Search

This article discusses the integration of Artificial Intelligence (AI) and Machine Learning (ML) technologies in cancer research. It highlights how these technologies are transforming the diagnosis, treatment, and prevention of cancer by providing sophisticated analytical capabilities. The paper explores the mathematical foundations and practical implementations of AI and ML techniques in various aspects of cancer research, including detection, diagnosis, prognosis, and personalized treatment strategies. It also reviews influential algorithms such as Support Vector Machines (SVM), Convolutional Neural Networks (CNNs), and clustering techniques, and their roles in improving diagnostic accuracy and treatment efficacy. Please note that this preprint has not been peer-reviewed. [Extracted from the article]

A research paper from the Kalasalingam Academy of Research and Education in Tamil Nadu, India, introduces a model called Taylor-Tunicate Swarm Algorithm-based Generative Adversarial Networks (Taylor-TSA-based GANs) for cancer prediction. The model incorporates the Taylor series with the Tunicate Swarm Algorithm and uses the Yeo-Johnson transformation for data transformation. The feature fusion is evaluated by Deep Stacked Autoencoder, and the fused feature is given as input to the cancer prediction done by GAN trained by Taylor-TSA. The research concludes that the developed model is effective and efficient, with high accuracy, a low false positive rate, and a high true positive rate. [Extracted from the article]

A report from the China University of Petroleum (East China) discusses the need for modern technology, specifically artificial intelligence, to support the diagnosis of breast cancer. The existing computer-aided diagnostic systems for breast cancer are costly and limited in their capabilities. The report proposes the use of improved algorithms and a simple integrated system for pre-diagnosis of breast cancer based on CNN and Pyqt5. The system utilizes tensorflow and pytorch frameworks and includes a human-computer interaction GUI system interface. The research has been peer-reviewed and more information can be obtained from the China University of Petroleum (East China). [Extracted from the article]

A study conducted by researchers at Prince Sattam bin Abdulaziz University in Saudi Arabia explores the issue of balancing generation and demand in interconnected microgrids (MGs) to address security, power quality, and reliability concerns. The study proposes an optimized fractional order load frequency control (LFC) scheme with cascaded outer and inner control loops. The proposed controller, based on a modified version of the liver cancer optimization algorithm (MLCA), achieves better disturbance rejection compared to traditional LFC methods. The study also considers the contribution of electric vehicles and the high penetration of renewables to test the stability of the proposed LFC technique. The results confirm the superior response and improved performance of the proposed controller. [Extracted from the article]

A recent study conducted at Shiraz University aimed to improve the accuracy of breast cancer diagnosis by using a feature selection algorithm based on particle swarm optimization (PSO) combined with machine learning methods. The researchers tested their algorithm on three common breast cancer datasets and found that it significantly improved accuracy while reducing the number of features needed for diagnosis. The study suggests that the proposed algorithm has the potential to enhance breast cancer diagnosis and reduce cost and time. Further information on the study can be found in the International Journal of Computational Intelligence Systems. [Extracted from the article]

Researchers at Chitkara University in Punjab, India have developed an improved lung cancer segmentation technique using nature-inspired optimization approaches. The study focused on the precise identification of tumor nodules in lung cancer Computed Tomography (CT) images. The researchers integrated four nature-inspired swarm intelligent techniques with the K-means algorithm to address the visual challenges of segmentation. The results showed that the K-means algorithm with Cuckoo Search Algorithm (CSA) significantly improved the quality of lung cancer segmentation compared to other optimization approaches. This research provides a valuable tool for researchers to improve the segmentation of medical image datasets for identifying the targeted region of interest. [Extracted from the article]

A recent report from Universiti Malaya discusses research on cancer treatment using optimal control supported by swarm intelligence. The study aims to develop hybrid techniques that combine optimal control theory with evolutionary algorithms and multi-objective swarm algorithms to reduce cancerous cells while minimizing the use of chemotherapy medications and toxicity. Two hybrid techniques were proposed and evaluated, with MOEA/D emerging as the most effective algorithm in reducing tumor size and cancer drug concentration. The study highlights the importance of integrating optimal control theory and evolutionary algorithms for optimizing cancer chemotherapy treatment. [Extracted from the article]

A study conducted by researchers at Sun Yat-sen University in Guangdong, China, has developed a novel classification model to predict the recurrence of early-stage nasopharyngeal carcinoma after radiotherapy. The model combines unsupervised diagnostic feature learning with Adaboost ensemble learning, resulting in an accuracy of 80.33%, sensitivity of 79.55%, specificity of 80.43%, and GMean of 79.99%. The researchers believe that this model can be a valuable tool for medical professionals in predicting the likelihood of recurrence in the cervical lymph nodes following radiotherapy for early-stage nasopharyngeal carcinoma. [Extracted from the article]

This article discusses a study that compares seven different algorithms for tracing fibre-like structures in biomedical images. The analysis of these structures can help in understanding processes like angiogenesis and the effects of certain treatments. The study found that no single algorithm outperformed the others in all metrics, but the Trace Ridges algorithm ranked first in terms of total distance error. The algorithm is fully automatic and combines various image-processing techniques to accurately delineate the fibre-like structures. The article also provides information on where to access the code for the Trace Ridges algorithm. Please note that this preprint has not been peer-reviewed. [Extracted from the article]

Researchers from the College of Animal Sciences and Technology in Tongliao, China have developed a novel machine learning method for the early detection of brain tumors. The method combines the advantages of Gated Recurrent Unit (GRU) networks and the Enhanced Hybrid Dwarf Mongoose Optimization (EHDMO) algorithm to analyze MRI images and accurately detect brain tumors. The proposed method achieved high sensitivity, specificity, positive predictive value, negative predictive value, and accuracy, outperforming other recent methods. This research provides a promising approach to automate and improve brain tumor detection using advanced technology. [Extracted from the article]

Insilico Medicine, an AI-driven biotech company, has developed a groundbreaking algorithm called Quantum-assisted Fragment-based Automated Structure Generator (QFASG) that aids in automated drug design. QFASG uses advanced chemoinformatic techniques to create new small-molecule structures from a library of molecular fragments. The researchers successfully applied QFASG to generate new small-molecule inhibitors for two pharmacological targets involved in cancer pathogenesis. The algorithm's fully automated pipeline streamlines the process of structure generation and optimization, providing researchers with a powerful tool for accelerating the drug discovery process. [Extracted from the article]

Researchers from Hebei University in Baoding, China have developed a new algorithm for diagnosing neuroblastoma, a type of malignant solid tumor in children. The algorithm uses a network model based on the U-Net structure, with DenseNet as the encoder, to extract features from whole slide images of neuroblastoma. The algorithm achieved high accuracy in segmenting and counting poorly differentiated and differentiated cells, which can help determine the histopathological types and prognostic effects of neuroblastoma. The research has been peer-reviewed and published in the journal Signal Image and Video Processing. [Extracted from the article]

Researchers from Sohag University have developed a new algorithm, called RBNRO-DE, for gene selection in cancer classification using high-dimensional data. The algorithm was tested on 22 cancer datasets and compared to other meta-heuristic algorithms. The results showed that the RBNRO-DE algorithm achieved optimal convergence and classification accuracy up to 100%, with a feature reduction size of 98%. This research highlights the potential of RNA sequencing as a technique for gene profiling and quantification in cancer research. [Extracted from the article]

Researchers at Lovely Professional University in Phagwara, India have developed a hybrid feature selection technique to improve the speed and performance of machine learning models in diagnosing breast cancer. The technique combines Regularized Neighborhood Component Analysis (RNCA) and Binary Teaching Learning Based Optimization (BTLBO) algorithms to select the best features for classification. The results of the study showed that the hybrid model outperformed other feature selection methods in terms of classification accuracy, recall, and AUC measures. This research has been peer-reviewed and published in The International Arab Journal of Information Technology. [Extracted from the article]

A recent study by researchers at the University of Pennsylvania School of Medicine has examined the role of health care algorithms in perpetuating racial and ethnic disparities. The study found that removing race from a kidney function algorithm had unintended consequences, such as reducing chemotherapy access and eligibility for clinical trials for Black patients. The researchers emphasized the importance of intentionality in algorithm development and suggested strategies to mitigate disparities, including using non-race variables and refining algorithms to minimize disparities across groups. The study highlights the need for transparency and a race-aware approach in algorithm development to promote health care equity. [Extracted from the article]

A study conducted by researchers at the Nanyang Institute of Technology in Henan, China, proposes a new methodology for the early diagnosis of melanoma skin cancer using dermoscopic images. The method involves scaling and enhancing the quality of the images, extracting features based on the Gray-Level Co-occurrence Matrix (GLCM), and using a newly developed version of the Archimedes Optimization Algorithm (DAOA) to select the most relevant features. The selected features are then classified using a Support Vector Machine (SVM) to distinguish between benign and malignant lesions. The proposed method achieved high values for performance indicators and demonstrated an accuracy of 88%, sensitivity of 96%, specificity of 81%, precision of 97%, and F-measure of 97% for the diagnosis of melanoma. [Extracted from the article]

Northwestern University researchers have developed an AI-powered transfer learning approach that repurposes publicly available data to predict combinations of gene perturbations that can transform cell type or restore diseased cells to health. This approach has the potential to control cell behavior and transitions across cell types, which could be applied to regrowing injured tissues or transforming cancer cells back into normal cells. The researchers trained their AI to learn how gene expression gives rise to cell behavior using publicly available gene expression data and developed an algorithm to predict gene combinations that are most likely to induce a desired reprogramming transition. This approach addresses the main challenges of controlling cell behavior and can be applied to various biomedical conditions. [Extracted from the article]

A recent study conducted by the School of Computer Science at Cairo University focused on the early detection of hepatocellular carcinoma (HCC), a type of liver cancer, in Egyptian patients. The study proposed a model that utilizes machine learning algorithms to examine circulating microRNAs (miRNAs) as diagnostic and predictive markers for HCC. The model consists of three phases: data preprocessing, feature selection using a new algorithm called Binary African Vulture Optimization Algorithm (BAVO), and classification with support vector machine and k-folds cross-validation. The results showed that miRNAs-483-5p, 21, and 155 may serve as potential biomarkers for the early detection and prognosis of HCC. [Extracted from the article]

A recent report from the School of Electrical Engineering in Tamil Nadu, India discusses the use of machine learning and computer vision in cancer classification. The researchers highlight the potential of these technologies in speeding up the diagnosis of cancer and improving treatment planning. The report focuses on nine major cancer types and examines the use of various imaging modalities and machine learning algorithms in their classification. The objective of the study is to provide researchers and medical experts with a comprehensive understanding of the current state of cancer classification using computer vision and machine learning, with the aim of enhancing cancer detection and therapy precision. [Extracted from the article]

A recent study conducted at Anhui University in China has proposed a new algorithm called the adaptive conjugate gradient accelerated evolutionary algorithm (ACG-EA) for optimizing cancer treatment plans in intensity-modulated proton therapy. This technique is considered one of the most advanced cancer treatment methods due to the unique characteristics of proton radiation. The ACG-EA algorithm aims to generate diverse high-quality treatment plans simultaneously, addressing the limitations of existing optimization methods. Experimental results have shown promising performance in six clinical cancer cases. This research has been peer-reviewed and published in the journal Applied Soft Computing. [Extracted from the article]

A study conducted by the ACECR Institute of Higher Education in Isfahan, Iran, aimed to improve the performance of the Computer-Aided Detection (CAD) system for breast cancer detection using thermal images. The researchers developed an intelligent method that involved feature extraction, feature selection, classification, and artificial intelligence techniques. The method was evaluated using breast thermograms from 200 subjects, and the results showed high accuracy, sensitivity, and specificity when using different classifier algorithms. This study demonstrates the effectiveness of the intelligent method in improving the accuracy of breast cancer detection. [Extracted from the article]

Researchers from the University of Anbar have developed a deep learning algorithm using EfficientNet B3 for the detection of lung cancer. The algorithm aims to improve detection accuracy and potentially revolutionize medical imaging and patient care. The model was able to classify four different types of lung cancer with an accuracy rate of 96%, showing a 2.13% improvement compared to the best-trained classifier. The researchers believe that this model has the potential to enhance lung cancer detection and support early diagnosis. [Extracted from the article]

A consortium led by scientists from the German Cancer Research Center (DKFZ) and the National Center for Tumor Diseases (NCT) has developed an online tool called "Metrics Reloaded" to help users select the most suitable algorithm for AI-supported image analysis. The tool provides information on the strengths, weaknesses, and limitations of different validation metrics used to evaluate the performance of algorithms in medical image analysis. The researchers aim to improve the quality and reliability of AI-supported image analysis results, promoting confidence in routine clinical practice. The tool is applicable to various categories of image analysis problems and can be used for different types of medical images as well as other areas of image analysis. [Extracted from the article]

A research study conducted at Delhi Technological University in Delhi, India, has developed a new algorithm-based technique for diagnosing breast cancer. The study utilized the Wisconsin Breast Cancer Dataset and employed both SVM and KNN algorithms for data analysis. The proposed hybrid algorithm, called SSA-GWO, achieved an accuracy of 99.42% when applied to the dataset. The research concludes that the hybrid algorithm shows promise for diagnosing breast cancer in challenging situations. [Extracted from the article]

A new report discusses research findings on cancer gene selection using omics data. Researchers at Henan University in Kaifeng, People's Republic of China, have developed a two-stage prior LASSO (TSPLASSO) algorithm for gene selection. The algorithm incorporates prior knowledge of cancer genes and performs sample classification and variable selection simultaneously. Numerical simulations show that TSPLASSO improves the accuracy of variable selection by 5%-400% in various datasets. The TSPLASSO algorithm is considered efficient, stable, and practical for exploring biomedical and health informatics from omics data. [Extracted from the article]

Researchers from HITEC University in Taxila, Pakistan have developed a framework for classifying brain tumors using MRI scans. The framework utilizes a hybrid deep learning model and an optimal information fusion framework to improve accuracy. The researchers addressed the challenge of imbalanced training data by using a sparse autoencoder network to generate new images. They also utilized Bayesian optimization to initialize the hyperparameters of two pretrained neural networks. The proposed framework achieved an accuracy of 99.80% and showed improvement compared to existing methods. [Extracted from the article]

A research study conducted at GLA University in Mathura, India, explores the use of metaheuristic feature selection algorithms to improve the accuracy of machine learning models for breast cancer classification. The study introduces a hybrid approach that combines the Gravitational Search Optimization Algorithm (GSOA) and Emperor Penguin Optimization (EPO) to identify influential features while eliminating irrelevant ones. The research aims to determine the minimum number of features needed to achieve higher accuracy in breast cancer classification. The experimental results demonstrate promising outcomes, with an accuracy of 97.66%, sensitivity of 0.9687, specificity of 1.000, precision of 1.000, F1-score of 0.9516, and area under the curve (AUC) of 0.9980. [Extracted from the article]

A recent report from the University College of Engineering in Nagercoil, India highlights the use of infrared thermography as an effective screening method for detecting breast cancer. The report discusses the application of deep learning algorithms in thermography to increase the accuracy of detection. The researchers propose an automated and optimized convolution neural network-based system for tumor segmentation of breast thermogram images, using a bio-inspired optimization technique called the mayfly algorithm. The results of the study suggest that this technique can assist physicians in making better decisions regarding breast cancer diagnosis. [Extracted from the article]

Researchers from Tehran University of Medical Sciences have developed a new approach for automating the segmentation of glioblastoma multiforme (GBM) tumors from MRI images. The technique utilizes the Marker-controlled watershed segmentation (MCWS) algorithm, along with other image processing techniques, to improve segmentation accuracy. The study highlights the importance of reliable and accurate image segmentation for effective diagnosis and treatment planning of GBM tumors. The MCWS technique is considered an effective and efficient approach for segmenting challenging medical images. [Extracted from the article]

A recent study conducted by researchers at the University of Sydney explored the adaptability of artificial intelligence (AI) models to the Australian context of mammography for breast cancer diagnosis. The study examined the impact of image enhancement on model performance and analyzed the relationship between AI outputs and histopathological features. The results showed that AI models performed better when trained on a subset of mammograms with high concordance between radiologists' annotations and when image enhancement techniques were applied. The study concluded that AI models can enhance the accuracy of breast cancer diagnosis when certain factors, such as concordance classification, image enhancement, and transfer learning, are taken into account. [Extracted from the article]

A study conducted at the Affiliated Hospital of Guangdong Medical University in China explores the relationship between gut microbial homeostasis and liver cancer. The researchers propose an eigenvalue-based goodness-of-fit algorithm to evaluate intestinal microorganisms and liver cancer. They also analyze the diagnostic role of lgEr/lgFp on hepatocellular carcinoma and its relationship with AFP. The study concludes that there is a significant difference in the lgEr/lgFp ratio between the high AFP cirrhosis group and the liver cancer group, highlighting the influence of intestinal homeostasis on the development of liver cancer. [Extracted from the article]

A study conducted by researchers at Chengdu University of Traditional Chinese Medicine in Sichuan, China, explores the use of artificial intelligence in diagnosing breast cancer. The researchers propose a new method that utilizes a modified ZFNet network and an extreme learning machine (ELM) to enhance classification performance. The study compares the performance of their method to other well-known methods using various metrics and concludes that their approach, known as ZFNet-SWChOA-ELM, demonstrates the highest level of performance. This research has been peer-reviewed and provides valuable insights into the use of evolving deep convolutional neural networks for breast cancer diagnosis. [Extracted from the article]

A recent study conducted by researchers at the Nanyang Institute of Technology in China has developed a novel method for detecting oral cancer using an optimized version of Convolutional Neural Network (CNN). The researchers incorporated the Seagull Optimization Algorithm and Particle Swarm Optimization Algorithm to optimize the CNN architecture specifically for oral cancer detection. By combining these algorithms, the proposed method enhances the performance and accuracy of the CNN in identifying cancerous regions in oral images. The results of the study showed that the proposed CSOA-based CNN system achieved the highest accuracy rate (96.94%) compared to other methods, indicating its superior performance in oral cancer detection. The researchers concluded that their innovative integration of these algorithms with CNN, along with advanced image processing techniques, provides a reliable and effective solution for early detection of oral cancer. [Extracted from the article]

Researchers from Coimbatore, India have developed a two-phase deep learning-based framework to recognize and classify brain cancers in magnetic resonance images (MRIs). The first phase utilizes a new DTA approach to identify tumor MRI images from healthy individuals, while the second phase employs a hybrid features fusion-based brain tumor classification technique. The researchers evaluated several segmentation algorithms for MRI and PET scans, including Ant Colony Optimization, Wavelet Transform, Gradient Vector Flow, Gray level Co-occurrence matrix, and Artificial Bee Colony. The study found that the GVF strategy performed better with MRI images, while the ABC and ACO approaches performed similarly with PET scans. [Extracted from the article]