Machine-learning-based classification of the histological subtype of non-small-cell lung cancer using MRI texture analysis

Navigating the unseen peril: safeguarding medical imaging in the age of AI

In response to the increasing significance of artificial intelligence (AI) in healthcare, there has been increased attention - including a Presidential executive order to create an AI Safety Institute - to the potential threats posed by AI. While much attention has been given to the conventional risks AI poses to cybersecurity, and critical infrastructure, here we provide an overview of some unique challenges of AI for the medical community. Above and beyond obvious concerns about vetting algorithms that impact patient care, there are additional subtle yet equally important things to consider: the potential harm AI poses to its own integrity and the broader medical information ecosystem. Recognizing the role of healthcare professionals as both consumers and contributors to AI training data, this article advocates for a proactive approach in understanding and shaping the data that underpins AI systems, emphasizing the need for informed engagement to maximize the benefits of AI while mitigating the risks.

Topological embedding and directional feature importance in ensemble classifiers for multi-class classification

Cancer is the second leading cause of disease-related death worldwide, and machine learning-based identification of novel biomarkers is crucial for improving early detection and treatment of various cancers. A key challenge in applying machine learning to high-dimensional data is deriving important features in an interpretable manner to provide meaningful insights into the underlying biological mechanisms We developed a class-based directional feature importance (CLIFI) metric for decision tree methods and demonstrated its use for The Cancer Genome Atlas proteomics data. The CLIFI metric was incorporated into four algorithms, Random Forest (RF), LAtent VAriable Stochastic Ensemble of Trees (LAVASET), and Gradient Boosted Decision Trees (GBDTs), and a new extension incorporating the LAVA step into GBDTs (LAVABOOST). Both LAVA methods incorporate topological information from protein interactions into the decision function. The different models' performance in classifying 28 cancers resulted in F1-scores of 92.6% (RF), 92.0% (LAVASET), 89.3% (LAVABOOST) and 85.7% (GBDT), with no method outperforming all others for individual cancer type prediction. The CLIFI metric enables visualisation of the model's decision-making functions. The resulting CLIFI value distributions indicated heterogeneity in the expression of several proteins (MYH11, ERα, BCL2) across different cancer types (including brain glioma, breast, kidney, thyroid and prostate cancer) aligning with the original raw expression data. In conclusion, we have developed an integrated, directional feature importance metric for multi-class decision tree-based classification models that facilitates interpretable feature importance assessment. The CLIFI metric can be combined with incorporating topological information into the decision functions of models to introduce inductive bias, enhancing interpretability.

A depth analysis of recent innovations in non-invasive techniques using artificial intelligence approach for cancer prediction

The fight against cancer, a relentless global health crisis, emphasizes the urgency for efficient and automated early detection methods. To address this critical need, this review assesses recent advances in non-invasive cancer prediction techniques, comparing conventional machine learning (CML) and deep neural networks (DNNs). Focusing on these seven major cancers, we analyze 310 publications spanning the years 2018 to 2024, focusing on detection accuracy as the key metric to identify the most effective predictive models, highlighting critical gaps in current methodologies, and suggesting directions for future research. We further delved into factors like datasets, features, and modalities to gain a comprehensive understanding of each approach's performance. Separate review tables for each cancer type and approach facilitated comparisons between top performers (accuracy exceeding 99%) and low performers (65.83 to 85.8%). Our exploration of public databases and commonly used classifiers revealed that optimal combinations of features, datasets, and models can achieve up to 100% accuracy for both CML and DNN. However, significant variations in accuracy (up to 35%) were observed, particularly when optimization was lacking. Notably, colorectal cancer exhibited the lowest accuracy (DNN 69%, CML 65.83%). A five-point comparative analysis (best/worst models, performance gap, average accuracy, and research trends) revealed that while DNN research is gaining momentum, CML approaches remain competitive, even outperforming DNN in some cases. This study presents an in-depth comparative analysis of CML and DNN techniques for cancer detection. This knowledge can inform future research directions and contribute to the development of increasingly accurate and reliable cancer detection tools.

Radiomics in distinguishing between lung adenocarcinoma and lung squamous cell carcinoma: a systematic review and meta-analysis

Objectives

The aim of this study was to systematically review the studies on radiomics models in distinguishing between lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) and evaluate the classification performance of radiomics models using images from various imaging techniques.

Materials and methods

PubMed, Embase and Web of Science Core Collection were utilized to search for radiomics studies that differentiate between LUAD and LUSC. The assessment of the quality of studies included utilized the improved Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) and Radiomics Quality Score (RQS). Meta-analysis was conducted to assess the classification performance of radiomics models using various imaging techniques.

Results

The qualitative analysis included 40 studies, while the quantitative synthesis included 21 studies. Median RQS for 40 studies was 12 (range -5~19). Sixteen studies were deemed to have a low risk of bias and low concerns regarding applicability. The radiomics model based on CT images had a pooled sensitivity of 0.78 (95%CI: 0.71~0.83), specificity of 0.85 (95%CI:0.73~0.92), and the area under summary receiver operating characteristic curve (SROC-AUC) of 0.86 (95%CI:0.82~0.89). As for PET images, the pooled sensitivity was 0.80 (95%CI: 0.61~0.91), specificity was 0.77 (95%CI: 0.60~0.88), and the SROC-AUC was 0.85 (95%CI: 0.82~0.88). PET/CT images had a pooled sensitivity of 0.87 (95%CI: 0.72~0.94), specificity of 0.88 (95%CI: 0.80~0.93), and an SROC-AUC of 0.93 (95%CI: 0.91~0.95). MRI images had a pooled sensitivity of 0.73 (95%CI: 0.61~0.82), specificity of 0.80 (95%CI: 0.65~0.90), and an SROC-AUC of 0.79 (95%CI: 0.75~0.82).

Conclusion

Radiomics models demonstrate potential in distinguishing between LUAD and LUSC. Nevertheless, it is crucial to conduct a well-designed and powered prospective radiomics studies to establish their credibility in clinical application.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=412851, identifier CRD42023412851.

Artificial Intelligence in Metabolomics: A Current Review

Metabolomics and artificial intelligence (AI) form a synergistic partnership. Metabolomics generates large datasets comprising hundreds to thousands of metabolites with complex relationships. AI, aiming to mimic human intelligence through computational modeling, possesses extraordinary capabilities for big data analysis. In this review, we provide a recent overview of the methodologies and applications of AI in metabolomics studies in the context of systems biology and human health. We first introduce the AI concept, history, and key algorithms for machine learning and deep learning, summarizing their strengths and weaknesses. We then discuss studies that have successfully used AI across different aspects of metabolomic analysis, including analytical detection, data preprocessing, biomarker discovery, predictive modeling, and multi-omics data integration. Lastly, we discuss the existing challenges and future perspectives in this rapidly evolving field. Despite limitations and challenges, the combination of metabolomics and AI holds great promises for revolutionary advancements in enhancing human health.

Unravelling the diagnostic pathology and molecular biomarkers in lung cancer

The progress in lung cancer treatment is closely interlinked with the progress in diagnostic methods. There are four steps before commencing lung cancer treatment: estimation of the patient's performance status, assessment of disease stage (tumour, node, metastasis), recognition of histological subtype, and detection of biomarkers. The resection rate in lung cancer is <30% and >70% of patients need systemic therapy, which is individually adjusted. Accurate histological diagnosis is very important and it is the basis of further molecular diagnosis. In many cases only small biopsy samples are available and the rules for their assessment are defined in this review. The use of immunochemistry with at least thyroid transcription factor 1 (TTF1) and p40 is decisive in distinction between lung adenocarcinoma and squamous cell carcinoma. Molecular diagnosis and detection of known driver mutations is necessary for introducing targeted therapy and use of multiplex gene panel assays using next-generation sequencing is recommended. Immunotherapy with checkpoint inhibitors is the second promising method of systemic therapy with best results in tumours with high programmed death-ligand 1 (PD-L1) expression on cancer cells. Finally, the determination of a full tumour pattern will be possible using artificial intelligence in the near future.

A Neoteric Feature Extraction Technique to Predict the Survival of Gastric Cancer Patients

BACKGROUND

At the time of cancer diagnosis, it is crucial to accurately classify malignant gastric tumors and the possibility that patients will survive.

OBJECTIVE

This study aims to investigate the feasibility of identifying and applying a new feature extraction technique to predict the survival of gastric cancer patients.

METHODS

A retrospective dataset including the computed tomography (CT) images of 135 patients was assembled. Among them, 68 patients survived longer than three years. Several sets of radiomics features were extracted and were incorporated into a machine learning model, and their classification performance was characterized. To improve the classification performance, we further extracted another 27 texture and roughness parameters with 2484 superficial and spatial features to propose a new feature pool. This new feature set was added into the machine learning model and its performance was analyzed. To determine the best model for our experiment, Random Forest (RF) classifier, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes (NB) (four of the most popular machine learning models) were utilized. The models were trained and tested using the five-fold cross-validation method.

RESULTS

Using the area under ROC curve (AUC) as an evaluation index, the model that was generated using the new feature pool yields AUC = 0.98 ± 0.01, which was significantly higher than the models created using the traditional radiomics feature set (p < 0.04). RF classifier performed better than the other machine learning models.

CONCLUSIONS

This study demonstrated that although radiomics features produced good classification performance, creating new feature sets significantly improved the model performance.

On-cloud decision-support system for non-small cell lung cancer histology characterization from thorax computed tomography scans

Non-Small Cell Lung Cancer (NSCLC) accounts for about 85% of all lung cancers. Developing non-invasive techniques for NSCLC histology characterization may not only help clinicians to make targeted therapeutic treatments but also prevent subjects from undergoing lung biopsy, which is challenging and could lead to clinical implications. The motivation behind the study presented here is to develop an advanced on-cloud decision-support system, named LUCY, for non-small cell LUng Cancer histologY characterization directly from thorax Computed Tomography (CT) scans. This aim was pursued by selecting thorax CT scans of 182 LUng ADenocarcinoma (LUAD) and 186 LUng Squamous Cell carcinoma (LUSC) subjects from four openly accessible data collections (NSCLC-Radiomics, NSCLC-Radiogenomics, NSCLC-Radiomics-Genomics and TCGA-LUAD), in addition to the implementation and comparison of two end-to-end neural networks (the core layer of whom is a convolutional long short-term memory layer), the performance evaluation on test dataset (NSCLC-Radiomics-Genomics) from a subject-level perspective in relation to NSCLC histological subtype location and grade, and the dynamic visual interpretation of the achieved results by producing and analyzing one heatmap video for each scan. LUCY reached test Area Under the receiver operating characteristic Curve (AUC) values above 77% in all NSCLC histological subtype location and grade groups, and a best AUC value of 97% on the entire dataset reserved for testing, proving high generalizability to heterogeneous data and robustness. Thus, LUCY is a clinically-useful decision-support system able to timely, non-invasively and reliably provide visually-understandable predictions on LUAD and LUSC subjects in relation to clinically-relevant information.

Rapid label-free detection of early-stage lung adenocarcinoma and tumor boundary via multiphoton microscopy

Lung cancer is the most commonly diagnosed cancer and the leading cause of cancer-related deaths in China. Rapid and precise evaluation of tumor tissue during lung cancer surgery can reduce operative time and improve negative-margin assessment, thus increasing disease-free and overall survival rates. This study aimed to explore the potential of label-free multiphoton microscopy (MPM) for imaging adenocarcinoma tissues, detecting histopathological features, and distinguishing between normal and cancerous lung tissues. We showed that second harmonic generation (SHG) signals exhibit significant specificity for collagen fibers, enabling the quantification of collagen features in lung adenocarcinomas. In addition, we developed a collagen score that could be used to distinguish between normal and tumor areas at the tumor boundary, showing good classification performance. Our findings demonstrate that MPM imaging technology combined with an image-based collagen feature extraction method can rapidly and accurately detect early-stage lung adenocarcinoma tissues.

A comprehensive analysis of recent advancements in cancer detection using machine learning and deep learning models for improved diagnostics

PURPOSE

There are millions of people who lose their life due to several types of fatal diseases. Cancer is one of the most fatal diseases which may be due to obesity, alcohol consumption, infections, ultraviolet radiation, smoking, and unhealthy lifestyles. Cancer is abnormal and uncontrolled tissue growth inside the body which may be spread to other body parts other than where it has originated. Hence it is very much required to diagnose the cancer at an early stage to provide correct and timely treatment. Also, manual diagnosis and diagnostic error may cause of the death of many patients hence much research are going on for the automatic and accurate detection of cancer at early stage.

METHODS

In this paper, we have done the comparative analysis of the diagnosis and recent advancement for the detection of various cancer types using traditional machine learning (ML) and deep learning (DL) models. In this study, we have included four types of cancers, brain, lung, skin, and breast and their detection using ML and DL techniques. In extensive review we have included a total of 130 pieces of literature among which 56 are of ML-based and 74 are from DL-based cancer detection techniques. Only the peer reviewed research papers published in the recent 5-year span (2018-2023) have been included for the analysis based on the parameters, year of publication, feature utilized, best model, dataset/images utilized, and best accuracy. We have reviewed ML and DL-based techniques for cancer detection separately and included accuracy as the performance evaluation metrics to maintain the homogeneity while verifying the classifier efficiency.

RESULTS

Among all the reviewed literatures, DL techniques achieved the highest accuracy of 100%, while ML techniques achieved 99.89%. The lowest accuracy achieved using DL and ML approaches were 70% and 75.48%, respectively. The difference in accuracy between the highest and lowest performing models is about 28.8% for skin cancer detection. In addition, the key findings, and challenges for each type of cancer detection using ML and DL techniques have been presented. The comparative analysis between the best performing and worst performing models, along with overall key findings and challenges, has been provided for future research purposes. Although the analysis is based on accuracy as the performance metric and various parameters, the results demonstrate a significant scope for improvement in classification efficiency.

CONCLUSION

The paper concludes that both ML and DL techniques hold promise in the early detection of various cancer types. However, the study identifies specific challenges that need to be addressed for the widespread implementation of these techniques in clinical settings. The presented results offer valuable guidance for future research in cancer detection, emphasizing the need for continued advancements in ML and DL-based approaches to improve diagnostic accuracy and ultimately save more lives.

An Innovative Faster R-CNN-Based Framework for Breast Cancer Detection in MRI

Replacing lung cancer as the most commonly diagnosed cancer globally, breast cancer (BC) today accounts for 1 in 8 cancer diagnoses and a total of 2.3 million new cases in both sexes combined. An estimated 685,000 women died from BC in 2020, corresponding to 16% or 1 in every 6 cancer deaths in women. BC represents a quarter of a total of cancer cases in females and by far the most commonly diagnosed cancer in women in 2020. However, when detected in the early stages of the disease, treatment methods have proven to be very effective in increasing life expectancy and, in many cases, patients fully recover. Several medical imaging modalities, such as X-rays Mammography (MG), Ultrasound (US), Computer Tomography (CT), Magnetic Resonance Imaging (MRI), and Digital Tomosynthesis (DT) have been explored to support radiologists/physicians in clinical decision-making workflows for the detection and diagnosis of BC. In this work, we propose a novel Faster R-CNN-based framework to automate the detection of BC pathological Lesions in MRI. As a main contribution, we have developed and experimentally (statistically) validated an innovative method improving the "breast MRI preprocessing phase" to select the patient's slices (images) and associated bounding boxes representing pathological lesions. In this way, it is possible to create a more robust training (benchmarking) dataset to feed Deep Learning (DL) models, reducing the computation time and the dimension of the dataset, and more importantly, to identify with high accuracy the specific regions (bounding boxes) for each of the patient's images, in which a possible pathological lesion (tumor) has been identified. As a result, in an experimental setting using a fully annotated dataset (released to the public domain) comprising a total of 922 MRI-based BC patient cases, we have achieved, as the most accurate trained model, an accuracy rate of 97.83%, and subsequently, applying a ten-fold cross-validation method, a mean accuracy on the trained models of 94.46% and an associated standard deviation of 2.43%.

Machine Learning and AI in Cancer Prognosis, Prediction, and Treatment Selection: A Critical Approach

Cancer is a leading cause of morbidity and mortality worldwide. While progress has been made in the diagnosis, prognosis, and treatment of cancer patients, individualized and data-driven care remains a challenge. Artificial intelligence (AI), which is used to predict and automate many cancers, has emerged as a promising option for improving healthcare accuracy and patient outcomes. AI applications in oncology include risk assessment, early diagnosis, patient prognosis estimation, and treatment selection based on deep knowledge. Machine learning (ML), a subset of AI that enables computers to learn from training data, has been highly effective at predicting various types of cancer, including breast, brain, lung, liver, and prostate cancer. In fact, AI and ML have demonstrated greater accuracy in predicting cancer than clinicians. These technologies also have the potential to improve the diagnosis, prognosis, and quality of life of patients with various illnesses, not just cancer. Therefore, it is important to improve current AI and ML technologies and to develop new programs to benefit patients. This article examines the use of AI and ML algorithms in cancer prediction, including their current applications, limitations, and future prospects.

Robustness Fine-Tuning Deep Learning Model for Cancers Diagnosis Based on Histopathology Image Analysis

Histopathology is the most accurate way to diagnose cancer and identify prognostic and therapeutic targets. The likelihood of survival is significantly increased by early cancer detection. With deep networks' enormous success, significant attempts have been made to analyze cancer disorders, particularly colon and lung cancers. In order to do this, this paper examines how well deep networks can diagnose various cancers using histopathology image processing. This work intends to increase the performance of deep learning architecture in processing histopathology images by constructing a novel fine-tuning deep network for colon and lung cancers. Such adjustments are performed using regularization, batch normalization, and hyperparameters optimization. The suggested fine-tuned model was evaluated using the LC2500 dataset. Our proposed model's average precision, recall, F1-score, specificity, and accuracy were 99.84%, 99.85%, 99.84%, 99.96%, and 99.94%, respectively. The experimental findings reveal that the suggested fine-tuned learning model based on the pre-trained ResNet101 network achieves higher results against recent state-of-the-art approaches and other current powerful CNN models.

Lung Cancer Diagnosis System Based on Volatile Organic Compounds (VOCs) Profile Measured in Exhaled Breath

Lung cancer is one of the world’s lethal diseases and detecting it at an early stage is crucial and difficult. This paper proposes a computer-aided lung cancer diagnosis system using volatile organic compounds (VOCs) data. A silicon microreactor, which consists of thousands of micropillars coated with an ammonium aminooxy salt, is used to capture the volatile organic compounds (VOCs) in the patients’ exhaled breath by means of oximation reactions. The proposed system ranks the features using the Pearson correlation coefficient and maximum relevance–minimum redundancy (mRMR) techniques. The selected features are fed to nine different classifiers to determine if the lung nodule is malignant or benign. The system is validated using a locally acquired dataset that has 504 patients’ data. The dataset is balanced and has 27 features of volatile organic compounds (VOCs). Multiple experiments were completed, and the best accuracy result is 87%, which was achieved using random forest (RF) either by using all 27 features without selection or by using the first 17 features obtained using maximum relevance–minimum redundancy (mRMR) while using an 80–20 train-test split. The correlation coefficient, maximum relevance–minimum redundancy (mRMR), and random forest (RF) importance agreed that C4H8O (2-Butanone) ranks as the best feature. Using only C4H8O (2-Butanone) for training, the accuracy results using the support vector machine, logistic regression, bagging and neural network classifiers are 86%, which approaches the best result. This shows the potential for these volatile organic compounds (VOCs) to serve as a significant screening tests for the diagnosis of lung cancer.

Lung nodule diagnosis and cancer histology classification from computed tomography data by convolutional neural networks: A survey

Lung cancer is among the deadliest cancers. Besides lung nodule classification and diagnosis, developing non-invasive systems to classify lung cancer histological types/subtypes may help clinicians to make targeted treatment decisions timely, having a positive impact on patients' comfort and survival rate. As convolutional neural networks have proven to be responsible for the significant improvement of the accuracy in lung cancer diagnosis, with this survey we intend to: show the contribution of convolutional neural networks not only in identifying malignant lung nodules but also in classifying lung cancer histological types/subtypes directly from computed tomography data; point out the strengths and weaknesses of slice-based and scan-based approaches employing convolutional neural networks; and highlight the challenges and prospective solutions to successfully apply convolutional neural networks for such classification tasks. To this aim, we conducted a comprehensive analysis of relevant Scopus-indexed studies involved in lung nodule diagnosis and cancer histology classification up to January 2022, dividing the investigation in convolutional neural network-based approaches fed with planar or volumetric computed tomography data. Despite the application of convolutional neural networks in lung nodule diagnosis and cancer histology classification is a valid strategy, some challenges raised, mainly including the lack of publicly-accessible annotated data, together with the lack of reproducibility and clinical interpretability. We believe that this survey will be helpful for future studies involved in lung nodule diagnosis and cancer histology classification prior to lung biopsy by means of convolutional neural networks.

Selection of Filtering and Image Texture Analysis in the Radiographic Images Processing of Horses' Incisor Teeth Affected by the EOTRH Syndrome

Equine odontoclastic tooth resorption and hypercementosis (EOTRH) is one of the horses’ dental diseases, mainly affecting the incisor teeth. An increase in the incidence of aged horses and a painful progressive course of the disease create the need for improved early diagnosis. Besides clinical findings, EOTRH recognition is based on the typical radiographic findings, including levels of dental resorption and hypercementosis. This study aimed to introduce digital processing methods to equine dental radiographic images and identify texture features changing with disease progression. The radiographs of maxillary incisor teeth from 80 horses were obtained. Each incisor was annotated by separate masks and clinically classified as 0, 1, 2, or 3 EOTRH degrees. Images were filtered by Mean, Median, Normalize, Bilateral, Binomial, CurvatureFlow, LaplacianSharpening, DiscreteGaussian, and SmoothingRecursiveGaussian filters independently, and 93 features of image texture were extracted using First Order Statistics (FOS), Gray Level Co-occurrence Matrix (GLCM), Neighbouring Gray Tone Difference Matrix (NGTDM), Gray Level Dependence Matrix (GLDM), Gray Level Run Length Matrix (GLRLM), and Gray Level Size Zone Matrix (GLSZM) approaches. The most informative processing was selected. GLCM and GLRLM return the most favorable features for the quantitative evaluation of radiographic signs of the EOTRH syndrome, which may be supported by filtering by filters improving the edge delimitation.

Computer-Assisted Image Processing System for Early Assessment of Lung Nodule Malignancy

Simple Summary

Lung cancer is the second most common cancer in men after prostate cancer and in women after breast cancer, but it is the leading cause of cancer death among both genders. This manuscript proposes a new computer-aided diagnosis system that uses only a single computed tomography scan to diagnose the pulmonary nodule as benign or malignant. This system helps in the early detection of the pulmonary nodules and shows its ability to identify the pulmonary nodules precisely.

Abstract

Lung cancer is one of the most dreadful cancers, and its detection in the early stage is very important and challenging. This manuscript proposes a new computer-aided diagnosis system for lung cancer diagnosis from chest computed tomography scans. The proposed system extracts two different kinds of features, namely, appearance features and shape features. For the appearance features, a Histogram of oriented gradients, a Multi-view analytical Local Binary Pattern, and a Markov Gibbs Random Field are developed to give a good description of the lung nodule texture, which is one of the main distinguishing characteristics between benign and malignant nodules. For the shape features, Multi-view Peripheral Sum Curvature Scale Space, Spherical Harmonics Expansion, and a group of some fundamental morphological features are implemented to describe the outer contour complexity of the nodules, which is main factor in lung nodule diagnosis. Each feature is fed into a stacked auto-encoder followed by a soft-max classifier to generate the initial malignancy probability. Finally, all these probabilities are combined together and fed to the last network to give the final diagnosis. The system is validated using 727 nodules which are subset from the Lung Image Database Consortium (LIDC) dataset. The system shows very high performance measures and achieves 92.55%, 91.70%, and 93.40% for the accuracy, sensitivity, and specificity, respectively. This high performance shows the ability of the system to distinguish between the malignant and benign nodules precisely.

Selection of Image Texture Analysis and Color Model in the Advanced Image Processing of Thermal Images of Horses following Exercise

Simple Summary

Detecting horse state after exercise is critical for maximizing athletic performance. The horse’s response to fatigue includes exercise termination or exercise continuation at a lower intensity, which significantly limit the results achieved in races and equestrian competition. As conventional methods of detecting and quantifying exercise effort have shown some limitations, infrared thermography was proposed as a method of contactless detection of exercise effect. The promising correlation between body surface temperature and exercise-dependent blood biomarkers has been demonstrated. As the application of conventional thermography is limited by low specificity, advanced thermal image analysis was proposed here to visualize the link between blood biomarkers and texture of thermal images. Twelve horses underwent standardized exercise tests for six consecutive days, and both thermal images and blood samples were collected before and after each test. The images were analyzed using four color models (RGB, red-green-blue; YUV, brightness-UV-components; YIQ, brightness-IQ-components; HSB, hue-saturation-brightness) and eight texture-features approaches, including 88 features in total. In contrast to conventional temperature measures, as many as twelve texture features in two color models (RGB, YIQ) were linked with blood biomarker levels as part of the horse’s response to exercise.

Abstract

As the detection of horse state after exercise is constantly developing, a link between blood biomarkers and infrared thermography (IRT) was investigated using advanced image texture analysis. The aim of the study was to determine which combinations of RGB (red-green-blue), YUI (brightness-UV-components), YIQ (brightness-IQ-components), and HSB (hue-saturation-brightness) color models, components, and texture features are related to the blood biomarkers of exercise effect. Twelve Polish warmblood horses underwent standardized exercise tests for six consecutive days. Both thermal images and blood samples were collected before and after each test. All 144 obtained IRT images were analyzed independently for 12 color components in four color models using eight texture-feature approaches, including 88 features. The similarity between blood biomarker levels and texture features was determined using linear regression models. In the horses’ thoracolumbar region, 12 texture features (nine in RGB, one in YIQ, and two in HSB) were related to blood biomarkers. Variance, sum of squares, and sum of variance in the RGB were highly repeatable between image processing protocols. The combination of two approaches of image texture (histogram statistics and gray-level co-occurrence matrix) and two color models (RGB, YIQ), should be considered in the application of digital image processing of equine IRT.

The Effect of Rider:Horse Bodyweight Ratio on the Superficial Body Temperature of Horse's Thoracolumbar Region Evaluated by Advanced Thermal Image Processing

Appropriate matching of rider-horse sizes is becoming an increasingly important issue of riding horses' care, as the human population becomes heavier. Recently, infrared thermography (IRT) was considered to be effective in differing the effect of 10.6% and 21.3% of the rider:horse bodyweight ratio, but not 10.1% and 15.3%. As IRT images contain many pixels reflecting the complexity of the body's surface, the pixel relations were assessed by image texture analysis using histogram statistics (HS), gray-level run-length matrix (GLRLM), and gray level co-occurrence matrix (GLCM) approaches. The study aimed to determine differences in texture features of thermal images under the impact of 10-12%, >12 ≤15%, >15 <18% rider:horse bodyweight ratios, respectively. Twelve horses were ridden by each of six riders assigned to light (L), moderate (M), and heavy (H) groups. Thermal images were taken pre- and post-standard exercise and underwent conventional and texture analysis. Texture analysis required image decomposition into red, green, and blue components. Among 372 returned features, 95 HS features, 48 GLRLM features, and 96 GLCH features differed dependent on exercise; whereas 29 HS features, 16 GLRLM features, and 30 GLCH features differed dependent on bodyweight ratio. Contrary to conventional thermal features, the texture heterogeneity measures, InvDefMom, SumEntrp, Entropy, DifVarnc, and DifEntrp, expressed consistent measurable differences when the red component was considered.

Advances in Thermal Image Analysis for the Detection of Pregnancy in Horses Using Infrared Thermography

Infrared thermography (IRT) was applied as a potentially useful tool in the detection of pregnancy in equids, especially native or wildlife. IRT measures heat emission from the body surface, which increases with the progression of pregnancy as blood flow and metabolic activity in the uterine and fetal tissues increase. Conventional IRT imaging is promising; however, with specific limitations considered, this study aimed to develop novel digital processing methods for thermal images of pregnant mares to detect pregnancy earlier with higher accuracy. In the current study, 40 mares were divided into non-pregnant and pregnant groups and imaged using IRT. Thermal images were transformed into four color models (RGB, YUV, YIQ, HSB) and 10 color components were separated. From each color component, features of image texture were obtained using Histogram Statistics and Grey-Level Run-Length Matrix algorithms. The most informative color/feature combinations were selected for further investigation, and the accuracy of pregnancy detection was calculated. The image texture features in the RGB and YIQ color models reflecting increased heterogeneity of image texture seem to be applicable as potential indicators of pregnancy. Their application in IRT-based pregnancy detection in mares allows for earlier recognition of pregnant mares with higher accuracy than the conventional IRT imaging technique.

A Convolutional Neural Network-Based Intelligent Medical System with Sensors for Assistive Diagnosis and Decision-Making in Non-Small Cell Lung Cancer

In many regions of the world, early diagnosis of non-small cell lung cancer (NSCLC) is a major challenge due to the large population and lack of medical resources, which is difficult toeffectively address via limited physician manpower alone. Therefore, we developed a convolutional neural network (CNN)-based assisted diagnosis and decision-making intelligent medical system with sensors. This system analyzes NSCLC patients' medical records using sensors to assist staging a diagnosis and provides recommended treatment plans to physicians. To address the problem of unbalanced case samples across pathological stages, we used transfer learning and dynamic sampling techniques to reconstruct and iteratively train the model to improve the accuracy of the prediction system. In this paper, all data for training and testing the system were obtained from the medical records of 2,789,675 patients with NSCLC, which were recorded in three hospitals in China over a five-year period. When the number of case samples reached 8000, the system achieved an accuracy rate of 0.84, which is already close to that of the doctors (accuracy: 0.86). The experimental results proved that the system can quickly and accurately analyze patient data and provide decision information support for physicians.

Multi-Input Dual-Stream Capsule Network for Improved Lung and Colon Cancer Classification

Lung and colon cancers are two of the most common causes of death and morbidity in humans. One of the most important aspects of appropriate treatment is the histopathological diagnosis of such cancers. As a result, the main goal of this study is to use a multi-input capsule network and digital histopathology images to build an enhanced computerized diagnosis system for detecting squamous cell carcinomas and adenocarcinomas of the lungs, as well as adenocarcinomas of the colon. Two convolutional layer blocks are used in the proposed multi-input capsule network. The CLB (Convolutional Layers Block) employs traditional convolutional layers, whereas the SCLB (Separable Convolutional Layers Block) employs separable convolutional layers. The CLB block takes unprocessed histopathology images as input, whereas the SCLB block takes uniquely pre-processed histopathological images. The pre-processing method uses color balancing, gamma correction, image sharpening, and multi-scale fusion as the major processes because histopathology slide images are typically red blue. All three channels (Red, Green, and Blue) are adequately compensated during the color balancing phase. The dual-input technique aids the model's ability to learn features more effectively. On the benchmark LC25000 dataset, the empirical analysis indicates a significant improvement in classification results. The proposed model provides cutting-edge performance in all classes, with 99.58% overall accuracy for lung and colon abnormalities based on histopathological images.

Application of Photo Texture Analysis and Weather Data in Assessment of Air Quality in Terms of Airborne PM10 and PM2.5 Particulate Matter

The study was undertaken in Krakow, which is situated in Lesser Poland Voivodeship, where bad PM₁₀ air-quality indicators occurred on more than 100 days in the years 2010–2019. Krakow has continuous air quality measurement in seven locations that are run by the Province Environmental Protection Inspectorate. The research aimed to create regression and classification models for PM₁₀ and PM_2.5 estimation based on sky photos and basic weather data. For this research, one short video with a resolution of 1920 × 1080 px was captured each day. From each film, only five frames were used, the information from which was averaged. Then, texture analysis was performed on each averaged photo frame. The results of the texture analysis were used in the regression and classification models. The regression models’ quality for the test datasets equals 0.85 and 0.73 for PM₁₀ and 0.63 for PM_2.5. The quality of each classification model differs (0.86 and 0.73 for PM₁₀, and 0.80 for PM_2.5). The obtained results show that the created classification models could be used in PM₁₀ and PM_2.5 air quality assessment. Moreover, the character of the obtained regression models indicates that their quality could be enhanced; thus, improved results could be obtained.