You Just Want to Be Able to Communicate With Your Child": Parents' Perspectives on Communication and AAC Use for Beginning Communicators on the Autism Spectrum.

PURPOSE: For young children on the autism spectrum who are beginning communicators, augmentative and alternative communication (AAC) can support language development and participation in meaningful interactions. AAC is more likely to be effective when services align with the needs and priorities of the child's family. To better understand family perspectives, this study investigated the communication and AAC experiences of parents of young beginning communicators on the autism spectrum. METHOD: The study used a phenomenological qualitative design. Eight caregivers of seven children on the autism spectrum participated in semistructured interviews, and thematic analysis was used to identify themes within the data. RESULTS: Five main themes and 15 subthemes emerged from the data. Parents situated communication and AAC experiences within the context of complex, busy lives. They discussed the value of communication and benefits of AAC, but described numerous challenges related to obtaining, learning, and implementing AAC that evolved over time as needs and skills changed. Parents discussed their children's individuality and the need for AAC systems and services to fit the unique needs of their child and their family. They also emphasized ways in which communication outcomes were affected by factors external to the child and the family, including factors related to professional services and the U.S. health care and educational systems. CONCLUSIONS: The results affirm the need to consider the family and the broader social system when providing AAC services to young children on the autism spectrum. Provision of family-centered services is critical to successful AAC. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.24881562.

Accurate single-molecule spot detection for image-based spatial transcriptomics with weakly supervised deep learning.

Image-based spatial transcriptomics methods enable transcriptome-scale gene expression measurements with spatial information but require complex, manually tuned analysis pipelines. We present Polaris, an analysis pipeline for image-based spatial transcriptomics that combines deep-learning models for cell segmentation and spot detection with a probabilistic gene decoder to quantify single-cell gene expression accurately. Polaris offers a unifying, turnkey solution for analyzing spatial transcriptomics data from multiplexed error-robust FISH (MERFISH), sequential fluorescence in situ hybridization (seqFISH), or in situ RNA sequencing (ISS) experiments. Polaris is available through the DeepCell software library (https://github.com/vanvalenlab/deepcell-spots) and https://www.deepcell.org.

Accurate single-molecule spot detection for image-based spatial transcriptomics with weakly supervised deep learning.

Image-based spatial transcriptomics methods enable transcriptome-scale gene expression measurements with spatial information but require complex, manually-tuned analysis pipelines. We present Polaris, an analysis pipeline for image-based spatial transcriptomics that combines deep learning models for cell segmentation and spot detection with a probabilistic gene decoder to quantify single-cell gene expression accurately. Polaris offers a unifying, turnkey solution for analyzing spatial transcriptomics data from MERFSIH, seqFISH, or ISS experiments. Polaris is available through the DeepCell software library (https://github.com/vanvalenlab/deepcell-spots) and https://www.deepcell.org.

A Foundation Model for Cell Segmentation.

Cells are a fundamental unit of biological organization, and identifying them in imaging data - cell segmentation - is a critical task for various cellular imaging experiments. While deep learning methods have led to substantial progress on this problem, most models in use are specialist models that work well for specific domains. Methods that have learned the general notion of "what is a cell" and can identify them across different domains of cellular imaging data have proven elusive. In this work, we present CellSAM, a foundation model for cell segmentation that generalizes across diverse cellular imaging data. CellSAM builds on top of the Segment Anything Model (SAM) by developing a prompt engineering approach for mask generation. We train an object detector, CellFinder, to automatically detect cells and prompt SAM to generate segmentations. We show that this approach allows a single model to achieve human-level performance for segmenting images of mammalian cells (in tissues and cell culture), yeast, and bacteria collected across various imaging modalities. We show that CellSAM has strong zero-shot performance and can be improved with a few examples via few-shot learning. We also show that CellSAM can unify bioimaging analysis workflows such as spatial transcriptomics and cell tracking. A deployed version of CellSAM is available at https://cellsam.deepcell.org/.

Implementing directives that involve prepositions with children with autism: a comparison of spoken cues with two types of augmented input.

Some children with autism face considerable challenges with comprehension, including difficulties following spoken directives involving prepositional relations. The use of augmented input through visual modalities might be an effective means for supplementing spoken language. The purpose of this preliminary study was to compare spoken input with two augmented input modalities (i.e., speech + visual cues) in terms of children's ability to follow directives involving prepositions. The augmented input modalities consisted of static scene cues (i.e., photographic or pictorial visual scenes that portray relevant concepts and their relationships) and dynamic scene cues (i.e., full-motion video clips that depict the actions underlying relevant concepts and their relationships). A within-subjects design involving nine children with autism or pervasive developmental disorders-not otherwise specified was used to examine the effectiveness of the three input conditions. Results indicated that both static scene cues and dynamic scene cues were more effective than spoken cues, but there were no differences between static scene cues and dynamic scene cues. Results are discussed in terms of appropriate instructional inputs for children with autism. Limitations are noted and directions for future research are posited.

Effects of an Augmentative and Alternative Communication Technology Decoding Feature on Single-Word Reading by Individuals With Down Syndrome and Limited Functional Speech.

PURPOSE: Literacy skills are foundational to participation in adolescent and adult life, and decoding skills (i.e., sounding out to read words) are critical to literacy learning. Literacy also increases communication options for individuals with developmental disabilities who use augmentative and alternative communication (AAC). Yet, current AAC technologies are limited in their support of literacy development (especially decoding skills) for the individuals with developmental disabilities who require them. The purpose of this study was to conduct a preliminary evaluation of a new AAC feature designed to support decoding skills. METHOD: Three individuals who had limited functional speech and limited literacy skills, specifically two adolescents and one young adult with Down syndrome, participated in the study. The study used a single-subject, multiple-probe, across-participants design. RESULTS: All three participants demonstrated increases in reading performance, including decoding of novel words. High variability in performance was observed, however, and no participant reached reading mastery. Still, analysis reveals that for all participants, interacting using the new app feature increased reading. CONCLUSIONS: These results offer preliminary evidence that an AAC technology feature that provides models of decoding (upon selection of AAC picture symbols) can support individuals with Down syndrome in building decoding skills. While not intended to replace instruction, this initial study offers initial evidence in its efficacy as a supplemental avenue for supporting literacy in individuals with developmental disabilities who use AAC.

Effect of Video Augmentative and Alternative Communication Technology on Communication During Play With Peers for Children With Autism Spectrum Disorder.

PURPOSE: Children with autism spectrum disorder (ASD) are at risk for exclusion from play with their peers due to difficulty with communication skills. Video augmentative and alternative communication (AAC) technology has the potential to support communication within the context of play using videos with integrated visual scene displays. This study investigated the effect of a video AAC intervention on the number of turns in which children with ASD demonstrated symbolic communication during interactions with a peer without disabilities. Maintenance of skills, generalization to untrained play scenarios, and stakeholder perceptions of the video AAC technology were also investigated. METHOD: This study used a single-case, multiple-probe design across participant dyads. It included baseline, intervention, maintenance, and generalization phases. Six children with ASD and six peers participated in the study. RESULTS AND CONCLUSIONS: All six participants with ASD demonstrated an increase in the number of turns in which they demonstrated at least one symbolic communication act following intervention, although one participant demonstrated variability in baseline performance, making it difficult to draw conclusions. Results provide preliminary evidence that instruction with video AAC technology can support communication for children with ASD during play interactions with peers.

Applying technology to visually support language and communication in individuals with autism spectrum disorders.

The burgeoning role of technology in society has provided opportunities for the development of new means of communication for individuals with Autism Spectrum Disorders (ASD). This paper offers an organizational framework for describing traditional and emerging augmentative and alternative communication (AAC) technology, and highlights how tools within this framework can support a visual approach to everyday communication and improve language instruction. The growing adoption of handheld media devices along with applications acquired via a consumer-oriented delivery model suggests a potential paradigm shift in AAC for people with ASD.