The current work introduces the hybrid ensemble framework for the detection and segmentation of colorectal cancer. This framework will incorporate both supervised classification and unsupervised clustering methods to present more understandable and accurate diagnostic results. The method entails several steps with CNN models: ADa-22 and AD-22, transformer networks, and an SVM classifier, all inbuilt. The CVC ClinicDB dataset supports this process, containing 1650 colonoscopy images classified as polyps or non-polyps. The best performance in the ensembles was done by the AD-22 + Transformer + SVM model, with an AUC of 0.99, a training accuracy of 99.50%, and a testing accuracy of 99.00%. This group also saw a high accuracy of 97.50% for Polyps and 99.30% for Non-Polyps, together with a recall of 97.80% for Polyps and 98.90% for Non-Polyps, hence performing very well in identifying both cancerous and healthy regions. The framework proposed here uses K-means clustering in combination with the visualisation of bounding boxes, thereby improving segmentation and yielding a silhouette score of 0.73 with the best cluster configuration. It discusses how to combine feature interpretation challenges into medical imaging for accurate localization and precise segmentation of malignant regions. A good balance between performance and generalization shall be done by hyperparameter optimization-heavy learning rates; dropout rates and overfitting shall be suppressed effectively. The hybrid schema of this work treats the deficiencies of the previous approaches, such as incorporating CNN-based effective feature extraction, Transformer networks for developing attention mechanisms, and finally the fine decision boundary of the support vector machine. Further, we refine this process via unsupervised clustering for the purpose of enhancing the visualisation of such a procedure. Such a holistic framework, hence, further boosts classification and segmentation results by generating understandable outcomes for more rigorous benchmarking of detecting colorectal cancer and with higher reality towards clinical application feasibility.

“PolynetDWTCADx” is a sophisticated hybrid model that was developed to identify and distinguish colorectal cancer. In this study, the CKHK-22 dataset, comprising 24 classes, served as the introduction. The proposed method, which combines CNNs, DWTs, and SVMs, enhances the accuracy of feature extraction and classification. The study employs DWT to optimize and enhance two integrated CNN models before classifying them with SVM following a systematic procedure. PolynetDWTCADx was the most effective model that we evaluated. It was capable of attaining a moderate level of recall, as well as an area under the curve (AUC) and accuracy during testing. The testing accuracy was 92.3%, and the training accuracy was 95.0%. This demonstrates that the model is capable of distinguishing between noncancerous and cancerous lesions in the colon. We can also employ the semantic segmentation algorithms of the U-Net architecture to accurately identify and segment cancerous colorectal regions. We assessed the model’s exceptional success in segmenting and providing precise delineation of malignant tissues using its maximal IoU value of 0.93, based on intersection over union (IoU) scores. When these techniques are added to PolynetDWTCADx, they give doctors detailed visual information that is needed for diagnosis and planning treatment. These techniques are also very good at finding and separating colorectal cancer. PolynetDWTCADx has the potential to enhance the recognition and management of colorectal cancer, as this study underscores.

Colorectal cancer (CRC) is the second most common cause of cancer-related mortality worldwide, underscoring the necessity for computer-aided diagnosis (CADx) systems that are interpretable, accurate, and robust. This study presents a practical CADx system that combines Vision Transformers (ViTs) and DeepLabV3 + to accurately identify and segment colorectal lesions in colonoscopy images.The system addresses class balance and real-world complexity with PCA-based dimensionality reduction, data augmentation, and strategic preprocessing using recently curated CKHK-22 dataset comprising more than 14,000 annotated images of CVC-ClinicDB, Kvasir-2, and Hyper-Kvasir. ViT, ResNet-50, DenseNet-201, and VGG-16 were used to quantify classification performance. ViT achieved best-in-class accuracy (97%), F1-score (0.95), and AUC (92%) in test data. The DeepLabV3 + achieved segmentation state-of-the-art for tasks of localisation with 0.88 Dice Coefficient and 0.71 Intersection over Union (IoU), ensuring sharp delineation of areas that are malignant. The CADx system accommodates real-time inference and served through Google Cloud for information that accommodates scalable clinical implementation. The image-level segmentation effectiveness is evidenced by comparison with visual overlay and expert-manually deliminated masks, and its precision is illustrated by computation of precision, recall, F1-score, and AUC. The hybrid strategy not only outperforms traditional CNN strategies but also overcomes important clinical needs such as detection early, balance of highly disparate classes, and clear explanation. The proposed ViT–DeepLabV3 + system establishes a basis for advanced AI support to colorectal diagnosis by utilizing self-attention strategies and learning with different scales of context. The system offers a high-capacity, reproducible computerised colorectal cancer screening and monitoring solution and can be best deployed where resources are scarce, and it can be highly desirable for clinical deployment.

Colorectal cancer (CRC) continues to be a significant global health issue as a result of the difficulties associated with the early and precise detection of lesions through colonoscopy. We propose CADxPolyDetect, a clinically explainable hybrid deep learning system for multi-class colorectal lesion detection using augmented colonoscopy images, to address diagnostic limitations that arise from class imbalance, interpretability gaps, and spatial complexity in colonoscopic images. A five-stage experimental pipeline is integrated into the framework. Initially, the original Hyper Kvasir dataset (10,672 images) is augmented to 23,000 images using Deep Convolutional Generative Adversarial Networks (DCGAN) and class balanced using SMOTE. Three pre-trained CNNs—ResNet-50, DenseNet-201, and VGG-16—are implemented in Stage 2 to execute end-to-end feature extraction. Transformer networks are integrated with these CNNs in Stage 3 to capture global spatial dependencies. Stage 4 incorporates multi-class support vector machines (SVM) for the final classification of 23 colorectal conditions. Stage 5 improves interpretability by utilising Grad-CAM to produce clinically relevant heatmaps that localise malignant polyps and facilitate transparent decision-making. The DenseNet-201 + Transformer + Multi-Class SVM model showed the best results of all the setups tested, achieving an overall accuracy of 98%, an F1-score of 0.98, a precision of 97%, and a recall of 99%, based on a 70:30 split of training and testing data. Robustness, precision, and clinical trust are guaranteed through the integration of attention-based visualisations, deep ensemble learning, and augmented data. Therefore, CADxPolyDetect sets a new benchmark in AI-supported colonoscopy by offering a decision support system that is easy to understand and can grow to meet needs for the early detection and screening of colorectal cancer.

Effective mitigation and response to disasters require fast and accurate classification and localisation of natural disasters. We herein propose EcoDisasterLocNet, a hybrid architecture of Grad-CAM + + and DenseNet-201 that integrates fine-grained and interpretable disaster localisation with accurate spatial classification. The architecture is learned on a balanced and augmented 10,537-image dataset spread over four classes: earthquake, wildfire, flood, and cyclone. 75% of the images were utilised for training while 15% and 10% of the images respectively tested and validated the architecture. Optimised DenseNet-201 produced the best results where it obtained 99.90% training accuracy, 94.24% validation accuracy, and 95.16% testing accuracy along with 95.26%/95.16%/95.19% precision/recall/F1-score. This hybrid ensemble (ERI-2025) was initially evaluated alongside standalone CNN models. Grad-CAM and Grad-CAM + + visualisations were used to emphasise disaster-related Grad-CAM and Grad-CAM + + visualisations were used to emphasise disaster-related regions (e.g., fissures, wildfires, flood regions, cyclone eyes) for localisation. Grad-CAM + + enhanced the IoU from 0.27 to 0.51 to 0.39–0.51 while maintaining a Dice coefficient of 2.00. The superiority of DenseNet-201 in both classification and localisation tasks was confirmed by comparative evaluation against other CNN architectures The hybrid design of the proposed framework is adaptable to multimodal and spatiotemporal datasets in future research, and it provides a scalable, interpretable, and high-precision solution for real-time disaster monitoring.