Reliable Noninvasive Glucose Sensing via CNN-Based Spectroscopy

• URL: http://arxiv.org/abs/2506.13819v1
• Date: Sun, 15 Jun 2025 03:01:15 GMT
• Title: Reliable Noninvasive Glucose Sensing via CNN-Based Spectroscopy
• Authors: El Arbi Belfarsi, Henry Flores, Maria Valero,
• Abstract summary: We present a dual-modal AI framework based on short-wave infrared (SWIR) spectroscopy.<n>The first modality employs a multi-wavelength SWIR imaging system coupled with convolutional neural networks (CNNs) to capture spatial features linked to glucose absorption.<n>The second modality uses a compact photodiode voltage sensor and machine learning regressors (e.g., random forest) on normalized optical signals.
• Score: 0.36868085124383626
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this study, we present a dual-modal AI framework based on short-wave infrared (SWIR) spectroscopy. The first modality employs a multi-wavelength SWIR imaging system coupled with convolutional neural networks (CNNs) to capture spatial features linked to glucose absorption. The second modality uses a compact photodiode voltage sensor and machine learning regressors (e.g., random forest) on normalized optical signals. Both approaches were evaluated on synthetic blood phantoms and skin-mimicking materials across physiological glucose levels (70 to 200 mg/dL). The CNN achieved a mean absolute percentage error (MAPE) of 4.82% at 650 nm with 100% Zone A coverage in the Clarke Error Grid, while the photodiode system reached 86.4% Zone A accuracy. This framework constitutes a state-of-the-art solution that balances clinical accuracy, cost efficiency, and wearable integration, paving the way for reliable continuous non-invasive glucose monitoring.

Related papers

• Synthetic-to-Real Transfer Learning for Chromatin-Sensitive PWS Microscopy [0.0]
  We present CFU Net, a hierarchical segmentation architecture trained with a three stage curriculum on synthetic CFU data.<n>Our approach uses physics based rendering that incorporates empirically supported packing statistics, Mie scattering models, and modality specific noise, combined with a curriculum that progresses from adversarial pretraining to spectroscopic fine tuning and histology validation.
  arXiv  Detail & Related papers  (2025-10-25T10:00:34Z)
• DeepAf: One-Shot Spatiospectral Auto-Focus Model for Digital Pathology [37.648157065553185]
  We introduce a novel automated microscopic system powered by DeepAf.<n>DeepAf combines spatial and spectral features through a hybrid architecture for single-shot focus prediction.<n>System achieves 0.90 AUC in cancer classification at 4x magnification, a significant achievement at lower magnification than typical 20x WSI scans.
  arXiv  Detail & Related papers  (2025-10-06T19:28:08Z)
• Detecting immune cells with label-free two-photon autofluorescence and deep learning [2.096497520824982]
  We trained a convolutional neural network (CNN) to classify cell types based on this label-free AF as input.<n>A low-complexity squeezeNet architecture was able to achieve reliable immune cell classification results.<n>In the future, such predictive DL models could directly detect specific immune cells in unstained images.
  arXiv  Detail & Related papers  (2025-06-17T12:14:02Z)
• Automated Measurement of Optic Nerve Sheath Diameter Using Ocular Ultrasound Video [14.016658180958444]
  This paper presents a novel method to automatically identify the optimal frame from video sequences for ONSD measurement.<n>The proposed method achieved a mean error, mean squared deviation, and intraclass correlation coefficient (ICC) of 0.04, 0.054, and 0.782, respectively.
  arXiv  Detail & Related papers  (2025-06-03T12:14:51Z)
• Attention on the Wires (AttWire): A Foundation Model for Detecting Devices and Catheters in X-ray Fluoroscopic Images [0.4064887614767072]
  A novel attention mechanism was designed to guide a convolution neural network (CNN) model to the areas of wires in X-ray images.<n>A lightweight foundation model can be created to detect multiple objects simultaneously with higher precision and real-time speed.
  arXiv  Detail & Related papers  (2025-03-08T12:20:22Z)
• Mamba-based Deep Learning Approaches for Sleep Staging on a Wireless Multimodal Wearable System without Electroencephalography [3.7428541180163126]
  We investigate Mamba-based deep learning approaches for sleep staging on signals from the ANNE One system.<n>We trained Mamba-based models with convolutional-recurrent neural network (CRNN) and the recurrent neural network (RNN) architectures.<n>Deep learning models can infer major sleep stages from the ANNE One and can be successfully applied to data from adults attending a tertiary care sleep clinic.
  arXiv  Detail & Related papers  (2024-12-20T14:43:02Z)
• Domain-specific augmentations with resolution agnostic self-attention mechanism improves choroid segmentation in optical coherence tomography images [3.8485899972356337]
  The choroid is a key vascular layer of the eye, supplying oxygen to the retinal photoreceptors. Current methods to measure the choroid often require use of multiple, independent semi-automatic and deep learning-based algorithms. We propose a Robust, Resolution-agnostic and Efficient Attention-based network for CHoroid segmentation (REACH)
  arXiv  Detail & Related papers  (2024-05-23T11:35:23Z)
• Interpretable cancer cell detection with phonon microscopy using multi-task conditional neural networks for inter-batch calibration [39.759100498329275]
  We present a conditional neural network framework to simultaneously achieve inter-batch calibration. We validate our approach by training and validating on different experimental batches. We extend our model to reconstruct denoised signals, enabling physical interpretation of salient features indicating disease state.
  arXiv  Detail & Related papers  (2024-03-26T12:20:10Z)
• Classification robustness to common optical aberrations [64.08840063305313]
  This paper proposes OpticsBench, a benchmark for investigating robustness to realistic, practically relevant optical blur effects. Experiments on ImageNet show that for a variety of different pre-trained DNNs, the performance varies strongly compared to disk-shaped kernels. We show on ImageNet-100 with OpticsAugment that can be increased by using optical kernels as data augmentation.
  arXiv  Detail & Related papers  (2023-08-29T08:36:00Z)
• DopUS-Net: Quality-Aware Robotic Ultrasound Imaging based on Doppler Signal [48.97719097435527]
  DopUS-Net combines the Doppler images with B-mode images to increase the segmentation accuracy and robustness of small blood vessels. An artery re-identification module qualitatively evaluate the real-time segmentation results and automatically optimize the probe pose for enhanced Doppler images.
  arXiv  Detail & Related papers  (2023-05-15T18:19:29Z)
• Evaluation of the potential of Near Infrared Hyperspectral Imaging for monitoring the invasive brown marmorated stink bug [53.682955739083056]
  The brown marmorated stink bug (BMSB), Halyomorpha halys, is an invasive insect pest of global importance that damages several crops. The present study consists in a preliminary evaluation at the laboratory level of Near Infrared Hyperspectral Imaging (NIR-HSI) as a possible technology to detect BMSB specimens.
  arXiv  Detail & Related papers  (2023-01-19T11:37:20Z)
• Multiple Time Series Fusion Based on LSTM An Application to CAP A Phase Classification Using EEG [56.155331323304]
  Deep learning based electroencephalogram channels' feature level fusion is carried out in this work. Channel selection, fusion, and classification procedures were optimized by two optimization algorithms.
  arXiv  Detail & Related papers  (2021-12-18T14:17:49Z)
• Osteoporosis Prescreening using Panoramic Radiographs through a Deep Convolutional Neural Network with Attention Mechanism [65.70943212672023]
  Deep convolutional neural network (CNN) with an attention module can detect osteoporosis on panoramic radiographs. dataset of 70 panoramic radiographs (PRs) from 70 different subjects of age between 49 to 60 was used.
  arXiv  Detail & Related papers  (2021-10-19T00:03:57Z)
• Neural network-based on-chip spectroscopy using a scalable plasmonic encoder [0.4397520291340694]
  Conventional spectrometers are limited by trade-offs set by size, cost, signal-to-noise ratio (SNR), and spectral resolution. Here, we demonstrate a deep learning-based spectral reconstruction framework using a compact and low-cost on-chip sensing scheme.
  arXiv  Detail & Related papers  (2020-12-01T22:50:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.