Daniel Sanchez-Morillo

arXiv2025

Smart Device Development for Gait Monitoring: Multimodal Feedback in an Interactive Foot Orthosis, Walking Aid, and Mobile Application

Smart assistive technologies such as sensor-based footwear and walking aids offer promising opportunities for gait rehabilitation through real-time feedback and patient-centered monitoring. While biofeedback applications show great potential, current research rarely explores integrated closed-loop systems with device- and modality-specific feedback. In this work, we present a modular sensor-based system combining a smart foot orthosis and an instrumented forearm crutch to deliver real-time vibrotactile biofeedback. The system integrates plantar pressure and motion sensing, vibrotactile feedback, and wireless communication via a smartphone application. We conducted a user study with eight participants to validate the system's feasibility for mobile gait detection and app usability, and to evaluate different vibrotactile feedback types across the orthosis and forearm crutch. The results indicate that pattern-based vibrotactile feedback was rated as more useful and suitable for regular use than simple vibration alerts. Moreover, participants reported clear perceptual differences between feedback delivered via the orthosis and the forearm crutch, indicating device-dependent feedback perception. The findings highlight the relevance of feedback strategy design beyond hardware implementation and inform the development of user-centered haptic biofeedback systems.

cs.HC↗

arXiv2023

Deep learning-based instance segmentation for the precise automated quantification of digital breast cancer immunohistochemistry images

The quantification of biomarkers on immunohistochemistry breast cancer images is essential for defining appropriate therapy for breast cancer patients, as well as for extracting relevant information on disease prognosis. This is an arduous and time-consuming task that may introduce a bias in the results due to intra- and inter-observer variability which could be alleviated by making use of automatic quantification tools. However, this is not a simple processing task given the heterogeneity of breast tumors that results in non-uniformly distributed tumor cells exhibiting different staining colors and intensity, size, shape, and texture, of the nucleus, cytoplasm and membrane. In this research work, we demonstrate the feasibility of using a deep learning-based instance segmentation architecture for the automatic quantification of both nuclear and membrane biomarkers applied to IHC-stained slides. We have solved the cumbersome task of training set generation with the design and implementation of a web platform, which has served as a hub for communication and feedback between researchers and pathologists as well as a system for the validation of the automatic image processing models. Through this tool, we have collected annotations over samples of HE, ER and Ki-67 (nuclear biomarkers) and HER2 (membrane biomarker) IHC-stained images. Using the same deep learning network architecture, we have trained two models, so-called nuclei- and membrane-aware segmentation models, which, once successfully validated, have revealed to be a promising method to segment nuclei instances in IHC-stained images. The quantification method proposed in this work has been integrated into the developed web platform and is currently being used as a decision-support tool by pathologists.

eess.IV↗