A prospective study was undertaken to investigate the potential value of morphometry and artificial neural networks (ANN) for the discrimination of benign and malignant gastric lesions. Two thousand five hundred cells from 23 cases of cancer, 19 cases of gastritis and 58 cases of ulcer were selected as a training set, and an additional 8524 cells from an equal number of cases of cancer, gastritis and ulcer were used as a test set. Images of routine processed gastric smears stained by the Papanicolaou technique were processed by a custom image analysis system. The application of the learning vector quantization (LVQ) classifier enabled correct classification of > 97% of benign cells and > 95% of malignant cells, obtaining an overall accuracy of > 97%. This study presents the capabilities of ANN, and also indicates that ANN and image morphometry may offer useful information on the potential of malignancy in gastric cells.
Download full-text PDF |
Source |
|---|
Publication Analysis
Top Keywords
Similar Publications
Decision tree-based learning and laboratory data mining: an efficient approach to amebiasis testing.
Parasit Vectors
January 2025
Faculty of Information Technology, Mutah University, Mutah, Jordan.
Background: Amebiasis represents a significant global health concern. This is especially evident in developing countries, where infections are more common. The primary diagnostic method in laboratories involves the microscopy of stool samples.
View Article and Find Full Text PDFAccuracy of remote, video-based supraventricular tachycardia detection in patients undergoing elective electrical cardioversion: a prospective cohort.
J Clin Monit Comput
January 2025
Department of Electrical Engineering, Eindhoven University of Technology, Groene Loper 3, 5612 AZ, Eindhoven, the Netherlands.
Unobtrusive pulse rate monitoring by continuous video recording, based on remote photoplethysmography (rPPG), might enable early detection of perioperative arrhythmias in general ward patients. However, the accuracy of an rPPG-based machine learning model to monitor the pulse rate during sinus rhythm and arrhythmias is unknown. We conducted a prospective, observational diagnostic study in a cohort with a high prevalence of arrhythmias (patients undergoing elective electrical cardioversion).
View Article and Find Full Text PDFPrediction of mortality in heart failure by machine learning. Comparison with statistical modeling.
Eur J Intern Med
January 2025
Istituti Clinici Scientifici Maugeri, IRCCS, Institute of Bari, Bari, Italy.
Background: Assessing the relative performance of machine learning (ML) methods and conventional statistical methods in predicting prognosis in heart failure (HF) still remains a challenging research field.
Methods: The primary outcome was three-year mortality. The following 5 machine learning approaches were used for modeling: Random Forest (RF), Gradient Boosting, Extreme Gradient Boosting (XGBoost), Support Vector Machine, and Multilayer perceptron.
The Use of Artificial Intelligence and Wearable Inertial Measurement Units in Medicine: Systematic Review.
JMIR Mhealth Uhealth
January 2025
Institute for AI and Informatics in Medicine, Technical University of Munich, Munich, Germany.
Background: Artificial intelligence (AI) has already revolutionized the analysis of image, text, and tabular data, bringing significant advances across many medical sectors. Now, by combining with wearable inertial measurement units (IMUs), AI could transform health care again by opening new opportunities in patient care and medical research.
Objective: This systematic review aims to evaluate the integration of AI models with wearable IMUs in health care, identifying current applications, challenges, and future opportunities.
A machine-learning-integrated portable electrochemiluminescence sensing platform for the visualization and high-throughput immunoassays.
Talanta
January 2025
College of Chemistry and Environmental Engineering, Shenzhen University, Shenzhen, Guangdong 518060, PR China. Electronic address:
Electrochemiluminescence (ECL)-based point-of-care testing (POCT) has the potential to facilitate the rapid identification of diseases, offering advantages such as high sensitivity, strong selectivity, and minimal background interference. However, as the throughput of these devices increases, the issues of increased energy consumption and cross-contamination of samples remain. In this study, a high-throughput ECL biosensor platform with the assistance of machine learning algorithms is developed by combining a microcolumn array electrode, a microelectrochemical workstation, and a smartphone with custom software.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!