Hyperspectral image-based analysis of thermal damage for ex-vivo bovine liver utilizing radiofrequency ablation

Advancing laser ablation assessment in hyperspectral imaging through machine learning

Hyperspectral imaging (HSI) is gaining increasing relevance in medicine, with an innovative application being the intraoperative assessment of the outcome of laser ablation treatment used for minimally invasive tumor removal. However, the high dimensionality and complexity of HSI data create a need for end-to-end image processing workflows specifically tailored to handle these data. This study addresses this challenge by proposing a multi-stage workflow for the analysis of hyperspectral data and allows investigating the performance of different components and modalities for ablation detection and segmentation. To address dimensionality reduction, we integrated principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) to capture dominant variations and reveal intricate structures, respectively. Additionally, we employed the Faster Region-based Convolutional Neural Network (Faster R-CNN) to accurately localize ablation areas. The two-stage detection process of Faster R-CNN, along with the choice of dimensionality reduction technique and data modality, significantly influenced the performance in detecting ablation areas. The evaluation of the ablation detection on an independent test set demonstrated a mean average precision of approximately 0.74, which validates the generalization ability of the models. In the segmentation component, the Mean Shift algorithm showed high quality segmentation without manual cluster definition. Our results prove that the integration of PCA, t-SNE, and Faster R-CNN enables improved interpretation of hyperspectral data, leading to the development of reliable ablation detection and segmentation systems.

Deep learning-assisted multispectral imaging for early screening of skin diseases

INTRODUCTION

Melanocytic nevi (MN), warts, seborrheic keratoses (SK), and psoriasis are four common types of skin surface lesions that typically require dermatoscopic examination for definitive diagnosis in clinical dermatology settings. This process is labor-intensive and resource-consuming. Traditional methods for diagnosing skin lesions rely heavily on the subjective judgment of dermatologists, leading to issues in diagnostic accuracy and prolonged detection times.

OBJECTIVES

This study aims to introduce a multispectral imaging (MSI)-based method for the early screening and detection of skin surface lesions. By capturing image data at multiple wavelengths, MSI can detect subtle spectral variations in tissues, significantly enhancing the differentiation of various skin conditions.

METHODS

The proposed method utilizes a pixel-level mosaic imaging spectrometer to capture multispectral images of lesions, followed by reflectance calibration and standardization. Regions of interest were manually extracted, and the spectral data were subsequently exported for analysis. An improved one-dimensional convolutional neural network is then employed to train and classify the data.

RESULTS

The new method achieves an accuracy of 96.82 % on the test set, demonstrating its efficacy.

CONCLUSION

This multispectral imaging approach provides a non-contact and non-invasive method for early screening, effectively addressing the subjective identification of lesions by dermatologists and the prolonged detection times associated with conventional methods. It offers enhanced diagnostic accuracy for a variety of skin lesions, suggesting new avenues for dermatological diagnostics.

Automated hyperspectral imaging for non-invasive characterization of human eye vasculature: A potential tool for ocular vascular evaluation

The vascular supply to the human eye plays a vital role in maintaining ocular health, making its non-invasive evaluation essential for diagnosing and managing various ocular disorders. This paper presents a novel approach utilizing hyperspectral imaging (HSI) to non-invasively characterize human eye vasculature. The proposed system aims to specifically identify the blood atrium and veins of the human eye at 470 nm and 750 nm, respectively, using quantitative phase analysis and k-means clustering. The study involved capturing diffused reflection spectra and hyperspectral images of the human eye at different wavelengths to reveal distinctive vascular features. The results of ten volunteers demonstrate promising capabilities in automated differentiation of atrium and veins, as well as the potential for mapping varicose veins in the lower limb. This non-invasive and non-contact imaging technique shows great promise in facilitating accurate and detailed evaluation of ocular blood flow, providing valuable information for clinical diagnosis and treatment in ophthalmology and vascular medicine fields.

Custom Hyperspectral Imaging System Reveals Unique Spectral Signatures of Heart, Kidney, and Liver Tissues

The rapid advancement of diagnostic and therapeutic optical techniques for oncology demands a good understanding of the optical properties of biological tissues. This study explores the capabilities of hyperspectral (HS) cameras as a non-invasive and non-contact optical imaging system to distinguish and highlight spectral differences inbiological soft tissuesof three structures (kidney, heart, and liver) for use inendoscopic interventionoropen surgery. The study presents an optical system consisting of two individual setups, the transmission setup, and the reflection setup, both incorporating anHS camerawith apolychromatic light sourcewithin the range of 380 to 1050 nm to measure tissue's light transmission (Tr) and diffuse light reflectance (Rd), respectively. The optical system was calibrated with a customizedliquid optical phantom, then 30 samples from various organs were investigated fortissue characterizationby measuring both Tr and Rd at the visible and near infrared (VIS-NIR) band. We exploited the ANOVA test, subsequently by a Tukey's test on the created three independent clusters (kidney vs. heart: group I / kidney vs. liver: group II / heart vs. liver: group III) to identify the optimum wavelength for each tissue regarding their spectroscopic optical properties in the VIS-NIR spectrum. The optimum spectral span for the determined light Tr of the three groups was 640 ∼ 680 nm, and the ideal range was 720 ∼ 760 nm for the measured light Rd for mutual group I and group II. However, the group III range was different at a range of 520 ∼ 560 nm. Therefore, the investigation provides vital information concerning theoptimum spectral scalefor the computed light Tr and Rd of the investigatedbiological tissues(kidney, liver, and heart) to be employed in diagnostic andtherapeutic medical applications.

Prediction of In Vivo Laser-Induced Thermal Damage with Hyperspectral Imaging Using Deep Learning

Thermal ablation is an acceptable alternative treatment for primary liver cancer, of which laser ablation (LA) is one of the least invasive approaches, especially for tumors in high-risk locations. Precise control of the LA effect is required to safely destroy the tumor. Although temperature imaging techniques provide an indirect measurement of the thermal damage, a degree of uncertainty remains about the treatment effect. Optical techniques are currently emerging as tools to directly assess tissue thermal damage. Among them, hyperspectral imaging (HSI) has shown promising results in image-guided surgery and in the thermal ablation field. The highly informative data provided by HSI, associated with deep learning, enable the implementation of non-invasive prediction models to be used intraoperatively. Here we show a novel paradigm “peak temperature prediction model” (PTPM), convolutional neural network (CNN)-based, trained with HSI and infrared imaging to predict LA-induced damage in the liver. The PTPM demonstrated an optimal agreement with tissue damage classification providing a consistent threshold (50.6 ± 1.5 °C) for the damage margins with high accuracy (~0.90). The high correlation with the histology score (r = 0.9085) and the comparison with the measured peak temperature confirmed that PTPM preserves temperature information accordingly with the histopathological assessment.