Fractals in Neuroimaging.

Several natural phenomena can be described by studying their statistical scaling patterns, hence leading to simple geometrical interpretation. In this regard, fractal geometry is a powerful tool to describe the irregular or fragmented shape of natural features, using spatial or time-domain statistical scaling laws (power-law behavior) to characterize real-world physical systems. This chapter presents some works on the usefulness of fractal features, mainly the fractal dimension and the related Hurst exponent, in the characterization and identification of pathologies and radiological features in neuroimaging, mainly, magnetic resonance imaging.

Breaking Barriers: Exploring Neurotransmitters through In Vivo vs. In Vitro Rivalry.

Neurotransmitter analysis plays a pivotal role in diagnosing and managing neurodegenerative diseases, often characterized by disturbances in neurotransmitter systems. However, prevailing methods for quantifying neurotransmitters involve invasive procedures or require bulky imaging equipment, therefore restricting accessibility and posing potential risks to patients. The innovation of compact, in vivo instruments for neurotransmission analysis holds the potential to reshape disease management. This innovation can facilitate non-invasive and uninterrupted monitoring of neurotransmitter levels and their activity. Recent strides in microfabrication have led to the emergence of diminutive instruments that also find applicability in in vitro investigations. By harnessing the synergistic potential of microfluidics, micro-optics, and microelectronics, this nascent realm of research holds substantial promise. This review offers an overarching view of the current neurotransmitter sensing techniques, the advances towards in vitro microsensors tailored for monitoring neurotransmission, and the state-of-the-art fabrication techniques that can be used to fabricate those microsensors.

EMaGer: A Wearable Full-Circumference HD-EMG Sensor and Data Augmentation Method for Robust Hand Gesture Recognition.

This work presents EMaGer, a new 360° 64-channel high-density electromyography (HD-EMG) bracelet combined with an original data augmentation method for improved robustness in gesture recognition. By leveraging homogeneous electrode density and powerful deep learning techniques, the sensor is capable of rotation invariance around the arm axis, thus increasing gesture recognition robustness to electrode movement and inter-session evaluation. The system is made of a 4x16 electrode array covering the full circumference of the limb, and uses a sampling frequency of 1 kHz and a 16-bit resolution. The sensor's uniform and adjustable geometry paired with an array barrel shifting data augmentation (ABSDA) technique allows a convolutional neural network to maintain a 76.98% inter-session classification accuracy for a 6 gestures dataset, from a baseline intra-session accuracy of 93.75%. High inter-session classification accuracy decreases the training burden for users of EMG control systems such as myoelectric prostheses by minimizing calibration requirements. The same methods applied with different state-of-the-art sensors are demonstrated to be less effective. Thus, this work evidences the importance of co-designing the EMG sensor system with the gesture inference algorithms to leverage synergistic properties and solve state-of-the-art challenges.Clinical relevance- This paper establishes a method that alleviates clinical manipulations in setting up and calibrating myoelectric prosthetic devices.

Novel Wearable HD-EMG Sensor With Shift-Robust Gesture Recognition Using Deep Learning.

In this work, we present a hardware-software solution to improve the robustness of hand gesture recognition to confounding factors in myoelectric control. The solution includes a novel, full-circumference, flexible, 64-channel high-density electromyography (HD-EMG) sensor called EMaGer. The stretchable, wearable sensor adapts to different forearm sizes while maintaining uniform electrode density around the limb. Leveraging this uniformity, we propose novel array barrel-shifting data augmentation (ABSDA) approach used with a convolutional neural network (CNN), and an anti-aliased CNN (AA-CNN), that provides shift invariance around the limb for improved classification robustness to electrode movement, forearm orientation, and inter-session variability. Signals are sampled from a 4×16 HD-EMG array of electrodes at a frequency of 1 kHz and 16-bit resolution. Using data from 12 non-amputated participants, the approach is tested in response to sensor rotation, forearm rotation, and inter-session scenarios. The proposed ABSDA-CNN method improves inter-session accuracy by 25.67% on average across users for 6 gesture classes compared to conventional CNN classification. A comparison with other devices shows that this benefit is enabled by the unique design of the EMaGer array. The AA-CNN yields improvements of up to 63.05% accuracy over non-augmented methods when tested with electrode displacements ranging from -45 ° to +45 ° around the limb. Overall, this article demonstrates the benefits of co-designing sensor systems, processing methods, and inference algorithms to leverage synergistic and interdependent properties to solve state-of-the-art problems.

End-to-End Dialogue Generation Using a Single Encoder and a Decoder Cascade With a Multidimension Attention Mechanism.

Human dialogues often show underlying dependencies between turns, with each interlocutor influencing the queries/responses of the other. This article follows this by proposing a neural architecture for conversation modeling that looks at the dialogue history of both sides. It consists of a generative model where one encoder feeds three decoders to process three successive turns of dialogue for predicting the next utterance, with a multidimension attention mechanism aggregating the past and current contexts for a cascade effect on each decoder. As a result, a more comprehensive account of the dialogue evolution is obtained than by focusing on a single turn or the last encoder context, or on the user side alone. The response generation performance of the model is evaluated on three corpora of different sizes and topics, and a comparison is made with six recent generative neural architectures, using both automatic metrics and human judgments. Our results show that the proposed architecture equals or improves the state-of-the-art for adequacy and fluency, particularly when large open-domain corpora are used in the training. Moreover, it allows better tracking of the dialogue state evolution for response explainability.

Design of an Integrated Micro-Viscometer for Monitoring Engine Oil.

This paper proposes a novel integrated micro-viscometer for engine-oil monitoring. The final solution consists of a capacitive micromachined ultrasonic transducer (CMUT) and an application-specific integrated circuit (ASIC). The CMUT is used to generate and capture acoustic waves while immersed in engine oil. The low power transceiver ASIC is interfaced with the CMUT structure for actuation and reception. An integrated charge pump boosts the supply voltage from 3.3 to 22 V to generate the DC polarization voltage of the CMUT. The receiver has a power consumption of 72 µW with an input-referred noise current of 3.2pAHz and a bandwidth of 7 MHz. The CMUT array occupies an area of 3.5 × 1 mm, whereas the ASIC has a chip area of 1 × 1 mm. The system was tested using engine oils of different types and ages at different temperatures. Measurement results show a significant frequency shift due to the dynamic viscosity change that occurs as oil ages. A shift of -1.9 kHz/cP was measured, which corresponds to a shift of 33 Hz/mile. This work paves the way for high accuracy-integrated solutions for oil condition monitoring and is expected to play a significant role in a more economic and environmentally friendly usage of oil.

Towards an advanced neurotechnological system: colorimetric sensing with a novel grism-based spectrometer, functionalized gold nanoparticles and a heterogeneous embedded system.

Neurotransmitter sensing in the brain is crucial for the understanding of neuro-degenerative diseases. Most modern methods for the purpose rely on bulky instruments or are disruptive to the neurotransmitter medium. In this work, we describe and evaluate the design of a novel, compact and non-invasive instrument for neurotransmitter detection based on the colorimetric sensing method. The instrument includes a grism-based spectrometer that measures the wavelength shift of gold nanoparticles that are functionalized with aptamers to act as neurotransmitter-specific markers. It also includes microfluidic and electronic subsystems for sample preparation and control, and processing of the obtained signal. The instrument is tested with gold nanoparticles and its performance is compared to that of a commercial instrument, showing that the designed prototype matches the commercial instrument in performance while being much smaller, and it can surpass it with further improvements. This article is part of the theme issue 'Advanced neurotechnologies: translating innovation for health and well-being'.

Intuitive real-time control strategy for high-density myoelectric hand prosthesis using deep and transfer learning.

Myoelectric hand prostheses offer a way for upper-limb amputees to recover gesture and prehensile abilities to ease rehabilitation and daily life activities. However, studies with prosthesis users found that a lack of intuitiveness and ease-of-use in the human-machine control interface are among the main driving factors in the low user acceptance of these devices. This paper proposes a highly intuitive, responsive and reliable real-time myoelectric hand prosthesis control strategy with an emphasis on the demonstration and report of real-time evaluation metrics. The presented solution leverages surface high-density electromyography (HD-EMG) and a convolutional neural network (CNN) to adapt itself to each unique user and his/her specific voluntary muscle contraction patterns. Furthermore, a transfer learning approach is presented to drastically reduce the training time and allow for easy installation and calibration processes. The CNN-based gesture recognition system was evaluated in real-time with a group of 12 able-bodied users. A real-time test for 6 classes/grip modes resulted in mean and median positive predictive values (PPV) of 93.43% and 100%, respectively. Each gesture state is instantly accessible from any other state, with no mode switching required for increased responsiveness and natural seamless control. The system is able to output a correct prediction within less than 116 ms latency. 100% PPV has been attained in many trials and is realistically achievable consistently with user practice and/or employing a thresholded majority vote inference. Using transfer learning, these results are achievable after a sensor installation, data recording and network training/fine-tuning routine taking less than 10 min to complete, a reduction of 89.4% in the setup time of the traditional, non-transfer learning approach.

A Fully Embedded Adaptive Real-Time Hand Gesture Classifier Leveraging HD-sEMG and Deep Learning.

This paper presents a real-time fine gesture recognition system for multi-articulating hand prosthesis control, using an embedded convolutional neural network (CNN) to classify hand-muscle contractions sensed at the forearm. The sensor consists in a custom non-intrusive, compact, and easy-to-install 32-channel high-density surface electromyography (HDsEMG) electrode array, built on a flexible printed circuit board (PCB) to allow wrapping around the forearm. The sensor provides a low-noise digitization interface with wireless data transmission through an industrial, scientific and medical (ISM) radio link. An original frequency-time-space cross-domain preprocessing method is proposed to enhance gesture-specific data homogeneity and generate reliable muscle activation maps, leading to 98.15% accuracy when using a majority vote over 5 subsequent inferences by the proposed CNN. The obtained real-time gesture recognition, within 100 to 200 ms, and CNN properties show reliable and promising results to improve on the state-of-the-art of commercial hand prostheses. Moreover, edge computing using a specialized embedded artificial intelligence (AI) platform ensures reliable, secure and low latency real-time operation as well as quick and easy access to training, fine-tuning and calibration of the neural network. Co-design of the signal processing, AI algorithms and sensing hardware ensures a reliable and power-efficient embedded gesture recognition system.

Computer-Aided Diagnosis System of Alzheimer's Disease Based on Multimodal Fusion: Tissue Quantification Based on the Hybrid Fuzzy-Genetic-Possibilistic Model and Discriminative Classification Based on the SVDD Model.

: An improved computer-aided diagnosis (CAD) system is proposed for the early diagnosis of Alzheimer's disease (AD) based on the fusion of anatomical (magnetic resonance imaging (MRI)) and functional (8F-fluorodeoxyglucose positron emission tomography (FDG-PET)) multimodal images, and which helps to address the strong ambiguity or the uncertainty produced in brain images. The merit of this fusion is that it provides anatomical information for the accurate detection of pathological areas characterized in functional imaging by physiological abnormalities. First, quantification of brain tissue volumes is proposed based on a fusion scheme in three successive steps: modeling, fusion and decision. (1) Modeling which consists of three sub-steps: the initialization of the centroids of the tissue clusters by applying the Bias corrected Fuzzy C-Means (FCM) clustering algorithm. Then, the optimization of the initial partition is performed by running genetic algorithms. Finally, the creation of white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF) tissue maps by applying the Possibilistic FCM clustering algorithm. (2) Fusion using a possibilistic operator to merge the maps of the MRI and PET images highlighting redundancies and managing ambiguities. (3) Decision offering more representative anatomo-functional fusion images. Second, a support vector data description (SVDD) classifier is used that must reliably distinguish AD from normal aging and automatically detects outliers. The "divide and conquer" strategy is then used, which speeds up the SVDD process and reduces the load and cost of the calculating. The robustness of the tissue quantification process is proven against noise (20% level), partial volume effects and when inhomogeneities of spatial intensity are high. Thus, the superiority of the SVDD classifier over competing conventional systems is also demonstrated with the adoption of the 10-fold cross-validation approach for synthetic datasets (Alzheimer disease neuroimaging (ADNI) and Open Access Series of Imaging Studies (OASIS)) and real images. The percentage of classification in terms of accuracy (%), sensitivity (%), specificity (%) and area under ROC curve was 93.65%, 90.08%, 92.75% and 0.973; 91.46%, 92%, 91.78% and 0.967; 85.09%, 86.41%, 84.92% and 0.946 in the case of the ADNI, OASIS and real images respectively.

A Compact Visible Light Spectrometer for Molecular Detection with Spherical Gold Nanoparticles.

Spectrometers are widely used in molecular detection. However most of them are bulky, power consuming, and quite expensive. This work presents the prototype of a compact visible spectrometer alternative that is battery-operated, and designed for autonomous operation and quick spectrum detection. It targets spherical gold nanoparticles spectroscopy, but other applications are possible thanks to a high-precision mechanism to move the sensor, which allows the spectrometer to cover a broad range of wavelengths in the visible spectrum.

Microfluidic Spectrophotometer for Neurotransmitter Detection Based on Gold Nanoparticles: Preliminary Results.

A microfluidic-based spectrophotometer for neurotransmitters sensing is presented in this paper. In addition, a neurotransmitter photo-fingerprint is analyzed to evaluate the feasibility of selective neurotransmitter detection using optical techniques. The aim of this work is to detect major neurotransmitters (NTs) using a compact, portable and cost effective optical system for selective and real time NT concentration monitoring. Micro-spectroscopic detection of NTs is challenging because most of them are transparent to visible light. Nevertheless, they interfere with the absorption spectrum of gold nanoparticles (Au-NP), which exhibit maximum absorbance in the range of 520 nm. We observed an Au-NP maximum absorbance shift of up to 4nm in presence of NTs. Based on this shift, it is possible to detect NTs using visible ligh by using vertical-cavity surface-emitting laser (VCSEL) as light sources and an integrated system-on-chip (SoC) spectrophotometer.

A loop-based neural architecture for structured behavior encoding and decoding.

We present a new type of artificial neural network that generalizes on anatomical and dynamical aspects of the mammal brain. Its main novelty lies in its topological structure which is built as an array of interacting elementary motifs shaped like loops. These loops come in various types and can implement functions such as gating, inhibitory or executive control, or encoding of task elements to name a few. Each loop features two sets of neurons and a control region, linked together by non-recurrent projections. The two neural sets do the bulk of the loop's computations while the control unit specifies the timing and the conditions under which the computations implemented by the loop are to be performed. By functionally linking many such loops together, a neural network is obtained that may perform complex cognitive computations. To demonstrate the potential offered by such a system, we present two neural network simulations. The first illustrates the structure and dynamics of a single loop implementing a simple gating mechanism. The second simulation shows how connecting four loops in series can produce neural activity patterns that are sufficient to pass a simplified delayed-response task. We also show that this network reproduces electrophysiological measurements gathered in various regions of the brain of monkeys performing similar tasks. We also demonstrate connections between this type of neural network and recurrent or long short-term memory network models, and suggest ways to generalize them for future artificial intelligence research.

Miniaturized FDDA and CMOS Based Potentiostat for Bio-Applications.

A novel fully differential difference CMOS potentiostat suitable for neurotransmitter sensing is presented. The described architecture relies on a fully differential difference amplifier (FDDA) circuit to detect a wide range of reduction-oxidation currents, while exhibiting low-power consumption and low-noise operation. This is made possible thanks to the fully differential feature of the FDDA, which allows to increase the source voltage swing without the need for additional dedicated circuitry. The FDDA also reduces the number of amplifiers and passive elements in the potentiostat design, which lowers the overall power consumption and noise. The proposed potentiostat was fabricated in 0.18 µm CMOS, with 1.8 V supply voltage. The device achieved 5 µA sensitivity and 0.99 linearity. The input-referred noise was 6.9 µV rms and the flicker noise was negligible. The total power consumption was under 55 µW. The complete system was assembled on a 20 mm × 20 mm platform that includes the potentiostat chip, the electrode terminals and an instrumentation amplifier for redox current buffering, once converted to a voltage by a series resistor. the chip dimensions were 1 mm × 0.5 mm and the other PCB components were off-chip resistors, capacitors and amplifiers for data acquisition. The system was successfully tested with ferricyanide, a stable electroactive compound, and validated with dopamine, a popular neurotransmitter.

A wide range and high sensitivity four-channel compact electrochemical biosensor for neurotransmitter detection on a microfluidic platform.

We present a four-channel, high-sensitivity and linearity electrochemical biosensor for neurotransmitter (NT) detection and measurement. Using a multi-channel microfluidic platform makes this biosensor capable of detecting NT-related currents going from nanoamperes to milliamperes, with a sensitivity of the order of picoamperes. Moreover, by using a fully differential potentiostat architecture, the biosensor offers a high common-mode rejection ratio (90 dB), making it appropriate for low-noise and high-sensitive applications. The system was implemented on a 15 mm × 15 mm PCB with direct interface to the microfluidic chambers. It was calibrated with a 5 mM ferrocyanide solution and successfully tested with dopamine at three concentrations. The system shows a minimum sensistivity of 100 pA and consumes 60 mW.

Towards a multi-wavelength spectroscopy platform for blood characterization and analysis.

Passing multiple light wavelengths through a blood sample makes it possible to investigate the presence and composition of cells, metabolytes and analytes such as blood cells, glucose, lactate and oxygen, providing valuable indications for diagnostic and health monitoring. In this paper, we present a test prototype of a multi-wavelength blood spectroscopy platform integrated with a microfluidic substrate to collect and convey blood samples through a series of micro-LEDs and a photo-detector. This spectroscopy platform is a proof of concept for a system that can collect absorbance and transmittance parameters of blood samples at several wavelengths within the visible and NIR spectrum, and transmit them wirelessly to a base station for real-time calculation and analysis. In-vitro measurements are performed with the proposed prototype with 5 channels covering wavelength from 400 nm to 940 nm A full characterization results of the proposed device are presented.

Computational analyses of arteriovenous malformations in neuroimaging.

Computational models have been investigated for the analysis of the physiopathology and morphology of arteriovenous malformation (AVM) in recent years. Special emphasis has been given to image fusion in multimodal imaging and 3-dimensional rendering of the AVM, with the aim to improve the visualization of the lesion (for diagnostic purposes) and the selection of the nidus (for therapeutic aims, like the selection of the region of interest for the gamma knife radiosurgery plan). Searching for new diagnostic and prognostic neuroimaging biomarkers, fractal-based computational models have been proposed for describing and quantifying the angioarchitecture of the nidus. Computational modeling in the AVM field offers promising tools of analysis and requires a strict collaboration among neurosurgeons, neuroradiologists, clinicians, computer scientists, and engineers. We present here some updated state-of-the-art exemplary cases in the field, focusing on recent neuroimaging computational modeling with clinical relevance, which might offer useful clinical tools for the management of AVMs in the future.

Operant conditioning: a minimal components requirement in artificial spiking neurons designed for bio-inspired robot's controller.

In this paper, we investigate the operant conditioning (OC) learning process within a bio-inspired paradigm, using artificial spiking neural networks (ASNN) to act as robot brain controllers. In biological agents, OC results in behavioral changes learned from the consequences of previous actions, based on progressive prediction adjustment from rewarding or punishing signals. In a neurorobotics context, virtual and physical autonomous robots may benefit from a similar learning skill when facing unknown and unsupervised environments. In this work, we demonstrate that a simple invariant micro-circuit can sustain OC in multiple learning scenarios. The motivation for this new OC implementation model stems from the relatively complex alternatives that have been described in the computational literature and recent advances in neurobiology. Our elementary kernel includes only a few crucial neurons, synaptic links and originally from the integration of habituation and spike-timing dependent plasticity as learning rules. Using several tasks of incremental complexity, our results show that a minimal neural component set is sufficient to realize many OC procedures. Hence, with the proposed OC module, designing learning tasks with an ASNN and a bio-inspired robot context leads to simpler neural architectures for achieving complex behaviors.

Automated detection of circinate exudates in retina digital images using empirical mode decomposition and the entropy and uniformity of the intrinsic mode functions.

This work presents a new automated system to detect circinate exudates in retina digital images. It operates as follows: the true color image is converted to gray levels, and contrast-limited adaptive histogram equalization (CLAHE) is applied to it before undergoing empirical mode decomposition (EMD) as intrinsic mode functions (IMFs). The entropies and uniformities of the first two IMFs are then computed to form a feature vector that is fed to a support vector machine (SVM) for classification. The experimental results using a set of 45 images (23 normal images and 22 images with circinate exudates taken from the STARE database) and tenfold cross-validation indicate that the proposed approach outperforms previous works found in the literature, with perfect classification. In addition, the image processing time was <4 min, making the presented circinate exudate detection system fit for use in a clinical environment.

New approach for automatic classification of Alzheimer's disease, mild cognitive impairment and healthy brain magnetic resonance images.

Explored is the utility of modelling brain magnetic resonance images as a fractal object for the classification of healthy brain images against those with Alzheimer's disease (AD) or mild cognitive impairment (MCI). More precisely, fractal multi-scale analysis is used to build feature vectors from the derived Hurst's exponents. These are then classified by support vector machines (SVMs). Three experiments were conducted: in the first the SVM was trained to classify AD against healthy images. In the second experiment, the SVM was trained to classify AD against MCI and, in the third experiment, a multiclass SVM was trained to classify all three types of images. The experimental results, using the 10-fold cross-validation technique, indicate that the SVM achieved 97.08% ± 0.05 correct classification rate, 98.09% ± 0.04 sensitivity and 96.07% ± 0.07 specificity for the classification of healthy against MCI images, thus outperforming recent works found in the literature. For the classification of MCI against AD, the SVM achieved 97.5% ± 0.04 correct classification rate, 100% sensitivity and 94.93% ± 0.08 specificity. The third experiment also showed that the multiclass SVM provided highly accurate classification results. The processing time for a given image was 25 s. These findings suggest that this approach is efficient and may be promising for clinical applications.