Forest ecosystems face increasing wildfire threats, demanding prompt and precise detection methods to ensure efficient fire control. However, real-time forest fire data accessibility and timeliness require improvement. Our study addresses the challenge through the introduction of the Unmanned Aerial Vehicles (UAVs) based forest fire database (UAVs-FFDB), characterized by a dual composition. Firstly, it encompasses a collection of 1653 high-resolution RGB raw images meticulously captured utilizing a standard S500 quadcopter frame in conjunction with a RaspiCamV2 camera. Secondly, the database incorporates augmented data, culminating in a total of 15560 images, thereby enhancing the diversity and comprehensiveness of the dataset. These images were captured within a forested area adjacent to Adana Alparslan Türkeş Science and Technology University in Adana, Turkey. Each raw image in the dataset spans dimensions from 353 × 314 to 640 × 480, while augmented data ranges from 398 × 358 to 640 × 480, resulting in a total dataset size of 692 MB for the raw data subset. In contrast, the augmented data subset accounts for a considerably larger size, totaling 6.76 GB. The raw images are obtained during a UAV surveillance mission, with the camera precisely angled a -180-degree to be horizontal to the ground. The images are taken from altitudes alternating between 5 - 15 meters to diversify the field of vision and to build a more inclusive database. During the surveillance operation, the UAV speed is 2 m/s on average. Following this, the dataset underwent meticulous annotation using the advanced annotation platform, Makesense.ai, enabling accurate demarcation of fire boundaries. This resource equips researchers with the necessary data infrastructure to develop innovative methodologies for early fire detection and continuous monitoring, enhancing efforts to protect ecosystems and human lives while promoting sustainable forest management practices. Additionally, the UAVs-FFDB dataset serves as a foundational cornerstone for the advancement and refinement of state-of-the-art AI-based methodologies, aiming to automate fire classification, recognition, detection, and segmentation tasks with unparalleled precision and efficacy.

Data analytics and artificial intelligence (AI) have been used to predict patient outcomes after colorectal cancer surgery. A prospectively maintained colorectal cancer database was used, covering 4336 patients who underwent colorectal cancer surgery between 2003 and 2019. The 47 patient parameters included demographics, peri- and post-operative outcomes, surgical approaches, complications, and mortality. Data analytics were used to compare the importance of each variable and AI prediction models were built for length of stay (LOS), readmission, and mortality. Accuracies of at least 80% have been achieved. The significant predictors of LOS were age, ASA grade, operative time, presence or absence of a stoma, robotic or laparoscopic approach to surgery, and complications. The model with support vector regression (SVR) algorithms predicted the LOS with an accuracy of 83% and mean absolute error (MAE) of 9.69 days. The significant predictors of readmission were age, laparoscopic procedure, stoma performed, preoperative nodal (N) stage, operation time, operation mode, previous surgery type, LOS, and the specific procedure. A BI-LSTM model predicted readmission with 87.5% accuracy, 84% sensitivity, and 90% specificity. The significant predictors of mortality were age, ASA grade, BMI, the formation of a stoma, preoperative TNM staging, neoadjuvant chemotherapy, curative resection, and LOS. Classification predictive modelling predicted three different colorectal cancer mortality measures (overall mortality, and 31- and 91-days mortality) with 80–96% accuracy, 84–93% sensitivity, and 75–100% specificity. A model using all variables performed only slightly better than one that used just the most significant ones.

Effective detection and classification of forest fire imagery are critical for timely and efficient wildfire management. Convolutional Neural Networks (CNNs) have demonstrated potential in this domain but encounter limitations when addressing varying scales, resolutions, and complex spatial dependencies inherent in wildfire datasets. Building upon our prior work on the Unmanned Aerial Vehicle-based Forest Fire Database (UAVs-FFDB) and the multi-headed CNN (MHCNN), this study introduces a novel architecture, namely, the Adaptive Hierarchical Multi-Headed Convolutional Neural Network with Modified Convolutional Block Attention Module (AHMHCNN-mCBAM). This enhanced framework addresses prior challenges by integrating adaptive pooling, concatenated convolutions for multi-scale feature extraction, and an improved attention mechanism incorporating shared fully connected layers, Glorot initialization, rectified linear units (ReLU), layer normalization, and attention-gating. AHMHCNN-mCBAM incorporates Gated Recurrent Unit (GRU) and Bidirectional Long Short-Term Memory (BiLSTM) networks for temporal context modeling to further refine classification accuracy. Experiments conducted on the UAVs-FFDB dataset achieved outstanding results, including 100% accuracy, a 100% Cohen’s kappa coefficient (cKappa), and compact model parameter sizes of 1.49 million (M), 0.25 M, and 0.12 M. On the Fire Luminosity Airborne-based Machine Learning Evaluation (FLAME) dataset, the model attained accuracy rates of 99.83%, 99.10%, and 99.32%, with corresponding cKappa values of 99.66%, 98.20%, and 98.65%. Compared to the baseline hierarchical MHCNN with CBAM (HMHCNN-CBAM), AHMHCNN-mCBAM demonstrated significant performance gains, including a 6.80% and 6.59% increase in accuracy, a 9.26% and 14.11% improvement in cKappa, and a 13.87% and 13.76% reduction in parameter size on the UAVs-FFDB and FLAME datasets, respectively. Additionally, AHMHCNN-mCBAM outperformed HMHCNN-CBAM in recall (25% improvement), precision (21.95%), F1-score (14.94%), and false discovery rate (FDR) reduction (25.01%), while achieving a 100% reduction in error rate (EWR). Leveraging Explainable Artificial Intelligence (XAI) techniques, the model provides interpretable insights into decision-making processes.

COVID-19, caused by SARS-CoV-2, has been declared as a global pandemic by WHO. Early diagnosis of COVID-19 patients may reduce the impact of coronavirus using modern computational methods like deep learning. Various deep learning models based on CT and chest X-ray images are studied and compared in this study as an alternative solution to reverse transcription-polymerase chain reactions. This study consists of three stages: planning, conduction, and analysis/reporting. In the conduction stage, inclusion and exclusion criteria are applied to the literature searching and identification. Then, we have implemented quality assessment rules, where over 75 scored articles in the literature were included. Finally, in the analysis/reporting stage, all the papers are reviewed and analysed. After the quality assessment of the individual papers, this study adopted 57 articles for the systematic literature review. From these reviews, the critical analysis of each paper, including the represented matrix for the model evaluation, existing contributions, and motivation, has been tracked with suitable illustrations. We have also interpreted several insights of each paper with appropriate annotation. Further, a set of comparisons has been enumerated with suitable discussion. Convolutional neural networks are the most commonly used deep learning architecture for COVID-19 disease classification and identification from X-ray and CT images. Various prior studies did not include data from a hospital setting nor did they consider data preprocessing before training a deep learning model.

Background: Total mesorectal excision is the gold standard for rectal cancer surgery, with laparoscopic and robot-assisted approaches commonly employed. While robot-assisted surgery may offer technical advantages, there is limited evidence comparing short-term outcomes of laparoscopic and robot-assisted techniques, particularly in Western European populations. This study aimed to assess the short-term outcomes of laparoscopic vs robot-assisted total mesorectal excision for rectal cancer. Methods: This multicenter, international, retrospective cohort study included 1749 patients who underwent laparoscopic or robot-assisted total mesorectal excision from January 2014 to January 2024. Inverse probability of treatment weighting was applied to minimize confounding. Primary outcomes were length of stay, operative time, and conversion rates. Secondary outcomes included complications and pathological outcomes within 90 days, and readmissions and reinterventions within 30 days. Results: The final cohort included 680.9 laparoscopic and 1057.5 robot-assisted cases after weighting. Robot-assisted surgery showed lower conversion rates (6.1% vs 3.5%, P = .025), higher rates of primary anastomosis (80.1% vs 92.1%, P < .001), and fewer stoma formations (78.4% vs 63.7%, P < .001). Pathological outcomes indicated a higher rate of complete mesorectal excision in the robot-assisted group (77.2% vs 86.0%, P < .001), though these data were not available for all centers. Operative time was longer in the robot-assisted cohort (181.0 vs 220.0 minutes, P < .001), but no significant differences were observed in postoperative complications, length of stay, anastomotic leakage, or 30-day reintervention rates. Conclusion: Robot-assisted surgery low anterior resection demonstrated improved short-term outcomes with lower conversion rates, higher rates of complete mesorectal excision, and higher restorative procedure rates, which may influence longer term oncological and patient quality of life outcomes. Trial registration: https://www.isrctn.com/ISRCTN75281193

Background/Objectives: Rectal cancer is a major global health issue with high morbidity and mortality rates. Local recurrence (LR) significantly impacts patient outcomes, decreasing survival rates and often necessitating extensive secondary treatments. While robot-assisted total mesorectal excision (R-TME) is becoming a preferred method for rectal cancer surgery due to its improved precision and visualisation, long-term data on LR and predictors of recurrence remain limited. This study aims to determine the 3-year LR rate following R-TME and to identify predictors of recurrence to enhance patient selection and the personalisation of treatment. Methods: This retrospective international multicentre cohort study included 1039 consecutive rectal cancer patients who underwent R-TME between 2013 and 2020, with a minimum of 3 years of follow-up. Data from tertiary colorectal centres in the United Kingdom, the Netherlands, Spain, France, Italy, and Belgium were analysed. Potential predictors of LR were identified using backward elimination, and four machine learning models were evaluated for predicting LR. Results: The 3-year LR rate was 3.8%. Significant predictors of LR included advanced clinical M-staging, length of the hospital stay, postoperative ileus, postoperative complications, pathological N-staging, the completeness of resection, and the resection margin distance. The eXtreme Gradient Boosting model performed best for LR prediction, with a final accuracy of 77.1% and an AUC of 0.76. Conclusions: R-TME in high-volume centres achieves low 3-year LR rates, suggesting that robot-assisted surgery offers oncological safety and advantages in rectal cancer management. This study underscores the importance of surgical precision, patient selection, and standardised perioperative care, supporting further investment in robotic training to improve long-term patient outcomes.