Jul 2026· Revista Española de Patología· Vol 59 3, pp.
100885
· 0 citations· 35 references
Medicine
TL;DR
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.
Abstract
The accurate categorisation of histopathological images is crucial for the reliable identification of morphologically similar cancers, including lung and colon cancer. According to the WHO and IARC, lung cancer accounted for approximately 2.48 million new cases and 1.8 million deaths worldwide in 2022, making it the leading cause of cancer-related mortality worldwide. Colorectal cancer also represents a major global health burden, with more than 1.9 million new cases and approximately 930,000 deaths reported in 2020 alone. These rising burdens highlight the need for robust computational pathology systems capable of accurate morphological discrimination. In this paper, we propose MorphoViT-CNN, a hybrid model that combines a Vision Transformer for capturing global contextual information with Convolutional Neural Networks (CNNs) for extracting fine grained local features. A morphology-aware segmentation module is designed to incorporate cellular shape, size, and texture attributes, while self-distillation improves the consistency of internal representations without requiring external supervision. Supervised contrastive learning further enhances inter-class separability, particularly in label-limited settings. The model was evaluated on the LC25000 dataset using five-fold cross validation, and ablation studies were conducted to assess the contribution of each component. MorphoViT-CNN demonstrated superior accuracy and precision-recall performance compared with leading CNN and transformer-based baselines, while significantly reducing misclassification among challenging histological subtypes. Its interpretable and multi-scale architecture provides a scalable framework for integration into computational pathology workflows. Future work will explore multimodal integration and foundation model pre-training to further enhance its applicability to precision oncology.
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.
Subrata Sinha, Saurav Mali, S. Rajkhowa et al.· Scientific Reports· 0 citations
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
Lung cancer is one of the deadliest malignancies, known for rapid growth and has high potential of spreading the original tumor cells to other cells of the body. According to GLOBOCAN 2020, there were 2.2 million new lung cancer cases and 1.8 million deaths, making up 18% of global cancer deaths. The American Lung Association (ALA) reports that only 25.8% of cases are detected early, with a 5-year survival rate. Early detection is crucial but remains difficult due to nonspecific symptoms and current imaging limitations. This study proposes a deep Convolutional Neural Network (CNN) approach to improve lung cancer detection by facilitating accurate, automated diagnosis of lung nodules in early stage cancer. We combine two advanced deep learning models, VGG16 and U-Net++, to enhance the classification of medical images. The approach leverages VGG16’s strengths in feature extraction and U-Net++’s robust multiscale processing to handle the diverse shapes and sizes of tumors in lung tissue. These models are ensembled to advance our capabilities in processing medical images. Features extracted from both models are concatenated to create a comprehensive and flexible representation of the input data. The feature set is flattened and then undergoes further processing using Dense layers, Batch Normalization, and Dropout layers to improve generalization and prevent overfitting. The final output layer classifies the images as ‘Benign,’ ‘Malignant,’ or ‘Normal.’ Extensive experiments on a lung image dataset demonstrate significant classification improvements over individual models. Performance evaluation using metrics such as accuracy, precision, recall, and F1-score shows higher results for the ensemble model. 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. Our proposed brings improvement in accuracy, segmentation and feature extraction and thereby proves to be one among the top models available.
Sanjeevkumar B., V. S. P., S. Babu et al.· Scientific Reports· 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
Colorectal cancer (CRC) is the third most common cancer worldwide and the second leading cause of cancer-related deaths globally, with approximately 1,926,425 new cases and 904,019 deaths reported in 2022. Accurate histologic grading plays a critical role in prognosis and treatment planning for colorectal adenocarcinoma. In recent years, artificial intelligence and its subcategories, including machine learning and deep learning, have been increasingly employed for automated cancer detection and classification. An appropriate and well-organized dataset is the essential first step to achieve this goal. This paper introduces CRC-HGD, a histopathological microscopy image dataset of 1,914 images obtained from 214 colorectal adenocarcinoma patients (Grade I: 106, Grade II: 75, Grade III: 33). The specimens are H&E-stained colorectal tissue sections acquired at the Poursina Hakim Research Center of Isfahan University of Medical Sciences, Iran, diagnosed between 2014 and 2019, and graded according to the World Health Organization (WHO) criteria into three grades: well-differentiated (Grade I), moderately differentiated (Grade II), and poorly differentiated (Grade III). For each specimen, four magnification levels are provided: 4x, 10x, 20x, and 40x. The dataset is accessible via Mendeley Data (https://doi.org/10.17632/yfp5sfj47m.4) and at http://databiox.com, where the latest version is also available. The distinctive feature of this dataset is the provision of labeled specimens across all three differentiation grades at multiple magnification levels, enabling comprehensive computational analysis of colorectal cancer grading.
Elham Amjadi, A. Bahreini, Sayed Mohammad Hasan Emami et al.· 0 citations
Exact and precise segmenting of nuclei in cancer diagnostics is a very important aspect of computer-assisted diagnosis and grading of carcinoma of the breast. Nonetheless, obscure medical findings pose a few challenges in training deep neural networks from the beginning. Through this research, we put forward a combination of deep learning structures on the basis of U-Net for automated breast nuclei segmentation in H&E stained histological findings and pictures, with a little more concentration on Triple Negative Breast Cancer (TNBC). The proposed structures were evaluated Baseline U-Net and U-Net types employing pretrained encoder backbones (VGG16, ResNet50, EfficientNetB0, and MobileNetV2). These different were assessed using Intersection over Union (IoU), Dice coefficient, precision based on picture elements in capturing photos, Precision–Recall evaluation, and ROC-AUC.
Neelapu Manju Nageshwari, Sanda Akhila, N. Reddy et al.· 2026 7th International Confe...· 0 citations
