1,721,002 research outputs found
YOLO-PAM: Parasite-Attention-Based Model for Efficient Malaria Detection
No full textMalaria is a potentially fatal infectious disease caused by the Plasmodium parasite. The mortality rate can be significantly reduced if the condition is diagnosed and treated early. However, in many underdeveloped countries, the detection of malaria parasites from blood smears is still performed manually by experienced hematologists. This process is time-consuming and error-prone. In recent years, deep-learning-based object-detection methods have shown promising results in automating this task, which is critical to ensure diagnosis and treatment in the shortest possible time. In this paper, we propose a novel Transformer- and attention-based object-detection architecture designed to detect malaria parasites with high efficiency and precision, focusing on detecting several parasite sizes. The proposed method was tested on two public datasets, namely MP-IDB and IML. The evaluation results demonstrated a mean average precision exceeding 83.6% on distinct Plasmodium species within MP-IDB and reaching nearly 60% on IML. These findings underscore the effectiveness of our proposed architecture in automating malaria parasite detection, offering a potential breakthrough in expediting diagnosis and treatment processes
Radio DINO: A foundation model for advanced radiomics and AI-driven medical imaging analysis
Full text linkRadiomics is transforming medical imaging by extracting complex features that enhance disease diagnosis, prognosis, and treatment evaluation. However, traditional approaches face significant challenges, such as the need for manual feature engineering, high dimensionality, and limited sample sizes. This paper presents Radio DINO, a novel family of deep learning foundation models that leverage self-supervised learning (SSL) techniques from DINO and DINOV2, pretrained on the RadImageNet dataset. The novelty of our approach lies in (1) developing Radio DINO to capture rich semantic embeddings, enabling robust feature extraction without manual intervention, (2) demonstrating superior performance across various clinical tasks on the MedMNISTv2 dataset, surpassing existing models, and (3) enhancing the interpretability of the model by providing visualizations that highlight its focus on clinically relevant image regions. Our results show that Radio DINO has the potential to democratize advanced radiomics tools, making them accessible to healthcare institutions with limited resources and ultimately improving diagnostic and prognostic outcomes in radiology
Diversità di briofite e licheni terricoli in aree dunali della Sardegna e cambiamenti dovuti all'invasione di specie esotiche e disturbo antropico
No full textA deep architecture based on attention mechanisms for effective end-to-end detection of early and mature malaria parasites
Full text linkMalaria is a severe infectious disease caused by the Plasmodium parasite. The early and accurate detection of this disease is crucial to reducing the number of deaths it causes. However, the current method of detecting malaria parasites involves manual examination of blood smears, which is a time-consuming and labor-intensive process, mainly performed by skilled hematologists, especially in underdeveloped countries. To address this problem, we have developed two deep learning-based systems, YOLO-SPAM and YOLO-SPAM++, which can detect the parasites responsible for malaria at an early stage. Our evaluation of these systems using two public datasets of malaria parasite images, MP-IDB and IML, shows that they outperform the current state-of-the-art, with more than 11M fewer parameters than the baseline YOLOv5m6. YOLO-SPAM++ demonstrated a substantial 10% improvement over YOLO-SPAM and up to 20% against the best-performing baseline in preliminary experiments conducted on the Plasmodium Falciparum species of MP-IDB. On the other hand, YOLO-SPAM showed slightly better results than YOLO-SPAM++ in subsets without tiny parasites, while YOLO-SPAM++ performed better in subsets with tiny parasites, with precision values up to 94%. Further cross-species generalization validations, conducted by merging training sets of various species within MP-IDB, showed that YOLO-SPAM++ consistently outperformed YOLOv5 and YOLO-SPAM across all species, emphasizing its superior performance and precision in detecting tiny parasites. These architectures can be integrated into computer-aided diagnosis systems to create more reliable and robust systems for the early detection of malaria
Bryophyte and lichen communities on oak in a mediterranean-montane area of Sardinia (Italy)
No full textBryophyte and lichen epiphytic communities were studied in the Mediterranean-montane area of M. Artu in Sardinia (Italy) by mean of releves carried out in different oak forest types, with the aim of pointing out differences due to anthropogenic activities. Altogether, 15 bryophyte species and 74 lichen species were found. Releves were classified using cluster analysis. In well-preserved forests, communities dominated by bryophytes and close to the climax associations Antitrichietum californicae and Leptodontetum smithii are present, together with elements of the Lobarion pulmonariae. Lichen communities of the Xanthorion parietinae (Physcietum adscendentis, Parmelietum acetabulae and Ramalinetum fastigiatae) are dominant in the most disturbed conditions, rarely accompanied by elements of the Leucodontetum schiroides. In closed coppice and young woodland a community dominated by Neckera complanata, Metzgeria furcata, Frullania dilatata, Phlyctis argena and Physconia venusta is present, probably close to the Antitrichietum curtipendulae. In mature forests of Q. pubescens and open coppices of Q. ilex, a similar community is also present, though richer in lichen species, and with Frullania dilatata as the only dominant livewort. Widespread temperate species are most frequent in disturbed conditions, while suboceanic species are more common in well-preserved and closed woodland. Mat- and tail-forms of the bryophytes are dominant in well-preserved forest, together with crustose lichens. Broad- and narrow-lobed lichens are dominant in the most disturbed conditions. This is the first study on epiphytic cryptogamic communities of the island
FIRESTART: Fire Ignition Recognition with Enhanced Smoothing Techniques and Real-Time Tracking
No full textFires can potentially cause significant harm to both people and the environment. Recently, there has been a growing interest in real-time fire and smoke detection to provide practical assistance. Detecting fires in outdoor areas is crucial to safeguard human lives and the environment. This is especially important in situations where more than traditional smoke detectors may be required. In this work, we propose FIRESTART, which aims to achieve accurate and robust ignition detection for prompt identification and response to fire incidents. The proposed framework utilizes a lightweight deep learning architecture and post-processing techniques for fire-starting interval detection. Its evaluation was conducted on the ONFIRE dataset, comparing it with several state-of-the-art methods. The results are encouraging, particularly from computational and real-time use perspectives
YOLO-Tryppa: A Novel YOLO-Based Approach for Rapid and Accurate Detection of Small Trypanosoma Parasites
Full text linkEarly 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
SAMMI: Segment Anything Model for Malaria Identification
Full text linkMalaria, a life-threatening disease caused by the Plasmodium parasite, is a pressing global health challenge. Timely detection is critical for effective treatment. This paper introduces a novel computer-aided diagnosis system for detecting Plasmodium parasites in blood smear images, aiming to enhance automation and accessibility in comprehensive screening scenarios. Our approach integrates the Segment Anything Model for precise unsupervised parasite detection. It then employs a deep learning framework, combining Convolutional Neural Networks and Vision Transformer to accurately classify malaria-infected cells. We rigorously evaluate our system using the IML public dataset and compare its performance against various off-the-shelf object detectors. The results underscore the efficacy of our method, demonstrating superior accuracy in detecting and classifying malaria-infected cells. This innovative Computer-aided diagnosis system presents a reliable and near real-time solution for malaria diagnosis, offering significant potential for widespread implementation in healthcare settings. By automating the diagnosis process and ensuring high accuracy, our system can contribute to timely interventions, thereby advancing the fight against malaria globally
Understanding cheese ripeness: An artificial intelligence-based approach for hierarchical classification
Full text linkWithin the contemporary dairy industry, the effective monitoring of cheese ripeness constitutes a critical yet challenging task. This paper proposes the first public dataset encompassing images of cheese wheels that depict various products at distinct stages of ripening and introduces an innovative hybrid approach, integrating machine learning and computer vision techniques to automate the detection of cheese ripeness. By leveraging deep learning and shallow learning techniques, the proposed method endeavors to overcome the limitations associated with conventional assessment methodologies. It aims to provide automation, precision, and consistency in the evaluation of cheese ripeness, delving into a hierarchical classification for the simultaneous classification of distinct cheese types and ripeness levels and presenting a comprehensive solution to enhance the efficiency of the cheese production process. By employing a lightweight hierarchical feature aggregation methodology, this investigation navigates the intricate landscape of preprocessing steps, feature selection, and diverse classifiers. We report a noteworthy achievement, attaining a best F-measure score of 0.991 through the merging of features extracted from EfficientNet and DarkNet-53, opening the field to concretely address the complexity inherent in cheese quality assessment
Influence of Carpobrotus spp. On epigeous cryptogamic communities on coastal sand dunes of Sardinia (Italy)
No full text- …
