Hyperspectral imaging based method for fast characterization of kidney stone types

Clinical Applications of Machine Learning for Urolithiasis and Benign Prostatic Hyperplasia: A Systematic Review

INTRODUCTION

Previous systematic reviews related to machine learning (ML) in urology often overlooked the literature related to endourology. Therefore, we aim to conduct a more focused systematic review examining the use of ML algorithms for benign prostatic hyperplasia (BPH) or urolithiasis. In addition, we are the first group to evaluate these articles using the STREAM-URO framework.

METHODS

Searches of MEDLINE, Embase, and the Cochrane CENTRAL databases were conducted from inception through July 12, 2021. Keywords included those related to ML, endourology, urolithiasis, and BPH. Two reviewers screened the citations that were eligible for title, abstract and full-text screening, with conflicts resolved by a third reviewer. Two reviewers extracted information from the studies, with discrepancies resolved by a third reviewer. The data collected was then qualitatively synthesized by consensus. Two reviewers evaluated each article according to the STREAM-URO checklist with discrepancies resolved by a third reviewer.

RESULTS

After identifying 459 unique citations, 63 articles were retained for data extraction. Most articles consisted of tabular (n=32) and computer vision (n=23) tasks. The two most common problem types were classification (n=40) and regression (n=12). In general, most studies utilized neural networks as their ML algorithm (n=36). Among the 63 studies retrieved, 58 were related to urolithiasis and five focused on BPH. The urolithiasis studies were designed for outcome prediction (n=20), stone classification (n=18), diagnostics (n=17), and therapeutics (n=3). The BPH studies were designed for outcome prediction (n=2), diagnostics (n=2), and therapeutics (n=1). On average, the urolithiasis and BPH articles met 13.8 (SD 2.6), and 13.4 (4.1) of the 26 STREAM-URO framework criteria, respectively.

CONCLUSIONS

The majority of the retrieved studies successfully helped with outcome prediction, diagnostics, and therapeutics for both urolithiasis and BPH. While ML shows great promise in improving patient care, it is important to adhere to the recently developed STREAM-URO framework to ensure the development of high-quality ML studies.

Label-Free Detection of Human Coronaviruses in Infected Cells Using Enhanced Darkfield Hyperspectral Microscopy (EDHM)

Human coronaviruses (HCoV) are causative agents of mild to severe intestinal and respiratory infections in humans. In the last 15 years, we have witnessed the emergence of three zoonotic, highly pathogenic HCoVs. Thus, early and accurate detection of these viral pathogens is essential for preventing transmission and providing timely treatment and monitoring of drug resistance. Herein, we applied enhanced darkfield hyperspectral microscopy (EDHM), a novel non-invasive, label-free diagnostic tool, to rapidly and accurately identify two strains of HCoVs, i.e., OC43 and 229E. The EDHM technology allows collecting the optical image with spectral and spatial details in a single measurement without direct contact between the specimen and the sensor. Thus, it can directly map spectral signatures specific for a given viral strain in a complex biological milieu. Our study demonstrated distinct spectral patterns for HCoV-OC43 and HCoV-229E virions in the solution, serving as distinguishable parameters for their differentiation. Furthermore, spectral signatures obtained for both HCoV strains in the infected cells displayed a considerable peak wavelength shift compared to the uninfected cell, indicating that the EDHM is applicable to detect HCoV infection in mammalian cells.

Automatic detection of basal cell carcinoma by hyperspectral imaging

The purpose of this study was to test the ability of hyperspectral imaging (HSI) combined with unsupervised anomaly detectors to automatically differentiate basal cell carcinoma (BCC) from normal skin. Hyperspectral images of the face of a female patient with a BCC of the lower lip were acquired using a visible/near-infrared HSI system and two anomaly detection algorithms (Reed-Xiaoli and Reed-Xiaoli/Uniform Target hybrid anomaly detectors) were used to detect pathological tissue from normal skin. The results revealed that the receiver operating characteristic curve of the Reed-Xiaoli/Uniform Target hybrid detector was higher than that of the Reed-Xiaoli detector in the range of false positive rates between 0 and 0.8. The area under curve values were good (0.7074 and 0.8607, respectively) with Reed-Xiaoli/Uniform Target hybrid detector performing better. In conclusion, HSI combined with either of two anomaly detectors can play a promising role in the automated screening of BCC.

Near-infrared hyperspectral imaging for monitoring the thickness distribution of thin poly(3,4-ethylenedioxythiophene):poly(styrene sulfonate) (PEDOT:PSS) layers

The thickness of thin layers of the conductive polymer PEDOT:PSS in the range between about 60 and 300 nm was determined by a near-infrared spectroscopic method using a hyperspectral camera. The reflection spectra of the layers do not contain bands, but consist of a moderate slope of the overall reflectance in the range between 1320 and 1850 nm. Despite the low thickness, the spectra show an extremely strong dependence on the thickness of the layers, which allows their use for quantitative measurements. The prediction of quantitative thickness data from the reflection spectra was based on a chemometric approach using the partial least squares (PLS) algorithm. Calibration was carried out by means of spin-coated layers of PEDOT:PSS, whose thickness was determined by white-light interferometry and stylus profilometry. Finally, this resulted in a calibration model with a root mean square error of prediction (RMSEP) of about 9 nm. After external validation of this model, it was used for quantitative imaging of the thickness distribution in PEDOT:PSS layers. The precision of the predicted values was confirmed by comparison with data from the reference methods. Moreover, it was shown that this approach can be also used for hyperspectral imaging of the thickness of thin printed layers and structures of this conductive polymer on polymer film or paper with excellent thickness resolution. This analytical approach opens new possibilities for in-line process control by large-scale monitoring of thickness and homogeneity of thin layers of conductive polymers.

Monitoring of the residual moisture content in finished textiles during converting by NIR hyperspectral imaging

Hyperspectral imaging was used for large-scale monitoring of the residual moisture in wide textile webs at the end of the drying process that follows their washing or finishing by impregnation in aqueous solutions or dispersions. Such data are essential for optimizing the energy efficiency and the precise control of the drying process. Quantitative analysis of the recorded spectral data was carried out with multivariate regression methods such as the partial least squares (PLS) algorithm. Reference data for calibration of the prediction models were determined by gravimetry. The drying of textile materials from both natural or synthetic fibers possessing different water absorption capacities (cotton, polyamide, polyester), which were partially finished with an optical brightener, was investigated. Moisture contents in the range from 0 to about 12 wt% were considered in the calibration models. For all systems, the root mean square error of prediction (RMSEP) for the residual moisture was found to be about 0.5 wt%, that is, about 1 g/m². In addition to the quantitative determination of the water content, hyperspectral imaging provides detailed information about its spatial distribution across the textile web, which may help to improve the control of the drying process. In particular, it was demonstrated that the developed methods were capable of detecting and visualizing inhomogeneous moisture distributions. Averaging of the individual values of the moisture content predicted from all spectra across the surface of the textile samples resulted in a very close correlation with the corresponding gravimetric reference values. Due to the averaging process, the difference between both values is generally lower than RMSEP even in case of samples with inhomogeneous distribution of the moisture. The high precision and the broad capabilities of the developed analytic methods for in-line monitoring of the moisture content hold the potential for an efficient process control in technical textile converting processes.

Towards an understanding of the chemo-mechanical influences on kidney stone failure via the material point method

This paper explores the use of the meshfree computational mechanics method, the Material Point Method (MPM), to model the composition and damage of typical renal calculi, or kidney stones. Kidney stones are difficult entities to model due to their complex structure and failure behavior. Better understanding of how these stones behave when they are broken apart is a vital piece of knowledge to medical professionals whose aim is to remove these stone by breaking them within a patient’s body. While the properties of individual stones are varied, the common elements and proportions are used to generate synthetic stones that are then placed in a digital experiment to observe their failure patterns. First a more traditional engineering model of a Brazil test is used to create a tensile fracture within the center of these stones to observe the effect of stone consistency on failure behavior. Next a novel application of MPM is applied which relies on an ultrasonic wave being carried by surrounding fluid to model the ultrasonic treatment of stones commonly used by medical practitioners. This numerical modeling of Extracorporeal Shock Wave Lithotripsy (ESWL) reveals how these different stones failure in a more real-world situation and could be used to guide further research in this field for safer and more effective treatments.

Hyperspectral imaging in wound care: A systematic review

Multispectral and hyperspectral imaging (HSI) are emerging imaging techniques with the potential to transform the way patients with wounds are cared for, but it is not clear whether current systems are capable of delivering real-time tissue characterisation and treatment guidance. We conducted a systematic review of HSI systems that have been assessed in patients, published over the past 32 years. We analysed 140 studies, including 10 different HSI systems. Current in vivo HSI systems generate a tissue oxygenation map. Tissue oxygenation measurements may help to predict those patients at risk of wound formation or delayed healing. No safety concerns were reported in any studies. A small number of studies have demonstrated the capabilities of in vivo label-free HSI, but further work is needed to fully integrate it into the current clinical workflow for different wound aetiologies. As an emerging imaging modality for medical applications, HSI offers great potential for non-invasive disease diagnosis and guidance when treating patients with both acute and chronic wounds.

Hyperspectral imaging in wound care: A systematic review

Multispectral and hyperspectral imaging (HSI) are emerging imaging techniques with the potential to transform the way patients with wounds are cared for, but it is not clear whether current systems are capable of delivering real-time tissue characterisation and treatment guidance. We conducted a systematic review of HSI systems that have been assessed in patients, published over the past 32 years. We analysed 140 studies, including 10 different HSI systems. Current in vivo HSI systems generate a tissue oxygenation map. Tissue oxygenation measurements may help to predict those patients at risk of wound formation or delayed healing. No safety concerns were reported in any studies. A small number of studies have demonstrated the capabilities of in vivo label-free HSI, but further work is needed to fully integrate it into the current clinical workflow for different wound aetiologies. As an emerging imaging modality for medical applications, HSI offers great potential for non-invasive disease diagnosis and guidance when treating patients with both acute and chronic wounds.

In-Vivo and Ex-Vivo Tissue Analysis through Hyperspectral Imaging Techniques: Revealing the Invisible Features of Cancer

In contrast to conventional optical imaging modalities, hyperspectral imaging (HSI) is able to capture much more information from a certain scene, both within and beyond the visual spectral range (from 400 to 700 nm). This imaging modality is based on the principle that each material provides different responses to light reflection, absorption, and scattering across the electromagnetic spectrum. Due to these properties, it is possible to differentiate and identify the different materials/substances presented in a certain scene by their spectral signature. Over the last two decades, HSI has demonstrated potential to become a powerful tool to study and identify several diseases in the medical field, being a non-contact, non-ionizing, and a label-free imaging modality. In this review, the use of HSI as an imaging tool for the analysis and detection of cancer is presented. The basic concepts related to this technology are detailed. The most relevant, state-of-the-art studies that can be found in the literature using HSI for cancer analysis are presented and summarized, both in-vivo and ex-vivo. Lastly, we discuss the current limitations of this technology in the field of cancer detection, together with some insights into possible future steps in the improvement of this technology.

Detecting brain tumor in pathological slides using hyperspectral imaging

Hyperspectral imaging (HSI) is an emerging technology for medical diagnosis. This research work presents a proof-of-concept on the use of HSI data to automatically detect human brain tumor tissue in pathological slides. The samples, consisting of hyperspectral cubes collected from 400 nm to 1000 nm, were acquired from ten different patients diagnosed with high-grade glioma. Based on the diagnosis provided by pathologists, a spectral library of normal and tumor tissues was created and processed using three different supervised classification algorithms. Results prove that HSI is a suitable technique to automatically detect high-grade tumors from pathological slides.

Kidney stone nano-structure - Is there an opportunity for nanomedicine development?

BACKGROUND

Kidney stone analysis techniques are well-established in the field of materials characterization and provide information for the chemical composition and structure of a sample. Nanomedicine, on the other hand, is a field with an increasing rate of scientific research, a big budget and increasingly developing market. The key scientific question is if there is a possibility for the development of a nanomedicine to treat kidney stones.

MAJOR CONCLUSIONS

The main calculi characterization techniques such as X-ray Diffraction and Fourier Transform Infrared Spectroscopy can provide information about the composition of a kidney stone but not for its nanostructure. On the other hand, Small Angle X-ray Scattering and Nitrogen Porosimetry can show the nanostructural parameters of the calculi. The combination of the previously described parameters can be used for the development of nano-drugs for the treatment of urolithiasis, while no such nano-drugs exist yet.

GENERAL SIGNIFICANCE

In this study, we focus on the most well-known techniques for kidney stone analysis, the urolithiasis management and the search for possible nanomedicine for the treatment of kidney stone disease. We combine the results from five different analysis techniques in order to represent a three dimensional model and we propose a hypothetical nano-drug with gold nanoparticles. This article is part of a Special Issue entitled "Recent Advances in Bionanomaterials" Guest Editor: Dr. Marie-Louise Saboungi and Dr. Samuel D. Bader.

Development of an image pre-processor for operational hyperspectral laryngeal cancer detection

Hyperspectral imaging (HSI) is a technology with high potential in the field of non-invasive detection of cancer. However, in complex imaging situations like HSI of the larynx with a rigid endoscope, various image interferences can disable a proper classification of cancerous tissue. We identified three main problems: i) misregistration of single images in a HS cube due to patient heartbeat ii) image noise and iii) specular reflections (SR). Consequently, an image pre-processor is developed in the current paper to overcome these image interferences. It encompasses i) image registration ii) noise removal by minimum noise fraction (MNF) transformation and iii) a novel SR detection method. The results reveal that the pre-processor improves classification performance, while the newly developed SR detection method outperforms global thresholding technique hitherto used by 46%. The novel pre-processor will be used for future studies towards the development of an operational scheme for HS-based larynx cancer detection. RGB image of the larynx derived from the hyperspectral cube and corresponding specular reflections (a) manually segmented and (b) detected by a novel specular reflection detection method.

High precision mapping of kidney stones using μ-IR spectroscopy to determine urinary lithogenesis

Evolution of urinary lithiasis is determined by the metabolism and life-style of the related patient. The appropriate classification of the stone is mandatory for the identification of the lithogenic process. In this study, cros-sections from a single stone of each of the most frequent urolithiasis types (calcium oxalate mono and dihydrate and carbonate apatite) have been selected and imaged using IR microspectroscopy. Moreover, the use of high definition sFTIR (synchrotron source) has revealed hidden information to the conventional FTIR. This work has demonstrated that minor components become key factors on the description of the stages of stone formation. Intensity map for COM (1630 cm(-1) peak). The high spatial definition achieved is key for the precise description of the kidney stone history.

Taking advantage of hyperspectral imaging classification of urinary stones against conventional infrared spectroscopy

The analysis of urinary stones is mandatory for the best management of the disease after the stone passage in order to prevent further stone episodes. Thus the use of an appropriate methodology for an individualized stone analysis becomes a key factor for giving the patient the most suitable treatment. A recently developed hyperspectral imaging methodology, based on pixel-to-pixel analysis of near-infrared spectral images, is compared to the reference technique in stone analysis, infrared (IR) spectroscopy. The developed classification model yields >90% correct classification rate when compared to IR and is able to precisely locate stone components within the structure of the stone with a 15 µm resolution. Due to the little sample pretreatment, low analysis time, good performance of the model, and the automation of the measurements, they become analyst independent; this methodology can be considered to become a routine analysis for clinical laboratories.

Medical hyperspectral imaging: a review

Hyperspectral imaging (HSI) is an emerging imaging modality for medical applications, especially in disease diagnosis and image-guided surgery. HSI acquires a three-dimensional dataset called hypercube, with two spatial dimensions and one spectral dimension. Spatially resolved spectral imaging obtained by HSI provides diagnostic information about the tissue physiology, morphology, and composition. This review paper presents an overview of the literature on medical hyperspectral imaging technology and its applications. The aim of the survey is threefold: an introduction for those new to the field, an overview for those working in the field, and a reference for those searching for literature on a specific application.

Medical hyperspectral imaging: a review

Hyperspectral imaging (HSI) is an emerging imaging modality for medical applications, especially in disease diagnosis and image-guided surgery. HSI acquires a three-dimensional dataset called hypercube, with two spatial dimensions and one spectral dimension. Spatially resolved spectral imaging obtained by HSI provides diagnostic information about the tissue physiology, morphology, and composition. This review paper presents an overview of the literature on medical hyperspectral imaging technology and its applications. The aim of the survey is threefold: an introduction for those new to the field, an overview for those working in the field, and a reference for those searching for literature on a specific application.

Microspectroscopic infrared specular reflection chemical imaging of multi-component urinary stones: MIR vs. FIR

Specular reflection infrared microspectroscopy was used for chemical imaging of cross-sectioned urinary stones to determine their chemical composition and morphology simultaneously. Absorption spectral bands were recovered from reflection spectra by Kramers-Kronig transform. FUse of far-infrared radiation provides high-contrast images and allows more precise constituent distribution determinations than mid-infrared because band asymmetry after the transform caused by diffuse reflection is less in the far-infrared.

Classification of oat and groat kernels using NIR hyperspectral imaging

An innovative procedure to classify oat and groat kernels based on coupling hyperspectral imaging (HSI) in the near infrared (NIR) range (1006-1650 nm) and chemometrics was designed, developed and validated. According to market requirements, the amount of groat, that is the hull-less oat kernels, is one of the most important quality characteristics of oats. Hyperspectral images of oat and groat samples have been acquired by using a NIR spectral camera (Specim, Finland) and the resulting data hypercubes were analyzed applying Principal Component Analysis (PCA) for exploratory purposes and Partial Least Squares-Discriminant Analysis (PLS-DA) to build the classification models to discriminate the two kernel typologies. Results showed that it is possible to accurately recognize oat and groat single kernels by HSI (prediction accuracy was almost 100%). The study demonstrated also that good classification results could be obtained using only three wavelengths (1132, 1195 and 1608 nm), selected by means of a bootstrap-VIP procedure, allowing to speed up the classification processing for industrial applications. The developed objective and non-destructive method based on HSI can be utilized for quality control purposes and/or for the definition of innovative sorting logics of oat grains.