Optimizing double-layered convolutional neural networks for efficient lung cancer classification through hyperparameter optimization and advanced image pre-processing techniques

BMC Medical Informatics and Decision Making, Journal Year: 2024, Volume and Issue: 24(1)

Published: May 27, 2024

Abstract Lung cancer remains a leading cause of cancer-related mortality globally, with prognosis significantly dependent on early-stage detection. Traditional diagnostic methods, though effective, often face challenges regarding accuracy, early detection, and scalability, being invasive, time-consuming, prone to ambiguous interpretations. This study proposes an advanced machine learning model designed enhance lung stage classification using CT scan images, aiming overcome these limitations by offering faster, non-invasive, reliable tool. Utilizing the IQ-OTHNCCD dataset, comprising scans from various stages healthy individuals, we performed extensive preprocessing including resizing, normalization, Gaussian blurring. A Convolutional Neural Network (CNN) was then trained this preprocessed data, class imbalance addressed Synthetic Minority Over-sampling Technique (SMOTE). The model’s performance evaluated through metrics such as precision, recall, F1-score, ROC curve analysis. results demonstrated accuracy 99.64%, F1-score values exceeding 98% across all categories. SMOTE enhanced ability classify underrepresented classes, contributing robustness These findings underscore potential in transforming diagnostics, providing high classification, which could facilitate detection tailored treatment strategies, ultimately improving patient outcomes.

Language: Английский

---

Efficient artificial intelligence approaches for medical image processing in healthcare: comprehensive review, taxonomy, and analysis

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(8)

Published: July 29, 2024

Abstract In healthcare, medical practitioners employ various imaging techniques such as CT, X-ray, PET, and MRI to diagnose patients, emphasizing the crucial need for early disease detection enhance survival rates. Medical Image Analysis (MIA) has undergone a transformative shift with integration of Artificial Intelligence (AI) Machine Learning (ML) Deep (DL), promising advanced diagnostics improved healthcare outcomes. Despite these advancements, comprehensive understanding efficiency metrics, computational complexities, interpretability, scalability AI based approaches in MIA is essential practical feasibility real-world environments. Existing studies exploring applications lack consolidated review covering major stages specifically focused on evaluating approaches. The absence structured framework limits decision-making researchers, practitioners, policymakers selecting implementing optimal healthcare. Furthermore, standardized evaluation metrics complicates methodology comparison, hindering development efficient This article addresses challenges through review, taxonomy, analysis existing AI-based taxonomy covers image processing stages, classifying each stage method further analyzing them origin, objective, method, dataset, reveal their strengths weaknesses. Additionally, comparative conducted evaluate over five publically available datasets: ISIC 2018, CVC-Clinic, 2018 DSB, DRIVE, EM terms accuracy, precision, Recall, F-measure, mIoU, specificity. popular public datasets are briefly described analyzed. resulting provides landscape facilitating evidence-based guiding future research efforts toward scalable meet current needs.

Language: Английский

---

A comprehensive analysis of recent advancements in cancer detection using machine learning and deep learning models for improved diagnostics

Journal of Cancer Research and Clinical Oncology, Journal Year: 2023, Volume and Issue: 149(15), P. 14365 - 14408

Published: Aug. 4, 2023

Language: Английский

---

Lung Cancer Detection and Classification from Chest CT Images Using an Ensemble Deep Learning Approach

Published: May 2, 2024

Nowadays, Cancer's devastating impact is growing, taking thousands of lives prematurely each day. Lung cancer stands at the forefront this grim reality. Timely and accurate diagnosis crucial, as it directly correlates with effective treatment improved patient outcomes. In paper, we proposed an ensemble deep-learning method for detecting classifying lung cancers that greatly Computer Aided Diagnosis (CAD) system. Initially, three deep convolutional neural networks (CNN) Transfer Learning Approaches, MobileNetV2, VGG19, Resnet50, were used individually to perform classification. Then, these models are combined better in using fusion chest CT PET-CT images. This approach leverages strengths ResNet50's pretrained weights feature extraction, then extracted features concatenated classification through weighted average technique. After extensive experimental analysis, model achieved a test accuracy 98.93%, which than individual performance (98.67% 98.20% 97.67% ResNet50). It can be efficient diagnostic tool detection, prediction results learning outperform recent approaches.

Language: Английский

---

FedLRes: enhancing lung cancer detection using federated learning with convolution neural network (ResNet50)

Neural Computing and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 3, 2025

Language: Английский

---

A Hybrid LECNN Architecture: A Computer-Assisted Early Diagnosis System for Lung Cancer Using CT Images

International Journal of Computational Intelligence Systems, Journal Year: 2025, Volume and Issue: 18(1)

Published: Feb. 18, 2025

Language: Английский

---

Holistic evaluation and generalization enhancement of CART-ANOVA based transfer learning approach for brain tumor classifications

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 107, P. 107829 - 107829

Published: April 3, 2025

Language: Английский

---

Enhancing lung cancer detection through integrated deep learning and transformer models

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: May 4, 2025

Lung cancer has been stated as one of the prevalent killers up to this present time and clearly underlines rationale for early diagnosis enhance life expectancy patients afflicted with condition. The reasons behind usage transformer deep learning classifiers detection lung include accuracy, robustness along capability handle evaluate large data sets much more. Such models can be more complex help utilize multiple modalities give extensive information that will critical in ascertaining right at time. However, existing works encounter several limitations including reliance on annotated data, overfitting, high computation complexity, interpretability. Third, issue stability these models' performance when applied actual clinical datasets is still an open question; even bigger greatly reduce utilization practice. To tackle these, we develop a novel Cancer Nexus Synergy (CanNS), which applies A. Swin-Transformer UNet (SwiNet) Model segmentation, Xception-LSTM GAN (XLG) CancerNet classification, Devilish Levy Optimization (DevLO) fine-tuning parameters. This paper breaks new ground presented elements are incorporated manner co-operatively elevates diagnostic capabilities while same being computationally light resilient. These SwiNet segmented analysis, XLG precise classification cases, DevLO optimizes parameters system, making system sensible efficient. outcomes indicate CanNS framework enhances detection's sensitivity, specificity compared previous approaches.

Language: Английский

---

A Novel Machine Learning Model for Efficacy Prediction of Immunotherapy-Chemotherapy in NSCLC Based on CT Radiomics

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 178, P. 108638 - 108638

Published: May 21, 2024

Language: Английский

---

DFPT-CNN: A Dual Feature Extraction and Pretrained CNN Synergy for Minimal Computational Overhead and Enhanced Accuracy in Multi-Class Medical Image Classification

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 58573 - 58585

Published: Jan. 1, 2024

In the advanced computer vision era, Convolutional Neural Network (CNN) plays a pivotal role in image processing, as they excel at automatically extracting important patterns, and structures, for accurate analysis across diverse domains. However, achieving higher accuracy often leads to intensifying computational timing demands. To address challenge, this research introduces novel dual feature extraction methodology. This approach is implemented using two distinct modules, employed different stages of model: (1) Edge Gradient-Dimensionality Reduction (EGDR) module which encapsulates pixel edge gradient features from raw input frame, leading dimensionality reduction by factor 0.5; (2) Subtle Local Feature Extraction (SLFE) pooling algorithm module, prioritizes local subtle over maximum or average content. The combination these proves particularly effective enhancing classification while minimizing overhead training duration. Subsequently, comprehensive training, validation, testing were conducted on selected multi-class chest computed tomography medical dataset various state-of-the-art CNN architectures such VGG-16, InceptionV3, ResNet50 identify most suitable model further experimentation with proposed method. CNN-SLFE framework EGDR achieved significant 17.94% time compared non-EGDR concurrently enhanced an improvement 1.17 existing frameworks module.

Language: Английский

---