Early detection of Trypanosoma parasites is critical for the prompt treatment of trypanosomiasis, a neglected tropical disease that poses severe health and socioeconomic challenges in affected regions. To address the limitations of traditional manual microscopy and prior automated methods, we propose YOLO-Tryppa, a novel YOLO-based framework specifically engineered for the rapid and accurate detection of small Trypanosoma parasites in microscopy images. YOLO-Tryppa incorporates ghost convolutions to reduce computational complexity while maintaining robust feature extraction and introduces a dedicated P2 prediction head to improve the localization of small objects. By eliminating the redundant P5 prediction head, the proposed approach achieves a significantly lower parameter count and reduced GFLOPs. Experimental results on the public Tryp dataset demonstrate that YOLO-Tryppa outperforms the previous state of the art by achieving an AP50 of 71.3%, thereby setting a new benchmark for both accuracy and efficiency. These improvements make YOLO-Tryppa particularly well-suited for deployment in resource-constrained settings, facilitating more rapid and reliable diagnostic practices.

Accurate segmentation of the nasal cavity and paranasal sinuses in CT scans is crucial for disease assessment, treatment planning, and surgical navigation. It also facilitates the advanced computational modeling of airflow dynamics and enhances endoscopic surgery preparation. This work presents a novel ensemble framework for 3D nasal CT segmentation that synergistically combines CNN-based and transformer-based architectures, 3D-NASE. By integrating 3D U-Net, UNETR, Swin UNETR, SegResNet, DAF3D, and V-Net with majority and soft voting strategies, our approach leverages both local details and global context to improve segmentation accuracy and robustness. Results on the NasalSeg dataset demonstrate that the proposed ensemble method surpasses previous state-of-the-art results by achieving a $35.88\%$ improvement in the DICE score and reducing the standard deviation by $4.53\%$. These promising results highlight the potential of our method to advance clinical workflows in diagnosis, treatment planning, and surgical navigation while also promoting further research into computationally efficient and highly accurate segmentation techniques.

Accurate segmentation of the nasal cavity and paranasal sinuses in CT scans is crucial for disease assessment, treatment planning, and surgical navigation. It also facilitates the advanced computational modeling of airflow dynamics and enhances endoscopic surgery preparation. This work presents a novel ensemble framework for 3D nasal CT segmentation that synergistically combines CNN-based and transformer-based architectures, 3D-NASE. By integrating 3D U-Net, UNETR, and Swin UNETR with majority and soft voting strategies, our approach leverages both local details and global context to improve segmentation accuracy and robustness. Results on the NasalSeg dataset demonstrate that the proposed ensemble method surpasses previous state-of-the-art results by achieving a 35.95% improvement in the DICE score and reducing the standard deviation by 4.57%. These promising results highlight the potential of our method to advance clinical workflows in diagnosis, treatment planning, and surgical navigation while also promoting further research into computationally efficient and highly accurate segmentation techniques.

When reading a newspaper article or social media post, an unaware readermay fall victim to propaganda without realizing it. In order to promote crit-ical thinking, having a tool that informs readers when a text is potentiallypersuasive is highly important. In this work, we explore a way to providea quantitative measure representing the level of persuasiveness in a generictext. To achieve this goal, we propose a RoBERTa-based framework that an-alyzes text to identify persuasion techniques and, based on these, computes anovel proposed metric, Pscore, reflecting the overall degree of persuasiveness.We train the model on two tasks, sentence classification and token classifi-cation, using the SemEval 2023 dataset for persuasion technique detection,achieving 82% and 80% in Micro-F1, respectively. To validate the Pscore, weuse the Persuasive Pairs dataset, which contains pairs of semantically simi-lar texts where one is more persuasive than the other. Using the score, ourpipeline correctly discriminated 77% of the pairs. Finally, we apply the vali-dated score to the persuasive text sanitization task, using the Qwen3 modelfamily to rephrase the most persuasive text in each pair of the PersuasivePairs dataset. We then evaluate the models’ ability to rephrase sentenceswhile reducing their persuasiveness, and measure the Pscore before and aftersanitization, showing a significant reduction of 93.55%.