SRTRP-Net: A multi-task learning network for segmentation and prediction of stereotactic radiosurgery treatment response in brain metastases.

Before the Stereotactic Radiosurgery (SRS) treatment, it is of great clinical significance to avoid secondary genetic damage and guide the personalized treatment plans for patients with brain metastases (BM) by predicting the response to SRS treatment of brain metastatic lesions. Thus, we developed a multi-task learning model termed SRTRP-Net to provide prior knowledge of BM ROI and predict the SRS treatment response of the lesion. In dual-encoder tumor segmentation Network (DTS-Net), two parallel encoders encode the original and mirrored multi-modal MRI images. The differences in the dual-encoder features between foreground and background are enhanced by the symmetrical visual difference block (SVDB). In the bottom layer of the encoder, a transformer is used to extract local contextual features in the spatial and depth dimensions of low-resolution images. Then, the decoder of DTS-Net provides the prior knowledge for predicting the response to SRS treatment by performing BM segmentation. SRS response prediction network (SRP-Net) directly utilizes shared multi-modal MRI features weighted by the signed distance map (SDM) of the masks. The bidirectional multi-dimensional feature fusion module (BMDF) fuses the shared features and the clinical text information features to obtain comprehensive tumor information for characterizing tumors and predicting SRS treatment response. Experiments based on internal and external clinical datasets have shown that SRTRP-Net achieves comparable or better results. We believe that SRTRP-Net can help clinicians accurately develop personalized first-time treatment regimens for BM patients and improve their survival.

Effect of dense phase carbon dioxide treatment on the flavor, texture, and quality changes in new-paocai.

This study investigated the effect of dense phase carbon dioxide (DPCD) treatment on the organoleptic properties of new-paocai. Optimal DPCD treatment (25 MPa/40 °C/40 min) was determined by conducting single-factor and orthogonal experiments with the sensory, bactericidal, and electronic eye evaluations. DPCD treatment (25 MPa/40 °C/40 min) did not significantly affect the nitrite, pH, total acid, and organic acid of the new-paocai brine, and the texture of the radish slices did not display substantial changes. Gas chromatography-mass spectrometry (GC-MS) was employed to characterize the new-paocai brine flavor, revealing 63 and 60 respective flavor compounds with and without DPCD treatment. In addition, DPCD treatment significantly reduced the total organic volatile compound content in the paocai from 48.182 µg/mL to 35.952 µg/mL, DPCD has a great influence on volatile flavor substances. The electronic nose (E-nose) effectively distinguished the flavor differences in the new-paocai brine with and without DPCD treatment. This study combined new food processing technology with traditional food production, could provide a new idea for pickle production technology.

Comparison of Different Varieties on Quality Characteristics and Microbial Activity of Fresh-Cut Pineapple during Storage.

This study compared the quality and storage characteristics of four pineapple varieties to select those displaying adequate storage resistance and those suitable for freshly cut processing. Four varieties of pineapple, namely Tainong No.16, Tainong No.17, Tainong No.11, and Bali, were used to analyze the quality differences in freshly cut pineapple during storage by measuring the quality, physiological indicators, and total microbial count. The results indicated that the nutritional quality and storability of freshly cut pineapples differed significantly among the varieties. During refrigeration at 4 °C, Tainong No.11 and Bali displayed the shortest storage period of 4 d, while Tainong No.17 and Tainong No.16 presented storage periods of 5 d and 6 d, respectively. A sensory evaluation indicated that the Tainong No.16 variety was superior in terms of consumer preference, while the Bali slices were generally rated lower than the other cultivars. Additionally, the sensory properties, weight loss, firmness, and ascorbic acid (AA) content of Tainong No.16 changed the least during storage, with values of 60.75%, 6.48%, 75.15%, and 20.44%, respectively. Overall, the quality order of the four varieties of freshly cut pineapples during storage was: Tainong No.16 > Tainong No.17 > Tainong No.11 > Bali. Moreover, two-way ANOVA showed that the main effect of variety and storage time on the storage quality of fresh-cut pineapple was significant (p < 0.05). The interaction effect of variety and storage time on other quality characteristics of fresh-cut pineapple was significant (p < 0.05) except for Titratable acid (TA) and AA. In conclusion, Tainong No.16 displayed higher storage potential than the other varieties. The results of this work provide application possibilities to promote the successful processing of pineapple cultivars as freshly cut produce.

Learning From Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation.

This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations (weak supervisions). Most existing approaches aim to generate accurate pixel-level labels from weak supervisions. However, we observe that those generated labels still inevitably contain noisy labels. Motivated by this observation, we present a novel perspective and formulate this task as a problem of learning with pixel-level label noise. Existing noisy label methods, nevertheless, mainly aim at image-level tasks, which can not capture the relationship between neighboring labels in one image. Therefore, we propose a graph-based label noise detection and correction framework to deal with pixel-level noisy labels. In particular, for the generated pixel-level noisy labels from weak supervisions by Class Activation Map (CAM), we train a clean segmentation model with strong supervisions to detect the clean labels from these noisy labels according to the cross-entropy loss. Then, we adopt a superpixel-based graph to represent the relations of spatial adjacency and semantic similarity between pixels in one image. Finally we correct the noisy labels using a Graph Attention Network (GAT) supervised by detected clean labels. We comprehensively conduct experiments on PASCAL VOC 2012, PASCAL-Context, MS-COCO and Cityscapes datasets. The experimental results show that our proposed semi-supervised method achieves the state-of-the-art performances and even outperforms the fully-supervised models on PASCAL VOC 2012 and MS-COCO datasets in some cases.

Antifungal Effect of Chitosan/Nano-TiO2 Composite Coatings against Colletotrichum gloeosporioides, Cladosporium oxysporum and Penicillium steckii.

Postharvest pathogens such as C. gloeosporioides (MA), C.oxysporum (ME) and P. steckii (MF) are the causal agents of disease in mangoes. This paper presents an in vitro investigation into the antifungal effect of a chitosan (CTS)/nano-titanium dioxide (TiO2) composite coating against MA, ME and MF. The results indicated that, the rates of MA, ME and MF mortality following the single chitosan treatment were 63.3%, 84.8% and 43.5%, respectively, while the rates of mycelial inhibition were 84.0%, 100% and 25.8%, respectively. However, following the addition of 0.5% nano-TiO2 into the CTS, both the mortality and mycelial inhibition rates for MA and ME reached 100%, and the mortality and mycelial inhibition rate for MF also increased significantly, reaching 75.4% and 57.3%, respectively. In the MA, the dry weight of mycelia after the CTS/0.5% nano-TiO2 treatment decreased by 36.3% in comparison with the untreated group, while the conductivity value was about 1.7 times that of the untreated group, and the protein dissolution rate and extravasation degree of nucleic acids also increased significantly. Thus, this research revealed the potential of CTS/nano-TiO2 composite coatings in the development of new antimicrobial materials.

Gold-silver alloy film based surface plasmon resonance sensor for biomarker detection.

In this study, we developed a gold­silver alloy film based surface plasmon resonance (AuAg-SPR) sensor with wavelength interrogation to detect cancer antigen 125 (CA125) using a sandwich immunoassay. We first theoretically simulated the sensitivity of conventional gold film based SPR (Au-SPR) sensor and AuAg-SPR sensor, and conducted a series of experiments to investigate the sensitive characteristics of AuAg-SPR sensor, including the angle and refractive index (RI) sensitivity. We then conducted CA125 detection experiments on these two types of sensors. The results demonstrated that the limit of detection (LOD) of CA125 on the AuAg-SPR sensor was 0.1 U/mL (0.8 ng/mL) based on its direct reaction with an immobilised antibody, which was two orders of magnitude lower than that of the Au-SPR sensor (10 U/mL). The total changes in the resonance wavelength (∆λR) of the former were 1.7-fold those of the latter. The volume fractions of the adsorbates (fad) and effective RIs (nadlayer) in each adlayer were then calculated and the effect of the antibody size on the detection results was analysed. The AuAg-SPR sensors had a higher sensitivity than the conventional Au-SPR sensors for detecting CA125 due to their electric field characteristics. Therefore, these will have better application prospects.