Improving Laryngoscopy Image Analysis Through Integration of Global Information and Local Features in VoFoCD Dataset.

The diagnosis and treatment of vocal fold disorders heavily rely on the use of laryngoscopy. A comprehensive vocal fold diagnosis requires accurate identification of crucial anatomical structures and potential lesions during laryngoscopy observation. However, existing approaches have yet to explore the joint optimization of the decision-making process, including object detection and image classification tasks simultaneously. In this study, we provide a new dataset, VoFoCD, with 1724 laryngology images designed explicitly for object detection and image classification in laryngoscopy images. Images in the VoFoCD dataset are categorized into four classes and comprise six glottic object types. Moreover, we propose a novel Multitask Efficient trAnsformer network for Laryngoscopy (MEAL) to classify vocal fold images and detect glottic landmarks and lesions. To further facilitate interpretability for clinicians, MEAL provides attention maps to visualize important learned regions for explainable artificial intelligence results toward supporting clinical decision-making. We also analyze our model's effectiveness in simulated clinical scenarios where shaking of the laryngoscopy process occurs. The proposed model demonstrates outstanding performance on our VoFoCD dataset. The accuracy for image classification and mean average precision at an intersection over a union threshold of 0.5 (mAP50) for object detection are 0.951 and 0.874, respectively. Our MEAL method integrates global knowledge, encompassing general laryngoscopy image classification, into local features, which refer to distinct anatomical regions of the vocal fold, particularly abnormal regions, including benign and malignant lesions. Our contribution can effectively aid laryngologists in identifying benign or malignant lesions of vocal folds and classifying images in the laryngeal endoscopy process visually.

Acetylmelodorinol isolated from Sphaerocoryne affinis seeds inhibits cell proliferation and activates apoptosis on HeLa cells.

BACKGROUND: Cervical cancer is a major global health concern with a high prevalence in low- and middle-income countries. Natural products, particularly plant-derived compounds, have shown immense potential for developing anticancer drugs. In this study, we aimed to investigate the anticancer properties of the pericarp and seeds of Sphaerocoryne affinis fruit on human cervical carcinoma cells (HeLa) and isolate the bioactive compound from the active fraction. METHODS: We prepared solvent fractions from the ethanol extracts of the pericarp and the seed portion by partitioning and assessing their cytotoxicity on HeLa cells. Subsequently, we collected acetylmelodorinol (AM), an anticancer compound, from the ethyl acetate fraction of seeds and determined its structure using nuclear magnetic resonance. We employed cytotoxicity assay, western blotting, Annexin V apoptosis assay, measurement of intracellular reactive oxygen species (ROS) levels, 4',6-diamidino-2-phenylindole (DAPI) staining, and a terminal deoxynucleotidyl transferase dUTP nick end labeling (TUNEL) assay, to evaluate the anticancer properties of AM on HeLa. RESULTS: The solvent fractions from the seed displayed considerably higher cytotoxic activity against HeLa cells than those of the pericarp. We isolated and identified acetylmelodorinol as an anticancer compound from the ethyl acetate fraction from S. affinis seed extract. Treatment with acetylmelodorinol inhibited HeLa cell proliferation with an IC50 value of 2.62 ± 0.57 µg/mL. Furthermore, this study demonstrated that acetylmelodorinol treatment disrupted cell cycle progression by reducing the expression of cyclin E, CDK1/2, and AKT/mTOR pathways, increasing the intracellular ROS levels, reducing BCL-2/BCL-XL expression, causing DNA fragmentation and nuclear shrinkage, and triggering apoptosis through caspase 3 and 9 activation in a dose-and time-dependent manner. CONCLUSION: In contrast to previous reports, this study focuses on the inhibitory effects of AM on the AKT/mTOR pathway, leading to a reduction in cell proliferation in cervical cancer cells. Our findings highlight the promising potential of acetylmelodorinol as an effective treatment for cervical cancer. Additionally, this study establishes a foundation for investigating the molecular mechanisms underlying AM's properties, fostering further exploration into plant-based cancer therapies.

Potent anti-cancer activity of Sphaerocoryne affinis fruit against cervical cancer HeLa cells via inhibition of cell proliferation and induction of apoptosis.

BACKGROUND: Cervical cancer remains a significant global health issue, highlighting the need for effective therapeutic strategies. Given that Sphaerocoryne affinis (SA) has shown potential anti-cancer activity in several cancer types, herein, we investigate the effects of SA fruit (SAF) on human cervical cancer HeLa cells and their underlying mechanisms of action. METHODS: SAF extract cytotoxicity was assessed in various cancer cell lines. The effects of the hexane fraction (SAF-Hex) on HeLa cell viability, cell cycle protein expression, apoptosis, and DNA damage were evaluated using cytotoxicity assays, Western blotting, quantitative PCR, 4',6-diamidino-2-phenylindole (DAPI) staining, and a terminal deoxynucleotidyl transferase dUTP nick end labeling (TUNEL) assay. RESULTS: SAF-Hex selectively inhibited HeLa cell viability with an IC50 of 4.20 ± 0.36 µg/mL and a selectivity index of 5.11 ± 0.58. The time-dependent cytotoxicity assay showed decreased cell survival after 48 h of treatment, accompanied by morphological changes and apoptotic bodies in HeLa cells. SAF-Hex also suppressed HeLa cell cycle proteins (Cyclin E, CDK2, and CDK1), reduced PCNA transcription, and diminished AKT and mTOR activation, thus inhibiting cell proliferation. The increased γH2AX expression, DNA fragmentation, and caspases-3 and -9 activation indicated SAF-Hex-induced DNA damage and apoptosis. However, the BAX/BCL-2 ratio remained unchanged, and BAX and BCL2 expression was attenuated. CONCLUSION: SAF-Hex effectively inhibits HeLa cell proliferation and induces DNA damage in that cervical cancer cell line activating apoptosis through the intrinsic pathway. Interestingly, the BAX/BCL-2 ratio remained unchanged while BAX and BCL2 transcription was attenuated. Hence, further research is required to explore this unexpected finding and facilitate the development of novel therapies targeting cervical cancer HeLa cells.

Camouflaged Instance Segmentation In-the-Wild: Dataset, Method, and Benchmark Suite.

This paper pushes the envelope on decomposing camouflaged regions in an image into meaningful components, namely, camouflaged instances. To promote the new task of camouflaged instance segmentation of in-the-wild images, we introduce a dataset, dubbed CAMO++, that extends our preliminary CAMO dataset (camouflaged object segmentation) in terms of quantity and diversity. The new dataset substantially increases the number of images with hierarchical pixel-wise ground truths. We also provide a benchmark suite for the task of camouflaged instance segmentation. In particular, we present an extensive evaluation of state-of-the-art instance segmentation methods on our newly constructed CAMO++ dataset in various scenarios. We also present a camouflage fusion learning (CFL) framework for camouflaged instance segmentation to further improve the performance of state-of-the-art methods. The dataset, model, evaluation suite, and benchmark will be made publicly available on our project page.

H2 S Dosimetry by CuO: Towards Stable Sensors by Unravelling the Underlying Solid-State Chemistry.

The precise detection of the toxic gas H2 S requires reliable sensitivity and specificity of sensors even at minute concentrations of as low as 10 ppm, the value corresponding to typical exposure limits. CuO can be used for H2 S dosimetry, based on the formation of conductive CuS and the concomitant significant increase in conductance. In theory, at elevated temperature the reaction is reversed and CuO is formed, ideally enabling repeated and long-term use of one sensor. Yet, the performance of CuO tends to drop upon cycling. Utilizing defined CuO nanorods we thoroughly elucidated the associated detrimental chemical changes directly on the sensors, by Raman and electron microscopy analysis of each step during sensing (CuO→CuS) and regeneration (CuS→CuO) cycles. We find the decrease in the sensing performance is mainly caused by the irreversible formation of CuSO4 during regeneration. The findings allowed us to develop strategies to reduce CuSO4 formation and thus to substantially maintain the sensing stability even for repeated cycles. We achieved CuO-based dosimeters possessing a response time of a few minutes only, even for 10 ppm H2 S, and prolonged life-time.

Masked Face Analysis via Multi-Task Deep Learning.

Face recognition with wearable items has been a challenging task in computer vision and involves the problem of identifying humans wearing a face mask. Masked face analysis via multi-task learning could effectively improve performance in many fields of face analysis. In this paper, we propose a unified framework for predicting the age, gender, and emotions of people wearing face masks. We first construct FGNET-MASK, a masked face dataset for the problem. Then, we propose a multi-task deep learning model to tackle the problem. In particular, the multi-task deep learning model takes the data as inputs and shares their weight to yield predictions of age, expression, and gender for the masked face. Through extensive experiments, the proposed framework has been found to provide a better performance than other existing methods.

Video Salient Object Detection Using Spatiotemporal Deep Features.

This paper presents a method for detecting salient objects in videos, where temporal information in addition to spatial information is fully taken into account. Following recent reports on the advantage of deep features over conventional handcrafted features, we propose a new set of spatiotemporal deep (STD) features that utilize local and global contexts over frames. We also propose new spatiotemporal conditional random field (STCRF) to compute saliency from STD features. STCRF is our extension of CRF to the temporal domain and describes the relationships among neighboring regions both in a frame and over frames. STCRF leads to temporally consistent saliency maps over frames, contributing to accurate detection of salient objects' boundaries and noise reduction during detection. Our proposed method first segments an input video into multiple scales and then computes a saliency map at each scale level using STD features with STCRF. The final saliency map is computed by fusing saliency maps at different scale levels. Our experiments, using publicly available benchmark datasets, confirm that the proposed method significantly outperforms the state-of-the-art methods. We also applied our saliency computation to the video object segmentation task, showing that our method outperforms existing video object segmentation methods.

Elimination of dengue by community programs using Mesocyclops(Copepoda) against Aedes aegypti in central Vietnam.

From September 2000 to June 2003, a community-based program for dengue control using local predacious copepods of the genus Mesocyclops was conducted in three rural communes in the central Vietnam provinces of Quang Nam, Quang Ngai, and Khanh Hoa. Post-project, three subsequent entomologic surveys were conducted until March 2004. The number of households and residents in the communes were 5,913 and 27,167, respectively, and dengue notification rates for these communes from 1996 were as high as 2,418.5 per 100,000 persons. Following knowledge, attitude, and practice evaluations, surveys of water storage containers indicated that Mesocyclops spp. already occurred in 3-17% and that large tanks up to 2,000 liters, 130-300-liter jars, wells, and some 220-liter metal drums were the most productive habitats for Aedes aegypti. With technical support, the programs were driven by communal management committees, health collaborators, schoolteachers, and pupils. From quantitative estimates of the standing crop of third and fourth instars from 100 households, Ae. aegypti were reduced by approximately 90% by year 1, 92.3-98.6% by year 2, and Ae. aegypti immature forms had been eliminated from two of three communes by June 2003. Similarly, from resting adult collections from 100 households, densities were reduced to 0-1 per commune. By March 2004, two communes with no larvae had small numbers but the third was negative; one adult was collected in each of two communes while one became negative. Absolute estimates of third and fourth instars at the three intervention communes and one left untreated had significant correlations (P = 0.009-< 0.001) with numbers of adults aspirated from inside houses on each of 15 survey periods. By year 1, the incidence of dengue disease in the treated communes was reduced by 76.7% compared with non-intervention communes within the same districts, and no dengue was evident in 2002 and 2003, compared with 112.8 and 14.4 cases per 100,000 at district level. Since we had similar success in northern Vietnam from 1998 to 2000, this study demonstrates that this control model is broadly acceptable and achievable at community level but vigilance is required post-project to prevent reinfestation.