Identification of Melanoma From Hyperspectral Pathology Image Using 3D Convolutional Networks

LMTTM-VMI: Linked Memory Token Turing Machine for 3D volumetric medical image classification

Biomedical imaging is vital for the diagnosis and treatment of various medical conditions, yet the effective integration of deep learning technologies into this field presents challenges. Traditional methods often struggle to efficiently capture the spatial characteristics and intricate structural features of 3D volumetric medical images, limiting memory utilization and model adaptability. To address this, we introduce a Linked Memory Token Turing Machine (LMTTM), which utilizes external linked memory to efficiently process spatial dependencies and structural complexities within 3D volumetric medical images, aiding in accurate diagnoses. LMTTM can efficiently record the features of 3D volumetric medical images in an external linked memory module, enhancing complex image classification through improved feature accumulation and reasoning capabilities. Our experiments on six 3D volumetric medical image datasets from the MedMNIST v2 demonstrate that our proposed LMTTM model achieves average ACC of 82.4%, attaining state-of-the-art (SOTA) performance. Moreover, ablation studies confirmed that the Linked Memory outperforms its predecessor, TTM's original Memory, by up to 5.7%, highlighting LMTTM's effectiveness in 3D volumetric medical image classification and its potential to assist healthcare professionals in diagnosis and treatment planning. The code is released at https://github.com/hongkai-wei/LMTTM-VMI.

Deep learning-based hyperspectral technique identifies metastatic lymph nodes in oral squamous cell carcinoma-A pilot study

AIMS

To establish a system based on hyperspectral imaging and deep learning for the detection of cancer cells in metastatic lymph nodes.

MAIN METHODS

The continuous sections of metastatic lymph nodes from 45 oral squamous cell carcinoma (OSCC) patients were collected. An improved ResUNet algorithm was established for deep learning to analyze the spectral curve differences between cancer cells and lymphocytes, and that between tumor tissue and normal tissue.

KEY FINDINGS

It was found that cancer cells, lymphocytes, and erythrocytes in the metastatic lymph nodes could be distinguished basing hyperspectral image, with overall accuracy (OA) as 87.30% and average accuracy (AA) as 85.46%. Cancerous area could be recognized by hyperspectral image and deep learning, and the average intersection over union (IOU) and accuracy were 0.6253 and 0.7692, respectively.

SIGNIFICANCE

This study indicated that deep learning-based hyperspectral techniques can identify tumor tissue in OSCC metastatic lymph nodes, achieving high accuracy of pathological diagnosis, high work efficiency, and reducing work burden. But these are preliminary results limited to a small sample.

MT-SCnet: multi-scale token divided and spatial-channel fusion transformer network for microscopic hyperspectral image segmentation

Introduction

Hybrid architectures based on convolutional neural networks and Transformers, effectively captures both the local details and the overall structural context of lesion tissues and cells, achieving highly competitive segmentation results in microscopic hyperspectral image (MHSI) segmentation tasks. However, the fixed tokenization schemes and single-dimensional feature extraction and fusion in existing methods lead to insufficient global feature extraction in hyperspectral pathology images.

Methods

Base on this, we propose a multi-scale token divided and spatial-channel fusion transformer network (MT-SCnet) for MHSIs segmentation. Specifically, we first designed a Multi-Scale Token Divided module. It divides token at different scale based on mirror padding and promotes information interaction and fusion between different tokens to obtain more representative features for subsequent global feature extraction. Secondly, a novel spatial channel fusion transformer was designed to capture richer features from spatial and channel dimensions, and eliminates the semantic gap between features from different dimensions based on cross-attention fusion block. Additionally, to better restore spatial information, deformable convolutions were introduced in decoder.

Results

The Experiments on two MHSI datasets demonstrate that MT-SCnet outperforms the comparison methods.

Discussion

This advance has significant implications for the field of MHSIs segmentation. Our code is freely available at https://github.com/sharycao/MT-SCnet.

Towards reliable hyperspectral imaging biomarkers of CT26 murine tumor model

The non-invasive monitoring of tumor growth can offer invaluable diagnostic insights and enhance our understanding of tumors and their microenvironment. Integrating hyperspectral imaging (HSI) with three-dimensional optical profilometry (3D OP) makes contactless and non-invasive tumor diagnosis possible by utilizing the inherent tissue contrast provided by visible (VIS) and near-infrared (NIR) light. Consequently, valuable information regarding tumors and healthy tissues can be extracted from the acquired hyperspectral images. Until now, very few methods have been used to monitor tumor models in vivo daily and non-invasively. In this research, we conducted a 14-day study monitoring BALB/c mice with subcutaneously grown CT26 murine colon carcinomas in vivo, commencing on the day of tumor cell injection. We extracted physiological properties such as total hemoglobin (THB) and tissue oxygenation (StO 2 ) using the inverse adding-doubling (IAD) algorithm and manually segmented the tissues. We then selected the ten most relevant features describing tumors using the Max-Relevance Min-Redundancy (MRMR) algorithm and utilized 30 classic and advanced machine learning (ML) algorithms to discriminate tumors from healthy tissues. Finally, we tested the robustness of feature selection and model performance by smoothing tissue parameter maps extracted by IAD with a variable kernel and omitting selected training data. We could discriminate CT26 tumor models from surrounding healthy tissues with an area under the curve (AUC) of up to 1 for models based on the gradient boosting method, linear discriminant analysis, and random forests. Our findings help pave the way for precise and robust imaging biomarkers that could aid tumor diagnosis and advance clinical practice.

SPMLD: A skin pathological image dataset for non-melanoma with detailed lesion area annotation

Skin tumors are the most common tumors in humans and the clinical characteristics of three common non-melanoma tumors (IDN, SK, BCC) are similar, resulting in a high misdiagnosis rate. The accurate differential diagnosis of these tumors needs to be judged based on pathological images. However, a shortage of experienced dermatological pathologists leads to bias in the diagnostic accuracy of these skin tumors in China. In this paper, we establish a skin pathological image dataset, SPMLD, for three non-melanoma to achieve automatic and accurate intelligent identification for them. Meanwhile, we propose a lesion-area-based enhanced classification network with the KLS module and an attention module. Specifically, we first collect thousands of H&E-stained tissue sections from patients with clinically and pathologically confirmed IDN, SK, and BCC from a single-center hospital. Then, we scan them to construct a pathological image dataset of these three skin tumors. Furthermore, we mark the complete lesion area of the entire pathology image to better learn the pathologist's diagnosis process. In addition, we applied the proposed network for lesion classification prediction on the SPMLD dataset. Finally, we conduct a series of experiments to demonstrate that this annotation and our network can effectively improve the classification results of various networks. The source dataset and code are available at https://github.com/efss24/SPMLD.git.

TAJ-Net: a two-stage clustered cell segmentation network with adaptive joint learning of spatial and spectral information

Pulmonary adenocarcinoma is the primary cause of cancer-related death worldwide and pathological diagnosis is the "golden standard" based on the regional distribution of cells. Thus, regional cell segmentation is a key step while it is challenging due to the following reasons: 1) It is hard for pure semantic and instance segmentation methods to obtain a high-quality regional cell segmentation result; 2) Since the spatial appearances of pulmonary cells are very similar which even confuse pathologists, annotation errors are usually inevitable. Considering these challenges, we propose a two-stage 3D adaptive joint training framework (TAJ-Net) to segment-then-classify cells with extra spectral information as the supplementary information of spatial information. Firstly, we propose to leverage a few-shot method with limited data for cell mask acquisition to avoid the disturbance of cluttered backgrounds. Secondly, we introduce an adaptive joint training strategy to remove noisy samples through two 3D networks and one 1D network for cell type classification rather than segmentation. Subsequently, we propose a patch mapping method to map classification results to the original images to obtain regional segmentation results. In order to verify the effectiveness of TAJ-Net, we build two 3D hyperspectral datasets, i.e., pulmonary adenocarcinoma (3,660 images) and thyroid carcinoma (4623 images) with 40 bands. The first dataset will be released for further research. Experiments show that TAJ-Net achieves much better performance in clustered cell segmentation, and it can regionally segment different kinds of cells with high overlap and blurred edges, which is a difficult task for the state-of-the-art methods. Compared to 2D models, the hyperspectral image-based 3D model reports a significant improvement of up to 11.5% in terms of the Dice similarity coefficient in the pulmonary adenocarcinoma dataset.

A Self-Supervised Learning Based Framework for Eyelid Malignant Melanoma Diagnosis in Whole Slide Images

Eyelid malignant melanoma (MM) is a rare disease with high mortality. Accurate diagnosis of such disease is important but challenging. In clinical practice, the diagnosis of MM is currently performed manually by pathologists, which is subjective and biased. Since the heavy manual annotation workload, most pathological whole slide image (WSI) datasets are only partially labeled (without region annotations), which cannot be directly used in supervised deep learning. For these reasons, it is of great practical significance to design a laborsaving and high data utilization diagnosis method. In this paper, a self-supervised learning (SSL) based framework for automatically detecting eyelid MM is proposed. The framework consists of a self-supervised model for detecting MM areas at the patch-level and a second model for classifying lesion types at the slide level. A squeeze-excitation (SE) attention structure and a feature-projection (FP) structure are integrated to boost learning on details of pathological images and improve model performance. In addition, this framework also provides visual heatmaps with high quality and reliability to highlight the likely areas of the lesion to assist the evaluation and diagnosis of the eyelid MM. Extensive experimental results on different datasets show that our proposed method outperforms other state-of-the-art SSL and fully supervised methods at both patch and slide levels when only a subset of WSIs are annotated. It should be noted that our method is even comparable to supervised methods when all WSIs are fully annotated. To the best of our knowledge, our work is the first SSL method for automatic diagnosis of MM at the eyelid and has a great potential impact on reducing the workload of human annotations in clinical practice.

Classification of Benign-Malignant Thyroid Nodules Based on Hyperspectral Technology

In recent years, the incidence of thyroid cancer has rapidly increased. To address the issue of the inefficient diagnosis of thyroid cancer during surgery, we propose a rapid method for the diagnosis of benign and malignant thyroid nodules based on hyperspectral technology. Firstly, using our self-developed thyroid nodule hyperspectral acquisition system, data for a large number of diverse thyroid nodule samples were obtained, providing a foundation for subsequent diagnosis. Secondly, to better meet clinical practical needs, we address the current situation of medical hyperspectral image classification research being mainly focused on pixel-based region segmentation, by proposing a method for nodule classification as benign or malignant based on thyroid nodule hyperspectral data blocks. Using 3D CNN and VGG16 networks as a basis, we designed a neural network algorithm (V3Dnet) for classification based on three-dimensional hyperspectral data blocks. In the case of a dataset with a block size of 50 × 50 × 196, the classification accuracy for benign and malignant samples reaches 84.63%. We also investigated the impact of data block size on the classification performance and constructed a classification model that includes thyroid nodule sample acquisition, hyperspectral data preprocessing, and an algorithm for thyroid nodule classification as benign and malignant based on hyperspectral data blocks. The proposed model for thyroid nodule classification is expected to be applied in thyroid surgery, thereby improving surgical accuracy and providing strong support for scientific research in related fields.

CrossU-Net: Dual-modality cross-attention U-Net for segmentation of precancerous lesions in gastric cancer

Gastric precancerous lesions (GPL) significantly elevate the risk of gastric cancer, and precise diagnosis and timely intervention are critical for patient survival. Due to the elusive pathological features of precancerous lesions, the early detection rate is less than 10%, which hinders lesion localization and diagnosis. In this paper, we provide a GPL pathological dataset and propose a novel method for improving the segmentation accuracy on a limited-scale dataset, namely RGB and Hyperspectral dual-modal pathological image Cross-attention U-Net (CrossU-Net). Specifically, we present a self-supervised pre-training model for hyperspectral images to serve downstream segmentation tasks. Secondly, we design a dual-stream U-Net-based network to extract features from different modal images. To promote information exchange between spatial information in RGB images and spectral information in hyperspectral images, we customize the cross-attention mechanism between the two networks. Furthermore, we use an intermediate agent in this mechanism to improve computational efficiency. Finally, we add a distillation loss to align predicted results for both branches, improving network generalization. Experimental results show that our CrossU-Net achieves accuracy and Dice of 96.53% and 91.62%, respectively, for GPL lesion segmentation, providing a promising spectral research approach for the localization and subsequent quantitative analysis of pathological features in early diagnosis.

FD-Net: Feature Distillation Network for Oral Squamous Cell Carcinoma Lymph Node Segmentation in Hyperspectral Imagery

Oral squamous cell carcinoma (OSCC) has the characteristics of early regional lymph node metastasis. OSCC patients often have poor prognoses and low survival rates due to cervical lymph metastases. Therefore, it is necessary to rely on a reasonable screening method to quickly judge the cervical lymph metastastic condition of OSCC patients and develop appropriate treatment plans. In this study, the widely used pathological sections with hematoxylin-eosin (H&E) staining are taken as the target, and combined with the advantages of hyperspectral imaging technology, a novel diagnostic method for identifying OSCC lymph node metastases is proposed. The method consists of a learning stage and a decision-making stage, focusing on cancer and non-cancer nuclei, gradually completing the lesions' segmentation from coarse to fine, and achieving high accuracy. In the learning stage, the proposed feature distillation-Net (FD-Net) network is developed to segment the cancerous and non-cancerous nuclei. In the decision-making stage, the segmentation results are post-processed, and the lesions are effectively distinguished based on the prior. Experimental results demonstrate that the proposed FD-Net is very competitive in the OSCC hyperspectral medical image segmentation task. The proposed FD-Net method performs best on the seven segmentation evaluation indicators: MIoU, OA, AA, SE, CSI, GDR, and DICE. Among these seven evaluation indicators, the proposed FD-Net method is 1.75%, 1.27%, 0.35%, 1.9%, 0.88%, 4.45%, and 1.98% higher than the DeepLab V3 method, which ranks second in performance, respectively. In addition, the proposed diagnosis method of OSCC lymph node metastasis can effectively assist pathologists in disease screening and reduce the workload of pathologists.

Multi-kernel driven 3D convolutional neural network for automated detection of lung nodules in chest CT scans

The accurate position detection of lung nodules is crucial in early chest computed tomography (CT)-based lung cancer screening, which helps to improve the survival rate of patients. Deep learning methodologies have shown impressive feature extraction ability in the CT image analysis task, but it is still a challenge to develop a robust nodule detection model due to the salient morphological heterogeneity of nodules and complex surrounding environment. In this study, a multi-kernel driven 3D convolutional neural network (MK-3DCNN) is proposed for computerized nodule detection in CT scans. In the MK-3DCNN, a residual learning-based encoder-decoder architecture is introduced to employ the multi-layer features of the deep model. Considering the various nodule sizes and shapes, a multi-kernel joint learning block is developed to capture 3D multi-scale spatial information of nodule CT images, and this is conducive to improving nodule detection performance. Furthermore, a multi-mode mixed pooling strategy is designed to replace the conventional single-mode pooling manner, and it reasonably integrates the max pooling, average pooling, and center cropping pooling operations to obtain more comprehensive nodule descriptions from complicated CT images. Experimental results on the public dataset LUNA16 illustrate that the proposed MK-3DCNN method achieves more competitive nodule detection performance compared to some state-of-the-art algorithms. The results on our constructed clinical dataset CQUCH-LND indicate that the MK-3DCNN has a good prospect in clinical practice.

A framework for immunofluorescence image augmentation and classification based on unsupervised attention mechanism

Autoimmune encephalitis (AE) is a common neurological disorder. As a standard method for neuroautoantibody detection, pathologists use tissue matrix assays (TBA) for initial disease screening. In this study, microscopic fluorescence imaging was combined with deep learning to improve AE diagnostic accuracy. Due to the inter-class imbalance of medical data, we propose an innovative generative adversarial network supplemented with attention mechanisms to highlight key regions in images to synthesize high-quality fluorescence images. However, securing annotated medical data is both time-consuming and costly. To circumvent this problem, we employ a self-supervised learning approach that utilizes unlabeled fluorescence data to support downstream classification tasks. To better understand the fluorescence properties in the data, we introduce a multichannel input convolutional neural network that adds additional channels of fluorescence intensity. This study builds an AE immunofluorescence dataset and obtains the classification accuracy of 88.5% using our method, thus confirming the effectiveness of the proposed method.

Unsupervised dimensionality reduction of medical hyperspectral imagery in tensor space

BACKGROUND AND OBJECTIVES

Compared with traditional RGB images, medical hyperspectral imagery (HSI) has numerous continuous narrow spectral bands, which can provide rich information for cancer diagnosis. However, the abundant spectral bands also contain a large amount of redundancy information and increase computational complexity. Thus, dimensionality reduction (DR) is essential in HSI analysis. All vector-based DR methods ignore the cubic nature of HSI resulting from vectorization. To overcome the disadvantage of vector-based DR methods, tensor-based techniques have been developed by employing multi-linear algebra.

METHODS

To fully exploit the structure features of medical HSI and enhance computational efficiency, a novel method called unsupervised dimensionality reduction via tensor-based low-rank collaborative graph embedding (TLCGE) is proposed. TLCGE introduces entropy rate superpixel (ERS) segmentation algorithm to generate superpixels. Then, a low-rank collaborative graph weight matrix is constructed on each superpixel, greatly improving the efficiency and robustness of the proposed method. After that, TLCGE reduces dimensions in tensor space to well preserve intrinsic structure of HSI.

RESULTS

The proposed TLCGE is tested on cholangiocarcinoma microscopic hyperspectral data sets. To further demonstrate the effectiveness of the proposed algorithm, other machine learning DR methods are used for comparison. Experimental results on cholangiocarcinoma microscopic hyperspectral data sets validate the effectiveness of the proposed TLCGE.

CONCLUSIONS

The proposed TLCGE is a tensor-based DR method, which can maintain the intrinsic 3-D data structure of medical HSI. By imposing the low-rank and sparse constraints on the objective function, the proposed TLCGE can fully explore the local and global structures within each superpixel. The computational efficiency of the proposed TLCGE is better than other tensor-based DR methods, which can be used as a preprocessing step in real medical HSI classification or segmentation.

Bibliometric analysis of the current status and trends on medical hyperspectral imaging

Hyperspectral imaging (HSI) is a promising technology that can provide valuable support for the advancement of the medical field. Bibliometrics can analyze a vast number of publications on both macroscopic and microscopic levels, providing scholars with essential foundations to shape future directions. The purpose of this study is to comprehensively review the existing literature on medical hyperspectral imaging (MHSI). Based on the Web of Science (WOS) database, this study systematically combs through literature using bibliometric methods and visualization software such as VOSviewer and CiteSpace to draw scientific conclusions. The analysis yielded 2,274 articles from 73 countries/regions, involving 7,401 authors, 2,037 institutions, 1,038 journals/conferences, and a total of 7,522 keywords. The field of MHSI is currently in a positive stage of development and has conducted extensive research worldwide. This research encompasses not only HSI technology but also its application to diverse medical research subjects, such as skin, cancer, tumors, etc., covering a wide range of hardware constructions and software algorithms. In addition to advancements in hardware, the future should focus on the development of algorithm standards for specific medical research targets and cultivate medical professionals of managing vast amounts of technical information.

Enhancing Skin Cancer Detection and Classification in Dermoscopic Images through Concatenated MobileNetV2 and Xception Models

One of the most promising research initiatives in the healthcare field is focused on the rising incidence of skin cancer worldwide and improving early discovery methods for the disease. The most significant factor in the fatalities caused by skin cancer is the late identification of the disease. The likelihood of human survival may be significantly improved by performing an early diagnosis followed by appropriate therapy. It is not a simple process to extract the elements from the photographs of the tumors that may be used for the prospective identification of skin cancer. Several deep learning models are widely used to extract efficient features for a skin cancer diagnosis; nevertheless, the literature demonstrates that there is still room for additional improvements in various performance metrics. This study proposes a hybrid deep convolutional neural network architecture for identifying skin cancer by adding two main heuristics. These include Xception and MobileNetV2 models. Data augmentation was introduced to balance the dataset, and the transfer learning technique was utilized to resolve the challenges of the absence of labeled datasets. It has been detected that the suggested method of employing Xception in conjunction with MobileNetV2 attains the most excellent performance, particularly concerning the dataset that was evaluated: specifically, it produced 97.56% accuracy, 97.00% area under the curve, 100% sensitivity, 93.33% precision, 96.55% F1 score, and 0.0370 false favorable rates. This research has implications for clinical practice and public health, offering a valuable tool for dermatologists and healthcare professionals in their fight against skin cancer.

A deep learning model using hyperspectral image for EUS-FNA cytology diagnosis in pancreatic ductal adenocarcinoma

BACKGROUND AND AIMS

Endoscopic ultrasonography-guided fine-needle aspiration/biopsy (EUS-FNA/B) is considered to be a first-line procedure for the pathological diagnosis of pancreatic cancer owing to its high accuracy and low complication rate. The number of new cases of pancreatic ductal adenocarcinoma (PDAC) is increasing, and its accurate pathological diagnosis poses a challenge for cytopathologists. Our aim was to develop a hyperspectral imaging (HSI)-based convolution neural network (CNN) algorithm to aid in the diagnosis of pancreatic EUS-FNA cytology specimens.

METHODS

HSI images were captured of pancreatic EUS-FNA cytological specimens from benign pancreatic tissues (n = 33) and PDAC (n = 39) prepared using a liquid-based cytology method. A CNN was established to test the diagnostic performance, and Attribution Guided Factorization Visualization (AGF-Visualization) was used to visualize the regions of important classification features identified by the model.

RESULTS

A total of 1913 HSI images were obtained. Our ResNet18-SimSiam model achieved an accuracy of 0.9204, sensitivity of 0.9310 and specificity of 0.9123 (area under the curve of 0.9625) when trained on HSI images for the differentiation of PDAC cytological specimens from benign pancreatic cells. AGF-Visualization confirmed that the diagnoses were based on the features of tumor cell nuclei.

CONCLUSIONS

An HSI-based model was developed to diagnose cytological PDAC specimens obtained using EUS-guided sampling. Under the supervision of experienced cytopathologists, we performed multi-staged consecutive in-depth learning of the model. Its superior diagnostic performance could be of value for cytologists when diagnosing PDAC.

Transformers in medical imaging: A survey

Following unprecedented success on the natural language tasks, Transformers have been successfully applied to several computer vision problems, achieving state-of-the-art results and prompting researchers to reconsider the supremacy of convolutional neural networks (CNNs) as de facto operators. Capitalizing on these advances in computer vision, the medical imaging field has also witnessed growing interest for Transformers that can capture global context compared to CNNs with local receptive fields. Inspired from this transition, in this survey, we attempt to provide a comprehensive review of the applications of Transformers in medical imaging covering various aspects, ranging from recently proposed architectural designs to unsolved issues. Specifically, we survey the use of Transformers in medical image segmentation, detection, classification, restoration, synthesis, registration, clinical report generation, and other tasks. In particular, for each of these applications, we develop taxonomy, identify application-specific challenges as well as provide insights to solve them, and highlight recent trends. Further, we provide a critical discussion of the field's current state as a whole, including the identification of key challenges, open problems, and outlining promising future directions. We hope this survey will ignite further interest in the community and provide researchers with an up-to-date reference regarding applications of Transformer models in medical imaging. Finally, to cope with the rapid development in this field, we intend to regularly update the relevant latest papers and their open-source implementations at https://github.com/fahadshamshad/awesome-transformers-in-medical-imaging.

Comparing Performance of Spectral Image Analysis Approaches for Detection of Cellular Signals in Time-Lapse Hyperspectral Imaging Fluorescence Excitation-Scanning Microscopy

Hyperspectral imaging (HSI) technology has been applied in a range of fields for target detection and mixture analysis. While HSI was originally developed for remote sensing applications, modern uses include agriculture, historical document authentication, and medicine. HSI has also shown great utility in fluorescence microscopy. However, traditional fluorescence microscopy HSI systems have suffered from limited signal strength due to the need to filter or disperse the emitted light across many spectral bands. We have previously demonstrated that sampling the fluorescence excitation spectrum may provide an alternative approach with improved signal strength. Here, we report on the use of excitation-scanning HSI for dynamic cell signaling studies-in this case, the study of the second messenger Ca2+. Time-lapse excitation-scanning HSI data of Ca2+ signals in human airway smooth muscle cells (HASMCs) were acquired and analyzed using four spectral analysis algorithms: linear unmixing (LU), spectral angle mapper (SAM), constrained energy minimization (CEM), and matched filter (MF), and the performances were compared. Results indicate that LU and MF provided similar linear responses to increasing Ca2+ and could both be effectively used for excitation-scanning HSI. A theoretical sensitivity framework was used to enable the filtering of analyzed images to reject pixels with signals below a minimum detectable limit. The results indicated that subtle kinetic features might be revealed through pixel filtering. Overall, the results suggest that excitation-scanning HSI can be employed for kinetic measurements of cell signals or other dynamic cellular events and that the selection of an appropriate analysis algorithm and pixel filtering may aid in the extraction of quantitative signal traces. These approaches may be especially helpful for cases where the signal of interest is masked by strong cellular autofluorescence or other competing signals.

Cervical cell classification with deep-learning algorithms

Cervical cancer is a serious threat to the lives and health of women. The accurate analysis of cervical cell smear images is an important diagnostic basis for cancer identification. However, pathological data are often complex and difficult to analyze accurately because pathology images contain a wide variety of cells. To improve the recognition accuracy of cervical cell smear images, we propose a novel deep-learning model based on the improved Faster R-CNN, shallow feature enhancement networks, and generative adversarial networks. First, we used a global average pooling layer to enhance the robustness of the data feature transformation. Second, we designed a shallow feature enhancement network to improve the localization and recognition of weak cells. Finally, we established a data augmentation network to improve the detection capability of the model. The experimental results demonstrate that our proposed methods are superior to CenterNet, YOLOv5, and Faster R-CNN algorithms in some aspects, such as shorter time consumption, higher recognition precision, and stronger adaptive ability. Its maximum accuracy is 99.81%, and the overall mean average precision is 89.4% for the SIPaKMeD and Herlev datasets. Our method provides a useful reference for cervical cell smear image analysis. The missed diagnosis rate and false diagnosis rate are relatively high for cervical cell smear images of different pathologies and stages. Therefore, our algorithms need to be further improved to achieve a better balance. We will use a hyperspectral microscope to obtain more spectral data of cervical cells and input them into deep-learning models for data processing and classification research. First, we sent training samples of cervical cells into our proposed deep-learning model. Then, we used the proposed model to train eight types of cervical cells. Finally, we utilized the trained classifier to test the untrained samples and obtained the classification results. Fig 1. Deep-learning cervical cell classification framework.

Unsupervised Hyperspectral Band Selection via Multimodal Evolutionary Algorithm and Subspace Decomposition

Unsupervised band selection is an essential task to search for representative bands in hyperspectral dimension reduction. Most of existing studies utilize the inherent attribute of hyperspectral image (HSI) and acquire single optimal band subset while ignoring the diversity of subsets. Moreover, the ordered property in HSI is expected to be focused in order to avoid choosing redundant bands. In this paper, we proposed an unsupervised band selection method based on the multimodal evolutionary algorithm and subspace decomposition to alleviate the problems. To explore the diversity of band subsets, the multimodal evolutionary algorithm is first employed in spectral subspace decomposition to seek out multiple global or local solutions. Meanwhile, in view of ordered property, we concentrate more on increasing the difference between neighbor band subspaces. Furthermore, to utilize the obtained multiple diverse band subsets, an integrated utilization strategy is adopted to improve the predicted performance. Experimental results on three popular hyperspectral remote sensing datasets and one collected composition prediction dataset show the effectiveness of the proposed method, and the superiority over state-of-the-art methods on predicted accuracy.

Spectral Similarity Measures for In Vivo Human Tissue Discrimination Based on Hyperspectral Imaging

PROBLEM

Similarity measures are widely used as an approved method for spectral discrimination or identification with their applications in different areas of scientific research. Even though a range of works have been presented, only a few showed slightly promising results for human tissue, and these were mostly focused on pathological and non-pathological tissue classification.

METHODS

In this work, several spectral similarity measures on hyperspectral (HS) images of in vivo human tissue were evaluated for tissue discrimination purposes. Moreover, we introduced two new hybrid spectral measures, called SID-JM-TAN(SAM) and SID-JM-TAN(SCA). We analyzed spectral signatures obtained from 13 different human tissue types and two different materials (gauze, instruments), collected from HS images of 100 patients during surgeries.

RESULTS

The quantitative results showed the reliable performance of the different similarity measures and the proposed hybrid measures for tissue discrimination purposes. The latter produced higher discrimination values, up to 6.7 times more than the classical spectral similarity measures. Moreover, an application of the similarity measures was presented to support the annotations of the HS images. We showed that the automatic checking of tissue-annotated thyroid and colon tissues was successful in 73% and 60% of the total spectra, respectively. The hybrid measures showed the highest performance. Furthermore, the automatic labeling of wrongly annotated tissues was similar for all measures, with an accuracy of up to 90%.

CONCLUSION

In future work, the proposed spectral similarity measures will be integrated with tools to support physicians in annotations and tissue labeling of HS images.

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.

Rapid extraction of skin physiological parameters from hyperspectral images using machine learning

Noninvasive assessment of skin structure using hyperspectral images has been intensively studied in recent years. Due to the high computational cost of the classical methods, such as the inverse Monte Carlo (IMC), much research has been done with the aim of using machine learning (ML) methods to reduce the time required for estimating parameters. This study aims to evaluate the accuracy and the estimation speed of the ML methods for this purpose and compare them to the traditionally used inverse adding-doubling (IAD) algorithm. We trained three models – an artificial neural network (ANN), a 1D convolutional neural network (CNN), and a random forests (RF) model – to predict seven skin parameters. The models were trained on simulated data computed using the adding-doubling algorithm. To improve predictive performance, we introduced a stacked dynamic weighting (SDW) model combining the predictions of all three individually trained models. SDW model was trained by using only a handful of real-world spectra on top of the ANN, CNN and RF models that were trained using simulated data. Models were evaluated based on the estimated parameters’ mean absolute error (MAE), considering the surface inclination angle and comparing skin spectra with spectra fitted by the IAD algorithm. On simulated data, the lowest MAE was achieved by the RF model (0.0030), while the SDW model achieved the lowest MAE on in vivo measured spectra (0.0113). The shortest time to estimate parameters for a single spectrum was 93.05 μs. Results suggest that ML algorithms can produce accurate estimates of human skin optical parameters in near real-time.

Hyperspectral Imaging for Non-invasive Diagnostics of Melanocytic Lesions

Malignant melanoma poses a clinical diagnostic problem, since a large number of benign lesions are excised to find a single melanoma. This study assessed the accuracy of a novel non-invasive diagnostic technology, hyperspectral imaging, for melanoma detection. Lesions were imaged prior to excision and histopathological analysis. A deep neural network algorithm was trained twice to distinguish between histopathologically verified malignant and benign melanocytic lesions and to classify the separate subgroups. Furthermore, 2 different approaches were used: a majority vote classification and a pixel-wise classification. The study included 325 lesions from 285 patients. Of these, 74 were invasive melanoma, 88 melanoma in situ, 115 dysplastic naevi, and 48 non-dysplastic naevi. The study included a training set of 358,800 pixels and a validation set of 7,313 pixels, which was then tested with a training set of 24,375 pixels. The majority vote classification achieved high overall sensitivity of 95% and a specificity of 92% (95% confidence interval (95% CI) 0.024-0.029) in differentiating malignant from benign lesions. In the pixel-wise classification, the overall sensitivity and specificity were both 82% (95% CI 0.005-0.005). When divided into 4 subgroups, the diagnostic accuracy was lower. Hyperspectral imaging provides high sensitivity and specificity in distinguishing between naevi and melanoma. This novel method still needs further validation.

A hyperspectral dataset of precancerous lesions in gastric cancer and benchmarks for pathological diagnosis

Gastric cancer (GC) is one of the most common cancers worldwide. A lot of studies have found that early GC has good prognosis. Unfortunately, the diagnosis rate of early GC is suboptimal due to inadequate disease screening and the insidious nature of early lesions. Pathological diagnosis is usually regarded as the "gold standard" for the diagnosis of GC. However, traditional pathological diagnosis is tedious and time-consuming. With the development of deep learning, computer-aided diagnosis is widely used to assist pathologists for diagnosis. As conventional pathology, diagnosis is based on color images, it is not as informative as hyperspectral imaging, which introduces spectroscopy into imaging techniques. This article combines microscopic hyperspectral image (HSI) with deep learning networks to assist in the diagnosis of precancerous lesions in gastric cancer (PLGC). A large scale microscopic hyperspectral PLGC dataset with 924 effective scenes is built and self-supervised learning is adopted to provide pretrained models for HSI. These pretrained models effectively improve the performance of downstream classification tasks. Furthermore, a symmetrically deep connected network is proposed to train with images from different imaging modalities and improve the diagnostic accuracy to 96.59%.

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.

Deep Learning-Based Classification for Melanoma Detection Using XceptionNet

Skin cancer is one of the most common types of cancer in the world, accounting for at least 40% of all cancers. Melanoma is considered as the 19th most commonly occurring cancer among the other cancers in the human society, such that about 300,000 new cases were found in 2018. While cancer diagnosis is based on interventional methods such as surgery, radiotherapy, and chemotherapy, studies show that the use of new computer technologies such as image processing mechanisms in processes related to early diagnosis of this cancer can help the physicians heal this cancer. This paper proposes an automatic method for diagnosis of skin cancer from dermoscopy images. The proposed model is based on an improved XceptionNet, which utilized swish activation function and depthwise separable convolutions. This system shows an improvement in the classification accuracy of the network compared to the original Xception and other dome architectures. Simulations of the proposed method are compared with some other related skin cancer diagnosis state-of-the-art solutions, and the results show that the suggested method achieves higher accuracy compared to the other comparative methods.

New Trends in Melanoma Detection Using Neural Networks: A Systematic Review

Due to its increasing incidence, skin cancer, and especially melanoma, is a serious health disease today. The high mortality rate associated with melanoma makes it necessary to detect the early stages to be treated urgently and properly. This is the reason why many researchers in this domain wanted to obtain accurate computer-aided diagnosis systems to assist in the early detection and diagnosis of such diseases. The paper presents a systematic review of recent advances in an area of increased interest for cancer prediction, with a focus on a comparative perspective of melanoma detection using artificial intelligence, especially neural network-based systems. Such structures can be considered intelligent support systems for dermatologists. Theoretical and applied contributions were investigated in the new development trends of multiple neural network architecture, based on decision fusion. The most representative articles covering the area of melanoma detection based on neural networks, published in journals and impact conferences, were investigated between 2015 and 2021, focusing on the interval 2018-2021 as new trends. Additionally presented are the main databases and trends in their use in teaching neural networks to detect melanomas. Finally, a research agenda was highlighted to advance the field towards the new trends.

Skin Cancer Detection Using Kernel Fuzzy C-Means and Improved Neural Network Optimization Algorithm

Early diagnosis of malignant skin cancer from images is a significant part of the cancer treatment process. One of the principal purposes of this research is to propose a pipeline methodology for an optimum computer-aided diagnosis of skin cancers. The method contains four main stages. The first stage is to perform a preprocessing based on noise reduction and contrast enhancement. The second stage is to segment the region of interest (ROI). This study uses kernel fuzzy C-means for ROI segmentation. Then, some features from the ROI are extracted, and then, a feature selection is used for selecting the best ones. The selected features are then injected into a support vector machine (SVM) for final identification. One important part of the contribution in this study is to propose a developed version of a new metaheuristic, named neural network optimization algorithm, to optimize both parts of feature selection and SVM classifier. Comparison results of the method with 5 state-of-the-art methods showed the approach's higher superiority toward the others.

Glaucoma screening using an attention-guided stereo ensemble network

Glaucoma is a chronic eye disease, which causes gradual vision loss and eventually blindness. Accurate glaucoma screening at early stage is critical to mitigate its aggravation. Extracting high-quality features are critical in training of classification models. In this paper, we propose a deep ensemble network with attention mechanism that detects glaucoma using optic nerve head stereo images. The network consists of two main sub-components, a deep Convolutional Neural Network that obtains global information and an Attention-Guided Network that localizes optic disc while maintaining beneficial information from other image regions. Both images in a stereo pair are fed into these sub-components, the outputs are fused together to generate the final prediction result. Abundant image features from different views and regions are being extracted, providing compensation when one of the stereo images is of poor quality. The attention-based localization method is trained in a weakly-supervised manner and only image-level annotation is required, which avoids expensive segmentation labelling. Results from real patient images show that our approach increases recall (sensitivity) from the state-of-the-art 88.89% to 95.48%, while maintaining precision and performance stability. The marked reduction in false-negative rate can significantly enhance the chance of successful early diagnosis of glaucoma.