Jul 2026· 2026 International Conference on Intelligent and Sustainable AI Systems (ICOSAAS)· pp. 816-822· 0 citations· 15 references
Abstract
Lung cancer is the main cause of death related to cancer globally, taking the lives of about 1.8 million people each year. Detecting it early and accurately from CT scan images is very important for better patient results. Three sophisticated Convolutional Neural Network (CNN) models—ResNet50, DenseNet121, and EfficientNetB0—are used in this comprehensive study to automatically classify lung CT scan images into two categories (benign and malignant). The IQ-OTH/NCCD Lung Cancer Dataset, which is openly accessible on Kaggle, was used to train and evaluate the models. This dataset was created by Aditya Mahimkar and contains 1300 CT scan slices from 110 different patient cases. After preprocessing, only benign and malignant CT scan images were used for binary classification. To evaluate the performance of each model following training through transfer learning and fine-tuning, metrics such as accuracy, precision, recall, F1-score, and the confusion matrix were employed. ResNet50 outperformed DenseNet121 and EfficientNetB0 in terms of accuracy. A combined Weighted Ensemble Model that uses the probability outputs from all three networks was also created, which improved the overall classification performance and how well the model works in different situations. This study shows that using deep learning and combining models can be very helpful tools in detecting lung cancer during clinical screenings.
One of the main causes of cancer-related fatalities globally is lung cancer, and increasing patient survival requires early diagnosis. Lung cancer screening frequently uses computed tomography (CT) imaging, although manual interpretation can be laborious and reliant on radiologist skill. A deep learning-based framework for CT image-based lung cancer diagnosis and classification is presented in this work. Lung CT scans are divided into three groups by the suggested system: benign, malignant, and normal. Preprocessing methods including Intensity-based feature enhancement, Contrast Limited Adaptive Histogram Equalization (CLAHE), and normalizing are used to improve image quality and highlight significant features. Both local texture features and global contextual information are extracted from CT images using a hybrid deep learning model that combines ResNet18 and Vision Transformer (ViT). Additionally, data augmentation is used to enhance model generalization and lessen class imbalance. The Hybrid-RViT model, which combined ResNet18 and ViT, outperformed the competition with 97.13% accuracy. These findings show that the suggested methodology can efficiently facilitate automated lung cancer diagnosis and help physicians make decisions more quickly and accurately.
Belayet Hossen, Md Takbir Alam Manjar, Md Abu Shihab et al.· International Conference Com...· 0 citations
The proposed system demonstrates potential as an assistive tool for automated lung cancer screening, warranting further validation on larger and multi-institutional datasets before clinical application.
Vishwas V. Patange, Jagadish B. Jadhav, Sanjay L. Nalbalwar et al.· Scientific Reports· 0 citations
This study concludes that integrating VGG16 and U-Net+ into this CNN architecture can significantly enhance lung cancer detection performance by achieving a remarkable accuracy of 96% and provide a reliable tool for clinicians in early stage diagnosis and treatment monitoring.
Sanjeevkumar B., Varun S. P., S. Babu et al.· Scientific Reports· 0 citations
However, early-stage lung cancer is one of the major causes of death from cancer due to its symptoms being absent or hard to detect by conventional clinical analysis. The late diagnosis of this disease causes the effectiveness of the treatment to become poor and low survival rates. Traditional interpretation of medical imaging involves manual analysis which makes it burdensome, prone to variation between observers, and inefficient for screening in cases where many chest CT images need to be analyzed. This calls for efficient computer-based intelligent diagnostics systems that can provide effective, reliable, and fast classification results. In this paper, an EfficientNet-B0-based deep learning model for automated lung cancer classification using chest CT images is proposed. Preprocessing steps such as normalization, lung segmentation, resizing, and data augmentation are used. The custom dataset, specifically PulmoVision Lung Cancer CT Dataset (PLCD-2026), contains balanced image samples that correspond to healthy lungs, benign nodules, and malignancies in order to provide sufficient conditions for effective model training. EfficientNet-B0 learns discriminative anatomical and pathological features and remains computationally efficient by means of optimized network scaling. High classification capabilities of the developed approach can be proved by means of the evaluation procedure conducted in terms of accuracy, precision, recall, and F1-score, which proves reliable identification of different pulmonary diseases. Grad-based visualization is additional confirmation of proper localization of suspicious areas, contributing to the interpretability of the classification process. The developed framework provides an efficient tool for lung cancer detection, helps doctors to make decisions, saves their time, and ensures consistent clinical assessment.
R. Dhamotharan, T. Manikumar· International Conference Com...· 0 citations
The timely diagnosis of lung cancer is important in enhancing survival rate among patients
who have the disease but the use of traditional diagnostic techniques cannot always determine
the presence of minute pulmonary nodules during CT scan. The paper proposed a hybrid
machine learning system based on Convolutional Neural Networks (CNNs) and Transformers
to diagnose early lung cancer automatically on the basis of the IQ-OTH/NCCD CT scan
dataset. The CNN element isolates local fine-grained features on the images whereas the
Transformer element isolates long-range global relationships and a blend feature union
mechanism joins these representations to end up with final classification of normal, benign, or
malignant. Normalisation, resizing, noise removal and augmentation of the dataset were done
to enhance robustness of the model. The hybrid CNN-Transformer model was compared to the
basic models such as CNN alone and Vision Transformer (ViT) models. Experimental results
show that the hybrid model achieved an overall accuracy of 93.7%, with class-wise precision,
recall, and F1-scores of 95.1%, 94.7%, and 94.9% for normal, 91.2%, 90.5%, and 90.8% for
benign, and 94.9%, 95.3%, and 95.1% for malignant cases. The confusion matrix showed that
few misclassifications were experienced with benign and adjacent classes, and ROC analysis
provided AUC values of 0.978, 0.942, and 0.981 with normal, benign, and malignant,
respectively, to prove that there was an excellent discriminative performance. Such findings
suggest hybrid CNN-Transformer architecture is effective in combining local and global
features to produce reliable early detection of lung cancer. The model is more effective
compared to conventional CNN and Transformer methods and is highly interpretable, which is
why it has high potential to assist radiologists in making clinical decisions. The paper presents
the opportunity of hybrid deep learning designs in terms of enhancing diagnostic quality and
patient outcomes, and the future research will involve the use of 3D CT information, multimodal
imaging, or application in the clinical environment.
Adeiza Victor Nicholas· International Journal of Com...· 0 citations
Lung cancer remains one of the leading causes of cancer-related deaths worldwide, and early identification of malignant abnormalities plays an important role in improving patient survival rates. However, accurate lung cancer classification using CT imaging remains challenging because of limited dataset availability, class imbalance, overlapping lesion characteristics, and lack of interpretability in existing deep learning systems. This study presents a GenAI-driven CNN–RNN framework for explainable lung cancer classification using CT imaging and GAN-based augmentation. The proposed framework integrates convolutional neural networks for spatial feature extraction, LSTM-based recurrent learning for sequential dependency analysis, GAN-assisted augmentation for improving minority class representation, and attention-guided feature fusion for enhanced classification performance. The experimental evaluation was conducted using the publicly available IQ-OTH/NCCD lung cancer CT imaging dataset containing Normal, Benign, and Malignant categories. During preprocessing, normalization, resizing, and image enhancement operations were applied to improve image consistency before training. The framework was trained using the Adam optimizer with 50 epochs and evaluated using 5-fold cross-validation. Experimental results demonstrated that the proposed framework achieved an accuracy of 92.84%, precision of 91.76%, recall of 90.42%, F1-score of 91.08%, and ROC-AUC value of 0.94. Grad-CAM and SHAP visualization methods further improved interpretability by highlighting important lesion regions influencing prediction outcomes. The obtained findings suggest that the proposed CNN–RNN framework can support CT image-based lung cancer classification under limited dataset conditions for CT image-based lung cancer classification under limited medical imaging conditions.
Bodicherla Siva Sankar, D. Natarajasivan, M. Reddy· Frontiers in Artificial Inte...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
