Search

In 2020, the World Health Organization reported that breast cancer resulted in the deaths of 685,000 people worldwide, with 2.3 million women diagnosed with the disease. Breast cancer is the most common cancer globally, with 7.8 million women diagnosed in the past five years. Machine learning (ML) techniques can help identify breast cancer early and define its type by analyzing tumor size. ML models have been used for image classification and cancer prediction, and have been shown to be beneficial for breast cancer diagnosis. The current systematic review aims to highlight the gaps and shortcomings of previous works regarding the use of ML for breast cancer prediction based on image processing. The review updates publications to see the pros and cons of various ML and deep learning (DL) techniques, and can benefit medical practitioners seeking advanced therapies. The previous works mainly benefited from SVM, KNN, and DT in detecting BC; however, other techniques, especially the DL ones, can be useful. [ABSTRACT FROM AUTHOR]

Simple Summary: Lung and colon cancer are among the leading causes of cancer-related deaths globally, emphasizing the critical need for early and precise detection to improve treatment and patient outcomes. This research introduces a novel deep learning model for efficient lung and colon cancer detection, aiming to address the limitations of existing computationally intensive models. This study proposes a lightweight, parameter-efficient model suitable for mobile devices, utilizing a 1D convolutional neural network enhanced with Squeeze-and-Excitation layers. By achieving 100% accuracy on a large dataset of histopathological images, this research provides a significant advancement in cancer detection technology. The findings hold the potential to revolutionize medical diagnostics by enabling faster, more accessible, and reliable cancer screening, potentially leading to earlier interventions and improved survival rates. Lung and colon cancers are among the leading causes of cancer-related mortality worldwide. Early and accurate detection of these cancers is crucial for effective treatment and improved patient outcomes. False or incorrect detection is harmful. Accurately detecting cancer in a patient's tissue is crucial to their effective treatment. While analyzing tissue samples is complicated and time-consuming, deep learning techniques have made it possible to complete this process more efficiently and accurately. As a result, researchers can study more patients in a shorter amount of time and at a lower cost. Much research has been conducted to investigate deep learning models that require great computational ability and resources. However, none of these have had a 100 % accurate detection rate for these life-threatening malignancies. Misclassified or falsely detecting cancer can have very harmful consequences. This research proposes a new lightweight, parameter-efficient, and mobile-embedded deep learning model based on a 1D convolutional neural network with squeeze-and-excitation layers for efficient lung and colon cancer detection. This proposed model diagnoses and classifies lung squamous cell carcinomas and adenocarcinoma of the lung and colon from digital pathology images. Extensive experiment demonstrates that our proposed model achieves 100 % accuracy for detecting lung, colon, and lung and colon cancers from the histopathological (LC25000) lung and colon datasets, which is considered the best accuracy for around 0.35 million trainable parameters and around 6.4 million flops. Compared with the existing results, our proposed architecture shows state-of-the-art performance in lung, colon, and lung and colon cancer detection. [ABSTRACT FROM AUTHOR]

The convergence of tumor epigenetics and molecularly imprinted polymers (MIPs) holds promise in early cancer diagnostics. To the best of knowledge, none of the studies has achieved DNA methylation detection yet using MIPs and the proposed research will pioneer the application of MIPs for detecting DNA methylation, introducing a novel approach to enhance early diagnostic precision. [ABSTRACT FROM AUTHOR]

Metamaterials for refractive index sensing applications have garnered significant attention in recent years. However, achieving an optimal balance between high sensitivity and quality factor, which together determine the Figure of Merit of sensors, necessitates extensive optimization efforts. In this paper, we present the metaheuristic optimization of a refractive index-based plasmonic sensor operating at a wavelength of 1500 nm, which has the potential to open new avenues for applications in biomedical sensing and beyond. Particle Swarm Optimization is utilized to maximize the performance of the proposed infrared metamaterial sensor. The proposed design features two overlapping E-shaped silver patches placed on top of a grounded Al 2 O 3 substrate. This configuration results in a narrow-band absorption spectrum with peak resonances caused by the confinement of the electric field within the gaps of the E-shaped metallic arms. The metaheuristic optimization process yielded sensor dimensions that achieve a high sensitivity of 834.7 nm/RIU,Q = 865 and a Figure of Merit of 481.34 RIU - 1 , demonstrating outstanding performance in cancer cell detection. [ABSTRACT FROM AUTHOR]

In this paper, we present a graphene-based band-pass filter featuring rectangular-shaped resonators, based on research into the sensing characteristics of surface plasmon polaritons (SPP). The finite-difference time-domain (FDTD) method and simulations reveal that the transmission spectrum of this structure exhibits a dual-mode spectrum. This structure operates at two functional modes with wavelengths of 1135 nm and 1705 nm, and its compact size measures 330 nm × 480 nm. We investigated the effect of geometric parameters on the pass bands, finding transmission rates as high as 0.97 and 0.88, sensitivities of 2166.6 nm/RIU and 2000 nm/RIU, and figures of merit (FOM) of 50.38 and 38.46 RIU−1. Due to the minimal difference in the RI of cancer cells and the high sensitivity of the sensor, it is highly effective for cancer cell detection. Additionally, the accuracy of the sensor's performance is validated using a one-sample T-test, which confirms the precision and reliability of the designed sensor. [ABSTRACT FROM AUTHOR]

Fe3O4 magnetic nanoparticles exhibit significant potential for cancer detection due to their unique magnetic properties and versatility. This review examines their role in enhancing cancer biomarker detection, focusing on synthesis methods, surface modifications and diagnostic accuracy. Fe3O4 nanoparticles serve as sensitive MRI contrast agents, facilitating early cancer diagnosis and improving patient prognosis. Synthesis techniques influence their properties, morphology and dimensions, which affect performance. Surface modifications enhance targeting and reduce immunological reactions, enabling precise biomarker detection and effective drug delivery to tumours, minimizing damage to healthy tissue. Despite these advantages, challenges remain in optimizing delivery efficiency and overcoming medication resistance. Further research is required to understand the pharmacokinetics and pharmacodynamics of these nanoparticles, including their distribution, metabolism and physiological impacts. This review provides insights into the potential of Fe3O4 magnetic nanoparticles as cancer detection agents, aiming to guide future research towards developing safer and more efficient applications in medical diagnostics and treatment. [ABSTRACT FROM AUTHOR]

Background: This study aimed to analyze the relationship between the levels of tumor markers—specifically, carcinoembryonic antigen (CEA) and Ca19-9 antigen—determined in both serum (sCEA and sCa19-9) and intraoperative peritoneal washings (pCEA and pCa19-9) and the advanced stage of gastric cancer (including the occurrence of cancer cells in cytology from abdominal fluid). Methods: This study included 47 patients with histopathologically confirmed gastric cancer or gastroesophageal junction cancer who underwent surgical treatment. The material for the cytological examination and assessment of CEA and Ca19-9 concentrations in peritoneal fluid was collected intraoperatively. Later, blood was drawn to assess the CEA and Ca19-9 concentrations in blood serum. Results: There was a statistical correlation between a positive cytology result or the presence of peritoneal carcinomatosis and a positive result for the tumor markers obtained from abdominal washings. This correlation was not observed with marker levels obtained from blood serum. The pCEA marker was highly sensitive (93.3%) and specific (93.8%) for detecting cancer cells. The pCa19-9 marker was less effective in detecting cancer but matched pCEA in identifying the absence of cancer. No differences were observed in sCEA and sCA19-9 levels between patients who underwent neoadjuvant chemotherapy and those who did not receive this treatment. However, statistical analysis showed that this relationship did not apply to pCEA and pCa19-9 levels. Conclusions: Intraoperative determinations of tumor marker levels in peritoneal washings may be a predictive factor for a poor prognosis in patients with gastric cancer. [ABSTRACT FROM AUTHOR]

In the United Kingdom, radiographers with a qualification in image interpretation have interpreted mammograms since 1995. These radiographers work under the title of radiography advanced practitioners (RAP) or Consultant Radiographer. This study extends upon what has been very recently published by exploring further clinical, non-clinical and experiential factors that may impact the reporting performance of RAPs. Fifteen RAPs interpreted an image test set of 60 2D mammograms of known truth using the Detected-X software platform. Unknown to the reader, twenty cases contained a malignancy. Sensitivity, specificity, lesion sensitivity, receiver operating characteristic (ROC) and jack-knife free response operating characteristic (AFROC) values were established for each RAP. Specific features that had significant impact on accuracy were identified using Student's-T and Mann Whitney tests. RAPs with more than 10 years' experience in image interpretation, compared to those with less than 10 years' experience, demonstrated lower specificity (51.3% vs 84.8%, p = 0.0264), ROC (0.83 vs 0.91, p = 0.0264) and AFROC (0.75 vs 0.87, p = 0.0037) values. Further, higher sensitivity values of 90.7% were seen in those RAPs who had an eye test in the last year compared to those who had not, 82% (p = 0.021). Other changes are presented in the paper. These data reveal previously unidentified factors that impact the diagnostic efficacy of RAPs when interpreting mammographic images. Highlighting such findings will empower screening authorities to better examine ways of standardising performance and offer a baseline for performance benchmarks. This study for the first time performs an initial exploration of the factors that may be associated with RAP performance when interpreting screening mammograms. [ABSTRACT FROM AUTHOR]

Variational autoencoders (VAEs) are generative models known for learning compact and continuous latent representations of data. While they have proven effective in various applications, using latent representations for classification tasks presents challenges. Typically, a straightforward approach involves concatenating the mean and variance vectors and inputting them into a shallow neural network. In this paper, we introduce a novel approach for variational autoencoders, named VAE-GNA, which integrates Gaussian neurons into the latent space along with attention mechanisms. These neurons directly process mean and variance values through a suitable modified sigmoid function, not only improving classification, but also optimizing the training of the VAE in extracting features, in synergy with the classification network. Additionally, we investigate both additive and multiplicative attention mechanisms to enhance the model's capabilities. We applied the proposed method to automatic cancer detection using near-infrared (NIR) spectral data, showing that the experimental results of VAE-GNA surpass established baselines for spectral datasets. The results obtained indicate the feasibility and effectiveness of our approach. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) holds significant promise in transforming medical imaging, enhancing diagnostics, and refining treatment strategies. However, the reliance on extensive multicenter datasets for training AI models poses challenges due to privacy concerns. Federated learning provides a solution by facilitating collaborative model training across multiple centers without sharing raw data. This study introduces a federated attention-consistent learning (FACL) framework to address challenges associated with large-scale pathological images and data heterogeneity. FACL enhances model generalization by maximizing attention consistency between local clients and the server model. To ensure privacy and validate robustness, we incorporated differential privacy by introducing noise during parameter transfer. We assessed the effectiveness of FACL in cancer diagnosis and Gleason grading tasks using 19,461 whole-slide images of prostate cancer from multiple centers. In the diagnosis task, FACL achieved an area under the curve (AUC) of 0.9718, outperforming seven centers with an average AUC of 0.9499 when categories are relatively balanced. For the Gleason grading task, FACL attained a Kappa score of 0.8463, surpassing the average Kappa score of 0.7379 from six centers. In conclusion, FACL offers a robust, accurate, and cost-effective AI training model for prostate cancer pathology while maintaining effective data safeguards.

Abstract Cancer detection poses a significant challenge for researchers and clinical experts due to its status as the leading cause of global mortality. Early detection is crucial, but traditional cancer detection methods often rely on invasive procedures and time-consuming analyses, creating a demand for more efficient and accurate solutions. This paper addresses these challenges by utilizing automated cancer detection through AI-based techniques, specifically focusing on deep learning models. Convolutional Neural Networks (CNNs), including DenseNet121, DenseNet201, Xception, InceptionV3, MobileNetV2, NASNetLarge, NASNetMobile, InceptionResNetV2, VGG19, and ResNet152V2, are evaluated on image datasets for seven types of cancer: brain, oral, breast, kidney, Acute Lymphocytic Leukemia, lung and colon, and cervical cancer. Initially, images undergo segmentation techniques, proceeded by contour feature extraction where parameters such as perimeter, area, and epsilon are computed. The models are rigorously evaluated, with DenseNet121 achieving the highest validation accuracy as 99.94%, 0.0017 as loss, and the lowest Root Mean Square Error (RMSE) values as 0.036056 for training and 0.045826 for validation. These results revealed the capability of AI-based techniques in improving cancer detection accuracy, with DenseNet121 emerging as the most effective model in this study.

Breast cancer is globally known to be a major health concern that necessitates advancements in detection and classification methods. This study introduces a machine learning-based approach for breast cancer diagnosis using benign and malignant mammograms of breast cancer. A two-hidden-layer artificial neural network (ANN) model was designed to categorize breast cancer from mammographic images. Prior to analysis, the images were subjected to a sophisticated data augmentation process that leveraged data denoising, contrast enhancement, and the application of a generative adversarial network (GAN). This multi-enhancement preprocessing enriched the quality of the images and transformed them into a format more amenable to analysis by vectorizing the pixel data. The methodology involved rigorous training of the ANN on input images, resulting in a significant improvement in the model’s ability to classify breast cancer accurately. Experimental results demonstrate a notable enhancement in classification performance, with an increase in accuracy ranging from 22.5 to 42.5% compared to traditional scans. The final model achieved an impressive accuracy rate of unity, which considered all stages of image processing, including normal, contrast-enhanced, denoised, and GAN-enhanced scans. The outcomes of this research underlined the effectiveness of data augmentation and ANN in medical imaging. Future innovations in breast cancer diagnostics are elaborated by the potential to improve early detection and patient outcomes. The robust offered methodology for breast cancer detection is considered to be a significant contribution to biotechnological fields of interest.

Simple Summary: The incidence of endometrial cancer is increasing, creating a need for fast and efficient diagnostic methods. This study explores a new, non-invasive approach using urinary fluorescence spectroscopy to detect endometrial cancer. By analyzing morning urine samples and utilizing advanced machine learning techniques, we identified prospective spectral markers that differentiate between control, benign, and malignant gynecological patients. Our findings indicate good sensitivity and specificity, with high AUC from machine learning models, suggesting this method could significantly improve early cancer detection. This approach is easier and more affordable, especially in resource-limited settings. It has the potential to change the way endometrial cancer is diagnosed, offering a simpler and more accessible option for patients. Endometrial cancer is becoming increasingly common, highlighting the need for improved diagnostic methods that are both effective and non-invasive. This study investigates the use of urinary fluorescence spectroscopy as a potential diagnostic tool for endometrial cancer. Urine samples were collected from endometrial cancer patients (n = 77), patients with benign uterine tumors (n = 23), and control gynecological patients attending regular checkups or follow-ups (n = 96). These samples were analyzed using synchronous fluorescence spectroscopy to measure the total fluorescent metabolome profile, and specific fluorescence ratios were created to differentiate between control, benign, and malignant samples. These spectral markers demonstrated potential clinical applicability with AUC as high as 80%. Partial Least Squares Discriminant Analysis (PLS-DA) was employed to reduce data dimensionality and enhance class separation. Additionally, machine learning models, including Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), and Stochastic Gradient Descent (SGD), were utilized to distinguish between controls and endometrial cancer patients. PLS-DA achieved an overall accuracy of 79% and an AUC of 90%. These promising results indicate that urinary fluorescence spectroscopy, combined with advanced machine learning models, has the potential to revolutionize endometrial cancer diagnostics, offering a rapid, accurate, and non-invasive alternative to current methods. [ABSTRACT FROM AUTHOR]

Cancer cell‐triggered sol–gel transformation of mineralized hydrogel (PAA‐MnO2) is designed as a facile strategy for cancer detection by manipulating the mineralization process in the presence of cancer cells. The mineralization of polyacrylic acid (PAA) with calcium phosphate via carboxyl‐Ca2+ complex is initially inhibited by the incorporation of reactive oxygen species (ROS)‐sensitive manganese oxide (MnO2) with polymer dots (PDs). In this system, the mineralization can be induced after cleaving MnO2 into Mn2+ by high ROS levels in cancer cells, forming a PAA‐MnO2 mineralized hydrogel and resulting in a naked‐eye system for cancer monitoring. Naked‐eye monitoring of ROS‐responsive sol–gel transformation is performed using a circulator device containing circulating cells to discriminate cancer (HeLa, PC‐3, B16F10) from normal cells (CHO‐K1). With the incorporation of PDs, PAA‐MnO2 mineralized hydrogel not only provides physical transformation (stretchability, viscosity) but also fluorescence‐recovery and electroconductivity changes at different cancer‐cell concentrations (104–106 cells mL−1), including distinct strain–pressure responses that can be wirelessly monitored via smartphones. Furthermore, in vivo, experiments suggest that PAA‐MnO2 mineralized hydrogel can be formed in tumor‐bearing mice owing to its excellent ROS‐scavenging activity at the tumor site, as confirmed by SOD2 and gene‐expression analysis. Thus, this unique approach can potentially enable simple and effective cancer detection in future point‐of‐care diagnostics. [ABSTRACT FROM AUTHOR]

Background: The incidence of oral cancer is rising quickly among Indian people, primarily in the lower socioeconomic strata. Individuals who are economically and socially marginalised are more susceptible to mouth cancer. Aim: to determine the incidence of mouth cancer and precancerous lesions in participants who are Indian. Methods: To determine the prevalence, the oral cavity of 658 participants was clinically examined for any tissue growths, leathery changes, ulcerative changes, and white or red lesions. Results: In the current study, the overall prevalence of smoking and smokeless tobacco use was 65.2% (n=429) and 78.8% (n=518), respectively. Oral malignant and precancerous lesions were detected in 39.8% (n=262) of the samples. Of the individuals, 36.2% (n = 238) had positive samples from the buccal mucosa, whereas 6.1% (n = 40) had positive samples from the labial mucosa. Conclusions: Due to the high rates of tobacco use and related behaviours, oral cancer is quite common among Indian subjects, making the cessation centre a priority. To get better results, early screening and detection are also essential. [ABSTRACT FROM AUTHOR]

Nucleic acids, like DNA and RNA, serve as versatile recognition elements in electrochemical biosensors, demonstrating notable efficacy in detecting various cancer biomarkers with high sensitivity and selectivity. These biosensors offer advantages such as cost-effectiveness, rapid response, ease of operation, and minimal sample preparation. This review provides a comprehensive overview of recent developments in nucleic acid-based electrochemical biosensors for cancer diagnosis, comparing them with antibody-based counterparts. Specific examples targeting key cancer biomarkers, including prostate-specific antigen, microRNA-21, and carcinoembryonic antigen, are highlighted. The discussion delves into challenges and limitations, encompassing stability, reproducibility, interference, and standardization issues. The review suggests future research directions, exploring new nucleic acid recognition elements, innovative transducer materials and designs, novel signal amplification strategies, and integration with microfluidic devices or portable instruments. Evaluating these biosensors in clinical settings using actual samples from cancer patients or healthy donors is emphasized. These sensors are sensitive and specific at detecting non-communicable and communicable disease biomarkers. DNA and RNA's self-assembly, programmability, catalytic activity, and dynamic behavior enable adaptable sensing platforms. They can increase biosensor biocompatibility, stability, signal transduction, and amplification with nanomaterials. In conclusion, nucleic acids-based electrochemical biosensors hold significant potential to enhance cancer detection and treatment through early and accurate diagnosis. [ABSTRACT FROM AUTHOR]

Copyright of SDU Journal of Engineering Sciences & Design / Mühendislik Bilimleri ve Tasarım Dergisi is the property of Journal of Engineering Sciences & Design and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Imaging flow cytometry, which combines the advantages of flow cytometry and microscopy, has emerged as a powerful tool for cell analysis in various biomedical fields such as cancer detection. In this study, we develop multiplex imaging flow cytometry (mIFC) by employing a spatial wavelength division multiplexing technique. Our mIFC can simultaneously obtain brightfield and multi‐color fluorescence images of individual cells in flow, which are excited by a metal halide lamp and measured by a single detector. Statistical analysis results of multiplex imaging experiments with resolution test lens, magnification test lens, and fluorescent microspheres validate the operation of the mIFC with good imaging channel consistency and micron‐scale differentiation capabilities. A deep learning method is designed for multiplex image processing that consists of three deep learning networks (U‐net, very deep super resolution, and visual geometry group 19). It is demonstrated that the cluster of differentiation 24 (CD24) imaging channel is more sensitive than the brightfield, nucleus, or cancer antigen 125 (CA125) imaging channel in classifying the three types of ovarian cell lines (IOSE80 normal cell, A2780, and OVCAR3 cancer cells). An average accuracy rate of 97.1% is achieved for the classification of these three types of cells by deep learning analysis when all four imaging channels are considered. Our single‐detector mIFC is promising for the development of future imaging flow cytometers and for the automatic single‐cell analysis with deep learning in various biomedical fields. [ABSTRACT FROM AUTHOR]

Simple Summary: Gastric cancer is a major worldwide health concern, underscoring the importance of early detection to enhance patient outcomes. Traditional histological analysis, while considered the gold standard, is labour intensive and manual. Deep learning (DL) is a potential approach, but existing models fail to extract all of the visual data required for successful categorization. This work overcomes these constraints by using ensemble models that mix different deep-learning architectures to improve classification performance for stomach cancer diagnosis. Using the Gastric Histopathology Sub-Size Images Database, the ensemble models obtained an average accuracy of more than 99% at various resolutions. ResNet50, VGGNet, and ResNet34 performed better than EfficientNet and VitNet, with the ensemble model continuously delivering higher accuracy. These findings show that ensemble models may accurately detect important characteristics from smaller picture patches, allowing pathologists to diagnose stomach cancer early and increasing patient survival rates. Gastric cancer has become a serious worldwide health concern, emphasizing the crucial importance of early diagnosis measures to improve patient outcomes. While traditional histological image analysis is regarded as the clinical gold standard, it is labour intensive and manual. In recognition of this problem, there has been a rise in interest in the use of computer-aided diagnostic tools to help pathologists with their diagnostic efforts. In particular, deep learning (DL) has emerged as a promising solution in this sector. However, current DL models are still restricted in their ability to extract extensive visual characteristics for correct categorization. To address this limitation, this study proposes the use of ensemble models, which incorporate the capabilities of several deep-learning architectures and use aggregate knowledge of many models to improve classification performance, allowing for more accurate and efficient gastric cancer detection. To determine how well these proposed models performed, this study compared them with other works, all of which were based on the Gastric Histopathology Sub-Size Images Database, a publicly available dataset for gastric cancer. This research demonstrates that the ensemble models achieved a high detection accuracy across all sub-databases, with an average accuracy exceeding 99%. Specifically, ResNet50, VGGNet, and ResNet34 performed better than EfficientNet and VitNet. For the 80 × 80-pixel sub-database, ResNet34 exhibited an accuracy of approximately 93%, VGGNet achieved 94%, and the ensemble model excelled with 99%. In the 120 × 120-pixel sub-database, the ensemble model showed 99% accuracy, VGGNet 97%, and ResNet50 approximately 97%. For the 160 × 160-pixel sub-database, the ensemble model again achieved 99% accuracy, VGGNet 98%, ResNet50 98%, and EfficientNet 92%, highlighting the ensemble model's superior performance across all resolutions. Overall, the ensemble model consistently provided an accuracy of 99% across the three sub-pixel categories. These findings show that ensemble models may successfully detect critical characteristics from smaller patches and achieve high performance. The findings will help pathologists diagnose gastric cancer using histopathological images, leading to earlier identification and higher patient survival rates. [ABSTRACT FROM AUTHOR]

For many years, transrectal ultrasound‐guided (TRUS) prostate biopsies have been performed to establish a histological diagnosis of prostate cancer. This has been the recommended standard of care procedure, but has always carried risks, in particular the risk of post‐procedural sepsis, and the associated antibiotic burden and risk of development of antibiotic resistance. Transperineal (TP) prostate biopsies performed under local anaesthetic (LA) have been proposed as a possible solution to these issues, with potentially lower infectious complications, and avoidance of need for antibiotic prophylaxis. The European Association of Urology produced guidance in 2023 with 'weak' recommendations in favour of LATP biopsy as a new standard of care, citing its safety profile. Both the National Institute for Health and Care Excellence in the UK, and the American Urological Association in the United States, have concluded for now that the body of evidence is inadequate and not offered a similar recommendation. We discuss the available evidence, pros and cons of each technique, and the status of current trials in the field. We believe that clinical equipoise remains necessary, given the disparity in national and international guidelines highlighting the need for large randomised controlled trials to answer the question: is LATP biopsy really better than TRUS biopsy? [ABSTRACT FROM AUTHOR]

A novel design of an optical biosensor based on surface plasmon resonance using tin selenide (SnSe) and graphene is presented. Including biological solutions, the performance of the obtained biosensor over a wide range of refractive index variations is promising. It is designed such that its key parameters are optimized to detect different cancerous cells with high selectivity and sensing ability. The design and analysis of the sensor have been carried out by implementing a finite element method–based simulation platform. The results revealed that the designed sensor can provide a sensitivity of 121.0 deg.RIU−1, 134.2 deg.RIU−1, 142.9 deg.RIU−1, 143.6 deg.RIU−1, and 72.2 deg.RIU−1 for sensing skin, cervical, blood, adrenal gland, and breast cancerous cells respectively with maximum quality factor of 408 RIU−1 and a detection accuracy of 5.71. The results obtained using the proposed model of the SPR biosensor are promising. It could be a potential candidate for several sensing applications such as detecting different types of cancer disease in the early stages. Such detection is anticipated to save the lives of cancer patients. Comparing our results to work published recently, we were able to achieve an enhanced angular sensitivity (S) ranging from 72 to 143.6 deg.RIU−1, a detection accuracy (DA) ranging from 2.66 to 5.71, and a quality factor (QF) ranging from 190 to 408 RIU−1. [ABSTRACT FROM AUTHOR]

An innovative photonic crystal fiber (PCF) biosensor using surface plasmon resonance (SPR) to diagnose six distinct kinds of cancers (skin cancer, cervical cancer, adrenal gland cancer, blood cancer, and breast cancer types 1 and 2) in cells is demonstrated here and incorporates with two microchannels and a bimetallic configuration. The numerical analysis utilizes the finite element method (FEM) combined with perfectly matched layers (PML). The plasmonic material employed in the biosensor is gold (Au), and a supportive material, titanium dioxide (TiO2), is combined with Au. By combining these two materials, the sensor's performance is improved. The numerical calculations indicate that breast cancer type 2 has the highest wavelength sensitivity (24,285.71 nm/RIU) and amplitude sensitivity (3959 RIU−1). The rest of the cancer cells' wavelength sensitivities are 11,000.00 nm/RIU (skin cancer), 13,333.33 nm/RIU (cervical cancer), 15,000.00 nm/RIU (blood cancer), 17,142.85 nm/RIU (adrenal gland cancer), and 21,428.57 nm/RIU (breast cancer type 1). This advanced biosensor has several uses in biological sensing and medical technology, and it has the potential to revolutionize cancer identification and medical diagnosis. [ABSTRACT FROM AUTHOR]

The human papillomavirus (HPV) is a non-enveloped DNA virus transmitted through skin-to-skin contact that infects epithelial and mucosal tissue. It has over 200 known genotypes, classified by their pathogenicity as high-risk and low-risk categories. High-risk HPV genotypes are associated with the development of different types of cancers, including cervical cancer, which is a leading cause of mortality in women. In clinical practice and the market, the principal tests used to detect HPV are based on cytology, hybrid detection, and qPCR. However, these methodologies may not be ideal for the required timely diagnosis. Tests have been developed based on isothermal nucleic acid amplification tests (INAATs) as alternatives. These tests offer multiple advantages over the qPCR, such as not requiring specialized laboratories, highly trained personnel, or expensive equipment like thermocyclers. This review analyzes the different INAATs applied for the detection of HPV, considering the specific characteristics of each test, including the HPV genotypes, gene target, the limit of detection (LOD), detection methods, and detection time. Additionally, we discuss the tests available on the market that are approved by the Food and Drug Administration (FDA). Finally, we address the challenges and potential solutions for the large-scale implementation of INAATs, particularly in rural or underserved areas. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer ranks as the most prevalent cancer among women. Current screening includes regular mammography and subsequent biopsy if the mammography results are abnormal. These procedures are costly and uncomfortable. We propose an alternative non-invasive method based on X-ray scattering. Using a machine learning approach, we have examined almost 3000 measurements of cancerous and non-cancerous samples belonging to 110 patients and shown excellent results on cancer/non-cancer separation. This can lead to patient-friendly, fast, and economical solutions for breast cancer screening to complement mammography and reduce biopsy. It should be emphasized that this approach can be readily extended to other types of cancer and even other diseases. With breast cancer being one of the most widespread causes of death for women, there is an unmet need for its early detection. For this purpose, we propose a non-invasive approach based on X-ray scattering. We measured samples from 107 unique patients provided by the Breast Cancer Now Tissue Biobank, with the total dataset containing 2958 entries. Two different sample-to-detector distances, 2 and 16 cm, were used to access various structural biomarkers at distinct ranges of momentum transfer values. The biomarkers related to lipid metabolism are consistent with those of previous studies. Machine learning analysis based on the Random Forest Classifier demonstrates excellent performance metrics for cancer/non-cancer binary decisions. The best sensitivity and specificity values are 80% and 92%, respectively, for the sample-to-detector distance of 2 cm and 86% and 83% for the sample-to-detector distance of 16 cm. [ABSTRACT FROM AUTHOR]

Diagnostic encounters can be seen as complex socio‐material processes. Drawing on the new materialist ideas of Barad, we studied how an innovative technology became part of the intra‐actions between different human and non‐human materialities in a cervical cancer diagnostic process. While researching the development of a technology intended to improve cervical cancer detection, we carried out a series of observations of diagnostic encounters involving clinicians, patients and the device in a hospital. The intra‐actions between the different materialities had rhythmic properties, repeated activities and timings that varied in intensity, for example, movements, exchanged looks, and talk that helped co‐produce the diagnosis and maintain consent. Sadly, the device interfered with the rhythms, undermining the clinicians' desire to adopt it, despite it being more accurate at diagnosing ill health than previous assistive technologies. Studying rhythms as part of diagnostic encounters could help with the design and subsequent integration of novel technologies in healthcare, because they encompass relationships created by human and non‐human materialities. Importantly, highlighting the role of rhythms contributes another way diagnostic encounters are co‐produced between clinicians and patients, and how they can be disrupted, improving the understanding of how consent is maintained or lost. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI)-based image analysis has immense potential to support diagnostic histopathology, including cancer diagnostics. However, developing supervised AI methods requires large-scale annotated datasets. A potentially powerful solution is to augment training data with synthetic data. Latent diffusion models, which can generate high-quality, diverse synthetic images, are promising. However, the most common implementations rely on detailed textual descriptions, which are not generally available in this domain. This work proposes a method that constructs structured textual prompts from automatically extracted image features. We experiment with the PCam dataset, composed of tissue patches only loosely annotated as healthy or cancerous. We show that including image-derived features in the prompt, as opposed to only healthy and cancerous labels, improves the Fréchet Inception Distance (FID) by 88.6. We also show that pathologists find it challenging to detect synthetic images, with a median sensitivity/specificity of 0.55/0.55. Finally, we show that synthetic data effectively train AI models. [ABSTRACT FROM AUTHOR]

There is no significant difference between transperineal and transrectal biopsy infection rates without and with targeted antibiotic prophylaxis, respectively. The cancer detection rates were similar. Transperineal biopsy was associated with slightly more pain, but it improves antibiotic stewardship. The transrectal biopsy approach is traditionally used to detect prostate cancer. An alternative transperineal approach is historically performed under general anesthesia, but recent advances enable transperineal biopsy to be performed under local anesthesia. We sought to compare infectious complications of transperineal biopsy without antibiotic prophylaxis versus transrectal biopsy with targeted prophylaxis. We assigned biopsy-naïve participants to undergo transperineal biopsy without antibiotic prophylaxis versus transrectal biopsy with targeted prophylaxis (rectal culture screening for fluoroquinolone-resistant bacteria and antibiotic targeting to culture and sensitivity results) through a multicenter, randomized trial. The primary outcome was post-biopsy infection captured by a prospective medical review and patient report on a 7-d survey. The secondary outcomes included cancer detection, noninfectious complications, and a numerical rating scale (0–10) for biopsy-related pain and discomfort during and 7-d after biopsy. A total of 658 participants were randomized, with zero transperineal versus four (1.4%) transrectal biopsy infections (difference –1.4%; 95% confidence interval [CI] –3.2%, 0.3%; p = 0.059). The rates of other complications were very low and similar. Importantly, detection of clinically significant cancer was similar (53% transperineal vs 50% transrectal, adjusted difference 2.0%; 95% CI –6.0, 10). Participants in the transperineal arm experienced worse periprocedural pain (0.6 adjusted difference [0–10 scale], 95% CI 0.2, 0.9), but the effect was small and resolved by 7-d. Office-based transperineal biopsy is tolerable, does not compromise cancer detection, and did not result in infectious complications. Transrectal biopsy with targeted prophylaxis achieved similar infection rates, but requires rectal cultures and careful attention to antibiotic selection and administration. Consideration of these factors and antibiotic stewardship should guide clinical decision-making. In this multicenter randomized trial, we compare prostate biopsy infectious complications for the transperineal versus transrectal approach. The absence of infectious complications with transperineal biopsy without the use of preventative antibiotics is noteworthy, but not significantly different from transrectal biopsy with targeted antibiotic prophylaxis. [ABSTRACT FROM AUTHOR]

Recently, cancer has become one of the main diseases and causes of death of people all over the world. For this purpose, extensive research has been done on the prediction and early detection of this disease in the body of patients in different fields. Artificial intelligence and data mining approaches are among the methods that have helped researchers in diagnosing this disease. In this research, a machine learning approach for early and timely diagnosis of cancer disease is presented. For this purpose, it uses logistic regression techniques, Naive Bayes, two versions of Random Forest and Support Vector Machine, which work in parallel with each other. As a result of the integration of the techniques, the proposed system achieves higher accuracy and reduces errors compared to the basic methods. The performance of the proposed method was evaluated using different criteria and showed superior results compared to traditional methods. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is being used increasingly to detect fatal diseases such as cancer. The potential reduction in human error, rapid diagnosis, and consistency of judgment are the primary motives for using these applications. Artificial Neural Networks and Convolution Neural Networks are popular AI techniques being increasingly used in diagnosis. Numerous academics have explored and evaluated AI methods used in the detection of various cancer types for comparison and analysis. This study presents a thorough evaluation of the AI techniques used in cancer detection based on extensively researched studies and research trials published on the subject. The manuscript offers a thorough evaluation and comparison of the AI methods applied to the detection of five primary cancer types: breast cancer, lung cancer, colorectal cancer, prostate cancer, skin cancer, and digestive cancer. To determine how well these models compare with medical professionals’ judgments, the opinions of developed models and of experts are compared and provided in this paper. [ABSTRACT FROM AUTHOR]

In 2020, the World Health Organization reported that breast cancer resulted in the deaths of 685,000 people worldwide, with 2.3 million women diagnosed with the disease. Breast cancer is the most common cancer globally, with 7.8 million women diagnosed in the past five years. Machine learning (ML) techniques can help identify breast cancer early and define its type by analyzing tumor size. ML models have been used for image classification and cancer prediction, and have been shown to be beneficial for breast cancer diagnosis. The current systematic review aims to highlight the gaps and shortcomings of previous works regarding the use of ML for breast cancer prediction based on image processing. The review updates publications to see the pros and cons of various ML and deep learning (DL) techniques, and can benefit medical practitioners seeking advanced therapies. The previous works mainly benefited from SVM, KNN, and DT in detecting BC; however, other techniques, especially the DL ones, can be useful.

Summary: Background: Early detection of nasopharyngeal carcinoma (NPC) poses a significant challenge. The absence of highly sensitive and specific diagnostic biomarkers for nasopharyngeal carcinoma contributes to the unfavourable prognosis of NPC patients. Here, we aimed to establish a non-invasive approach for detecting NPC using circulating cell-free DNA (cfDNA). Methods: We investigated the potential of next-generation sequencing (NGS) of peripheral blood cells as a diagnostic tool for NPC. We collected data on genome-wide nucleosome footprint (NF), 5′-end motifs, fragmentation patterns, CNV information, and EBV content from 553 Chinese subjects, including 234 NPC patients and 319 healthy individuals. Through case–control analysis, we developed a diagnostic model for NPC, and validated its detection capability. Findings: Our findings revealed that the frequencies of NF, fragmentation, and motifs were significantly higher in NPC patients compared to healthy controls. We developed an NPC score based on these parameters that accurately distinguished NPC from non-NPC cases according to the American Joint Committee on Cancer staging system from non-NPC (validation set: area under curve (AUC) = 99.9% (95% CI: 99.8%–100%), se: 98.15%, sp: 100%). This model showed superior performance over plasma EBV DNA. Additionally, the NPC score effectively differentiated between NPC patients and healthy controls, even after clinical treatment. Furthermore, the NPC score was found to be independent of potential confounders such as age, sex, or TNM stage. Interpretation: We have developed and verified a non-invasive approach with substantial potential for clinical application in detecting NPC. Funding: A full list of funding bodies that contributed to this study can be found in Funding section.

Artificial intelligence (AI) is becoming all-pervasive, impacting our lives in ways that are sometimes visible, but at other times hidden. Algorithms that learn from data—be it consumer preferences, medical imaging data, or any other dataset—are influencing decisions and choices in every industry, and health care is no exception. When patient outcomes are at stake this raises questions of ethics, accountability, and accuracy. This article looks at how AI is currently being put to work in cardiology, how its range of applications might expand, and how health care professionals and technologists can work together to ensure that it is deployed in a way that is safe, efficient, and beneficial for all patients. [ABSTRACT FROM AUTHOR]