(Press-News.org) Background and objectives
Lung cancer remains the leading cause of cancer-related mortality worldwide. Early detection of pulmonary nodules is crucial for timely diagnosis and effective treatment. Conventional computer-aided detection systems have shown limitations, including high false-positive rates and low sensitivity. Recent advances in deep learning, particularly convolutional neural networks (CNNs), have shown great potential in improving the accuracy and reliability of nodule detection and classification. This study aimed to develop and evaluate an automatic method for lung nodule detection and classification using a CNN-based architecture applied to computed tomography images from the publicly available LIDC-IDRI database.
Methods
This retrospective study was conducted on 82 patients (10,496 computed tomography slices) selected from the LIDC-IDRI database. The proposed method consists of five main steps: image preprocessing, lung parenchyma segmentation using Otsu’s thresholding and morphological operations, detection of nodule candidates, feature extraction, and classification using a CNN model. The CNN architecture includes two convolutional layers (20 and 30 filters, 3×3 kernel), ReLU activation, max-pooling layers, and a Softmax output layer. The network was trained with a mini-batch size of 32 for 50 epochs using the Stochastic Gradient Descent with Momentum optimizer (learning rate = 0.001, momentum = 0.9). Model performance was evaluated in terms of sensitivity, specificity, precision, and accuracy.
Results
The proposed CNN model successfully detected pulmonary nodules and achieved accurate classification between benign and malignant nodules. On the LIDC-IDRI dataset, the model achieved a sensitivity of 98.7%, specificity of 97.5%, precision of 97.9%, and accuracy of 98.4%. Comparative analysis with recent studies, including hybrid CNN-long short-term memory and ResNet-based models, demonstrated that the proposed method provides competitive performance while maintaining lower computational complexity. The classification of nodule subtypes (solid, partially frosted, totally frosted) showed satisfactory discrimination results.
Conclusions
The proposed CNN-based system demonstrates the feasibility and robustness of deep learning for automatic lung nodule detection and classification. Despite strong results, the study acknowledges limitations such as single-database validation and a relatively small training size. Future work will focus on validating the model across other datasets (e.g., ELCAP, NELSON) and optimizing multi-class classification performance to enhance generalizability and clinical applicability.
Full text:
https://www.xiahepublishing.com/2472-0712/ERHM-2025-00032
The study was recently published in the Exploratory Research and Hypothesis in Medicine.
Exploratory Research and Hypothesis in Medicine (ERHM) publishes original exploratory research articles and state-of-the-art reviews that focus on novel findings and the most recent scientific advances that support new hypotheses in medicine. The journal accepts a wide range of topics, including innovative diagnostic and therapeutic modalities as well as insightful theories related to the practice of medicine. The exploratory research published in ERHM does not necessarily need to be comprehensive and conclusive, but the study design must be solid, the methodologies must be reliable, the results must be true, and the hypothesis must be rational and justifiable with evidence.
Follow us on X: @xiahepublishing
Follow us on LinkedIn: Xia & He Publishing Inc.
END
PULLMAN, Wash. — NBA teams that paid their core players inequitably won fewer games as a result of reduced cooperation, according to a Washington State University study with implications for workplace management.
While it draws on data from professional basketball, the study suggests that managers in the workplace should ensure they’re paying top performers fairly in relation to each other and emphasize the goal of team coordination — organized, synchronized effort, with each team member ...
As corporate commitments to environmental, social, and governance (ESG) goals reach an all-time high, a persistent blind spot remains: water. Long emphasized by Professor Yong Sik Ok of Korea University, who serves as President of the International ESG Association, water stewardship has lagged behind carbon emissions, which are now tracked with near-surgical precision. In contrast, corporate water management is often confined to vague qualitative disclosures and limited metrics.
To address this imbalance, a research team ...
Cells constantly monitor and recycle their proteins through a tightly regulated waste-disposal system. Proteins that are no longer needed are tagged and broken down by specialized cellular machinery. Recent advances in drug discovery seek to exploit this system by redirecting it toward disease-relevant targets.
This strategy relies on so-called molecular glues, small molecules that induce interactions between proteins that would not normally bind to each other. If a disease-causing protein can be brought into contact with a cellular degradation enzyme, it is selectively eliminated ...
Insulin resistance — when the body doesn't properly respond to insulin, a hormone that helps control blood glucose levels — is one of the fundamental causes of diabetes. In addition to diabetes, it is widely known that insulin resistance can lead to cardiovascular, kidney and liver diseases. While insulin resistance is tightly associated with obesity, it has been difficult to evaluate insulin resistance itself in the clinic. For ...
Despite being riddled with impurities and defects, solution-processed lead-halide perovskites are surprisingly efficient at converting solar energy into electricity. Their efficiency is approaching that of silicon-based solar cells, the industry standard. In a new study published in Nature Communications, physicists at the Institute of Science and Technology Austria (ISTA) present a comprehensive explanation of the mechanism behind perovskite efficiency that has long perplexed researchers.
How can a device assembled with minimal sophistication rival state-of-the-art technology ...
Osmotic energy, often called blue energy, is a promising way to generate sustainable electricity from the natural mixing of salt and fresh water. It exploits the voltage that arises when ions from saltwater pass through an ion-selective membrane toward water with a lower salt concentration. However, membranes that let ions flow quickly are usually less selective, and challenges such as maintaining charge separation and mechanical robustness have kept most osmotic energy systems at the experimental stage.
Researchers ...
An international study led by researchers from the Sant Pau Research Institute (IR Sant Pau) shows that advanced use of magnetic resonance imaging (MRI) allows much more accurate identification of patients with progressive supranuclear palsy (PSP) and corticobasal degeneration (CBD). These are two rare and clearly underdiagnosed atypical parkinsonian disorders.
The study, published in The Journal of Prevention of Alzheimer’s Disease, shows that this strategy improves early diagnosis and ...
ANN ARBOR, Mich. – Sudden cardiac arrest can happen to anyone, including teens, and a new national poll suggests many schools and families may not be fully prepared to respond.
Only about half of parents say they are aware that their teen’s school has an automated external defibrillator, or AED, on site. Even fewer know where it is located or feel confident that school staff could use it in an emergency, according to the University of Michigan Health C.S. Mott Children’s Hospital National Poll ...
Secondary infections caused by bacteria or viruses during hospital care remain a long-standing global challenge, despite advances in modern medicine. In particular, mixed bacterial–viral infections in critically ill or immunocompromised patients are extremely difficult to treat and are associated with significantly increased mortality.
At the same time, the rapid rise of antibiotic-resistant bacteria and the frequent emergence of viral variants have exposed the limitations of existing antibiotics and vaccines. These ...
EMBARGOED UNTIL MONDAY, FEBRUARY 16, 2026 12:01 A.M. EST
NOTE TO EDITOR: Multimedia elements available for download: https://bit.ly/3NWbA0I
Survey: 3 in 4 skip physical therapy homework, stunting progress
Key takeaways:
A new survey by The Ohio State University Wexner Medical Center reveals 76% of people admit they don’t complete their physical therapy homework.
Physical therapists say successful recovery involves adding home exercises to existing routines—like ...
