Comparative evaluations revealed that pre-processed images significantly improved classification consistency and accuracy, highlighting the benefits of color normalization techniques and Particle Swarm Optimization was employed for hyperparameter tuning.
Abstract
Among various types of cancers, lung cancer causes the highest mortality globally, necessitating prompt diagnosis for effective treatment. Traditionally, histopathological analysis of Hematoxylin and Eosin (H&E)-stained slides serves as the principal method for definitive diagnosis. However, manual interpretation is often hindered by staining variability. This research focuses on designing a Convolutional Neural Network (CNN) model tailored to classify various subtypes of lung carcinoma. It aims to overcome key diagnostic challenges, including variability in staining techniques. The publicly available LC25000 dataset comprising lung histopathological images was utilized. To mitigate staining variability and reduce noise, Reinhard color normalization and Gaussian filtering were applied during pre-processing. Particle Swarm Optimization (PSO) was employed for hyperparameter tuning, which helped in the development of a multi-scale CNN architecture tailored for robust classification. The optimized CNN model achieved a classification accuracy of 98.59% across three categories: two non-small cell lung malignant classes and one benign class. Comparative evaluations revealed that pre-processed images significantly improved classification consistency and accuracy, highlighting the benefits of color normalization techniques. The developed model exhibits strong diagnostic performance and improved resilience to staining variability. To support real-time clinical use, the model was successfully deployed as an Android-based mobile application. This application is publicly available and can be accessed at: https://github.com/jar3e1/AndroidApp.
One of the leading causes of cancer-related mortality worldwide is lung cancer. Improving patient survival requires early and precise diagnosis. Recent developments in deep learning make it possible to analyse histopathological lung pictures automatically. Because most deep learning models are opaque and considered black-box systems, their application in clinical practice is constrained. An explainable deep-learning framework for the categorisation of lung cancer is presented in this article. Gradient-weighted Class Activation Mapping (Grad-CAM) visualisation and a custom Convolutional Neural Network are also used. Three classes of histopathological lung tissue images: lung squamous cell carcinoma, lung adenocarcinoma, and normal tissue. Images are scaled to 224*224 pixels and preprocessed using data augmentation and normalisation techniques to enhance generalisation before training. With a test accuracy of 96.62%, the suggested Custom CNN is comparable to existing deep learning models like DenseNet121 (96.6%) and other CNN-based methods documented in earlier research. The suggested approach uses Grad-CAM to provide visual interpretability alongside classification performance.
Prathamesh Patil, Pradnya.S.Kulkarni· 2026 4th International Confe...· 0 citations
MorphoViT-CNN is proposed, a hybrid model that combines a Vision Transformer for capturing global contextual information with Convolutional Neural Networks (CNNs) for extracting fine grained local features and demonstrated superior accuracy and precision-recall performance compared with leading CNN and transformer-based baselines.
Pranjal Das, Rajagopal Kumar, Dushmanta Kumar Das· Revista Española de Patologí...· 0 citations
Breast cancer remains the leading cause of cancer-related mortality among women globally, necessitating accurate diagnosis through histopathological image analysis. However, manual examination of these images is time-consuming and susceptible to inter-observer variability, highlighting the critical need for reliable automated computer-aided diagnostic (CAD) systems. This study was conducted to systematically evaluate and optimize convolutional neural network (CNN) architectures for automated classification of breast cancer histopathology images, with a focus on mitigating overfitting and enhancing diagnostic accuracy through hybrid deep learning methodologies. The principal innovation is the development of a CNN-VGG16 hybrid architecture that strategically integrates pre-trained feature extraction with a customized CNN framework, hypothesized to substantially improve classification accuracy and model generalization. Three model configurations were developed and comparatively analyzed: (1) baseline CNN, (2) CNN with dropout regularization, and (3) hybrid CNN-VGG16 model. Input images underwent preprocessing, including resizing to 150×150 pixels, normalization, and data augmentation. All models were trained with identical hyperparameters: an Adam optimizer with a learning rate of 0.001, a batch size of 32, and 10 epochs. Dropout regularization with a fixed rate of 0.5 was applied to fully-connected layers to mitigate overfitting. Model evaluation was conducted utilizing standard performance metrics. The proposed CNN-VGG16 hybrid model achieved superior performance: accuracy of 85.19%, precision of 87.16%, recall of 92.75%, and F1-score of 88.37%. These metrics represent significant improvements of 4.2% relative to baseline CNN and 3.4% compared to the dropout-regularized variant, indicating substantially enhanced diagnostic capability and reduced false-negative rates. Strategic integration of pre-trained feature extraction with customizable CNN architectures significantly improves generalization and classification performance in histopathological image analysis. Future investigations should incorporate larger heterogeneous datasets, attention mechanisms, and explainable artificial intelligence (XAI) to enhance clinical interpretability and strengthen practitioner confidence in digital pathology systems
Fawaidul Badri, Ilham Ari, Elbaith Zaeni et al.· Journal of Electronics Elect...· 0 citations
Introduction: Lung cancer remains one of the leading causes of cancer-related mortality worldwide. Despite advances in diagnostic imaging, histopathological assessment continues to be the gold standard for accurate classification of lung cancer subtypes. However, manual interpretation of histopathological slides is time-consuming and susceptible to inter-observer variability, underscoring the need for efficient Computer-Aided Diagnostic (CAD) systems.
Aim: To develop a Convolutional Neural Network (CNN)- based model for automated classification of lung carcinoma histopathological images by integrating classical gradientbased edge detection techniques to enhance image quality and improve classification performance.
Materials and Methods: This retrospective analytical study was conducted in the ICMR-funded laboratory at Brainware University, Kolkata, West Bengal, India. The project commenced in February 2024 and is proposed to conclude in February 2027. To date, it has yielded a dataset of 11,580 histopathological images of lung tissue, categorised as Lung Adenocarcinoma (LUAD), Lung Squamous Cell Carcinoma (LSCC), and Non Malignant (BNM). The present work represents a split study and forms part of a larger ICMR-funded project spanning three years. This component focuses on LUAD, LSCC, and non-malignant lung tissue, thereby encompassing the two most common Non Small Cell Lung Cancer (NSCLC) subtypes (which together account for approximately 85% of lung cancers) along with a normal reference class. Edge enhancement was performed using Sobel and Scharr operators to emphasise structural boundaries. The processed images were used to train a custom-designed CNN architecture comprising three convolutional blocks, each followed by pooling layers, and fully connected layers for classification. The model was trained for 100 epochs with a batch size of 32 and evaluated using accuracy, precision, sensitivity, specificity, and F1-score as performance metrics.
Results: Sobel-based preprocessing yielded superior model performance compared with the Scharr method. The proposed CNN trained on Sobel-enhanced images achieved an overall classification accuracy of 93.55%, outperforming the 81.33% accuracy obtained with Scharr-based preprocessing. The Sobelenhanced model also demonstrated stronger generalisation, with AUC values of 0.98, 1.00, and 0.98 for the LUAD, BNM, and LSCC classes, respectively.
Conclusion: The integration of edge detection with CNN-based analysis effectively enhances the classification of lung cancer histopathological images. The Sobel operator notably improved model accuracy, precision, and generalisation, suggesting its potential suitability for highlighting morphological boundaries in tissue sections. Future work will extend this framework by exploring additional edge detection methods, implementing stain normalisation, and validating performance on external datasets to further optimise model robustness and clinical applicability.
Saurav Mali, Ankur Mukherjee, Biren Parikh et al.· Journal of Clinical and Diag...· 0 citations
Lung cancer remains one of the leading causes of cancer-related mortality worldwide, necessitating early and accurate diagnosis for improved patient survival. This paper proposes a Deep Learning Classification-Based Fast Segmentation (DLC-FS) framework for efficient detection and segmentation of lung cancer from computed tomography (CT) images. The proposed method integrates a lightweight convolutional neural network (CNN) classifier with an optimized U-Net-based segmentation architecture to achieve high accuracy with reduced computational complexity. The framework employs advanced preprocessing techniques, including normalization, noise reduction, and contrast enhancement, followed by feature extraction using deep convolutional layers. A hybrid loss function combining Dice loss and binary cross-entropy is utilized to improve segmentation precision. The model is trained and evaluated on publicly available lung cancer datasets, achieving a classification accuracy of 97.8%, precision of 96.5%, recall of 95.9%, and an F1-score of 96.2%. For segmentation performance, the proposed approach attains a Dice Similarity Coefficient (DSC) of 94.7%, Intersection over Union (IoU) of 92.3%, and reduces inference time by 28% compared to conventional U-Net models. Experimental results demonstrate that the proposed DLC-FS framework significantly outperforms existing state-of-the-art methods in both detection accuracy and computational efficiency. The fast segmentation capability makes the system suitable for real-time clinical applications, assisting radiologists in early diagnosis and treatment planning. Future work will focus on multi-modal data integration and deployment in edge-based healthcare systems.
R. Gnanakumari, Uma Maheshwari R., Arulkumar S. et al.· International journal of com...· 0 citations
Histopathological imaging of breast cancer remains a vital
clinical task. While deep learning techniques have shown strong diagnostic accuracy, most existing models suffer from poor interpretability, high computational demands, and limited clinical transparency. Therefore, this research aims to develop a simple, streamlined, and interpretable hybrid system for early, accurate, and reliable breast cancer detection to support real-time
clinical diagnosis.
A new hybrid architecture, Light-PSO-Net, was proposed by integrating a lightweight
convolutional neural network (MobileNetV2), Particle Swarm Optimisation (PSO) for global
hyperparameter optimisation, Principal Component Analysis (PCA) for dimensionality reduction, and a Fuzzy Inference System (FIS) to stratify risks in an interpretable manner. The publicly available BreaKHis dataset of breast cancer histopathology images at multiple magnifications, comprising benign and malignant tissues, was utilised to train and test the model. GradCAM visualisation highlighted spatial features used for classification, while PCA-FIS offered
semantic interpretability of the results. Model performance was evaluated using accuracy, F1-
score, confusion matrices, and ablation analyses.
The proposed framework achieved 95.5% classification accuracy and an F1 score of
0.9682, outperforming many other modern lightweight and hybrid deep learning systems. The
ablation analysis showed that PSO outperformed PCA in terms of convergence stability, predictive performance, and feature compactness and separability. The fuzzy reasoning module enhanced sensitivity to malignancy and provided categorisation of risk into low, medium, and
high risk. The model also demonstrated consistent results across different magnifications and
external validation conditions.
The combination of global maximisation, dimension minimisation, and rule-based
solutions helped the proposed model overcome key challenges in breast cancer diagnosis, such
as computational efficiency, interpretability, and clinical relevance. Unlike traditional black-box
models, Light-PSO-Net provides both pixel-level and decision-level explainability using GradCAM and fuzzy logic. Its lightweight design makes it suitable for resource-limited pathology
laboratories and edge healthcare environments. These findings emphasise the importance of integrating deep learning with explainable and optimisation-based systems for translational medical applications.
Light-PSO-Net provides a genuine, effective, and interpretable approach for classifying histopathological breast cancer. The proposed hybrid learn-then-reason pipeline shows
strong potential to assist pathologists in early diagnosis and improve clinical outcomes. Future
research will focus on multimodal integration, federated learning, adaptive fuzzy systems, and
multi-centre validation to enhance generalisability and support wider clinical adoption.