A Novel Ear Impression-Taking Method Using Structured Light Imaging and Machine Learning: A Pilot Proof of Concept Study with Patients' Feedback on Prototype.

INTRODUCTION: Taking an ear impression is a minimally invasive procedure. A review of existing literature suggests that contactless methods of scanning the ear have not been developed. We proposed to establish a correlation between external ear features with the ear canal and with this proof of concept to develop a prototype and an algorithm for capturing and predicting ear canal information. METHODS: We developed a novel prototype using structured light imaging to capture external images of the ear. Using a large database of existing ear impression images obtained by traditional methods, correlation analyses were carried out and established. A deep neural network was devised to build a predictive algorithm. Patients undergoing hearing aid evaluation undertook both methods of ear impression-taking. We evaluated their subjective feedback and determined if there was a close enough objective match between the images obtained from the impression techniques. RESULTS: A prototype was developed and deployed for trial, and most participants were comfortable with this novel method of ear impression-taking. Partial matching of the ear canal could be obtained from the images taken, and the predictive algorithm applied for a few sample images was within good standard of error with proof of concept established. DISCUSSION: Further studies are warranted to strengthen the predictive capabilities of the algorithm and determine optimal prototype imaging positions so that sufficient ear canal information can be obtained for three-dimensional printing. Ear impression-taking may then have the potential to be automated, with the possibility of same-day three-dimensional printing of the earmold to provide timely access.

Classification, registration and segmentation of ear canal impressions using convolutional neural networks.

Today, fitting bespoke hearing aids involves injecting silicone into patients' ears to produce ear canal molds. These are subsequently 3D scanned to create digital ear canal impressions. However, before digital impressions can be used they require a substantial amount of effort in manual 3D editing. In this article, we present computational methods to pre-process ear canal impressions. The aim is to create automation tools to assist the hearing aid design, manufacturing and fitting processes as well as normalizing anatomical data to assist the study of the outer ear canal's morphology. The methods include classifying the handedness of the impression into left and right ear types, orienting the geometries onto the same coordinate system sense, and removing extraneous artifacts introduced by the silicone mold. We investigate the use of convolutional neural networks for performing these semantic tasks and evaluate their accuracy using a dataset of 3000 ear canal impressions. The neural networks proved highly effective at performing these tasks with 95.8% adjusted accuracy in classification, 92.3% within 20° angular error in registration and 93.4% intersection over union in segmentation.

Lexicon for classifying ear-canal shapes.

The ear canal is usually described as an S-shaped funnel. In attempting to classify ear-canal shapes obtained from point clouds digitized from molds of 300 ears, the problem of designing criteria for distinguishing and organizing the canal shapes arose. In this work, we extracted features inspired by the S-shape characteristic (critical point, maximum, minimum, twist, writhe, translation, rotation) and, through them, introduced 14 types of ear-canal shapes. This classification allowed comparison of ears within a type and of ears between different types. It expanded our range of descriptors of canal shapes and unlocked perspectives for applications.

Martian biolith: A bioinspired regolith composite for closed-loop extraterrestrial manufacturing.

Given plans to revisit the lunar surface by the late 2020s and to take a crewed mission to Mars by the late 2030s, critical technologies must mature. In missions of extended duration, in situ resource utilization is necessary to both maximize scientific returns and minimize costs. While this present a significantly more complex challenge in the resource-starved environment of Mars, it is similar to the increasing need to develop resource-efficient and zero-waste ecosystems on Earth. Here, we make use of recent advances in the field of bioinspired chitinous manufacturing to develop a manufacturing technology to be used within the context of a minimal, artificial ecosystem that supports humans in a Martian environment.

Circular manufacturing of chitinous bio-composites via bioconversion of urban refuse.

Bioinspired manufacturing, in the sense of replicating the way nature fabricates, may hold great potential for supporting a socioeconomic transformation towards a sustainable society. Use of unmodified ubiquitous biological components suggests for a fundamentally sustainable manufacturing paradigm where materials are produced, transformed into products and degraded in closed regional systems with limited requirements for transport. However, adoption is currently limited by the fact that despite their ubiquitous nature, these biopolymers are predominantly harvested as industrial and agricultural products. In this study, we overcome this limitation by developing a link between bioinspired manufacturing and urban waste bioconversion. This result is paramount for the development of circular economic models, effectively connecting the organic by-products of civilization to locally decentralized, general-purpose manufacturing.

Large-scale additive manufacturing with bioinspired cellulosic materials.

Cellulose is the most abundant and broadly distributed organic compound and industrial by-product on Earth. However, despite decades of extensive research, the bottom-up use of cellulose to fabricate 3D objects is still plagued with problems that restrict its practical applications: derivatives with vast polluting effects, use in combination with plastics, lack of scalability and high production cost. Here we demonstrate the general use of cellulose to manufacture large 3D objects. Our approach diverges from the common association of cellulose with green plants and it is inspired by the wall of the fungus-like oomycetes, which is reproduced introducing small amounts of chitin between cellulose fibers. The resulting fungal-like adhesive material(s) (FLAM) are strong, lightweight and inexpensive, and can be molded or processed using woodworking techniques. We believe this first large-scale additive manufacture with ubiquitous biological polymers will be the catalyst for the transition to environmentally benign and circular manufacturing models.