Marko Mihajlovic

This study investigates the synergy between the virtual and real-world economies through e-commerce, where seller reputation is critical in guiding consumer decisions. As traditional businesses shift towards online retail, user reviews become essential, offering feedback to both sellers and potential buyers. Sentiment analysis through machine learning (ML) techniques presents significant advantages for consumers and retailers alike. This research proposes a novel approach combining bidirectional encoder representations from transformers (BERT) embeddings with an optimized XGBoost classification model to enhance sentiment analysis performance. A modified metaheuristic algorithm, derived from the firefly algorithm (FA), is introduced to optimize the model. Testing on publicly available datasets demonstrates that models optimized by this algorithm achieved a peak accuracy of .881336. Further statistical analyses substantiate these improvements, and SHAP interpretation on the best-performing model identifies key features impacting model predictions, shedding light on factors driving customer sentiment insights.

Instance segmentation in high-resolution images is essential for applications such as remote sensing, medical imaging, and precision agriculture, yet remains challenging due to factors such as small object sizes, irregular shapes, and occlusions. Tiling-based approaches, such as Slicing-Aided Hyper Inference (SAHI), alleviate some of these challenges by processing smaller patches but introduce border artifacts and increased computational cost. Overlapping tiles can mitigate certain boundary effects but often result in duplicate detections and boundary inconsistencies, particularly along patch edges. Conventional deduplication techniques, including Non-Maximum Suppression (NMS) and Non-Mask Merging (NMM), rely on Intersection over Union (IoU) thresholds and frequently fail to merge fragmented or adjacent masks with low mutual IoU that nonetheless correspond to the same object. To address deduplication and mask fragmentation, Spatial Mask Merging (SMM) is proposed as a graph clustering approach that integrates pixel-level overlap and boundary distance metrics while using R-tree indexing for efficient candidate retrieval. SMM was evaluated on the iSAID benchmark using standard segmentation metrics, with tile overlap configurations systematically examined to determine the optimal setting for segmentation accuracy. The method achieved a nearly 7% increase in precision, with consistent gains in F1 score and Panoptic Quality over existing approaches. The integration of R-tree indexing facilitated faster candidate retrieval, enabling computational performance improvements over standard merging algorithms alongside the observed accuracy gains.

Accurate segmentation of kidney microstructures in whole slide images (WSIs) is essential for the diagnosis and monitoring of renal diseases. In this study, an end-to-end instance segmentation pipeline was developed for the detection of glomeruli and blood vessels in hematoxylin and eosin (H&E) stained kidney tissue. A tiling-based strategy was employed using Slicing Aided Hyper Inference (SAHI) to manage the resolution and scale of WSIs and the performance of two segmentation models, YOLOv11 and YOLOv12, was comparatively evaluated. The influence of tile overlap ratios on segmentation quality and inference efficiency was assessed, with configurations identified that balance object continuity and computational cost. To address object fragmentation at tile boundaries, an Enhanced Syncretic Mask Merging algorithm was introduced, incorporating morphological and spatial constraints. The algorithm’s hyperparameters were optimized using Particle Swarm Optimization (PSO), with vessel and glomerulus-specific performance targets. The optimization process revealed key parameters affecting segmentation quality, particularly for vessel structures with fine, elongated morphology. When compared with a baseline without postprocessing, improvements in segmentation precision were observed, notably a 48% average increase for glomeruli and up to 17% for blood vessels. The proposed framework demonstrates a balance between accuracy and efficiency, supporting scalable histopathology analysis and contributing to the Vasculature Common Coordinate Framework (VCCF) and Human Reference Atlas (HRA).

Accurate segmentation of kidney microstructures in whole slide images (WSIs) is essential for diagnosing and monitoring renal diseases. This study proposes an end-to-end instance segmentation pipeline for detecting glomeruli and blood vessels in hematoxylin and eosin (H\&E) stained kidney tissue. Using Slicing Aided Hyper Inference (SAHI), we apply a tiling-based approach to manage the high resolution and scale of WSIs and evaluate the performance of two recent segmentation models, YOLOv11 and YOLOv12. Additionally, we evaluate the effect of different tile overlap ratios on segmentation quality and inference efficiency, identifying configurations that balance object continuity with computational cost. To address object fragmentation at tile boundaries, we introduce an Enhanced Syncretic Mask Merging algorithm, incorporating morphological and spatial constraints. Hyperparameters of the merging algorithm are optimized using Particle Swarm Optimization (PSO), targeting vessel and glomerulus specific performance. The optimization process identified parameters that most influenced performance, particularly for vessel segmentation, where fine structure posed challenges and edge fragmentation was less common. Experimental results demonstrate a 48\% average precision improvement in glomerulus segmentation with a maximum improvement of 17\% for blood vessels. The proposed framework effectively balances segmentation accuracy and inference efficiency, supporting high-throughput histopathology analysis and contributing to the Vasculature Common Coordinate Framework (VCCF) and Human Reference Atlas (HRA).