Tissue Classification Research Articles

Pseudo-Label Assisted nnU-Net enables automatic segmentation of 7T MRI from a single acquisition.

Automatic whole brain and lesion segmentation at 7T presents challenges, primarily from bias fields, susceptibility artifacts including distortions, and registration errors. Here, we sought to use deep learning algorithms (D/L) to do both skull stripping and whole brain segmentation on multiple imaging contrasts generated in a single Magnetization Prepared 2 Rapid Acquisition Gradient Echoes (MP2RAGE) acquisition on participants clinically diagnosed with multiple sclerosis (MS), bypassing registration errors. Brain scans Segmentation from 3T and 7T scanners were analyzed with software packages such as FreeSurfer, Classification using Derivative-based Features (C-DEF), nnU-net, and a novel 3T-to-7T transfer learning method, Pseudo-Label Assisted nnU-Net (PLAn). 3T and 7T MRIs acquired within 9 months from 25 study participants with MS (Cohort 1) were used for training and optimizing. Eight MS patients (Cohort 2) scanned only at 7T, but with expert annotated lesion segmentation, was used to further validate the algorithm on a completely unseen dataset. Segmentation results were rated visually by experts in a blinded fashion and quantitatively using Dice Similarity Coefficient (DSC). Of the methods explored here, nnU-Net and PLAn produced the best tissue segmentation at 7T for all tissue classes. In both quantitative and qualitative analysis, PLAn significantly outperformed nnU-Net (and other methods) in lesion detection in both cohorts. PLAn's lesion DSC improved by 16% compared to nnU-Net. Limited availability of labeled data makes transfer learning an attractive option, and pre-training a nnUNet model using readily obtained 3T pseudo-labels was shown to boost lesion detection capabilities at 7T.

Epstein-Barr virus positive mucocutaneous ulcer – A diagnostic challenge

A significant portion of the global population carries the asymptomatic Epstein-Barr virus (EBV). Transfusions of blood and blood derivatives, organ and tissue transplantation, and oropharyngeal secretions are the main routes of transmission. The World Health Organization recently recognized the EBV mucocutaneous ulcer (EBVMU) as a provisional pathological entity in its classification of hematopoietic and lymphoid tissues. It affects patients who are elderly or immunosuppressed. Histologically, it may be difficult to distinguish from Hodgkin lymphoma (HL). Although skin or mucosa are uncommon sites of HL involvement, diagnosis at these sites should be made with extreme caution. The prognosis for EBVMU is good; cases regress on their own or after immunosuppressive therapy is reduced. We present a 67-year-old woman with a non-healing oral cavity ulcer which was diagnosed as EBV-positive mucocutaneous ulcer.

Formalin-Fixed Paraffin-Embedded Proteomics of Malignant Mesothelioma and New Candidate Biomarkers Thioredoxin and Superoxide Dismutase 2 for Immunohistochemistry

The pathogenesis of malignant mesothelioma (MM) has been extensively investigated, focusing on stress derived from reactive oxygen species. We aimed to identify diagnostic biomarkers of MM by analyzing proteins in formalin-fixed paraffin-embedded specimens using liquid chromatography-mass spectrometry. We extracted proteins from formalin-fixed paraffin-embedded sections of MM tissues (n = 7) and compared their profiles with those of benign mesothelial tissues (n = 4) and alveolar tissue (n = 1). Proteomic data were statistically assessed and profiled using principal component analysis. We were successful in the classification of MM and healthy tissue. The levels of superoxide dismutase 2 (SOD2), an enzyme that converts superoxide anion into oxygen and hydrogen peroxide, and thioredoxin (TXN), which plays a crucial role in reducing disulfide bonds in proteins, primarily contributed to the classification. Other redox-related proteins, such as pyruvate dehydrogenase subunit X, and ceruloplasmin also contributed to the classification. Protein-protein interaction analysis demonstrated that these proteins play essential roles in MM pathogenesis. Immunohistochemistry revealed that TXN levels were significantly lower, whereas SOD2 levels were significantly higher in MM and lung cancer tissues than in controls. Proteomic profiling suggested that MM tissues experienced increased exposure to hydrogen peroxide and other reactive oxygen species. Combining immunohistochemistry for TXN and SOD2 allows for differentiation among MM, lung cancer, and control tissues; hence, TXN and SOD2 may be promising MM biomarkers and therapeutic targets.

Shedding Light on Colorectal Cancer: An in Vivo Raman Spectroscopy Approach Combined with Deep Learning Analysis

Raman spectroscopy has emerged as a powerful tool in medical, biochemical, and biological research with high specificity, sensitivity, and spatial and temporal resolution. Recent advanced Raman systems, such as portable Raman systems and fiber-optic probes, provide the potential for accurate in vivo discrimination between healthy and cancerous tissues. In our study, a portable Raman probe spectrometer was tested in immunosuppressed mice for the in vivo localization of colorectal cancer malignancies from normal tissue margins. The acquired Raman spectra were preprocessed, and principal component analysis (PCA) was performed to facilitate discrimination between malignant and normal tissues and to highlight their biochemical differences using loading plots. A transfer learning model based on a one-dimensional convolutional neural network (1D-CNN) was employed for the Raman spectra data to assess the classification accuracy of Raman spectra in live animals. The 1D-CNN model yielded an 89.9% accuracy and 91.4% precision in tissue classification. Our results contribute to the field of Raman spectroscopy in cancer diagnosis, highlighting its promising role within clinical applications.

Methods, applications, and future perspectives of intraoperative tissue identification

Over the last century, there has been a steady development of new technologies for intraoperative tissue identification and differentiation. The applications are varied, with thecore purpose being to identify target structures while preserving adjacent tissue and thereby follow ageneral paradigm of minimally invasive medicine. Particularly in oncology, afurther asset of these technologies is the identification or classification of neoplastic tissue to support and improve therapy, for example, in breast cancer surgery.Many technologies under consideration make use of the different physical characteristics of treated tissues, such as induced fluorescence, optical coherence, and electrical impedance.Recent developments are focusing on moving from ex vivo to in situ and from asynchronous to real-time assistance of the clinicians, for example, by means of optical emission spectroscopy. Refinements of existing and the creation of new methods will include AI tools to make them more powerful while reducing the inter-operator variability in operative interventions. This talk addresses several aspects of the usage and suitability of these technologies for intraoperative, therapy-supporting application.

CNSC-05. LOCAL AND GLOBAL FUNCTIONAL CONNECTOME DISRUPTION IN PATIENTS WITH GLIOMAS

Abstract The aim of the study was to map the disruption of functional connectome in patients with gliomas using resting-state functional MRI (rs-fMRI) acquired before surgery (3T scanner). 54 patients with gliomas were included (M = 34, mean age = 50.8 y). Manual segmentation of lesions was performed on T1w and T2w MRI scans. Whole-brain measures of network centrality, modularity, integration and segregation were computed for a set of Regions of Interest (ROIs) including the Harvard Oxford anatomical atlas and tumor-related ROIs (i.e., edema, solid tumor, necrotic core). The analysis was performed on adjacency matrices obtained with a cost of 0.15, i.e. considering the 15% of the edges with the largest correlation coefficient values for each subject. A p< 0.05, two-sided, FDR corrected threshold was used for statistical analysis. In newly diagnosed patients (n = 18), we found a decrease of Integration (Degree, Global Efficiency) and Centrality (Betweenness Centrality) and an increase of Segregation (Local Efficiency) in the tumor ROIs compared to healthy brain regions. A similar integration/segregation imbalance pattern was present across the edema, solid tumor and necrotic core, with the edema being the most similar to healthy grey matter and the necrosis being the more altered, possibly reflecting tumor cells’ density and neuronal disruption. In patients at recurrence (n = 36), the same pattern was found, though with a less clear separation among tissue classes, possibly due to the altered anatomical/functional environment caused by functional plastic rearrangement and the effects the treatment(s). Finally, a significant correlation with overall survival was found for local efficiency values of the edema (p< 0.05, r 0,53=, R2 = 28%). We found significant alterations of functional connectome measures in brain regions affected by the tumor, with a decrease of network integration and an increase of network segregation measures characterizing different levels of tumor infiltration and potentially correlating with clinical outcomes.

INNV-24. MACHINE LEARNING-BASED SPECTROSCOPIC TISSUE DIFFERENTIATION IN FLUORESCENCE-GUIDED NEUROSURGERY

Abstract Maximal resection of malignant gliomas is hindered by difficulty in distinguishing tumor margins. Fluorescence-guided resection with 5-ALA assists in reaching this goal. Previously, we characterized five fluorophore emissions that accurately represent any spectrum measured from human brain tumor biopsies with a wide-field hyperspectral device. In this study, the effectiveness of these five spectra was explored for different tumor classification tasks in 891 hyperspectral widefield measurements of 184 patients harboring low- (n=30) and high-grade gliomas (n=115), non-glial primary brain tumors (n=19), radiation necrosis (n=2), miscellaneous (n=10) and metastases (n=8), which corresponds to up to 15000 spectra for a given test. The statistical differences in fluorophore abundances between classes were determined and visualized using dimensionality reduction techniques, including principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE). Three machine-learning models were trained to classify tumor type (12 classes), grade (3 classes), and glioma margins (3 classes). Five algorithms were tested with varying hyperparameters for each classification task. We explored whether PCA projection onto five different axes than fluorophore abundances can provide more information for visualization and classification. The abundances of the five a priori fluorophore spectra matched or outperformed the five optimal PCA components for all classification tasks. These five axes capture 96-99% of the variance in the dataset. Using random forests and multilayer perceptrons, the classifiers achieved average test accuracies of 74-82%, 79%, and 81%, respectively. All five fluorophore abundances varied between tumor margin type as well as between grades (p < 0.01). For tissue type, at least four of five fluorophore abundances were found to be significantly different (p < 0.01) between all classes. These results demonstrate the differing contribution of fluorophores in different tissue classes tissue, as well as the five fluorophores value as potential optical biomarkers, opening new opportunities for intraoperative classification systems in fluorescence-guided neurosurgery.

Enhancing epidural needle guidance using a polarization-sensitive optical coherence tomography probe with convolutional neural networks.

Epidural anesthesia helpsmanage pain during different surgeries. Nonetheless, the precise placement of the epidural needle remains a challenge. In this study, we developed a probe based on polarization-sensitive optical coherence tomography (PS-OCT) to enhance the epidural anesthesia needle placement. The probe was tested on six porcine spinal samples. The multimodal imaging guidance used the OCT intensity mode and three distinct PS-OCT modes: (1) phase retardation, (2) optic axis, and (3) degree of polarization uniformity (DOPU). Each mode enabled the classification of different epidural tissues through distinct imaging characteristics. To further streamline the tissue recognition procedure, convolutional neural network (CNN) were used to autonomously identify the tissue types within the probe's field of view. ResNet50 models were developed for all four imaging modes. DOPU imaging was found to provide the highest cross-testing accuracy of 91.53%. These results showed the improved precision by PS-OCT in guiding epidural anesthesia needle placement.

A data‐driven constitutive model for soft biological tissues

AbstractConstitutive modeling of soft biological tissues is crucial for biomedical simulations and a deep understanding of tissue mechanics. Classical constitutive models have a fixed mathematical expression, however, the microstructure and the corresponding macro‐mechanical response of different tissue types can vary significantly. A model that works for one tissue may not work for another kind of tissue, and choosing the right model may become challenging. To solve this issue, this study introduces a new data‐driven approach to creating a unified model for predicting the mechanical response of various tissue classes. The proposed model is based on B‐Spline approximations and assumes the strain energy function can be divided into volumetric, isotropic, and anisotropic components. The B‐Spline ansatz replaces partial derivatives of free energy energy function with respect to invariants with control points and polynomial degree, and allows the use of existing dispersion models. The model adapts its control point values to reduce the error between data and prediction until a threshold is reached, and is thermodynamically consistent through the use of optimization constraints. The model is demonstrated on various biological tissues, showing excellent fitting capabilities with a minimal number of control points. The outcome is a generic framework that can model any tissue given the data from experiments and imaging techniques.

Pathologic Findings in Severe Coal Workers' Pneumoconiosis in Contemporary US Coal Miners.

The pathology of coal workers' pneumoconiosis (CWP) and its most severe form-progressive massive fibrosis (PMF)-in US coal miners has changed in recent years. Severe disease is occurring in younger miners and has been linked to an increase in silica dust exposure. To update the description of the pathologic features of CWP in contemporary miners compared to historical miners. This study is a retrospective expert classification of lung tissue from 85 historical and contemporary coal miners with PMF. Significant pathologic features were scored by using a standardized instrument with consensus achieved for major findings, including newly defined categories of PMF as coal-type, mixed-type, and silica-type. Pathologic features associated with silica dust exposure, including silica-type PMF, mineral dust alveolar proteinosis (MDAP), and immature (early stage) silicotic nodules, were increased in contemporary miners. Detailed descriptions of the pathology of contemporary CWP with illustrative figures are provided. Silica-related pathologies are more common in contemporary miners. Severe forms of CWP can be detected by subtyping PMF lesions (if present) or by identification of mature and immature silicotic nodules, coal mine dust-related alveolar proteinosis, and severe inflammation in coal miners' lungs. Silica-type PMF cases showed significantly higher levels of MDAP than either mixed- or coal-type PMF (P < .001). High profusion of birefringent silica/silicate particles was observed more frequently in cases with immature (early stage) silicotic nodules (P = .04). Severe inflammation was also significantly increased in contemporary miners (P = .03). Our findings underscore the urgent need to revise current exposure limits and monitoring of respirable crystalline silica in US coal mines.

Semi-Supervised Bladder Tissue Classification in Multi-Domain Endoscopic Images.

Accurate visual classification of bladder tissue during Trans-Urethral Resection of Bladder Tumor (TURBT) procedures is essential to improve early cancer diagnosis and treatment. During TURBT interventions, White Light Imaging (WLI) and Narrow Band Imaging (NBI) techniques are used for lesion detection. Each imaging technique provides diverse visual information that allows clinicians to identify and classify cancerous lesions. Computer vision methods that use both imaging techniques could improve endoscopic diagnosis. We address the challenge of tissue classification when annotations are available only in one domain, in our case WLI, and the endoscopic images correspond to an unpaired dataset, i.e. there is no exact equivalent for every image in both NBI and WLI domains. We propose a semi-surprised Generative Adversarial Network (GAN)-based method composed of three main components: a teacher network trained on the labeled WLI data; a cycle-consistency GAN to perform unpaired image-to-image translation, and a multi-input student network. To ensure the quality of the synthetic images generated by the proposed GAN we perform a detailed quantitative, and qualitative analysis with the help of specialists. The overall average classification accuracy, precision, and recall obtained with the proposed method for tissue classification are 0.90, 0.88, and 0.89 respectively, while the same metrics obtained in the unlabeled domain (NBI) are 0.92, 0.64, and 0.94 respectively. The quality of the generated images is reliable enough to deceive specialists. This study shows the potential of using semi-supervised GAN-based bladder tissue classification when annotations are limited in multi-domain data.

Quantifying the Dosimetric Impact of Tissue Hounsfield Unit Assignment in Deep Learning-based Synthetic CT Images For MRI-Only Radiation Therapy of The Head and Neck

MRI-only simulation for head and neck (HN) radiotherapy (RT) could allow for single-image modality planning with excellent soft tissue contrast. In the MRI-only simulation workflow, synthetic CTs (sCTs) are generated from MRI to provide electron density information for dose calculation. Bone/air regions produce little MRI signal which could lead to electron density misclassification in sCTs. Establishing the dosimetric impact of this error could inform quality assurance (QA) procedures using MRI-only RT planning. In this study we quantify differences in Hounsfield Unit (HU) values between paired CT/ sCTs of HN cancer patients and investigate the dosimetric impact on clinical treatment plans. Fourteen patients with head and neck cancer undergoing same-day CT and 3T MRI simulation were retrospectively identified. MRIs were deformed to the CT using multimodal deformable image registration. SCTs were generated from T1w DIXON MRI using a commercially available deep learning-based generator (MRIplanner, Spectronics). Tissue voxel assignment was quantified by creating a CT-derived HU threshold contour. CT/sCT HU differences for anatomical/target contours and tissue classification regions including air (<-250HU), adipose tissue (-250HU to -51HU), soft tissue (-50HU to 199HU), spongy (200HU to 499HU) and cortical bone (> 500HU) were quantified. T-test was used to determine if sCT/CT HU differences were significant. The frequency of structures that had a HU difference >70HU (the CT window-width setting for intra-cranial structures) was computed to establish structure classification accuracy. Clinical IMRT treatment plans created on CTs were retrospectively recalculated on sCT images using compared using the gamma metric. The mean ratio of sCT HUs relative to CT for air, adipose tissue, soft tissue, spongy and cortical bone were 1.7±0.3, 1.1±0.1, 1.0±0.1, 0.9±0.1 and 0.8±0.1 (value of 1 indicates perfect agreement). T-tests (significance set at t = 0.05) identified differences in HU values for air, spongy and cortical bone in sCT images compared to CT. The structures with sCT/CT HU differences > 70HU were the L/R cochlea and mandible, occurring in >78% of the tested cohort. These structures contain dense bone/air interfaces. Plans recalculated on sCTs yielded global/local gamma pass rates of 98.7%±1.2% (3mm,3%) and 95.5%±2.5% (1mm,1%). Mean differences in D95, D50, D10 and D2 dose volume histogram (DVH) metrics for organ-at-risk (OAR) and planning tumor volumes (PTV) were 0.8%±1.5% and 2.1% ± 1.2% respectively. In this cohort, HU differences in sCTs were observed but did not translate into a reduction in gamma pass rates and OAR/PTV DVH metrics. The acquisition of additional training data such as ultrashort echo time MRI could improve bone/air contrast and reduce bone/air sCT misclassifications. Further studies will establish the variation in sCT dosimetric accuracy using a larger retrospective cohort to inform QA limits on clinical sCT usage.

CT-based volumetric measures obtained through deep learning: Association with biomarkers of neurodegeneration.

Cranial computed tomography (CT) is an affordable and widely available imaging modality that is used to assess structural abnormalities, but not to quantify neurodegeneration. Previously we developed a deep-learning-based model that produced accurate and robust cranial CT tissue classification. We analyzed 917 CT and 744 magnetic resonance (MR) scans from the Gothenburg H70 Birth Cohort, and 204 CT and 241 MR scans from participants of the Memory Clinic Cohort, Singapore. We tested associations between six CT-based volumetric measures (CTVMs) and existing clinical diagnoses, fluid and imaging biomarkers, and measures of cognition. CTVMs differentiated cognitively healthy individuals from dementia and prodromal dementia patients with high accuracy levels comparable to MR-based measures. CTVMs were significantly associated with measures of cognition and biochemical markers of neurodegeneration. These findings suggest the potential future use of CT-based volumetric measures as an informative first-line examination tool for neurodegenerative disease diagnostics after further validation. Computed tomography (CT)-based volumetric measures can distinguish between patients with neurodegenerative disease and healthy controls, as well as between patients with prodromal dementia and controls. CT-based volumetric measures associate well with relevant cognitive, biochemical, and neuroimaging markers of neurodegenerative diseases. Model performance, in terms of brain tissue classification, was consistent across two cohorts of diverse nature. Intermodality agreement between our automated CT-based and established magnetic resonance (MR)-based image segmentations was stronger than the agreement between visual CT and MR imaging assessment.

A deep learning image analysis method for renal perfusion estimation in pseudo-continuous arterial spin labelling MRI

Accurate segmentation of renal tissues is an essential step for renal perfusion estimation and postoperative assessment of the allograft. Images are usually manually labeled, which is tedious and prone to human error. We present an image analysis method for the automatic estimation of renal perfusion based on perfusion magnetic resonance imaging. Specifically, non-contrasted pseudo-continuous arterial spin labeling (PCASL) images are used for kidney transplant evaluation and perfusion estimation, as a biomarker of the status of the allograft. The proposed method uses machine/deep learning tools for the segmentation and classification of renal cortical and medullary tissues and automates the estimation of perfusion values. Data from 16 transplant patients has been used for the experiments. The automatic analysis of differentiated tissues within the kidney, such as cortex and medulla, is performed by employing the time-intensity-curves of non-contrasted T1-weighted MRI series. Specifically, using the Dice similarity coefficient as a figure of merit, results above 93%, 92% and 82% are obtained for whole kidney, cortex, and medulla, respectively. Besides, estimated cortical and medullary perfusion values are considered to be within the acceptable ranges within clinical practice.

A retrospective comparative study on the diagnostic efficacy and the complications: between CassiII rotational core biopsy and core needle biopsy.

Accurate pathologic diagnosis and molecular classification of breast mass biopsy tissue is important for determining individualized therapy for (neo)adjuvant systemic therapies for invasive breast cancer. The CassiII rotational core biopsy system is a novel biopsy technique with a guide needle and a "stick-freeze" technology. The comprehensive assessments including the concordance rates of diagnosis and biomarker status between CassiII and core needle biopsy were evaluated in this study. Estrogen receptor (ER), progesterone receptor (PgR), human epidermal growth factor receptor 2 (HER2), and Ki67 were analyzed through immunohistochemistry. In total, 655 patients with breast cancer who underwent surgery after biopsy at Sir Run Run Shaw Hospital between January 2019 to December 2021 were evaluated. The concordance rates (CRs) of malignant surgical specimens with CassiII needle biopsy was significantly high compared with core needle biopsy. Moreover, CassiII needle biopsy had about 20% improvement in sensitivity and about 5% improvement in positive predictive value compared to Core needle biopsy. The characteristics including age and tumor size were identified the risk factors for pathological inconsistencies with core needle biopsies. However, CassiII needle biopsy was associated with tumor diameter only. The CRs of ER, PgR, HER2, and Ki67 using Cassi needle were 98.08% (kappa, 0.941; p<.001), 90.77% (kappa, 0.812; p<.001), 69.62% (kappa, 0.482; p<.001), and 86.92% (kappa, 0.552; p<.001), respectively. Post-biopsy complications with CassiII needle biopsy were also collected. The complications of CassiII needle biopsy including chest stuffiness, pain and subcutaneous ecchymosis are not rare. The underlying mechanism of subcutaneous congestion or hematoma after CassiII needle biopsy might be the larger needle diameter and the effect of temperature on coagulation function. In summary, CassiII needle biopsy is age-independent and has a better accuracy than CNB for distinguishing carcinoma in situ and invasive carcinoma.

Improved accuracy in colorectal cancer tissue decomposition through refinement of established deep learning solutions

Hematoxylin and eosin-stained biopsy slides are regularly available for colorectal cancer patients. These slides are often not used to define objective biomarkers for patient stratification and treatment selection. Standard biomarkers often pertain to costly and slow genetic tests. However, recent work has shown that relevant biomarkers can be extracted from these images using convolutional neural networks (CNNs). The CNN-based biomarkers predicted colorectal cancer patient outcomes comparably to gold standards. Extracting CNN-biomarkers is fast, automatic, and of minimal cost. CNN-based biomarkers rely on the ability of CNNs to recognize distinct tissue types from microscope whole slide images. The quality of these biomarkers (coined ‘Deep Stroma’) depends on the accuracy of CNNs in decomposing all relevant tissue classes. Improving tissue decomposition accuracy is essential for improving the prognostic potential of CNN-biomarkers. In this study, we implemented a novel training strategy to refine an established CNN model, which then surpassed all previous solutions . We obtained a 95.6% average accuracy in the external test set and 99.5% in the internal test set. Our approach reduced errors in biomarker-relevant classes, such as Lymphocytes, and was the first to include interpretability methods. These methods were used to better apprehend our model’s limitations and capabilities.

Oxidation-resistant nanosensor: A label free, on-chip sensing approach of protein concentration, salinity, tissue classification

Numerous studies have used the Drude model to optimize silver-based Metal-Insulator-Metal plasmonic sensors for some limited sensing applications; however, Lab-on-a-chip sensing for cell protein concentration measurement still needs to be accomplished. Furthermore, little study has been conducted on sensing for the salinity measurement of seawater, Bovine serum albumin concentration measurement, human tissue categorization, mitigating the oxidation issue of these sensors, and nanofabrication challenges. In this article, a Metal-Insulator-Metal based oxidation free material (gold modeled with Drude-Lorentz model) built round-edged hexagonal plasmonic refractive index sensor with nanorods embedded both in the straight waveguide and resonator has been investigated using the Finite element method (FEM) for all of the above sensing applications. This sensor achieves 19.05 nm/g/100mL and 1476.6 nm/ppm sensitivity for cell protein concentration and salinity measurement. The sensor’s max sensitivity and Sensing Resolution are 9231.7 nm/RIU and 1.083∗10−7. This sensor has also been employed as an electromagnetic interference-free temperature sensor using toluene, achieving 5.16 nm/°C sensitivity. Thus, this label-free and low-footprint sensor can be employed to study the salinity of seawater, which is linked with global warming and the earth’s hydrologic cycle, study protein concentration for nanomedicine applications, and Lab-on-chip sensing as an oxidation-free alternative to silver-based sensors.

Hybrid Intelligent Pattern Recognition Systems for Mass Segmentation and Classification: A Pilot Study on Full-Field Digital Mammograms

Governments and health authorities emphasize the importance of early detection of breast cancer, usually through mammography, to improve prognosis, increase therapeutic options and achieve optimum outcomes. Despite technological advances and the advent of full-field digital mammography (FFDM), diagnosis of breast abnormalities on mammographic images remains a challenge due to qualitative variations in different tissue types and densities. Highly accurate computer-aided diagnosis (CADx) systems could assist in the differentiation between normal and abnormal tissue and the classification of abnormal tissue as benign or malignant. In this paper, classical, advanced fuzzy sets and fusion techniques for image enhancement were combined with three different thresholding methods (Global, Otsu and type-2 fuzzy sets threshold) and three different classifying techniques (K-means, FCM and ANFIS) for the classification of breast masses on FFDM. The aim of this paper is to identify the performance of the advanced fuzzy sets, fuzzy sets type-2 segmentation, decisions based on K-means and FCM, and the ANFIS classifier. Sixty-three combinations were evaluated on ninety-seven digital mammographic masses (sixty-five benign and thirty-two malignant). The performance of the sixty-three combinations was evaluated by estimating the accuracy, the F1 score, and the area under the curve (AUC). LH-XWW enhancement method with Otsu thresholding and FCM classifier outperformed all other combinations with an accuracy of 95.17%, F1 score of 89.42% and AUC of 0.91. This algorithm seems to offer a promising CADx system for breast cancer diagnosis on FFDM.

Early breast cancer detection and differentiation tool based on tissue impedance characteristics and machine learning.

During Basic screening, it is challenging, if not impossible to detect breast cancer especially in the earliest stage of tumor development. However, measuring the electrical impedance of biological tissue can detect abnormalities even before being palpable. Thus, we used impedance characteristics data of various breast tissue to develop a breast cancer screening tool guided and augmented by a deep learning (DL). A DL algorithm was trained to ideally classify six classes of breast cancer based on electrical impedance characteristics data of the breast tissue. The tool correctly predicted breast cancer in data of patients whose breast tissue impedance was reported to have been measured when other methods detected no anomaly in the tissue. Furthermore, a DL-based approach using Long Short-Term Memory (LSTM) effectively classified breast tissue with an accuracy of 96.67%. Thus, the DL algorithm and method we developed accurately augmented breast tissue classification using electrical impedance and enhanced the ability to detect and differentiate cancerous tissue in very early stages. However, more data and pre-clinical is required to improve the accuracy of this early breast cancer detection and differentiation tool.

Impact of artificial intelligence on healthcare

Artificial intelligence (AI) is revolutionizing various medical practices, making them more affordable, efficient, and faster. Its uses range from diagnosis, management, monitoring, and outcome forecasting to individualized care. AI technology in psychotherapy can help conditions such as dementia, autism spectrum disorder, and schizophrenia, and due to its image processing, segmentation, and reconstruction capabilities, AI has found applications in a wide range of fields, including the diagnosis of cancer, the treatment of skin lesions, the prediction of metastasis of malignancies, the staging of lung nodules, the identification of COVID-19, and the classification of thyroid tissue. In addition to histopathology images, imaging techniques such as CT, MRI, mammography, fundus imaging, and even photographs can be used to diagnose patients. In this study, we tried to address the current status and future scope of AI to bring substantial upliftment to health care. It is anticipated that human intelligence and AI will coexist in the field of medicine in the future. Modern smart devices collect a huge amount of data that can be used for disease prevention, health promotion, monitoring, and diagnosis in medicine. AI will improve as long as we train them. With the development of sophisticated machinery, robotics, and virtual reality, the healthcare industry is likely to undergo revolutionary changes. AI has performance on par with that of human experts, with the added benefits of scalability and automation. Before becoming fully autonomous in nature, AI systems might need tight supervision due to their lack of training, limited knowledge, and limited flexibility in clinical settings.