Tumor detection of the thyroid and salivary glands using hyperspectral imaging and deep learning

Deep Learning and Hyperspectral Imaging for Liver Cancer Staging and Cirrhosis Differentiation

Liver malignancies, particularly hepatocellular carcinoma (HCC), pose a formidable global health challenge. Conventional diagnostic techniques frequently fall short in precision, especially at advanced HCC stages. In response, we have developed a novel diagnostic strategy that integrates hyperspectral imaging with deep learning. This innovative approach captures detailed spectral data from tissue samples, pinpointing subtle cellular differences that elude traditional methods. A sophisticated deep convolutional neural network processes this data, effectively distinguishing high-grade liver cancer from cirrhosis with an accuracy of 89.45%, a sensitivity of 90.29%, and a specificity of 88.64%. For HCC differentiation specifically, it achieves an impressive accuracy of 93.73%, sensitivity of 92.53%, and specificity of 90.07%. Our results underscore the potential of this technique as a precise, rapid, and non-invasive diagnostic tool that surpasses existing clinical methods in staging liver cancer and differentiating cirrhosis.

Advancing hyperspectral imaging and machine learning tools toward clinical adoption in tissue diagnostics: A comprehensive review

Hyperspectral imaging (HSI) has become an evident transformative apparatus in medical diagnostics. The review aims to appraise the present advancement and challenges in HSI for medical applications. It features a variety of medical applications namely diagnosing diabetic retinopathy, neurodegenerative diseases like Parkinson's and Alzheimer's, which illustrates its effectiveness in early diagnosis, early caries detection in periodontal disease, and dermatology by detecting skin cancer. Regardless of these advances, the challenges exist within every aspect that limits its broader clinical adoption. It has various constraints including difficulties with technology related to the complexity of the HSI system and needing specialist training, which may act as a drawback to its clinical settings. This article pertains to potential challenges expressed in medical applications and probable solutions to overcome these constraints. Successful companies that perform advanced solutions with HSI in terms of medical applications are being emphasized in this study to signal the high level of interest in medical diagnosis for systems to incorporate machine learning ML and artificial intelligence AI to foster precision diagnosis and standardized clinical workflow. This advancement signifies progressive possibilities of HSI in real-time clinical assessments. In conclusion despite HSI has been presented as a significant advanced medical imaging tool, addressing its limitations and probable solutions is for broader clinical adoption.

Endoscopic In Vivo Hyperspectral Imaging for Head and Neck Tumor Surgeries Using a Medically Approved CE-Certified Camera with Rapid Visualization During Surgery

Background: In vivo visualization of malignant tumors remains the main challenge during head and neck cancer surgery. This can result in inadequate tumor margin assessment and incomplete tumor resection, adversely affecting patient outcomes. Hyperspectral imaging (HSI) is a promising approach to address this issue. However, its application in surgery has been limited by the lack of medically approved HSI devices compliant with MDR regulations, as well as challenges regarding the integration into the surgical workflow. Methods: In this feasibility study, we employed endoscopic HSI during surgery to visualize the tumor sites of 12 head and neck cancer patients. We optimized the HSI workflow to minimize time required during surgery and to reduce the adaptation period needed for surgeons to adjust to the new workflow. Additionally, we implemented data processing to enable real-time classification and visualization of HSI within the intraoperative setting. HSI evaluation was conducted using principal component analysis and k-means clustering, with this clustering validated through comparison with expert annotations. Results: Our complete HSI workflow requires two to three minutes, with each HSI measurement-including evaluation and visualization-taking less than 10 s, achieving an accuracy of 79%, sensitivity of 72%, and specificity of 84%. Medical personnel became proficient with the HSI system after two surgeries. Conclusions: This study presents an HSI workflow for in vivo tissue differentiation during head and neck cancer surgery, providing accurate and visually accessible results within minimal time. This approach enhances the in vivo evaluation of tumor margins, leading to more clear margins and, consequently, improved patient outcomes.

Development and Evaluation of a Convolutional Neural Network for Microscopic Diagnosis Between Pleomorphic Adenoma and Carcinoma Ex-Pleomorphic Adenoma

AIMS

To develop a model capable of distinguishing carcinoma ex-pleomorphic adenoma from pleomorphic adenoma using a convolutional neural network architecture.

METHODS AND RESULTS

A cohort of 83 Brazilian patients, divided into carcinoma ex-pleomorphic adenoma (n = 42) and pleomorphic adenoma (n = 41), was used for training a convolutional neural network. The whole-slide images were annotated and fragmented into 743 869 (carcinoma ex-pleomorphic adenomas) and 211 714 (pleomorphic adenomas) patches, measuring 224 × 224 pixels. Training (80%), validation (10%), and test (10%) subsets were established. The Residual Neural Network (ResNet)-50 was chosen for its recognition and classification capabilities. The training and validation graphs, and parameters derived from the confusion matrix, were evaluated. The loss curve recorded 0.63, and the accuracy reached 0.93. Evaluated parameters included specificity (0.88), sensitivity (0.94), precision (0.96), F1 score (0.95), and area under the curve (0.97).

CONCLUSIONS

The study underscores the potential of ResNet-50 in the microscopic diagnosis of carcinoma ex-pleomorphic adenoma. The developed model demonstrated strong learning potential, but exhibited partial limitations in generalization, as indicated by the validation curve. In summary, the study established a promising baseline despite limitations in model generalization. This indicates the need to refine methodologies, investigate new models, incorporate larger datasets, and encourage inter-institutional collaboration for comprehensive studies in salivary gland tumors.

Advancements in Hyperspectral Imaging and Computer-Aided Diagnostic Methods for the Enhanced Detection and Diagnosis of Head and Neck Cancer

Background/Objectives: Head and neck cancer (HNC), predominantly squamous cell carcinoma (SCC), presents a significant global health burden. Conventional diagnostic approaches often face challenges in terms of achieving early detection and accurate diagnosis. This review examines recent advancements in hyperspectral imaging (HSI), integrated with computer-aided diagnostic (CAD) techniques, to enhance HNC detection and diagnosis. Methods: A systematic review of seven rigorously selected studies was performed. We focused on CAD algorithms, such as convolutional neural networks (CNNs), support vector machines (SVMs), and linear discriminant analysis (LDA). These are applicable to the hyperspectral imaging of HNC tissues. Results: The meta-analysis findings indicate that LDA surpasses other algorithms, achieving an accuracy of 92%, sensitivity of 91%, and specificity of 93%. CNNs exhibit moderate performance, with an accuracy of 82%, sensitivity of 77%, and specificity of 86%. SVMs demonstrate the lowest performance, with an accuracy of 76% and sensitivity of 48%, but maintain a high specificity level at 89%. Additionally, in vivo studies demonstrate superior performance when compared to ex vivo studies, reporting higher accuracy (81%), sensitivity (83%), and specificity (79%). Conclusion: Despite these promising findings, challenges persist, such as HSI's sensitivity to external conditions, the need for high-resolution and high-speed imaging, and the lack of comprehensive spectral databases. Future research should emphasize dimensionality reduction techniques, the integration of multiple machine learning models, and the development of extensive spectral libraries to enhance HSI's clinical utility in HNC diagnostics. This review underscores the transformative potential of HSI and CAD techniques in revolutionizing HNC diagnostics, facilitating more accurate and earlier detection, and improving patient outcomes.

MR Image Fusion-Based Parotid Gland Tumor Detection

The differentiation of benign and malignant parotid gland tumors is of major significance as it directly affects the treatment process. In addition, it is also a vital task in terms of early and accurate diagnosis of parotid gland tumors and the determination of treatment planning accordingly. As in other diseases, the differentiation of tumor types involves several challenging, time-consuming, and laborious processes. In the study, Magnetic Resonance (MR) images of 114 patients with parotid gland tumors are used for training and testing purposes by Image Fusion (IF). After the Apparent Diffusion Coefficient (ADC), Contrast-enhanced T1-w (T1C-w), and T2-w sequences are cropped, IF (ADC, T1C-w), IF (ADC, T2-w), IF (T1C-w, T2-w), and IF (ADC, T1C-w, T2-w) datasets are obtained for different combinations of these sequences using a two-dimensional Discrete Wavelet Transform (DWT)-based fusion technique. For each of these four datasets, ResNet18, GoogLeNet, and DenseNet-201 architectures are trained separately, and thus, 12 models are obtained in the study. A Graphical User Interface (GUI) application that contains the most successful of these trained architectures for each data is also designed to support the users. The designed GUI application not only allows the fusing of different sequence images but also predicts whether the label of the fused image is benign or malignant. The results show that the DenseNet-201 models for IF (ADC, T1C-w), IF (ADC, T2-w), and IF (ADC, T1C-w, T2-w) are better than the others, with accuracies of 95.45%, 95.96%, and 92.93%, respectively. It is also noted in the study that the most successful model for IF (T1C-w, T2-w) is ResNet18, and its accuracy is equal to 94.95%.

Hyperspectral imaging and its applications: A review

Hyperspectral imaging has emerged as an effective powerful tool in plentiful military, environmental, and civil applications over the last three decades. The modern remote sensing approaches are adequate for covering huge earth surfaces with phenomenal temporal, spectral, and spatial resolutions. These features make HSI more effective in various applications of remote sensing depending upon the physical estimation of identical material identification and manifold composite surfaces having accomplished spectral resolutions. Recently, HSI has attained immense significance in the research on safety and quality assessment of food, medical analysis, and agriculture applications. This review focuses on HSI fundamentals and its applications like safety and quality assessment of food, medical analysis, agriculture, water resources, plant stress identification, weed & crop discrimination, and flood management. Various investigators have promising solutions for automatic systems depending upon HSI. Future research may use this review as a baseline and future advancement analysis.

Intelligent tumor tissue classification for Hybrid Health Care Units

Introduction

In the evolving healthcare landscape, we aim to integrate hyperspectral imaging into Hybrid Health Care Units to advance the diagnosis of medical diseases through the effective fusion of cutting-edge technology. The scarcity of medical hyperspectral data limits the use of hyperspectral imaging in disease classification.

Methods

Our study innovatively integrates hyperspectral imaging to characterize tumor tissues across diverse body locations, employing the Sharpened Cosine Similarity framework for tumor classification and subsequent healthcare recommendation. The efficiency of the proposed model is evaluated using Cohen's kappa, overall accuracy, and f1-score metrics.

Results

The proposed model demonstrates remarkable efficiency, with kappa of 91.76%, an overall accuracy of 95.60%, and an f1-score of 96%. These metrics indicate superior performance of our proposed model over existing state-of-the-art methods, even in limited training data.

Conclusion

This study marks a milestone in hybrid healthcare informatics, improving personalized care and advancing disease classification and recommendations.

Test-time augmentation with synthetic data addresses distribution shifts in spectral imaging

PURPOSE

Surgical scene segmentation is crucial for providing context-aware surgical assistance. Recent studies highlight the significant advantages of hyperspectral imaging (HSI) over traditional RGB data in enhancing segmentation performance. Nevertheless, the current hyperspectral imaging (HSI) datasets remain limited and do not capture the full range of tissue variations encountered clinically.

METHODS

Based on a total of 615 hyperspectral images from a total of 16 pigs, featuring porcine organs in different perfusion states, we carry out an exploration of distribution shifts in spectral imaging caused by perfusion alterations. We further introduce a novel strategy to mitigate such distribution shifts, utilizing synthetic data for test-time augmentation.

RESULTS

The effect of perfusion changes on state-of-the-art (SOA) segmentation networks depended on the organ and the specific perfusion alteration induced. In the case of the kidney, we observed a performance decline of up to 93% when applying a state-of-the-art (SOA) network under ischemic conditions. Our method improved on the state-of-the-art (SOA) by up to 4.6 times.

CONCLUSION

Given its potential wide-ranging relevance to diverse pathologies, our approach may serve as a pivotal tool to enhance neural network generalization within the realm of spectral imaging.

SAHIS-Net: a spectral attention and feature enhancement network for microscopic hyperspectral cholangiocarcinoma image segmentation

Cholangiocarcinoma (CCA) poses a significant clinical challenge due to its aggressive nature and poor prognosis. While traditional diagnosis relies on color-based histopathology, hyperspectral imaging (HSI) offers rich, high-dimensional data holding potential for more accurate diagnosis. However, extracting meaningful insights from this data remains challenging. This work investigates the application of deep learning for CCA segmentation in microscopic HSI images, and introduces two novel neural networks: (1) Histogram Matching U-Net (HM-UNet) for efficient image pre-processing, and (2) Spectral Attention based Hyperspectral Image Segmentation Net (SAHIS-Net) for CCA segmentation. SAHIS-Net integrates a novel Spectral Attention (SA) module for adaptively weighing spectral information, an improved attention-aware feature enhancement (AFE) mechanism for better providing the model with more discriminative features, and a multi-loss training strategy for effective early stage feature extraction. We compare SAHIS-Net against several general and CCA-specific models, demonstrating its superior performance in segmenting CCA regions. These results highlight the potential of our approach for segmenting medical HSI images.

Deep neural networks can differentiate thyroid pathologies on infrared hyperspectral images

BACKGROUND AND OBJECTIVE

The thyroid is a gland responsible for producing important body hormones. Several pathologies can affect this gland, such as thyroiditis, hypothyroidism, and thyroid cancer. The visual histological analysis of thyroid specimens is a valuable process that enables pathologists to detect diseases with high efficiency, providing the patient with a better prognosis. Existing computer vision systems developed to aid in the analysis of histological samples have limitations in distinguishing pathologies with similar characteristics or samples containing multiple diseases. To overcome this challenge, hyperspectral images are being studied to represent biological samples based on their molecular interaction with light.

METHODS

In this study, we address the acquisition of infrared absorbance spectra from each voxel of histological specimens. This data is then used for the development of a multiclass fully-connected neural network model that discriminates spectral patterns, enabling the classification of voxels as healthy, cancerous, or goiter.

RESULTS

Through experiments using the k-fold cross-validation protocol, we obtained an average accuracy of 93.66 %, a sensitivity of 93.47 %, and a specificity of 96.93 %. Our results demonstrate the feasibility of using infrared hyperspectral imaging to characterize healthy tissue and thyroid pathologies using absorbance measurements. The proposed deep learning model has the potential to improve diagnostic efficiency and enhance patient outcomes.

An Ensemble Learning Method for Detection of Head and Neck Squamous Cell Carcinoma Using Polarized Hyperspectral Microscopic Imaging

Head and neck squamous cell carcinoma (HNSCC) has a high mortality rate. In this study, we developed a Stokes-vector-derived polarized hyperspectral imaging (PHSI) system for H&E-stained pathological slides with HNSCC and built a dataset to develop a deep learning classification method based on convolutional neural networks (CNN). We use our polarized hyperspectral microscope to collect the four Stokes parameter hypercubes (S0, S1, S2, and S3) from 56 patients and synthesize pseudo-RGB images using a transformation function that approximates the human eye's spectral response to visual stimuli. Each image is divided into patches. Data augmentation is applied using rotations and flipping. We create a four-branch model architecture where each branch is trained on one Stokes parameter individually, then we freeze the branches and fine-tune the top layers of our model to generate final predictions. Our results show high accuracy, sensitivity, and specificity, indicating that our model performed well on our dataset. Future works can improve upon these results by training on more varied data, classifying tumors based on their grade, and introducing more recent architectural techniques.

Polarized Hyperspectral Microscopic Imaging for Zebrafish

Zebrafish is a well-established animal model for developmental and disease studies. Its optical transparency at early developmental stages is ideal for tissue visualization. Interaction of light with zebrafish tissues provides information on their structure and properties. In this study, we developed a microscopic imaging system for improving the visualization of unstained zebrafish tissues on tissue slides, with two different setups: polarized light imaging and polarized hyperspectral imaging. Based on the polarized light imaging setup, we collected the RGB images of Stokes vector parameters (S0, S1, S2, and S3), and calculated the Stokes vector derived parameters: the degree of polarization (DOP), the degree of linear polarization (DOLP)). We also calculated Stokes vector data based on the polarized hyperspectral imaging setup. The preliminary results demonstrate that Stokes vector data in two imaging setups (polarized light imaging and polarized hyperspectral imaging) are capable of improving the visualization of different types of zebrafish tissues (brain, muscle, skin cells, blood vessels, and yolk). Using the images collected from larval zebrafish samples by polarized light imaging, we found that DOP and DOLP could show clearer structural information of the brain and of skin cells, muscle and blood vessels in the tail. Furthermore, DOP and DOLP parameters derived from images collected by polarized hyperspectral imaging could show clearer structural information of skin cells developing around yolk as well as the surrounding blood vessel network. In addition, polarized hyperspectral imaging could provide complementary spectral information to the spatial information on Stokes vector data of zebrafish tissues. The polarized light imaging & polarized hyperspectral imaging systems provide a better insight into the microstructures of zebrafish tissues.

Near-Infrared II Hyperspectral Imaging Improves the Accuracy of Pathological Sampling of Multiple Cancer Types

Pathological histology is the "gold standard" for clinical diagnosis of cancer. Incomplete or excessive sampling of the formalin-fixed excised cancer specimen will result in inaccurate histologic assessment or excessive workload. Conventionally, pathologists perform specimen sampling relying on naked-eye observation, which is subjective and limited by human perception. Precise identification of cancer tissue, size, and margin is challenging, especially for lesions with inconspicuous tumors. To overcome the limits of human eye perception (visible: 400-700 nm) and improve the sampling efficiency, in this study, we propose using a second near-infrared window (NIR-II: 900-1700 nm) hyperspectral imaging (HSI) system to assist specimen sampling on the strength of the verified deep anatomical penetration and low scattering characteristics of the NIR-II optical window. We used selected NIR-II HSI narrow bands to synthesize color images for human eye observation and also applied a machine learning-based algorithm on the complete NIR-II HSI data for automatic tissue classification to assist pathologists in specimen sampling. A total of 92 tumor samples were collected, including 7 types. Sixty-two (62/92) samples were used as the validation set. Five experienced pathologists marked the contour of the cancer tissue on conventional color images by using different methods, and compared it with the "gold standard," showing that NIR-II HSI-assisted methods had significant improvements in determining cancer tissue compared with conventional methods (conventional color image with or without X-ray). The proposed system can be easily integrated into the current workflow, with high imaging efficiency and no ionizing radiation. It may also find applications in intraoperative detection of residual lesions and identification of different tissues.

Emerging clinical applications in oncology for non-invasive multi- and hyperspectral imaging of cell and tissue autofluorescence

Hyperspectral and multispectral imaging of cell and tissue autofluorescence is an emerging technology in which fluorescence imaging is applied to biological materials across multiple spectral channels. This produces a stack of images where each matched pixel contains information about the sample's spectral properties at that location. This allows precise collection of molecularly specific data from a broad range of native fluorophores. Importantly, complex information, directly reflective of biological status, is collected without staining and tissues can be characterised in situ, without biopsy. For oncology, this can spare the collection of biopsies from sensitive regions and enable accurate tumour mapping. For in vivo tumour analysis, the greatest focus has been on oral cancer, whereas for ex vivo assessment head-and-neck cancers along with colon cancer have been the most studied, followed by oral and eye cancer. This review details the scope and progress of research undertaken towards clinical translation in oncology.

The value of deep neural networks in the pathological classification of thyroid tumors

BACKGROUND

To explore the distinguishing diagnostic value and clinical application potential of deep neural networks (DNN) for pathological images of thyroid tumors.

METHODS

A total of 799 pathological thyroid images of 559 patients with thyroid tumors were retrospectively analyzed. The pathological types included papillary thyroid carcinoma (PTC), medullary thyroid carcinoma (MTC), follicular thyroid carcinoma (FTC), adenomatous goiter, adenoma, and normal thyroid gland. The dataset was divided into a training set and a test set. Resnet50, Resnext50, EfficientNet, and Densenet121 were trained using the training set data and tested with the test set data to determine the diagnostic efficiency of different pathology types and to further analyze the causes of misdiagnosis.

RESULTS

The recall, precision, negative predictive value (NPV), accuracy, specificity, and F1 scores of the four models ranged from 33.33% to 100.00%. The area under curve (AUC) ranged from 0.822 to 0.994, and the Kappa coefficient ranged from 0.7508 to 0.7713. However, the performance of diagnosing FTC, adenoma, and adenomatous goiter was slightly inferior to other types of pathological tissues.

CONCLUSION

The DNN model achieved satisfactory results in the task of classifying thyroid tumors by learning thyroid pathology images. These results indicate the potential of the DNN model for the efficient diagnosis of thyroid tumor histopathology.

Systematic meta-analysis of computer-aided detection to detect early esophageal cancer using hyperspectral imaging

One of the leading causes of cancer deaths is esophageal cancer (EC) because identifying it in early stage is challenging. Computer-aided diagnosis (CAD) could detect the early stages of EC have been developed in recent years. Therefore, in this study, complete meta-analysis of selected studies that only uses hyperspectral imaging to detect EC is evaluated in terms of their diagnostic test accuracy (DTA). Eight studies are chosen based on the Quadas-2 tool results for systematic DTA analysis, and each of the methods developed in these studies is classified based on the nationality of the data, artificial intelligence, the type of image, the type of cancer detected, and the year of publishing. Deeks' funnel plot, forest plot, and accuracy charts were made. The methods studied in these articles show the automatic diagnosis of EC has a high accuracy, but external validation, which is a prerequisite for real-time clinical applications, is lacking.

Tissue Classification of Breast Cancer by Hyperspectral Unmixing

(1) Background: Assessing the resection margins during breast-conserving surgery is an important clinical need to minimize the risk of recurrent breast cancer. However, currently there is no technique that can provide real-time feedback to aid surgeons in the margin assessment. Hyperspectral imaging has the potential to overcome this problem. To classify resection margins with this technique, a tissue discrimination model should be developed, which requires a dataset with accurate ground-truth labels. However, establishing such a dataset for resection specimens is difficult. (2) Methods: In this study, we therefore propose a novel approach based on hyperspectral unmixing to determine which pixels within hyperspectral images should be assigned to the ground-truth labels from histopathology. Subsequently, we use this hyperspectral-unmixing-based approach to develop a tissue discrimination model on the presence of tumor tissue within the resection margins of ex vivo breast lumpectomy specimens. (3) Results: In total, 372 measured locations were included on the lumpectomy resection surface of 189 patients. We achieved a sensitivity of 0.94, specificity of 0.85, accuracy of 0.87, Matthew's correlation coefficient of 0.71, and area under the curve of 0.92. (4) Conclusion: Using this hyperspectral-unmixing-based approach, we demonstrated that the measured locations with hyperspectral imaging on the resection surface of lumpectomy specimens could be classified with excellent performance.

Conditional Generative Adversarial Network (cGAN) for Synthesis of Digital Histologic Images from Hyperspectral Images

Hyperspectral imaging (HSI) has been demonstrated in various digital pathology applications. However, the intrinsic high dimensionality of hyperspectral images makes it difficult for pathologists to visualize the information. The aim of this study is to develop a method to transform hyperspectral images of hemoxylin & eosin (H&E)-stained slides to natural-color RGB histologic images for easy visualization. Hyperspectral images were obtained at 40× magnification with an automated microscopic imaging system and downsampled by various factors to generate data equivalent to different magnifications. High-resolution digital histologic RGB images were cropped and registered to the corresponding hyperspectral images as the ground truth. A conditional generative adversarial network (cGAN) was trained to output natural color RGB images of the histological tissue samples. The generated synthetic RGBs have similar color and sharpness to real RGBs. Image classification was implemented using the real and synthetic RGBs, respectively, with a pretrained network. The classification of tumor and normal tissue using the HSI-synthesized RGBs yielded a comparable but slightly higher accuracy and AUC than the real RGBs. The proposed method can reduce the acquisition time of two imaging modalities while giving pathologists access to the high information density of HSI and the quality visualization of RGBs. This study demonstrated that HSI may provide a potentially better alternative to current RGB-based pathologic imaging and thus make HSI a viable tool for histopathological diagnosis.

Polarized hyperspectral microscopic imaging for collagen visualization on pathologic slides of head and neck squamous cell carcinoma

We developed a polarized hyperspectral microscope to collect four types of Stokes vector data cubes (S0, S1, S2, and S3) of the pathologic slides with head and neck squamous cell carcinoma (HNSCC). Our system consists of an optical light microscope with a movable stage, two polarizers, two liquid crystal variable retarders (LCVRs), and a SnapScan hyperspectral camera. The polarizers and LCVRs work in tandem with the hyperspectral camera to acquire polarized hyperspectral images. Synthetic pseudo-RGB images are generated from the four Stokes vector data cubes based on a transformation function similar to the spectral response of human eye for the visualization of hyperspectral images. Collagen is the most abundant extracellular matrix (ECM) protein in the human body. A major focus of studying the ECM in tumor microenvironment is the role of collagen in both normal and abnormal function. Collagen tends to accumulate in and around tumors during cancer development and growth. In this study, we acquired images from normal regions containing normal cells and collagen fibers and from tumor regions containing cancerous squamous cells and collagen fibers on HNSCC pathologic slides. The preliminary results demonstrated that our customized polarized hyperspectral microscope is able to improve the visualization of collagen on HNSCC pathologic slides under different situations, including thick fibers of normal stroma, thin fibers of normal stroma, fibers of normal muscle cells, fibers accumulated in tumors, fibers accumulated around tumors. Our preliminary results also demonstrated that the customized polarized hyperspectral microscope is capable of extracting the spectral signatures of collagen based on Stokes vector parameters and can have various applications in pathology and oncology.

Trends in AI-powered Classification of Thyroid Neoplasms Based on Histopathology Images - a Systematic Review

Background

Assessment of thyroid nodules histopathology using AI is crucial for an accurate diagnosis. This systematic review analyzes recent works employing deep learning approaches for classifying thyroid nodules based on histopathology images, evaluating their performance, and identifying limitations.

Methods

Eligibility criteria focused on peer-reviewed English papers published in the last 5 years, applying deep learning to categorize thyroid histopathology images. The PubMed database was searched using relevant keyword combinations.

Results

Out of 103 articles, 11 studies met inclusion criteria. They used convolutional neural networks to classify thyroid neoplasm. Most studies aimed for basic tumor subtyping; however, 3 studies targeted the prediction of tumor-associated mutation. Accuracy ranged from 77% to 100%, with most over 90%.

Discussion

The findings from our analysis reveal the effectiveness of deep learning in identifying discriminative morphological patterns from histopathology images, thus enhancing the accuracy of thyroid nodule histopathological classification. Key limitations were small sample sizes, subjective annotation, and limited dataset diversity. Further research with larger diverse datasets, model optimization, and real-world validation is essential to translate these tools into clinical practice.

Signal to noise ratio quantifies the contribution of spectral channels to classification of human head and neck tissues ex vivo using deep learning and multispectral imaging

SIGNIFICANCE

Accurate identification of tissues is critical for performing safe surgery. Combining multispectral imaging (MSI) with deep learning is a promising approach to increasing tissue discrimination and classification. Evaluating the contributions of spectral channels to tissue discrimination is important for improving MSI systems.

AIM

Develop a metric to quantify the contributions of individual spectral channels to tissue classification in MSI.

APPROACH

MSI was integrated into a digital operating microscope with three sensors and seven illuminants. Two convolutional neural network (CNN) models were trained to classify 11 head and neck tissue types using white light (RGB) or MSI images. The signal to noise ratio (SNR) of spectral channels was compared with the impact of channels on tissue classification performance as determined using CNN visualization methods.

RESULTS

Overall tissue classification accuracy was higher with use of MSI images compared with RGB images, both for classification of all 11 tissue types and binary classification of nerve and parotid ( p < 0.001 ). Removing spectral channels with SNR > 20 reduced tissue classification accuracy.

CONCLUSIONS

The spectral channel SNR is a useful metric for both understanding CNN tissue classification and quantifying the contributions of different spectral channels in an MSI system.

Deep Learning in Medical Hyperspectral Images: A Review

With the continuous progress of development, deep learning has made good progress in the analysis and recognition of images, which has also triggered some researchers to explore the area of combining deep learning with hyperspectral medical images and achieve some progress. This paper introduces the principles and techniques of hyperspectral imaging systems, summarizes the common medical hyperspectral imaging systems, and summarizes the progress of some emerging spectral imaging systems through analyzing the literature. In particular, this article introduces the more frequently used medical hyperspectral images and the pre-processing techniques of the spectra, and in other sections, it discusses the main developments of medical hyperspectral combined with deep learning for disease diagnosis. On the basis of the previous review, tne limited factors in the study on the application of deep learning to hyperspectral medical images are outlined, promising research directions are summarized, and the future research prospects are provided for subsequent scholars.

Visible near-infrared hyperspectral imaging and supervised classification for the detection of small intestinal necrosis tissue in vivo

Complete recognition of necrotic areas during small bowel tissue resection remains challenging due to the lack of optimal intraoperative aid identification techniques. This research utilizes hyperspectral imaging techniques to automatically distinguish normal and necrotic areas of small intestinal tissue. Sample data were obtained from the animal model of small intestinal tissue of eight Japanese large-eared white rabbits developed by experienced physicians. A spectral library of normal and necrotic regions of small intestinal tissue was created and processed using six different supervised classification algorithms. The results show that hyperspectral imaging combined with supervised classification algorithms can be a suitable technique to automatically distinguish between normal and necrotic areas of small intestinal tissue. This new technique could aid physicians in objectively identify normal and necrotic areas of small intestinal tissue.

Hyperspectral imaging for tumor segmentation on pigmented skin lesions

SIGNIFICANCE

Malignant skin tumors, which include melanoma and nonmelanoma skin cancers, are the most prevalent type of malignant tumor. Gross pathology of pigmented skin lesions (PSL) remains manual, time-consuming, and heavily dependent on the expertise of the medical personnel. Hyperspectral imaging (HSI) can assist in the detection of tumors and evaluate the status of tumor margins by their spectral signatures.

AIM

Tumor segmentation of medical HSI data is a research field. The goal of this study is to propose a framework for HSI-based tumor segmentation of PSL.

APPROACH

An HSI dataset of 28 PSL was prepared. Two frameworks for data preprocessing and tumor segmentation were proposed. Models based on machine learning and deep learning were used at the core of each framework.

RESULTS

Cross-validation performance showed that pixel-wise processing achieves higher segmentation performance, in terms of the Jaccard coefficient. Simultaneous use of spatio-spectral features produced more comprehensive tumor masks. A three-dimensional Xception-based network achieved performance similar to state-of-the-art networks while allowing for more detailed detection of the tumor border.

CONCLUSIONS

Good performance was achieved for melanocytic lesions, but margins were difficult to detect in some cases of basal cell carcinoma. The frameworks proposed in this study could be further improved for robustness against different pathologies and detailed delineation of tissue margins to facilitate computer-assisted diagnosis during gross pathology.

Review on the Application of Hyperspectral Imaging Technology of the Exposed Cortex in Cerebral Surgery

The study of brain science is vital to human health. The application of hyperspectral imaging in biomedical fields has grown dramatically in recent years due to their unique optical imaging method and multidimensional information acquisition. Hyperspectral imaging technology can acquire two-dimensional spatial information and one-dimensional spectral information of biological samples simultaneously, covering the ultraviolet, visible and infrared spectral ranges with high spectral resolution, which can provide diagnostic information about the physiological, morphological and biochemical components of tissues and organs. This technology also presents finer spectral features for brain imaging studies, and further provides more auxiliary information for cerebral disease research. This paper reviews the recent advance of hyperspectral imaging in cerebral diagnosis. Firstly, the experimental setup, image acquisition and pre-processing, and analysis methods of hyperspectral technology were introduced. Secondly, the latest research progress and applications of hyperspectral imaging in brain tissue metabolism, hemodynamics, and brain cancer diagnosis in recent years were summarized briefly. Finally, the limitations of the application of hyperspectral imaging in cerebral disease diagnosis field were analyzed, and the future development direction was proposed.

Hyperspectral and multispectral image processing for gross-level tumor detection in skin lesions: a systematic review

SIGNIFICANCE

Skin cancer is one of the most prevalent cancers worldwide. In the advent of medical digitization and telepathology, hyper/multispectral imaging (HMSI) allows for noninvasive, nonionizing tissue evaluation at a macroscopic level.

AIM

We aim to summarize proposed frameworks and recent trends in HMSI-based classification and segmentation of gross-level skin tissue.

APPROACH

A systematic review was performed, targeting HMSI-based systems for the classification and segmentation of skin lesions during gross pathology, including melanoma, pigmented lesions, and bruises. The review adhered to the 2020 Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines. For eligible reports published from 2010 to 2020, trends in HMSI acquisition, preprocessing, and analysis were identified.

RESULTS

HMSI-based frameworks for skin tissue classification and segmentation vary greatly. Most reports implemented simple image processing or machine learning, due to small training datasets. Methodologies were evaluated on heavily curated datasets, with the majority targeting melanoma detection. The choice of preprocessing scheme influenced the performance of the system. Some form of dimension reduction is commonly applied to avoid redundancies that are inherent in HMSI systems.

CONCLUSIONS

To use HMSI for tumor margin detection in practice, the focus of system evaluation should shift toward the explainability and robustness of the decision-making process.

Differential diagnostic value of the ResNet50, random forest, and DS ensemble models for papillary thyroid carcinoma and other thyroid nodules

Objective To explore the differential diagnostic efficiency of the residual network (ResNet)50, random forest (RF), and DS ensemble models for papillary thyroid carcinoma (PTC) and other pathological types of thyroid nodules.

Methods This study retrospectively analyzed 559 patients with thyroid nodules and collected thyroid pathological images and auxiliary examination results (laboratory and ultrasound results) to construct datasets. The pathological image dataset was used to train a ResNet50 model, the text dataset was used to train a random forest (RF) model, and a DS ensemble model was constructed from the results of the two models. The differential diagnostic values of the three models for PTC and other types of thyroid nodules were then compared.

Results The DS ensemble model had the highest sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (85.87%, 97.18%, 93.77%, and 0.982, respectively).

Conclusions Compared with Resnet50 and the RF models trained only on imaging data or text information, respectively, the DS ensemble model showed better diagnostic value for PTC.

Tumor cell identification and classification in esophageal adenocarcinoma specimens by hyperspectral imaging

Esophageal cancer is the sixth leading cause of cancer-related death worldwide. Histopathological confirmation is a key step in tumor diagnosis. Therefore, simplification in decision-making by discrimination between malignant and non-malignant cells of histological specimens can be provided by combination of new imaging technology and artificial intelligence (AI). In this work, hyperspectral imaging (HSI) data from 95 patients were used to classify three different histopathological features (squamous epithelium cells, esophageal adenocarcinoma (EAC) cells, and tumor stroma cells), based on a multi-layer perceptron with two hidden layers. We achieved an accuracy of 78% for EAC and stroma cells, and 80% for squamous epithelium. HSI combined with machine learning algorithms is a promising and innovative technique, which allows image acquisition beyond Red–Green–Blue (RGB) images. Further method validation and standardization will be necessary, before automated tumor cell identification algorithms can be used in daily clinical practice.

Automatic detection of head and neck squamous cell carcinoma on pathologic slides using polarized hyperspectral imaging and deep learning

The study is to incorporate polarized hyperspectral imaging (PHSI) with deep learning for automatic detection of head and neck squamous cell carcinoma (SCC) on hematoxylin and eosin (H&E) stained tissue slides. A polarized hyperspectral imaging microscope had been developed in our group. In this paper, we firstly collected the Stokes vector data cubes (S0, S1, S2, and S3) of histologic slides from 17 patients with SCC by the PHSI microscope, under the wavelength range from 467 nm to 750 nm. Secondly, we generated the synthetic RGB images from the original Stokes vector data cubes. Thirdly, we cropped the synthetic RGB images into image patches at the image size of 96×96 pixels, and then set up a ResNet50-based convolutional neural network (CNN) to classify the image patches of the four Stokes vector parameters (S0, S1, S2, and S3) by application of transfer learning. To test the performances of the model, each time we trained the model based on the image patches (S0, S1, S2, and S3) of 16 patients out of 17 patients, and used the trained model to calculate the testing accuracy based on the image patches of the rest 1 patient (S0, S1, S2, and S3). We repeated the process for 6 times and obtained 24 testing accuracies (S0, S1, S2, and S3) from 6 different patients out of the 17 patients. The preliminary results showed that the average testing accuracy (84.2%) on S3 outperformed the average testing accuracy (83.5%) on S0. Furthermore, 4 of 6 testing accuracies of S3 (96.0%, 87.3%, 82.8%, and 86.7%) outperformed the testing accuracies of S0 (93.3%, 85.2%, 80.2%, and 79.0%). The study demonstrated the potential of using polarized hyperspectral imaging and deep learning for automatic detection of head and neck SCC on pathologic slides.

Detecting Aggressive Papillary Thyroid Carcinoma Using Hyperspectral Imaging and Radiomic Features

Hyperspectral imaging (HSI) and radiomics have the potential to improve the accuracy of tumor malignancy prediction and assessment. In this work, we extracted radiomic features of fresh surgical papillary thyroid carcinoma (PTC) specimen that were imaged with HSI. A total of 107 unique radiomic features were extracted. This study includes 72 ex-vivo tissue specimens from 44 patients with pathology-confirmed PTC. With the dilated hyperspectral images, the shape feature of least axis length was able to predict the tumor aggressiveness with a high accuracy. The HSI-based radiomic method may provide a useful tool to aid oncologists in determining tumors with intermediate to high risk and in clinical decision making.

Unsupervised Super Resolution Network for Hyperspectral Histologic Imaging

Hyperspectral imaging (HSI) has many advantages in microscopic applications, including high sensitivity and specificity for cancer detection on histological slides. However, acquiring hyperspectral images of a whole slide with a high image resolution and a high image quality can take a long scanning time and require a very large data storage. One potential solution is to acquire and save low-resolution hyperspectral images and reconstruct the high-resolution ones only when needed. The purpose of this study is to develop a simple yet effective unsupervised super resolution network for hyperspectral histologic imaging with the guidance of RGB digital histology images. High-resolution hyperspectral images of hemoxylin & eosin (H&E) stained slides were obtained at 10× magnification and down-sampled 2×, 4×, and 5× to generate low-resolution hyperspectral data. High-resolution digital histologic RGB images of the same field of view (FOV) were cropped and registered to the corresponding high-resolution hyperspectral images. A neural network based on a modified U-Net architecture, which takes the low-resolution hyperspectral images and high-resolution RGB images as inputs, was trained with unsupervised methods to output high-resolution hyperspectral data. The generated high-resolution hyperspectral images have similar spectral signatures and improved image contrast than the original high-resolution hyperspectral images, which indicates that the super resolution network with RGB guidance can improve the image quality. The proposed method can reduce the acquisition time and save storage space taken up by hyperspectral images without compromising image quality, which will potentially promote the use of hyperspectral imaging technology in digital pathology and many other clinical applications.

Hyperspectral Imaging for Clinical Applications

Measuring morphological and biochemical features of tissue is crucial for disease diagnosis and surgical guidance, providing clinically significant information related to pathophysiology. Hyperspectral imaging (HSI) techniques obtain both spatial and spectral features of tissue without labeling molecules such as fluorescent dyes, which provides rich information for improved disease diagnosis and treatment. Recent advances in HSI systems have demonstrated its potential for clinical applications, especially in disease diagnosis and image-guided surgery. This review summarizes the basic principle of HSI and optical systems, deep-learning-based image analysis, and clinical applications of HSI to provide insight into this rapidly growing field of research. In addition, the challenges facing the clinical implementation of HSI techniques are discussed.

Coded Aperture Hyperspectral Image Reconstruction

In this work, we study and analyze the reconstruction of hyperspectral images that are sampled with a CASSI device. The sensing procedure was modeled with the help of the CS theory, which enabled efficient mechanisms for the reconstruction of the hyperspectral images from their compressive measurements. In particular, we considered and compared four different type of estimation algorithms: OMP, GPSR, LASSO, and IST. Furthermore, the large dimensions of hyperspectral images required the implementation of a practical block CASSI model to reconstruct the images with an acceptable delay and affordable computational cost. In order to consider the particularities of the block model and the dispersive effects in the CASSI-like sensing procedure, the problem was reformulated, as well as the construction of the variables involved. For this practical CASSI setup, we evaluated the performance of the overall system by considering the aforementioned algorithms and the different factors that impacted the reconstruction procedure. Finally, the obtained results were analyzed and discussed from a practical perspective.

Deep Learning Analysis of In Vivo Hyperspectral Images for Automated Intraoperative Nerve Detection

Nerves are critical structures that may be difficult to recognize during surgery. Inadvertent nerve injuries can have catastrophic consequences for the patient and lead to life-long pain and a reduced quality of life. Hyperspectral imaging (HSI) is a non-invasive technique combining photography with spectroscopy, allowing non-invasive intraoperative biological tissue property quantification. We show, for the first time, that HSI combined with deep learning allows nerves and other tissue types to be automatically recognized in in vivo hyperspectral images. An animal model was used, and eight anesthetized pigs underwent neck midline incisions, exposing several structures (nerve, artery, vein, muscle, fat, skin). State-of-the-art machine learning models were trained to recognize these tissue types in HSI data. The best model was a convolutional neural network (CNN), achieving an overall average sensitivity of 0.91 and a specificity of 1.0, validated with leave-one-patient-out cross-validation. For the nerve, the CNN achieved an average sensitivity of 0.76 and a specificity of 0.99. In conclusion, HSI combined with a CNN model is suitable for in vivo nerve recognition.

Explainable liver tumor delineation in surgical specimens using hyperspectral imaging and deep learning

Surgical removal is the primary treatment for liver cancer, but frequent recurrence caused by residual malignant tissue remains an important challenge, as recurrence leads to high mortality. It is unreliable to distinguish tumors from normal tissues merely under visual inspection. Hyperspectral imaging (HSI) has been proved to be a promising technology for intra-operative use by capturing the spatial and spectral information of tissue in a fast, non-contact and label-free manner. In this work, we investigated the feasibility of HSI for liver tumor delineation on surgical specimens using a multi-task U-Net framework. Measurements are performed on 19 patients and a dataset of 36 specimens was collected with corresponding pathological results serving as the ground truth. The developed framework can achieve an overall sensitivity of 94.48% and a specificity of 87.22%, outperforming the baseline SVM method by a large margin. In particular, we propose to add explanations on the well-trained model from the spatial and spectral dimensions to show the contribution of pixels and spectral channels explicitly. On that basis, a novel saliency-weighted channel selection method is further proposed to select a small subset of 5 spectral channels which provide essentially as much information as using all 224 channels. According to the dominant channels, the absorption difference of hemoglobin and bile content in the normal and malignant tissues seems to be promising markers that could be further exploited.

Membranous nephropathy classification using microscopic hyperspectral imaging and tensor patch-based discriminative linear regression

Optical kidney biopsy, serological examination, and clinical symptoms are the main methods for membranous nephropathy (MN) diagnosis. However, false positives and undetectable biochemical components in the results of optical inspections lead to unsatisfactory diagnostic sensitivity and pose obstacles to pathogenic mechanism analysis. In order to reveal detailed component information of immune complexes of MN, microscopic hyperspectral imaging technology is employed to establish a hyperspectral database of 68 patients with two types of MN. Based on the characteristic of the medical HSI, a novel framework of tensor patch-based discriminative linear regression (TDLR) is proposed for MN classification. Experimental results show that the classification accuracy of the proposed model for MN identification is 98.77%. The combination of tensor-based classifiers and hyperspectral data analysis provides new ideas for the research of kidney pathology, which has potential clinical value for the automatic diagnosis of MN.

Imaging-based navigation technologies in head and neck surgery

PURPOSE OF REVIEW

Image guided navigation has had significant impact in head and neck surgery, and has been most prolific in endonasal surgeries. Although conventional image guidance involves static computed tomography (CT) images attained in the preoperative setting, the continual evolution of surgical navigation technologies is fast expanding to incorporate both real-time data and bioinformation that allows for improved precision in surgical guidance. With the rapid advances in technologies, this article allows for a timely review of the current and developing techniques in surgical navigation for head and neck surgery.

RECENT FINDINGS

Current advances for cross-sectional-based image-guided surgery include fusion of CT with other imaging modalities (e.g., magnetic resonance imaging and positron emission tomography) as well as the uptake in intraoperative real-time 'on the table' imaging (e.g., cone-beam CT). These advances, together with the integration of virtual/augmented reality, enable potential enhancements in surgical navigation. In addition to the advances in radiological imaging, the development of optical modalities such as fluorescence and spectroscopy techniques further allows the assimilation of biological data to improve navigation particularly for head and neck surgery.

SUMMARY

The steady development of radiological and optical imaging techniques shows great promise in changing the paradigm of head and neck surgery.

Tongue Tumor Detection in Hyperspectral Images Using Deep Learning Semantic Segmentation

OBJECTIVE

The utilization of hyperspectral imaging (HSI) in real-time tumor segmentation during a surgery have recently received much attention, but it remains a very challenging task.

METHODS

In this work, we propose semantic segmentation methods, and compare them with other relevant deep learning algorithms for tongue tumor segmentation. To the best of our knowledge, this is the first work using deep learning semantic segmentation for tumor detection in HSI data using channel selection, and accounting for more spatial tissue context, and global comparison between the prediction map, and the annotation per sample. Results, and Conclusion: On a clinical data set with tongue squamous cell carcinoma, our best method obtains very strong results of average dice coefficient, and area under the ROC-curve of [Formula: see text], and [Formula: see text], respectively on the original spatial image size. The results show that a very good performance can be achieved even with a limited amount of data. We demonstrate that important information regarding tumor decision is encoded in various channels, but some channel selection, and filtering is beneficial over the full spectra. Moreover, we use both visual (VIS), and near-infrared (NIR) spectrum, rather than commonly used only VIS spectrum; although VIS spectrum is generally of higher significance, we demonstrate NIR spectrum is crucial for tumor capturing in some cases.

SIGNIFICANCE

The HSI technology augmented with accurate deep learning algorithms has a huge potential to be a promising alternative to digital pathology or a doctors' supportive tool in real-time surgeries.

[New Trends of Development in Precision Pathological Diagnosis Promoted by Artificial Intelligence]

Precision pathological diagnosis plays a vital role in precision medicine. Both the limited resources available to pathologists and the incessant demands for further refinement and quantification of clinical diagnosis are posing new challenges for pathologists to meet the needs for precision pathological diagnosis. It is expected that artificial intelligence (AI) will be the powerful tool that will help find solutions to this problem from different angles. The author of this article elaborated on a number of ways in which AI can help promote precision pathological diagnosis, including AI-assisted precision extraction of tissue samples, AI-assisted precision histopathologic diagnosis, AI-assisted histological grading and quantitative scoring, AI-assisted precision assessment of tumor biomarkers, AI-assisted prediction of molecular features and precision interpretation of biological information based on hematoxylin-eosin (HE) stained images, the realization of in-depth precision diagnosis based on AI-assisted information integration, and AI-assisted accurate prediction of patient survival and prognosis based on HE-stained images. The paper presents to the readers the future of smart pathology that AI will help usher in.

Feedforward Artificial Neural Network-Based Colorectal Cancer Detection Using Hyperspectral Imaging: A Step towards Automatic Optical Biopsy

Simple Summary

Detection of colorectal carcinoma is performed visually by investigators and is confirmed pathologically. With hyperspectral imaging, an expanded spectral range of optical information is now available for analysis. The acquired recordings were analyzed with a neural network, and it was possible to differentiate tumor from healthy mucosa in colorectal carcinoma by automatic classification with high reliability. Classification and visualization were performed based on a four-layer perceptron neural network. Based on a neural network, the classification of CA or AD resulted in a sensitivity of 86% and a specificity of 95%, by means of leave-one-patient-out cross-validation. Additionally, significant differences in terms of perfusion parameters (e.g., oxygen saturation) related to tumor staging and neoadjuvant therapy were observed. This is a step towards optical biopsy.

Abstract

Currently, colorectal cancer (CRC) is mainly identified via a visual assessment during colonoscopy, increasingly used artificial intelligence algorithms, or surgery. Subsequently, CRC is confirmed through a histopathological examination by a pathologist. Hyperspectral imaging (HSI), a non-invasive optical imaging technology, has shown promising results in the medical field. In the current study, we combined HSI with several artificial intelligence algorithms to discriminate CRC. Between July 2019 and May 2020, 54 consecutive patients undergoing colorectal resections for CRC were included. The tumor was imaged from the mucosal side with a hyperspectral camera. The image annotations were classified into three groups (cancer, CA; adenomatous margin around the central tumor, AD; and healthy mucosa, HM). Classification and visualization were performed based on a four-layer perceptron neural network. Based on a neural network, the classification of CA or AD resulted in a sensitivity of 86% and a specificity of 95%, by means of leave-one-patient-out cross-validation. Additionally, significant differences in terms of perfusion parameters (e.g., oxygen saturation) related to tumor staging and neoadjuvant therapy were observed. Hyperspectral imaging combined with automatic classification can be used to differentiate between CRC and healthy mucosa. Additionally, the biological changes induced by chemotherapy to the tissue are detectable with HSI.

Deep Learning for Biospectroscopy and Biospectral Imaging: State-of-the-Art and Perspectives

With the advances in instrumentation and sampling techniques, there is an explosive growth of data from molecular and cellular samples. The call to extract more information from the large data sets has greatly challenged the conventional chemometrics method. Deep learning, which utilizes very large data sets for finding hidden features therein and for making accurate predictions for a wide range of applications, has been applied in an unbelievable pace in biospectroscopy and biospectral imaging in the recent 3 years. In this Feature, we first introduce the background and basic knowledge of deep learning. We then focus on the emerging applications of deep learning in the data preprocessing, feature detection, and modeling of the biological samples for spectral analysis and spectroscopic imaging. Finally, we highlight the challenges and limitations in deep learning and the outlook for future directions.

Automatic detection of head and neck squamous cell carcinoma on pathologic slides using polarized hyperspectral imaging and machine learning

The aim of this study is to incorporate polarized hyperspectral imaging (PHSI) with machine learning for automatic detection of head and neck squamous cell carcinoma (SCC) on hematoxylin and eosin (H&E) stained tissue slides. A polarized hyperspectral imaging microscope had been developed in our group. In this paper, we imaged 20 H&E stained tissue slides from 10 patients with SCC of the larynx by the PHSI microscope. Several machine learning algorithms, including support vector machine (SVM), random forest, Gaussian naive Bayes, and logistic regression, were applied to the collected image data for the automatic detection of SCC on the H&E stained tissue slides. The performance of these methods was compared among the collected PHSI data, the pseudo-RGB images generated from the PHSI data, and the PHSI data after applying the principal component analysis (PCA) transformation. The results suggest that SVM is a superior classifier for the classification task based on the PHSI data cubes compared to the other three classifiers. The incorporate of four Stokes vector parameters improved the classification accuracy. Finally, the PCA transformed image data did not improve the accuracy as it might lose some important information from the original PHSI data. The preliminary results show that polarized hyperspectral imaging can have many potential applications in digital pathology.

Multiparametric Radiomics for Predicting the Aggressiveness of Papillary Thyroid Carcinoma Using Hyperspectral Images

Papillary thyroid carcinoma (PTC) is primarily treated by surgical resection. During surgery, surgeons often need intraoperative frozen analysis and pathologic consultation in order to detect PTC. In some cases pathologists cannot determine if the tumor is aggressive until the operation has been completed. In this work, we have taken tumor classification a step further by determining the tumor aggressiveness of fresh surgical specimens. We employed hyperspectral imaging (HSI) in combination with multiparametric radiomic features to complete this task. The study cohort includes 72 ex-vivo tissue specimens from 44 patients with pathology-confirmed PTC. A total of 67 features were extracted from this data. Using machine learning classification methods, we were able to achieve an AUC of 0.85. Our study shows that hyperspectral imaging and multiparametric radiomic features could aid in the pathological detection of tumor aggressiveness using fresh surgical spemens obtained during surgery.

Hyperspectral microscopy combined with DAPI staining for the identification of hepatic carcinoma cells

In this study, the DAPI staining is firstly reported for use in the identification of hepatic carcinoma cells based on hyperspectral microscopy. Nuclei in cancer cells usually contain more aneuploidies than that in normal cells, leading to the change of DNA content. Here, we stain hepatic carcinoma tissues and normal hepatic tissues with 4',6-diamidino-2-phenylindole (DAPI) which is sensitive to the DNA content as a fluorochrome binds to DNA. Consequently, the difference in DNA content between hepatic carcinoma cells and normal hepatic cells can be identified by the fluorescent spectral characteristics. Harnessing the hyperspectral microscopy, we find that the fluorescent properties of these two kinds of cells are different not only in the intensity but also in the spectral shape. These properties are exploited to train a support vector machine (SVM) model for classifying cells. The results show that the sensitivity and specificity for the identification of 1000 hepatic carcinoma samples are 99.3% and 99.1%, respectively.

Comprehensive review of surgical microscopes: technology development and medical applications

SIGNIFICANCE

Surgical microscopes provide adjustable magnification, bright illumination, and clear visualization of the surgical field and have been increasingly used in operating rooms. State-of-the-art surgical microscopes are integrated with various imaging modalities, such as optical coherence tomography (OCT), fluorescence imaging, and augmented reality (AR) for image-guided surgery.

AIM

This comprehensive review is based on the literature of over 500 papers that cover the technology development and applications of surgical microscopy over the past century. The aim of this review is threefold: (i) providing a comprehensive technical overview of surgical microscopes, (ii) providing critical references for microscope selection and system development, and (iii) providing an overview of various medical applications.

APPROACH

More than 500 references were collected and reviewed. A timeline of important milestones during the evolution of surgical microscope is provided in this study. An in-depth technical overview of the optical system, mechanical system, illumination, visualization, and integration with advanced imaging modalities is provided. Various medical applications of surgical microscopes in neurosurgery and spine surgery, ophthalmic surgery, ear-nose-throat (ENT) surgery, endodontics, and plastic and reconstructive surgery are described.

RESULTS

Surgical microscopy has been significantly advanced in the technical aspects of high-end optics, bright and shadow-free illumination, stable and flexible mechanical design, and versatile visualization. New imaging modalities, such as hyperspectral imaging, OCT, fluorescence imaging, photoacoustic microscopy, and laser speckle contrast imaging, are being integrated with surgical microscopes. Advanced visualization and AR are being added to surgical microscopes as new features that are changing clinical practices in the operating room.

CONCLUSIONS

The combination of new imaging technologies and surgical microscopy will enable surgeons to perform challenging procedures and improve surgical outcomes. With advanced visualization and improved ergonomics, the surgical microscope has become a powerful tool in neurosurgery, spinal, ENT, ophthalmic, plastic and reconstructive surgeries.

Diagnostic accuracy of deep-learning with anomaly detection for a small amount of imbalanced data: discriminating malignant parotid tumors in MRI

We hypothesized that, in discrimination between benign and malignant parotid gland tumors, high diagnostic accuracy could be obtained with a small amount of imbalanced data when anomaly detection (AD) was combined with deep leaning (DL) model and the L₂-constrained softmax loss. The purpose of this study was to evaluate whether the proposed method was more accurate than other commonly used DL or AD methods. Magnetic resonance (MR) images of 245 parotid tumors (22.5% malignant) were retrospectively collected. We evaluated the diagnostic accuracy of the proposed method (VGG16-based DL and AD) and that of classification models using conventional DL and AD methods. A radiologist also evaluated the MR images. ROC and precision-recall (PR) analyses were performed, and the area under the curve (AUC) was calculated. In terms of diagnostic performance, the VGG16-based model with the L₂-constrained softmax loss and AD (local outlier factor) outperformed conventional DL and AD methods and a radiologist (ROC-AUC = 0.86 and PR-ROC = 0.77). The proposed method could discriminate between benign and malignant parotid tumors in MR images even when only a small amount of data with imbalanced distribution is available.

Surgical Guidance for Removal of Cholesteatoma Using a Multispectral 3D-Endoscope

We develop a stereo-multispectral endoscopic prototype in which a filter-wheel is used for surgical guidance to remove cholesteatoma tissue in the middle ear. Cholesteatoma is a destructive proliferating tissue. The only treatment for this disease is surgery. Removal is a very demanding task, even for experienced surgeons. It is very difficult to distinguish between bone and cholesteatoma. In addition, it can even reoccur if not all tissue particles of the cholesteatoma are removed, which leads to undesirable follow-up operations. Therefore, we propose an image-based method that combines multispectral tissue classification and 3D reconstruction to identify all parts of the removed tissue and determine their metric dimensions intraoperatively. The designed multispectral filter-wheel 3D-endoscope prototype can switch between narrow-band spectral and broad-band white illumination, which is technically evaluated in terms of optical system properties. Further, it is tested and evaluated on three patients. The wavelengths 400 nm and 420 nm are identified as most suitable for the differentiation task. The stereoscopic image acquisition allows accurate 3D surface reconstruction of the enhanced image information. The first results are promising, as the cholesteatoma can be easily highlighted, correctly identified, and visualized as a true-to-scale 3D model showing the patient-specific anatomy.

Using hyperspectral imaging automatic classification of gastric cancer grading with a shallow residual network

The gastric cancer grading of patients determines their clinical treatment plan. We use hyperspectral imaging (HSI) gastric cancer section data to automatically classify the three different cancer grades (low grade, intermediate grade, and high grade) and healthy tissue. This paper proposed the use of HSI data combined with a shallow residual network (SR-Net) as the classifier. We collected hyperspectral data from gastric sections of 30 participants, with the wavelength range of hyperspectral data being 374 nm to 990 nm. We compared the classification results between hyperspectral data and color images. The results show that using hyperspectral data and a SR-Net an average classification accuracy of 91.44% could be achieved, which is 13.87% higher than that of the color image. In addition, we applied a modified SR-Net incorporated direct down-sampling, asymmetric filters, and global average pooling to reduce the parameters and floating-point operations. Compared with the regular residual network with the same number of blocks, the floating-point operations of a SR-Net are one order of magnitude less. The experimental results show that hyperspectral data with a SR-Net can achieve cutting-edge performance with minimum computational cost and therefore have potential in the study of gastric cancer grading.

Laparoscopic system for simultaneous high-resolution video and rapid hyperspectral imaging in the visible and near-infrared spectral range

SIGNIFICANCE

Hyperspectral imaging (HSI) can support intraoperative perfusion assessment, the identification of tissue structures, and the detection of cancerous lesions. The practical use of HSI for minimal-invasive surgery is currently limited, for example, due to long acquisition times, missing video, or large set-ups.

AIM

An HSI laparoscope is described and evaluated to address the requirements for clinical use and high-resolution spectral imaging.

APPROACH

Reflectance measurements with reference objects and resected human tissue from 500 to 1000 nm are performed to show the consistency with an approved medical HSI device for open surgery. Varying object distances are investigated, and the signal-to-noise ratio (SNR) is determined for different light sources.

RESULTS

The handheld design enables real-time processing and visualization of HSI data during acquisition within 4.6 s. A color video is provided simultaneously and can be augmented with spectral information from push-broom imaging. The reflectance data from the HSI system for open surgery at 50 cm and the HSI laparoscope are consistent for object distances up to 10 cm. A standard rigid laparoscope in combination with a customized LED light source resulted in a mean SNR of 30 to 43 dB (500 to 950 nm).

CONCLUSIONS

Compact and rapid HSI with a high spatial- and spectral-resolution is feasible in clinical practice. Our work may support future studies on minimally invasive HSI to reduce intra- and postoperative complications.