Search

With rising global temperatures, wildfires frequently occur worldwide during the summer season. The timely detection of these fires, based on unmanned aerial vehicle (UAV) images, can significantly reduce the damage they cause. Existing Convolutional Neural Network (CNN)-based fire detection methods usually use multiple convolutional layers to enhance the receptive fields, but this compromises real-time performance. This paper proposes a novel real-time semantic segmentation network called FireFormer, combining the strengths of CNNs and Transformers to detect fires. An agile ResNet18 as the encoding component tailored to fulfill the efficient fire segmentation is adopted here, and a Forest Fire Transformer Block (FFTB) rooted in the Transformer architecture is proposed as the decoding mechanism. Additionally, to accurately detect and segment small fire spots, we have developed a novel Feature Refinement Network (FRN) to enhance fire segmentation accuracy. The experimental results demonstrate that our proposed FireFormer achieves state-of-the-art performance on the publicly available forest fire dataset FLAME—specifically, with an impressive 73.13% IoU and 84.48% F1 Score. [ABSTRACT FROM AUTHOR]

Detection of computer-generated (CG) images can reveal the authenticity and originality of digital images. However, recent cutting-edge image generation methods make it very difficult to distinguish CG images from natural photographs. In this paper, a novel method based on color patterns and enhanced texture learning is proposed to tackle this problem. We designed and implemented the backbone network with a separation-fusion learning strategy by constructing a multi-branch neural network. The luminance and chrominance patterns in dual-color spaces (RGB and YCbCr) are leveraged to achieve a robust representation of image differences. A channel-spatial attention module and a global texture enhancement module are also integrated into a backbone network to enhance the learning of inherent traces. Experiments on several commonly used benchmark datasets and a newly constructed dataset with more realistic and diverse images demonstrate that the proposed algorithm outperforms state-of-the-art competitors by a large margin. [ABSTRACT FROM AUTHOR]

OBJECTIVES The goal of this study was to investigate the patterns and risk factors for recurrence in patients with oesophageal squamous cell carcinoma with a pathological complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT). METHODS Between January 2008 and December 2018, a total of 96 patients with pCR were enrolled in this study. Lymph nodes with a pCR [LN-ypCR response (+)] were defined as those lymph nodes without residual tumour but with the presence of treatment response to nCRT. Prognostic factors for recurrence-free survival (RFS) were analysed with Cox proportional hazards models and Fine-Gray competing risk models. Lymph node (LN) stations were counted according to the Japan Esophageal Society classification. RESULTS The median follow-up time was 51.5 months. Recurrence occurred in 15 cases (15.6%) with a 9.9-month median time to recurrence and a 15.6-month median survival after recurrence. The majority of recurrent diseases developed within the first 2 years postoperatively. Distant recurrences were detected in 14 cases (14.6%), in which the most common recurrence sites were no.104 LN and the lung, followed by no.16 LN. The mean RFS in the whole cohort was 116.6 months. The LN-ypCR response (+) was identified as the independent prognostic factor for worse RFS in both the multivariate Cox model and the Fine–Gray competing risk model (P  =   0.001 and P  =   0.002, respectively). CONCLUSIONS Relapse is not rare in oesophageal squamous cell carcinoma cases with pCR after nCRT. Distant recurrences, the predominant pattern of relapse, occur primarily within the first 2 years after oesophagectomy. Patients with pCR with an LN-ypCR response (+) have a higher risk for postoperative recurrence. [ABSTRACT FROM AUTHOR]

Barium titanate nanoparticles were used as a locator to help accurately break the scales on the surface of wool fibers under microwave vacuum treatment, as an anti-felting process of wool with low environmental impact. The nanoparticles loaded by ultrasound are sandwiched between the scales and fibers, which allows the microwave energy concentration to break the scales for the shrink resistance of wool and avoid damaging the main body of fibers synchronously. The friction and mechanical properties of wool under microwave treatment with different power, temperature and processing time were discussed, morphological and chemical analysis of the fibers after treatment was also carried out. The results suggested that compared with the uncoated fibers, the anti-felting performance of the coated fibers after treatment had been significantly improved, while maintaining the mechanical properties, the tip end of the scales on the wool surface were cut off and the volume of the felting ball was increased by 82.3%. The nanoparticles coating the wool were also easily cleaned without residue. This study provided a novel potential approach in the modification of wool fibers for anti-felting. [ABSTRACT FROM AUTHOR]

Background: Irritable bowel syndrome (IBS) is a functional gut disease characterized by visceral hypersensitivity and gut motor dysfunction. Serotonin (5-hydroxytryptamine, 5-HT) is an important enteric neurotransmitter. High levels of 5-HT aggravate IBS symptoms. The serotonin reuptake transporter (SERT) is a membrane-embedded transporter involved in IBS pathogenesis that plays an important role in regulating 5-HT signaling. Aim: We investigated whether gut motor function was altered in SERT-knockout (SERT-KO) rats. Additionally, we sought to determine whether Shugan decoction (SGD), a clinically experienced prescription for the treatment of IBS, exerts regulatory effects on intestinal motility in SERT-KO rats, and attempted to identify the mechanisms involved. Method: SERT-KO rats were produced by transcription activator-like effector nuclease (TALEN) technology. Fecal pellet output was measured for ten consecutive days to estimate distal colonic motility. Small intestinal motility was measured by charcoal-meal experiments. The colonic and small intestinal muscle contractile activities were measured by organ bath study. Western blot was used to analyze the muscarinic receptor expression in colon tissue. Result: Compared with that in wild-type (WT) rats, the defecation amount, amplitude of spontaneous contraction, and the tension of ACh-induced contraction of colonic longitudinal smooth muscle in SERT-KO rats were significantly increased. The expression of muscarinic receptor subtype-3 (M3R) in the colons of SERT-KO rats was also elevated. SGD can decrease defecation of SERT-KO rats. Moreover, SGD reduced the amplitude of spontaneous contraction, the frequency and tension of ACh-induced contraction of colonic longitudinal smooth muscle, and the expression of M3R in the colon in SERT-KO rats. Conclusions: SERT-KO rats showed increased defecation accompanied by enhanced colonic motility and M3R expression. The findings suggest that SGD modifies colonic dysmotility and reduces defecation in SERT-KO rats by down-regulating M3R expression in the colon. [ABSTRACT FROM AUTHOR]