Distinction of surgically resected gastrointestinal stromal tumor by near-infrared hyperspectral imaging

Development of a visible to 1600 nm hyperspectral imaging rigid-scope system using supercontinuum light and an acousto-optic tunable filter

In this study, we developed a rigid-scope system that can perform hyperspectral imaging (HSI) between visible and 1600 nm wavelengths using a supercontinuum light source and an acousto-optic tunable filter to emit specific wavelengths. The system optical performance was verified, and the classification ability was investigated. Consequently, it was demonstrated that HSI (490-1600 nm) could be performed. In addition, seven different targets could be classified by the neural network with an accuracy of 99.6%, recall of 93.7%, and specificity of 99.1% when the wavelength range of over 1000 nm (OTN) was extracted from HSI data as train data.

Visualization of hydrocarbon chain length and degree of saturation of fatty acids in mouse livers by combining near-infrared hyperspectral imaging and machine learning

Fatty acids play various physiological roles owing to their diverse structural characteristics, such as hydrocarbon chain length (HCL) and degree of saturation (DS). Although the distribution of fatty acids in biological tissues is associated with lipid metabolism, in situ imaging tools are still lacking for HCL and DS. Here, we introduce a framework of near-infrared (1000-1400 nm) hyperspectral label-free imaging with machine learning analysis of the fatty acid HCL and DS distribution in the liver at each pixel, in addition to the previously reported total lipid content. The training data of 16 typical fatty acids were obtained by gas chromatography from liver samples of mice fed with various diets. A two-dimensional mapping of these two parameters was successfully performed. Furthermore, the HCL/DS plot exhibited characteristic clustering among the different diet groups. Visualization of fatty acid distribution would provide insights for revealing the pathophysiological conditions of liver diseases and metabolism.

Evaluating the identification of the extent of gastric cancer by over-1000 nm near-infrared hyperspectral imaging using surgical specimens

Significance

Determining the extent of gastric cancer (GC) is necessary for evaluating the gastrectomy margin for GC. Additionally, determining the extent of the GC that is not exposed to the mucosal surface remains difficult. However, near-infrared (NIR) can penetrate mucosal tissues highly efficiently.

Aim

We investigated the ability of near-infrared hyperspectral imaging (NIR-HSI) to identify GC areas, including exposed and unexposed using surgical specimens, and explored the identifiable characteristics of the GC.

Approach

Our study examined 10 patients with diagnosed GC who underwent surgery between 2020 and 2021. Specimen images were captured using NIR-HSI. For the specimens, the exposed area was defined as an area wherein the cancer was exposed on the surface, the unexposed area as an area wherein the cancer was present although the surface was covered by normal tissue, and the normal area as an area wherein the cancer was absent. We estimated the GC (including the exposed and unexposed areas) and normal areas using a support vector machine, which is a machine-learning method for classification. The prediction accuracy of the GC region in every area and normal region was evaluated. Additionally, the tumor thicknesses of the GC were pathologically measured, and their differences in identifiable and unidentifiable areas were compared using NIR-HSI.

Results

The average prediction accuracy of the GC regions combined with both areas was 77.2%; with exposed and unexposed areas was 79.7% and 68.5%, respectively; and with normal regions was 79.7%. Additionally, the areas identified as cancerous had a tumor thickness of > 2    mm .

Conclusions

NIR-HSI identified the GC regions with high rates. As a feature, the exposed and unexposed areas with tumor thicknesses of > 2    mm were identified using NIR-HSI.

Near-Infrared Emission Material with Superlong Afterglow Performance and Its Multifunctional Applications

A new near-infrared (NIR) emission material, BaSi_1.5Ge_2.5O₉:Cr³⁺, with outstanding long afterglow properties is designed and synthesized successfully. Its structure, photoluminescence, and long afterglow emission features are studied in detail. Cr³⁺ occupies six-coordinated Ba²⁺ and Ge⁴⁺ sites in this system, which can emit characteristic broadband NIR light in the range of 700-1200 nm, and it has a long afterglow emission of more than 10 h. We calculated the band gap of the host at about 4.1 eV, the energy level distribution after Cr³⁺ doping, and the distribution of oxygen vacancies through density functional theory simulation, which theoretically proved the characteristic transition of Cr³⁺ and that the oxygen vacancies are crucial to form the defect energy levels. This is corroborated with the reflectance spectra, three-dimensional thermoluminescence spectra, and electron spin resonance (ESR) spectra. The oxygen-deficient environment favors the formation of oxygen vacancy defects and prevents the oxidation of Cr³⁺ to Cr⁶⁺, which are the key points for the luminescence and afterglow properties. A mechanistic model of defect formation and electron trapping and transport processes is successfully established. Finally, its multifunctional applications in information anticounterfeiting encryption, biological tissue penetration, and internal nondestructive testing and imaging are demonstrated.

Evaluation of Preprocessing Methods on Independent Medical Hyperspectral Databases to Improve Analysis

Currently, one of the most common causes of death worldwide is cancer. The development of innovative methods to support the early and accurate detection of cancers is required to increase the recovery rate of patients. Several studies have shown that medical Hyperspectral Imaging (HSI) combined with artificial intelligence algorithms is a powerful tool for cancer detection. Various preprocessing methods are commonly applied to hyperspectral data to improve the performance of the algorithms. However, there is currently no standard for these methods, and no studies have compared them so far in the medical field. In this work, we evaluated different combinations of preprocessing steps, including spatial and spectral smoothing, Min-Max scaling, Standard Normal Variate normalization, and a median spatial smoothing technique, with the goal of improving tumor detection in three different HSI databases concerning colorectal, esophagogastric, and brain cancers. Two machine learning and deep learning models were used to perform the pixel-wise classification. The results showed that the choice of preprocessing method affects the performance of tumor identification. The method that showed slightly better results with respect to identifing colorectal tumors was Median Filter preprocessing (0.94 of area under the curve). On the other hand, esophagogastric and brain tumors were more accurately identified using Min-Max scaling preprocessing (0.93 and 0.92 of area under the curve, respectively). However, it is observed that the Median Filter method smooths sharp spectral features, resulting in high variability in the classification performance. Therefore, based on these results, obtained with different databases acquired by different HSI instrumentation, the most relevant preprocessing technique identified in this work is Min-Max scaling.

Three Dimensional Lifetime-Multiplex Tomography Based on Time-Gated Capturing of Near-Infrared Fluorescence Images

We report a computed tomography (CT) technique for mapping near-infrared fluorescence (NIRF) lifetime as a multiplex three-dimensional (3D) imaging method, using a conventional NIR camera. This method is achieved by using a time-gated system composed of a pulsed laser and an NIR camera synchronized with a rotatable sample stage for NIRF-CT imaging. The fluorescence lifetimes in microsecond-order of lanthanides were mapped on reconstructed cross-sectional and 3D images, via back-projection of two-dimensional projected images acquired from multiple angles at each time point showing fluorescence decay. A method to select slopes (the observed decay rates in time-gated imaging) used for the lifetime calculation, termed as the slope comparison method, was developed for the accurate calculation of each pixel, resulting in reduction of image acquisition time. Time-gated NIRF-CT provides a novel choice for multiplex 3D observation of deep tissues in biology.

A systematic review on application of deep learning in digestive system image processing

With the advent of the big data era, the application of artificial intelligence represented by deep learning in medicine has become a hot topic. In gastroenterology, deep learning has accomplished remarkable accomplishments in endoscopy, imageology, and pathology. Artificial intelligence has been applied to benign gastrointestinal tract lesions, early cancer, tumors, inflammatory bowel diseases, livers, pancreas, and other diseases. Computer-aided diagnosis significantly improve diagnostic accuracy and reduce physicians' workload and provide a shred of evidence for clinical diagnosis and treatment. In the near future, artificial intelligence will have high application value in the field of medicine. This paper mainly summarizes the latest research on artificial intelligence in diagnosing and treating digestive system diseases and discussing artificial intelligence's future in digestive system diseases. We sincerely hope that our work can become a stepping stone for gastroenterologists and computer experts in artificial intelligence research and facilitate the application and development of computer-aided image processing technology in gastroenterology.

Advancements in the Diagnosis of Gastric Subepithelial Tumors

A diagnosis of subepithelial tumors (SETs) is sometimes difficult due to the existence of overlying mucosa on the lesions, which hampers optical diagnosis by conventional endoscopy and tissue sampling with standard biopsy forceps. Imaging modalities, by using computed tomography and endoscopic ultrasonography (EUS) are mandatory to noninvasively collect the target's information and to opt candidates for further evaluation. Particularly, EUS is an indispensable diagnostic modality for assessing the lesions precisely and evaluating the possibility of malignancy. The diagnostic ability of EUS appears increased by the combined use of contrast-enhancement or elastography. Histology is the gold standard for obtaining the final diagnosis. Tissue sampling requires special techniques to break the mucosal barrier. Although EUS-guided fine-needle aspiration (EUS-FNA) is commonly applied, mucosal cutting biopsy and mucosal incision-assisted biopsy are comparable methods to definitively obtain tissues from the exposed surface of lesions and seem more useful than EUS-FNA for small SETs. Recent advancements in artificial intelligence (AI) have a potential to drastically change the diagnostic strategy for SETs. Development and establishment of noninvasive methods including AI-assisted diagnosis are expected to provide an alternative to invasive, histological diagnosis.

Over 1000 nm Near-Infrared Multispectral Imaging System for Laparoscopic In Vivo Imaging

In this study, a laparoscopic imaging device and a light source able to select wavelengths by bandpass filters were developed to perform multispectral imaging (MSI) using over 1000 nm near-infrared (OTN-NIR) on regions under a laparoscope. Subsequently, MSI (wavelengths: 1000-1400 nm) was performed using the built device on nine live mice before and after tumor implantation. The normal and tumor pixels captured within the mice were used as teaching data sets, and the tumor-implanted mice data were classified using a neural network applied following a leave-one-out cross-validation procedure. The system provided a specificity of 89.5%, a sensitivity of 53.5%, and an accuracy of 87.8% for subcutaneous tumor discrimination. Aggregated true-positive (TP) pixels were confirmed in all tumor-implanted mice, which indicated that the laparoscopic OTN-NIR MSI could potentially be applied in vivo for classifying target lesions such as cancer in deep tissues.