Dragan Ahmetovic

Marco Colussi, Gabriele Civitarese, Dragan Ahmetovic et al.

Joint bleeding is a common condition for people with hemophilia and, if untreated, can result in hemophilic arthropathy. Ultrasound imaging has recently emerged as an effective tool to diagnose joint recess distension caused by joint bleeding. However, no computer-aided diagnosis tool exists to support the practitioner in the diagnosis process. This paper addresses the problem of automatically detecting the recess and assessing whether it is distended in knee ultrasound images collected in patients with hemophilia. After framing the problem, we propose two different approaches: the first one adopts a one-stage object detection algorithm, while the second one is a multi-task approach with a classification and a detection branch. The experimental evaluation, conducted with $483$ annotated images, shows that the solution based on object detection alone has a balanced accuracy score of $0.74$ with a mean IoU value of $0.66$, while the multi-task approach has a higher balanced accuracy value ($0.78$) at the cost of a slightly lower mean IoU value.

Dragan Ahmetovic, Matteo Manzoni, Filippo Corti et al.

Interacting with video games is challenging for people with upper-limb impairments, especially when multiple hand-based inputs are required in rapid succession. Human cooperation, where another person assists the player, has been proposed as a solution, but it is limited by copilot availability and co-location. An alternative is partial automation, where the player is assisted by a software agent. We present a study with 13 participants with upper-limb impairments, investigating how they collaborate with a copilot in both human cooperation and partial automation. The experiment is supported by GamePals, a configurable framework we developed to enable both human cooperation and partial automation in existing third-party video games.

Dragan Ahmetovic, Matteo Manzoni, Filippo Corti et al.

Shared control is a form of video gaming accessibility support that allows players with disabilities to delegate inaccessible controls to another person. Through interviews involving 14 individuals with lived experience of accessible gaming in shared control, we explore the ways in which shared control technologies are adopted in practice, the accessibility challenges they address, and how the support currently provided in shared control can be automated to remove the need for a human assistant. Findings indicate that shared control is essential for enabling access to otherwise inaccessible games, but its reliance on human support is a key limitation. Participants welcomed the idea of automating the support with software agents, while also identifying limitations and design requirements. Accordingly, this work contributes insights into current practices and proposes guidelines for developing automated support systems.

Marco Colussi, Dragan Ahmetovic, Sergio Mascetti

This paper presents MIAS-SAM, a novel approach for the segmentation of anomalous regions in medical images. MIAS-SAM uses a patch-based memory bank to store relevant image features, which are extracted from normal data using the SAM encoder. At inference time, the embedding patches extracted from the SAM encoder are compared with those in the memory bank to obtain the anomaly map. Finally, MIAS-SAM computes the center of gravity of the anomaly map to prompt the SAM decoder, obtaining an accurate segmentation from the previously extracted features. Differently from prior works, MIAS-SAM does not require to define a threshold value to obtain the segmentation from the anomaly map. Experimental results conducted on three publicly available datasets, each with a different imaging modality (Brain MRI, Liver CT, and Retina OCT) show accurate anomaly segmentation capabilities measured using DICE score. The code is available at: https://github.com/warpcut/MIAS-SAM

Sergio Mascetti, Mattia Ducci, Niccoló Cantù et al.

This contribution investigates how cross-platform development frameworks (CPDF) support the creation of mobile applications that are accessible to people with visual impairments through screen readers. We first systematically analyze screen-reader APIs available in native iOS and Android, and we examine whether and at what level the same functionalities are available in two popular CPDF: Xamarin and React Native. This analysis unveils that there are many functionalities shared between native iOS and Android APIs, but most of them are not available in React Native or Xamarin. In particular, not even all basic APIs are exposed by the examined CPDF. Accessing the unavailable APIs is still possible, but it requires an additional effort by the developers who need to know native APIs and to write platform specific code, hence partially negating the advantages of CPDF. To address this problem, we consider a representative set of native APIs that cannot be directly accessed from React Native and Xamarin and show sample implementations for accessing them.

Sergio Mascetti, Lorenzo Picinali, Andrea Gerino et al.

In the last years several solutions were proposed to support people with visual impairments or blindness during road crossing. These solutions focus on computer vision techniques for recognizing pedestrian crosswalks and computing their relative position from the user. Instead, this contribution addresses a different problem; the design of an auditory interface that can effectively guide the user during road crossing. Two original auditory guiding modes based on data sonification are presented and compared with a guiding mode based on speech messages. Experimental evaluation shows that there is no guiding mode that is best suited for all test subjects. The average time to align and cross is not significantly different among the three guiding modes, and test subjects distribute their preferences for the best guiding mode almost uniformly among the three solutions. From the experiments it also emerges that higher effort is necessary for decoding the sonified instructions if compared to the speech instructions, and that test subjects require frequent `hints' (in the form of speech messages). Despite this, more than 2/3 of test subjects prefer one of the two guiding modes based on sonification. There are two main reasons for this: firstly, with speech messages it is harder to hear the sound of the environment, and secondly sonified messages convey information about the "quantity" of the expected movement.