Detecting Vasodilation as Potential Diagnostic Biomarker in Breast Cancer Using Deep Learning-Driven Thermomics

Cancer detection in breast cells using a hybrid method based on deep complex neural network and data mining

INTRODUCTION

Diagnosis of cancer in breast cells is an important and vital issue in the field of medicine. In this context, the use of advanced methods such as deep complex neural networks and data mining can significantly improve the accuracy and speed of diagnosis. A hybrid approach that can be effective in breast cancer diagnosis is the use of deep complex neural networks and data mining. Due to their powerful nonlinear capabilities in extracting complex features from data, deep neural networks have a very good ability to detect patterns related to cancer. By analyzing millions of data related to breast cells and recognizing common and unusual patterns in them, these networks are able to diagnose cancer with high accuracy. Also, the use of data mining method plays an important role in this process.

METHODOLOGY

Using data mining algorithms and techniques, useful information can be extracted from the available data and the characteristics of healthy and cancerous cells can be separated. This information can be given as input to the deep neural network to achieve more accurate diagnosis. Another method to diagnose breast cancer is the use of thermography, which we use in this research along with data mining and deep learning.

RESULTS

Thermography uses an infrared camera to record the temperature of the target area. This method of breast cancer imaging is less expensive and completely safe compared to other methods. A total of 187 volunteers including 152 healthy people and 35 cancer patients were evaluated. Each person had ten thermographic images, resulting in a total of 1870 thermographic images. Four alternative deep complex neural network models, namely ResNet18, ResNet50, VGG19, and Xception, were used to identify thermal images, including benign and malignant images.

CONCULSION

The evaluation results showed that the use of a combined method based on deep complex neural network and data mining in the diagnosis of cancer in breast cells can bring a significant improvement in the accuracy and speed of diagnosis of this important disease.

Applicability of thermography for cancer diagnosis in small animals

Medical thermography is an imaging test used to monitor skin surface temperature. Although it is not a recent technique, significant advances have been made since the 2000s with the equipment modernization, leading to its popularization. In cancer diagnosis, the application of thermography is supported by the difference in thermal distribution between neoplastic processes and adjacent healthy tissue. The mechanisms involved in heat production by cancer cells include neoangiogenesis, increased metabolic rate, vasodilation, and the release of nitric oxide and pro-inflammatory substances. Currently, thermography has been widely studied in humans as a screening tool for skin and breast cancer, with positive results. In veterinary medicine, the technique has shown promise and has been described for skin and soft tissue tumors in felines, mammary gland tumors, osteosarcoma, mast cell tumors, and perianal tumors in dogs. This review discusses the fundamentals of the technique, monitoring conditions, and the role of thermography as a complementary diagnostic tool for cancer in veterinary medicine, as well as future perspectives for improvement.

Dynamic Vascular Imaging Using Active Breast Thermography

Mammography is considered the gold standard for breast cancer screening and diagnostic imaging; however, there is an unmet clinical need for complementary methods to detect lesions not characterized by mammography. Far-infrared 'thermogram' breast imaging can map the skin temperature, and signal inversion with components analysis can be used to identify the mechanisms of thermal image generation of the vasculature using dynamic thermal data. This work focuses on using dynamic infrared breast imaging to identify the thermal response of the stationary vascular system and the physiologic vascular response to a temperature stimulus affected by vasomodulation. The recorded data are analyzed by converting the diffusive heat propagation into a virtual wave and identifying the reflection using component analysis. Clear images of passive thermal reflection and thermal response to vasomodulation were obtained. In our limited data, the magnitude of vasoconstriction appears to depend on the presence of cancer. The authors propose future studies with supporting diagnostic and clinical data that may provide validation of the proposed paradigm.

Skin Temperature of Acupoints in Health and Disease: A Systematic Review

Introduction: Despite substantial progress made in the field of acupuncture research, the existence and specificity of acupoints remain controversial. In recent years, the concept of acupoint sensitization has emerged as a theoretical framework for understanding acupoints as dynamic functional entities that are sensitized in pathological conditions. Based on this premise, some have claimed that specific acupoints are thermally distinct between healthy and clinical populations, but no systematic review has been conducted to synthesize and evaluate the quality of studies supporting such claims. In this review, we provide a summary and quality assessment of the existing literature addressing the question of whether changes in skin temperature at specific acupoints are indicative of pathological conditions. Methods: A systematic literature search was performed in PubMed, EMBASE, and AltHealthWatch (EBSCO Host), by combining variations of search terms relevant to acupoints and temperature. The search was limited to the English language, and publication dates ranged from database inception to December 2020. Two authors independently screened all resulting abstracts and subsequently read full-text articles for eligibility. Information on study design, sample, acupoints, parameters of skin temperature assessments, and main findings were extracted from included studies. Quality of the thermal sensing methodology was evaluated using a thermal assessment checklist, adapted from the Thermographic Imaging in Sports and Exercise Medicine (TISEM) consensus checklist, and a modified Newcastle-Ottawa Scale (NOS) for case-control studies. Results: The search strategy yielded a total of 1771 studies, of which 10 articles met the eligibility criteria. Eight studies compared skin temperature at acupoints in healthy versus clinical populations, and two studies assessed within-subject changes in temperature of acupoints in relation to changes in health status. There were seven clinical conditions examined in the included studies: chronic bronchial asthma, chronic hepatitis, hyperplasia of mammary glands, infertility, intracranial hypertension, obesity, and primary dysmenorrhea. There were numerous methodological quality issues related to skin temperature measurements. Eight studies with case-control designs reported significant differences between healthy and clinical populations in temperature at certain acupoints. Two studies with pre-post designs reported that changes in health-disease status could be associated with changes in temperature at specific acupoints. Conclusion: A review of the available literature suggests that certain acupoints may be thermally distinct between healthy and unhealthy states. However, given the methodological limitations and heterogeneity across included studies, no definitive conclusion could be drawn as to whether changes in skin temperature at specific acupoints are indicative of pathological conditions.

Dual-Intended Deep Learning Model for Breast Cancer Diagnosis in Ultrasound Imaging

Automated medical data analysis demonstrated a significant role in modern medicine, and cancer diagnosis/prognosis to achieve highly reliable and generalizable systems. In this study, an automated breast cancer screening method in ultrasound imaging is proposed. A convolutional deep autoencoder model is presented for simultaneous segmentation and radiomic extraction. The model segments the breast lesions while concurrently extracting radiomic features. With our deep model, we perform breast lesion segmentation, which is linked to low-dimensional deep-radiomic extraction (four features). Similarly, we used high dimensional conventional imaging throughputs and applied spectral embedding techniques to reduce its size from 354 to 12 radiomics. A total of 780 ultrasound images—437 benign, 210, malignant, and 133 normal—were used to train and validate the models in this study. To diagnose malignant lesions, we have performed training, hyperparameter tuning, cross-validation, and testing with a random forest model. This resulted in a binary classification accuracy of 78.5% (65.1–84.1%) for the maximal (full multivariate) cross-validated model for a combination of radiomic groups.

Bio-Imaging-Based Machine Learning Algorithm for Breast Cancer Detection

Breast cancer is one of the most widespread diseases in women worldwide. It leads to the second-largest mortality rate in women, especially in European countries. It occurs when malignant lumps that are cancerous start to grow in the breast cells. Accurate and early diagnosis can help in increasing survival rates against this disease. A computer-aided detection (CAD) system is necessary for radiologists to differentiate between normal and abnormal cell growth. This research consists of two parts; the first part involves a brief overview of the different image modalities, using a wide range of research databases to source information such as ultrasound, histography, and mammography to access various publications. The second part evaluates different machine learning techniques used to estimate breast cancer recurrence rates. The first step is to perform preprocessing, including eliminating missing values, data noise, and transformation. The dataset is divided as follows: 60% of the dataset is used for training, and the rest, 40%, is used for testing. We focus on minimizing type one false-positive rate (FPR) and type two false-negative rate (FNR) errors to improve accuracy and sensitivity. Our proposed model uses machine learning techniques such as support vector machine (SVM), logistic regression (LR), and K-nearest neighbor (KNN) to achieve better accuracy in breast cancer classification. Furthermore, we attain the highest accuracy of 97.7% with 0.01 FPR, 0.03 FNR, and an area under the ROC curve (AUC) score of 0.99. The results show that our proposed model successfully classifies breast tumors while overcoming previous research limitations. Finally, we summarize the paper with the future trends and challenges of the classification and segmentation in breast cancer detection.

Impartially Validated Multiple Deep-Chain Models to Detect COVID-19 in Chest X-ray Using Latent Space Radiomics

The COVID-19 pandemic continues to spread globally at a rapid pace, and its rapid detection remains a challenge due to its rapid infectivity and limited testing availability. One of the simply available imaging modalities in clinical routine involves chest X-ray (CXR), which is often used for diagnostic purposes. Here, we proposed a computer-aided detection of COVID-19 in CXR imaging using deep and conventional radiomic features. First, we used a 2D U-Net model to segment the lung lobes. Then, we extracted deep latent space radiomics by applying deep convolutional autoencoder (ConvAE) with internal dense layers to extract low-dimensional deep radiomics. We used Johnson-Lindenstrauss (JL) lemma, Laplacian scoring (LS), and principal component analysis (PCA) to reduce dimensionality in conventional radiomics. The generated low-dimensional deep and conventional radiomics were integrated to classify COVID-19 from pneumonia and healthy patients. We used 704 CXR images for training the entire model (i.e., U-Net, ConvAE, and feature selection in conventional radiomics). Afterward, we independently validated the whole system using a study cohort of 1597 cases. We trained and tested a random forest model for detecting COVID-19 cases through multivariate binary-class and multiclass classification. The maximal (full multivariate) model using a combination of the two radiomic groups yields performance in classification cross-validated accuracy of 72.6% (69.4-74.4%) for multiclass and 89.6% (88.4-90.7%) for binary-class classification.

A Machine Learning Decision Support System (DSS) for Neuroendocrine Tumor Patients Treated with Somatostatin Analog (SSA) Therapy

The application of machine learning (ML) techniques could facilitate the identification of predictive biomarkers of somatostatin analog (SSA) efficacy in patients with neuroendocrine tumors (NETs). We collected data from 74 patients with a pancreatic or gastrointestinal NET who received SSA as first-line therapy. We developed three classification models to predict whether the patient would experience a progressive disease (PD) after 12 or 18 months based on clinic-pathological factors at the baseline. The dataset included 70 samples and 15 features. We initially developed three classification models with accuracy ranging from 55% to 70%. We then compared ten different ML algorithms. In all but one case, the performance of the Multinomial Naïve Bayes algorithm (80%) was the highest. The support vector machine classifier (SVC) had a higher performance for the recall metric of the progression-free outcome (97% vs. 94%). Overall, for the first time, we documented that the factors that mainly influenced progression-free survival (PFS) included age, the number of metastatic sites and the primary site. In addition, the following factors were also isolated as important: adverse events G3–G4, sex, Ki67, metastatic site (liver), functioning NET, the primary site and the stage. In patients with advanced NETs, ML provides a predictive model that could potentially be used to differentiate prognostic groups and to identify patients for whom SSA therapy as a single agent may not be sufficient to achieve a long-lasting PFS.

SPAER: Sparse Deep Convolutional Autoencoder Model to Extract Low Dimensional Imaging Biomarkers for Early Detection of Breast Cancer Using Dynamic Thermography

Early diagnosis of breast cancer unequivocally improves the survival rate of patients and is crucial for disease treatment. With the current developments in infrared imaging, breast screening using dynamic thermography seems to be a great complementary method for clinical breast examination (CBE) prior to mammography. In this study, we propose a sparse deep convolutional autoencoder model named SPAER to extract low-dimensional deep thermomics to aid breast cancer diagnosis. The model receives multichannel, low-rank, approximated thermal bases as input images. SPAER provides a solution for high-dimensional deep learning features and selects the predominant basis matrix using matrix factorization techniques. The model has been evaluated using five state-of-the-art matrix factorization methods and 208 thermal breast cancer screening cases. The best accuracy was for non-negative matrix factorization (NMF)-SPAER + Clinical and NMF-SPAER for maintaining thermal heterogeneity, leading to finding symptomatic cases with accuracies of 78.2% (74.3–82.5%) and 77.7% (70.9–82.1%), respectively. SPAER showed significant robustness when tested for additive Gaussian noise cases (3–20% noise), evaluated by the signal-to-noise ratio (SNR). The results suggest high performance of SPAER for preserveing thermal heterogeneity, and it can be used as a noninvasive in vivo tool aiding CBE in the early detection of breast cancer.