Automatic Segmentation of Monofilament Testing Sites in Plantar Images for Diabetic Foot Management.

Diabetic peripheral neuropathy is a major complication of diabetes mellitus, and it is the leading cause of foot ulceration and amputations. The Semmes-Weinstein monofilament examination (SWME) is a widely used, low-cost, evidence-based tool for predicting the prognosis of diabetic foot patients. The examination can be quick, but due to the high prevalence of the disease, many healthcare professionals can be assigned to this task several days per month. In an ongoing project, it is our objective to minimize the intervention of humans in the SWME by using an automated testing system relying on computer vision. In this paper we present the project's first part, constituting a system for automatically identifying the SWME testing sites from digital images. For this, we have created a database of plantar images and developed a segmentation system, based on image processing and deep learning-both of which are novelties. From the 9 testing sites, the system was able to correctly identify most 8 in more than 80% of the images, and 3 of the testing sites were correctly identified in more than 97.8% of the images.

Autonomous wheelchair for patient's transportation on healthcare institutions.

The transport of patients from the inpatient service to the operating room is a recurrent task in a hospital routine. This task is repetitive, non-ergonomic, time consuming, and requires the labor of patient transporters. In this paper is presented a system, named Connected Driverless Wheelchair, that can receive transportation requests directly from the hospital information management system, pick up patients at their beds, navigate autonomously through different floors, avoid obstacles, communicate with elevators, and drop patients off at the designated operating room. As a result, a prototype capable of transporting patients autonomously in hospital environments was obtained. Although it was impossible to test the final developed system at the hospital as planned, due to the COVID-19 pandemic, the extensive tests conducted at the robotics laboratory facilities, and our previous experience in integrating mobile robots in hospitals, allowed to conclude that it is perfectly prepared for this integration to be carried out. The achieved results are relevant since this is a system that may be applied to support these types of tasks in the future, making the transport of patients more efficient (both from a cost and time perspective), without unpredictable delays and, in some cases, safer.

PDMS Microlenses for Focusing Light in Narrow Band Imaging Diagnostics.

Minimally invasive medical devices can greatly benefit from Narrow Band Imaging (NBI) diagnostic capabilities, as different wavelengths allow penetration of distinct layers of the gastrointestinal tract mucosa, improving diagnostic accuracy and targeting different pathologies. An important performance parameter is the light intensity at a given power consumption of the medical device. A method to increase the illumination intensity in the NBI diagnostic technique was developed and applied to minimally invasive medical devices (e.g., endoscopic capsules), without increasing the size and power consumption of such instruments. Endoscopic capsules are generally equipped with light-emitting diodes (LEDs) operating in the RGB (red, green, and blue) visible light spectrum. A polydimethylsiloxane (PDMS) µ-lens was designed for a maximum light intensity at the target area of interest when placed on top of the LEDs. The PDMS µ-lens was fabricated using a low-cost hanging droplet method. Experiments reveal an increased illumination intensity by a factor of 1.21 for both the blue and green LEDs and 1.18 for the red LED. These promising results can increase the resolution of NBI in endoscopic capsules, which can contribute to early gastric lesions diagnosis.

High-selectivity neural probe based on a Fabry-Perot optical filter and a CMOS silicon photodiodes array at visible wavelengths.

This paper presents a silicon neural probe with a high-selectivity optical readout function and light emitting diodes for neurons photostimulation and fluorophore excitation. A high-selectivity Fabry-Perot optical filter on the top of a CMOS silicon photodiodes array can read the emitted fluorescence, which indicates the neurons physiological state. The design, fabrication, and characterization of the optical filter are presented. The SiO2 / TiO2 based optical filter thin films were deposited by RF sputtering. The performance of the optical filter deposited on the top of the silicon photodiodes array, implemented in the neural probe, was tested through in-vitro fluorescence measurements. The transmittance peak of the fabricated optical filter is 81.8% at 561 nm, with a full width at half maximum of 28 nm. The peak responsivity of the CMOS silicon photodiode with the optical filter deposited on its top is 273.6 mA / W at 578 nm. The in-vitro fluorescence measurements results show a CMOS photodiode current proportional to the fluorophore concentration with a good linearity (R2 = 0.9361). The results validate the use of the neural probe with the high-selectivity optical readout function to determine the presence of different fluorophore concentrations. The development of the device in a conventional CMOS process allows on-chip electronics readout.