Early detection and diagnosis is a must in secondary prevention of melanoma and other cancerous lesions of the skin. In this work, we present an online, reservoir-based, non-parametric estimation and classification model that allows for this functionality on pigmented lesions, such that detection thresholding can be tuned to maximize accuracy and/or minimize overall false negative rates. This system has been tested in a dataset consisting of 116 patients and a total of 124 hyperspectral images of nevi, raised nevi and melanomas, detecting up to 100% of the suspicious lesions at the expense of some false positives.
Prototyping hyperspectral imaging devices in current biomedical optics research requires taking into consideration various issues regarding optics, imaging, and instrumentation. In summary, an ideal imaging system should only be limited by exposure time, but there will be technological limitations (e.g., actuator delay and backlash, network delays, or embedded CPU speed) that should be considered, modeled, and optimized. This can be achieved by constructing a multiparametric model for the imaging system in question. The article describes a rotating-mirror scanning hyperspectral imaging device, its multiparametric model, as well as design and calibration protocols used to achieve its optimal performance. The main objective of the manuscript is to describe the device and review this imaging modality, while showcasing technical caveats, models and benchmarks, in an attempt to simplify and standardize specifications, as well as to incentivize prototyping similar future designs.
17 April 2025 in Sensors and Actuators B: Chemical
The following work presents how autoencoding all the possible hidden activations of a network for a given problem can provide insight about its structure, behavior, and vulnerabilities. The method, termed self-introspection, can show that a trained model showcases similar activation patterns (albeit randomly distributed due to initialization) when shown data belonging to the same category, and classification errors occur in fringe areas where the activations are not as clearly defined, suggesting some form of random, slowly varying, implicit encoding occurring within deep networks, that can be observed with this representation. Additionally, obtaining a low-dimensional representation of all the activations allows for (1) real-time model evaluation in the context of a multiclass classification problem, (2) the rearrangement of all hidden layers by their relevance in obtaining a specific output, and (3) the obtainment of a framework where studying possible counter-measures to noise and adversarial attacks is possible. Self-introspection can show how damaged input data can modify the hidden activations, producing an erroneous response. A few illustrative are implemented for feedforward and convolutional models and the MNIST and CIFAR-10 datasets, showcasing its capabilities as a model evaluation framework.