Prostate Cancer Detection and Analysis using Advanced Machine Learning

International Journal of Advanced Computer Science and Applications, Journal Year: 2023, Volume and Issue: 14(8)

Published: Jan. 1, 2023

Prostate cancer is one of the leading causes cancer-related deaths among men. Early detection prostate essential in improving survival rate patients. This study aimed to develop a machine-learning model for detecting and diagnosing using clinical radiological data. The dataset consists 200 patients with healthy controls extracted features from their Then, data trained evaluated several machines learning models, including logistic Regression, decision tree, random forest, support vector machine, neural network 10-fold cross-validation. Our results show that forest achieved highest accuracy 0.92, sensitivity 0.95 specificity 0.89. tree nearly similar 0.91, while regression, models lower accuracies 0.86, 0.87, 0.88, respectively. findings suggest machine can effectively detect diagnose may be most suitable this task.

Language: Английский

---

Novel Multiparametric Magnetic Resonance Imaging-Based Deep Learning and Clinical Parameter Integration for the Prediction of Long-Term Biochemical Recurrence-Free Survival in Prostate Cancer after Radical Prostatectomy

Cancers, Journal Year: 2023, Volume and Issue: 15(13), P. 3416 - 3416

Published: June 29, 2023

Radical prostatectomy (RP) is the main treatment of prostate cancer (PCa). Biochemical recurrence (BCR) following RP remains first sign aggressive disease; hence, better assessment potential long-term post-RP BCR-free survival crucial. Our study aimed to evaluate a combined clinical-deep learning (DL) model using multiparametric magnetic resonance imaging (mpMRI) for predicting in PCa. A total 437 patients with PCa who underwent mpMRI followed by between 2008 and 2009 were enrolled; radiomics features extracted from T2-weighted imaging, apparent diffusion coefficient maps, contrast-enhanced sequences manually delineating index tumors. Deep same set deep neural network based on pretrained EfficentNet-B0. Here, we present clinical (six variables), model, DL (DLM-Deep feature), clinical–radiomics (CRM-Multi), clinical–DL (CDLM-Deep feature) that built Cox models regularized least absolute shrinkage selection operator. We compared their prognostic performances stratified fivefold cross-validation. In median follow-up 61 months, 110/437 experienced BCR. CDLM-Deep feature achieved best performance (hazard ratio [HR] = 7.72), DLM-Deep (HR 4.37) or RM-Multi 2.67). CRM-Multi performed moderately. results confirm superior our mpMRI-derived algorithm over conventional radiomics.

Language: Английский

---

Prostate Cancer Detection in Colombian Patients through E-Senses Devices in Exhaled Breath and Urine Samples

Chemosensors, Journal Year: 2024, Volume and Issue: 12(1), P. 11 - 11

Published: Jan. 5, 2024

This work consists of a study to detect prostate cancer using E-senses devices based on electronic tongue and nose systems. Therefore, two groups confirmed control patients were invited participate through urine exhaled breath samples, where the group was categorized as Benign Prostatic Hyperplasia, Prostatitis, Healthy patients. Afterward, samples subsequently classified Pattern Recognition machine learning methods, results compared clinical history, obtaining 92.9% success rate in PCa samples’ classification accuracy by eTongue 100% eNose.

Language: Английский

---

Transfer Learning and Neural Network-Based Approach on Structural MRI Data for Prediction and Classification of Alzheimer’s Disease

Diagnostics, Journal Year: 2025, Volume and Issue: 15(3), P. 360 - 360

Published: Feb. 4, 2025

Background: Alzheimer’s disease (AD) is a neurodegenerative condition that has no definitive treatment, and its early diagnosis can help to prevent or slow down progress. Structural magnetic resonance imaging (sMRI) the progress of artificial intelligence (AI) have significant attention in AD detection. This study aims differentiate from NC distinguish between LMCI EMCI other two classes. Another goal diagnostic performance (accuracy AUC) sMRI for predicting stages. Methods: In this study, 398 participants were used ADNI OASIS global database including 98 individuals with AD, 102 mild cognitive impairment (EMCI), late (LMCI), 100 normal controls (NC). Results: The proposed model achieved high area under curve (AUC) values an accuracy 99.7%, which very remarkable all four classes: vs. AD: AUC = [0.985], NC: [0.961], [0.951], [0.989], LMCI: [1.000]. Conclusions: results reveal incorporates DenseNet169, transfer learning, class decomposition classify stages, particularly differentiating LMCI. performs well diagnostics at addition, accurate lead prediction prevention slowing before

Language: Английский

---

Prostate Biopsy Image Gleason Grading Classification using Machine Learning

Journal of Innovative Image Processing, Journal Year: 2025, Volume and Issue: 7(1), P. 146 - 160

Published: March 1, 2025

Prostate cancer diagnosis utilizes Gleason grading to analyze biopsy images establish severity levels. The analysis of prostate is an important step in automating the system, which helps and prognosis. subjective evaluation manual methods exposes vulnerabilities since they lead inconsistent results so automated solutions have become essential for precision reliability. Present machine learning algorithms show insufficient robustness because incorporate inadequate feature extraction approaches together with classifier choices. An ensemble Extra Trees model characteristics from serves as proposal classification. HSV color space produces three statistics (Mean, Standard Deviation, Skewness) colors addition entropy alongside four texture features derived GLCM includes Contrast, Energy, Homogeneity, Correlation. proposed receives against several classifiers include Nearest Neighbors, Linear SVM, Decision Tree, Random Forest. reaches 99% accuracy during testing proves better than baseline models thus indicating its potential trustworthy grading. significance this research improve efficiency using learning, aiding early treatment planning cancer.

Language: Английский

---

Supervised machine learning: A new method to predict the outcomes following exercise intervention in children with autism spectrum disorder

International Journal of Clinical and Health Psychology, Journal Year: 2023, Volume and Issue: 23(4), P. 100409 - 100409

Published: Sept. 7, 2023

The individual differences among children with autism spectrum disorder (ASD) may make it challenging to achieve comparable benefits from a specific exercise intervention program. A new method for predicting the possible outcomes and maximizing of ASD needs further exploration. Using mini-basketball training program (MBTP) studies improve symptom performance as an example, we used supervised machine learning predict based on ASD, investigated validated efficacy this method. In long-term study, included 41 who received MBTP. Before intervention, collected their clinical information, behavioral factors, brain structural indicators candidate factors. To perform regression classification tasks, random forest algorithm was selected, cross validation determine reliability prediction results. task social communication impairment outcome following MBTP in explainable variance evaluate predictive performance. distinguish core groups children, assessed accuracy. We discovered that models could (average explained 30.58%) accuracy 66.12%) MBTP, confirming can ASD. Our findings provide novel reliable identifying most likely benefit advance solid foundation establishing personalized recommendation system children.

Language: Английский

---

Prostate Cancer Detection from MRI Using Efficient Feature Extraction with Transfer Learning

Prostate Cancer, Journal Year: 2024, Volume and Issue: 2024, P. 1 - 28

Published: May 16, 2024

Prostate cancer is a common with significant implications for global health. Prompt and precise identification crucial efficient treatment strategizing enhanced patient results. This research study investigates the utilization of machine learning techniques to diagnose prostate cancer. It emphasizes utilizing deep models, namely VGG16, VGG19, ResNet50, ResNet50V2, extract relevant features. The random forest approach then uses these features classification. begins by doing thorough comparison examination architectures outlined above evaluate their effectiveness in extracting characteristics from imaging data. Key metrics such as sensitivity, specificity, accuracy are used assess models’ efficacy. With an 99.64%, ResNet50 outperformed other tested models when it came identifying important images Furthermore, analysis understanding factors aims offer valuable insights into decision-making process, thereby addressing critical problem clinical practice acceptance. classifier, powerful ensemble method renowned its adaptability ability handle intricate datasets, collected input. model seeks identify patterns feature space produce predictions on presence or absence In addition, tackles restricted availability datasets transfer methods refine using small amount annotated objective this improve generalize across different populations situations. study’s results useful because they show how well ResNet50V2 work field diagnosing cancer, forest’s classification abilities. provide basis creating reliable easily understandable learning-based diagnostic tools detecting will enhance possibility early diagnosis settings index terms learning, identification,

Language: Английский

---

Management of Patients With a Negative Multiparametric Prostate MRI Examination: AJR Expert Panel Narrative Review

American Journal of Roentgenology, Journal Year: 2023, Volume and Issue: 223(2)

Published: Oct. 25, 2023

Multiparametric MRI (mpMRI) of the prostate aids risk stratification patients with elevated PSA levels. Although most clinically significant cancers are detected by mpMRI, insignificant less evident. Thus, multiple international cancer guidelines now endorse routine use as a secondary screening test before biopsy. Nonetheless, management negative mpMRI results (defined PI-RADS category 1 or 2) remains unclear. This

Language: Английский

---

Transfer Learning Approach to Vascular Permeability Changes in Brain Metastasis Post-Whole-Brain Radiotherapy

Cancers, Journal Year: 2023, Volume and Issue: 15(10), P. 2703 - 2703

Published: May 10, 2023

The purpose of this study is to further validate the utility our previously developed CNN in an alternative small animal model BM through transfer learning. Unlike glioma model, mouse develops multifocal intracranial metastases, including both contrast enhancing and non-enhancing lesions on DCE MRI, thus serving as excellent brain tumor vascular permeability. Here, we conducted learning by transferring trained GBM MRI datasets mice. was re-trained learn about relationship between images target permeability maps extracted from Extended Tofts Model (ETM). transferred network found accurately predict presented with spatial correlation ETM PK maps. tested another cohort mice treated WBRT assess changes induced via radiotherapy. detected significantly increased parameter Ktrans WBRT-treated tumors (

Language: Английский

---

Towards Unsupervised Learning Driven Intelligence for Prediction of Prostate Cancer

Artificial Intelligence and Applications, Journal Year: 2024, Volume and Issue: 2(4), P. 263 - 270

Published: July 24, 2024

Prostate cancer is a widespread and global disease which affects adult males – it said that key causes of the include age, family history, ethnicity. In this study, Kaggle prostate dataset, comprising data from 100 patients with mixture both had did not have cancer, was used alongside machine learning prediction models for design unsupervised automated intelligent systems cancer. Two were designed underpinned by algorithms, namely fuzzy c-means agglomerative hierarchical clustering, where various able to make accuracies over 80% classification metrics, being predict an associated stage Both offer complimentary alternative each other, their relative merits are discussed in paper.

Language: Английский

---