Search

Asbestos is a known human carcinogen and the chief known cause of mesothelioma. In 1997, a group of experts developed the Helsinki Criteria, which established criteria for attribution of mesothelioma to asbestos. The criteria include two methods for causation attribution: 1) a history of significant occupational, domestic, or environmental exposure and/or 2) pathologic evidence of exposure to asbestos. In 2014, the Helsinki Criteria were updated, and these attribution criteria were not changed. However, since the Helsinki Criteria were first released in 1997, some pathologists, cell biologists, and others have claimed that a history of exposure cannot establish causation unless the lung asbestos fiber burden exceeds “the background range for the laboratory in question to attribute mesothelioma cases to exposure to asbestos.” This practice ignores the impact on fiber burden of clearance/translocation over time, which in part is why the Helsinki Criteria concluded that a history of exposure to asbestos was independently sufficient to attribute causation to asbestos. After reviewing the Helsinki Criteria, we conclude that their methodology is fatally flawed because a quantitative assessment of a background lung tissue fiber level cannot be established. The flaws of the Helsinki Criteria are both technical and substantive. The 1995 paper that served as the scientific basis for establishing background levels used inconsistent methods to determine exposures in controls and cases. In addition, historic controls cannot be used to establish background fiber levels for current cases because ambient exposures to asbestos have decreased over time and control cases pre-date current cases by decades. The use of scanning electron microscope (SEM) compounded the non-compatibility problem; the applied SEM cannot distinguish talc from anthophyllite because it cannot perform selected area electron diffraction, which is a crucial identifier in ATEM for distinguishing the difference between serpentine asbestos, amphibole asbestos, and talc.

Camouflaged object detection and segmentation is a new and challenging research topic in computer vision. There is a serious issue of lacking data on concealed objects such as camouflaged animals in natural scenes. In this paper, we address the problem of few-shot learning for camouflaged object detection and segmentation. To this end, we first collect a new dataset, CAMO-FS, for the benchmark. As camouflaged instances are challenging to recognize due to their similarity compared to the surroundings, we guide our models to obtain camouflaged features that highly distinguish the instances from the background. In this work, we propose FS-CDIS, a framework to efficiently detect and segment camouflaged instances via two loss functions contributing to the training process. Firstly, the instance triplet loss with the characteristic of differentiating the anchor, which is the mean of all camouflaged foreground points, and the background points are employed to work at the instance level. Secondly, to consolidate the generalization at the class level, we present instance memory storage with the scope of storing camouflaged features of the same category, allowing the model to capture further class-level information during the learning process. The extensive experiments demonstrated that our proposed method achieves state-of-the-art performance on the newly collected dataset. Code is available at https://github.com/danhntd/FS-CDIS.

This paper conducts a thorough examination of the 12th Video Browser Showdown (VBS) competition, a well-established international benchmarking campaign for interactive video search systems. The annual VBS competition has witnessed a steep rise in the popularity of multimodal embedding-based approaches in interactive video retrieval. Most of the thirteen systems participating in VBS 2023 utilized a CLIP-based cross-modal search model, allowing the specification of free-form text queries to search visual content. This shared emphasis on joint embedding models contributed to balanced performance across various teams. However, the distinguishing factors of the top-performing teams included the adept combination of multiple models and search modes, along with the capabilities of interactive interfaces to facilitate and refine the search process. Our work provides an overview of the state-of-the-art approaches employed by the participating systems and conducts a thorough analysis of their search logs, which record user interactions and results of their queries for each task. Our comprehensive examination of the VBS competition offers assessments of the effectiveness of the retrieval models, browsing efficiency, and user query patterns. Additionally, it provides valuable insights into the evolving landscape of interactive video retrieval and its future challenges.

The COVID-19 pandemic presents significant challenges due to its high transmissibility and mortality risk. Traditional diagnostic methods, such as RT-PCR, have limitations that hinder timely and accurate screening. In response, AI-powered computer-aided imaging analysis techniques have emerged as a promising alternative for COVID-19 diagnosis. In this paper, we propose a novel approach that combines the strengths of Convolutional Neural Network (CNN) and Vision Transformer (ViT) to enhance the performance of COVID-19 diagnosis models. CNN excels at capturing spatial features in medical images, while ViT leverages self-attention mechanisms inspired by human radiologists. Additionally, our approach draws inspiration from subclinical diagnosis, a collaborative process involving attending physicians and specialists, which has proven effective in achieving accurate and comprehensive diagnoses. To this end, we employ an early fusion strategy integrating CNN and ViT, then fed into a residual neural network. By fusing these complementary features, our approach achieves state-of-the-art performance in accurately identifying COVID-19 cases on two benchmark datasets: Chest X-ray and Clean-CC-CCII. This research has the potential to enable timely and accurate screening, aiding in the early detection and management of COVID-19 cases. Our findings contribute to the growing knowledge of AI-powered diagnostic techniques and demonstrate the potential for advanced imaging analysis methods to support medical professionals in combating the ongoing pandemic.

The Lifelog Search Challenge (LSC) is an interactive benchmarking evaluation workshop for lifelog retrieval systems. The challenge was first organised in 2018 aiming to find the system that can quickly retrieve relevant lifelog images for a given semantic query. This paper provides an analysis of the performance of all 17 systems participating in the 4th LSC workshop held at the 2021 Annual ACM International Conference on Multimedia Retrieval (ICMR). LSC’21 was the largest effort at comparing different approaches to interactive lifelog retrieval systems seen thus far. Findings from the challenge suggest that many different interactive factors contribute to the success (or otherwise) of participating teams. In this paper, we provide an overview of the LSC’21 challenge, introduce each team’s approach and explore these factors in depth and offer clues on how to develop a high-performing interactive lifelog search engine.

Extracellular vesicles (EVs) are cell-derived membrane particles that include exosomes, ectosomes, microvesicles, microparticles, apoptotic bodies, and other EV subsets. EVs are involved in intercellular communication and the transport of macromolecules between cells. Here, we propose and test the ability of red blood cell (RBC)-derived EVs (RBC-EVs) as putative drug carriers. EVs were produced by treating RBCs with Phorbol-12-myristate-13-acetate (PMA) and separating from the cells by differential centrifugation steps. RBC-EVs were characterized by size determination, flow cytometry, and scanning electron microscopy (SEM). EVs were loaded with DNA plasmids coding for the green fluorescent protein (GFP) by electroporation. The DNA-loaded EVs (DNA-EVs) were used to transfect THP-1-derived macrophages and analyzed by fluorescence microscopy and flow cytometry. The results showed that RBC-EVs had an almost spherical shape and a polydispersity in their size with an average of 197 ± 44 nm and with a zeta potential of −36 ± 8 mV. RBC-EVs were successfully loaded with DNA but associated with an increase of the polydispersity index (PdI) and showed a positive signal with Picogreen. DNA-EVs were almost completely taken up by macrophages within 24 h, however, resulting in the expression of the GFP in a subpopulation of macrophages. As the way, we designed that RBC-EVs could be potential nucleic acid carriers when the immune system was addressed. This study may contribute to the understanding of the role of EVs in the development of microvesicle-based vehicles.

Copyright of Informatica (03505596) is the property of Slovene Society Informatika and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

During a lifetime, a person can have many wonderful and memorable moments that he/she wants to keep. With the development of technology, people now can store a massive amount of lifelog information via images, videos or texts. Inspired by this, we develop a system to automatically generate caption from lifelog pictures taken from wearable cameras. Following up on our previous method introduced at the SoICT 2018 conference, we propose two improvements in our captioning method. We trained and tested the model on the baseline MSCOCO datasets and evaluated on different metrics. The results show better performance compared to our previous model and to some other image captioning methods. Our system also shows effectiveness in retrieving relevant data from captions and achieve high rank in ImageCLEF 2018 retrieval challenge.

Laryngoscopy images play a vital role in merging computer vision and otorhinolaryngology research. However, limited studies offer laryngeal datasets for comparative evaluation. Hence, this study introduces a novel dataset focusing on vocal fold images. Additionally, we propose a lightweight network utilizing knowledge distillation, with our student model achieving around 98.4% accuracy-comparable to the original EfficientNetB1 while reducing model weights by up to 88%. We also present an AI-assisted smartphone solution, enabling a portable and intelligent laryngoscopy system that aids laryngoscopists in efficiently targeting vocal fold areas for observation and diagnosis. To sum up, our contribution includes a laryngeal image dataset and a compressed version of the efficient model, suitable for handheld laryngoscopy devices. [ABSTRACT FROM AUTHOR]

Copyright of Informatica (03505596) is the property of Slovene Society Informatika and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

After years of unsustainable logging, dry deciduous dipterocarp forest (DDDF) has become poor in timber stocks and has been converted to industrial crops such as rubber. The objectives of this study were to assess teak (Tectona grandisL.f.) tree establishment under degraded DDDF conditions and to determine factors that influence the suitability of teak as a forest enrichment tree species. A set of 64 experimental plots of 4 900 m2each was set up and observed for 4–5 years for testing enrichment planting with teak under various combinations of two groups of factors: ecological conditions and forest status. Weighted, non-linear, multivariate regression models were used to detect key factors that influenced the suitability of teak. The results showed that at the age of 4 years the average dominant tree height (defined as 20% of the tallest trees in the experimental plot) reached 11.2, 7.8, 5.3 and 3.8 m for very good, good, average and poor suitability levels, respectively. Survival rates of planted teak from average to very good suitability levels were over 90%. Six key factors that affected the suitability of teak were waterlogging during the rainy season, altitude, stand volume of the degraded DDDF, soil type, percentage of sand and concentration of P2O5in the soil. Under the extreme ecological and environmental conditions of the DDDF, enrichment planting with teak gave promising results. [ABSTRACT FROM PUBLISHER]

Video retrieval is a challenging task in computer vision, especially with complex queries. In this paper, we consider a new type of complex query which simultaneously covers person and location information. The aim to search a specific person in a specific location. Bag-Of-Visual-Words (BOW) is widely known as an effective model for presenting rich-textured objects and scenes of places. Meanwhile, deep features are powerful for faces. Based on such state-of-the-art approaches, we introduce a framework to leverage BOW model and deep features for person-place video retrieval. First, we propose to use a linear kernel classifier instead of using L2 distance to estimate the similarity of faces, given faces are represented by deep features. Second, scene tracking is employed to deal with the cases face of the query person is not detected. Third, we evaluate several strategies for fusing individual person search and location search results. Experiments were conducted on standard benchmark dataset (TRECVID Instance Search 2016) with more than 300 GB in storage and 464 hours in duration. [ABSTRACT FROM AUTHOR]

We propose and analyze in details the revised model of XPROB, an infinite family of pool-based anonymous communication systems that can be used in various applications including high performance computing environments. XPROB overcomes the limitations of APROB Channel that only resists a global delaying adversary (GDA). Each instance of XPROB uses a pool mix as its core component to provide resistance against a global active adversary (GAA), a stronger yet more practical opponent than a GDA. For XPROB, a GAA can drop messages from users but cannot break the anonymity of the senders of messages. Analysis and experimental evaluations show that each instance of XPROB provides greater anonymity than APROB Channel for the same traffic load and user behaviors (rate and number of messages sent). In XPROB, any message can be delivered with high probability within a few rounds after its arrival into the system; thus, an opponent cannot be certain when a message will be delivered. Furthermore, users can choose their own preference balance between anonymity and delay. Through the evaluation, we prove that XPROB can provide anonymity for users in high-performance computing environments. [ABSTRACT FROM AUTHOR]

In many developing countries there is a prevailing conflict between biodiversity conservation and the need for poverty alleviation. One possible solution for solving that conflict is to find ways that help poor people directly benefit from conservation activities. This approach has been tested in a wetland conservation project in Phu My village, Kien Luong District, Kien Giang Province in Vietnam. The 2,000-hectare seasonally inundated grassland, dominated by the sedge Lepironia articulata (Cyperaceae), in Phu My Village is the last of its kind remaining in the Mekong Delta. In November 2004, a new model of protected area was therefore established. Unlike other protected areas in Vietnam where resource exploitation is prohibited, this is an “open” protected area in the sense that the local Khmer ethnic minority people are still allowed to harvest Lepironia as they have been doing for hundreds of years. The project provides local people with skills training and production equipment so that they can make fine handicrafts from the Lepironia they harvest. The project also helps with marketing handicraft products to higher profitable export markets. After three years of operating, the daily income of people who participated was on average twice as much as it was before the project began. The unique remnant wetland is protected, which would otherwise have been turned into a rice cultivation area according to the previous land use planning of Kien Giang Province. [ABSTRACT FROM AUTHOR]

Antimicrobial resistance (AMR) has been identified by the World Health Organization (WHO) as one of the ten major threats to global health. Advances in technology, including whole-genome sequencing, have provided new insights into the origin and mechanisms of AMR. However, our understanding of the short-term impact of antimicrobial pressure and resistance on the physiology of bacterial populations is limited. We aimed to investigate morphological and physiological responses of clinical isolates of E. coli under short-term exposure to key antimicrobials. We performed whole-genome sequencing on twenty-seven E. coli isolates isolated from children with sepsis to evaluate their AMR gene content. We assessed their antimicrobial susceptibility profile and measured their growth dynamics and morphological characteristics under exposure to varying concentrations of ciprofloxacin, ceftriaxone, tetracycline, gentamicin, and azithromycin. AMR was common, with all organisms resistant to at least one antimicrobial; a total of 81.5% were multi-drug-resistant (MDR). We observed an association between resistance profile and morphological characteristics of the E. coli over a three-hour exposure to antimicrobials. Growth dynamics experiments demonstrated that resistance to tetracycline promoted the growth of E. coli under antimicrobial-free conditions, while resistance to the other antimicrobials incurred a fitness cost. Notably, antimicrobial exposure heterogeneously suppressed bacterial growth, but sub-MIC concentrations of azithromycin increased the maximum growth rate of the clinical isolates. Our results outline complex interactions between organism and antimicrobials and raise clinical concerns regarding exposure of sub-MIC concentrations of specific antimicrobials. [ABSTRACT FROM AUTHOR]

Camouflaged objects are generally difficult to be detected in their natural environment even for human beings. In this paper, we propose a novel bio-inspired network, named the MirrorNet, that leverages both instance segmentation and bio-inspired attack stream for the camouflaged object segmentation. Differently from existing networks for segmentation, our proposed network possesses two segmentation streams: the main stream and the bio-inspired attack stream corresponding with the original image and its flipped image, respectively. The output from the bio-inspired attack stream is then fused into the main stream’s result for the final camouflage map to boost up the segmentation accuracy. Extensive experiments conducted on the public CAMO dataset demonstrate the effectiveness of our proposed network. Our proposed method achieves 89% in accuracy, outperforming the state-of-the-arts.

Temporal action proposal generation (TAPG) aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet plays an important role in many tasks of video analysis and understanding. Despite the great achievement in TAPG, most existing works ignore the human perception of interaction between agents and the surrounding environment by applying a deep learning model as a black-box to the untrimmed videos to extract video visual representation. Therefore, it is beneficial and potentially improves the performance of TAPG if we can capture these interactions between agents and the environment. In this paper, we propose a novel framework named Agent-Aware Boundary Network (ABN), which consists of two sub-networks: (1) an Agent-Aware Representation Network to obtain both agent-agent and agents-environment relationships in the video representation; and (2) a Boundary Generation Network to estimate the confidence score of temporal intervals. In the Agent-Aware Representation Network, the interactions between agents are expressed through local pathway, which operates at a local level to focus on the motions of agents whereas the overall perception of the surroundings are expressed through global pathway, which operates at a global level to perceive the effects of agents-environment. Comprehensive evaluations on 20-action THUMOS-14 and 200-action ActivityNet-1.3 datasets with different backbone networks (i.e C3D, SlowFast and Two-Stream) show that our proposed ABN robustly outperforms state-of-the-art methods regardless of the employed backbone network on TAPG. We further examine the proposal quality by leveraging proposals generated by our method onto temporal action detection (TAD) frameworks and evaluate their detection performances.