Bone metastasis scintigram generation using generative adversarial learning with multi-receptive field learning and two-stage training.

BACKGROUND: Deep learning is the primary method for conducting automated analysis of SPECT bone scintigrams. The lack of available large-scale data significantly hinders the development of well-performing deep learning models, as the performance of a deep learning model is positively correlated with the size of the dataset used. Therefore, there is an urgent demand for an automated data generation method to enlarge the dataset of SPECT bone scintigrams. PURPOSE: We introduce a deep learning-based generation model that can generate realistic but not identical samples from the original SPECT bone scintigrams. METHODS: Following the generative adversarial learning architecture, a bone metastasis scintigram generation model christened BMS-Gen is proposed. First, BMS-Gen takes multiple input conditions and employs multi-receptive field learning to ensure that the generated samples are as realistic as possible. Second, BMS-Gen adopts generative adversarial learning to retain the diversity of the generated samples. Last, BMS-Gen uses a two-stage training strategy to improve the quality of the generated samples. RESULTS: Experimental evaluation conducted on a set of clinical data of SPECT BM scintigrams has shown the performance of the proposed BMS-Gen, achieving the best overall scores of 1678.0, 69.33, and 19.51 for FID (Fréchet Inception Distance), MSE (Mean Square Error), and PSNR (Peak Signal-to-Noise Ratio) metrics. The introduction of samples generated by BMS-Gen contributes a maximum (minimum) increase of 3.01% (0.15%) on the F-1 score and a maximum (minimum) increase of 6.83% (2.21%) on the DSC score for the image classification and segmentation tasks, respectively. CONCLUSIONS: The proposed BMS-Gen model can be used as a promising tool for augmenting the data of bone scintigrams, greatly facilitating the development of deep learning-based automated analysis of SPECT bone scintigrams.

[Hydrogen and Oxygen Isotopic Characteristics and Influencing Factors of "Three Waters" in Shandian River Basin].

In this study, we collected precipitation from February 2020 to February 2022 and the surface water and groundwater in the wet (August) and dry (October) periods of 2021 in the Shandian River Basin. Stable isotope technology was used to analyze the temporal and spatial changes in the hydrogen and oxygen stable isotopes of the "three waters" in the basin to explore the relationship between water isomorphs and environmental factors and to reveal the water conversion relationship using the end element mixing model. The results showed that the slope and intercept of the local precipitation line were smaller than the local atmospheric precipitation line. The water vapor mainly came from westerly water vapor, polar air mass, and East Asian monsoon circulation. The precipitation isotope had a significant temperature effect. In terms of time, the isotopes of surface water and groundwater were more enriched in the dry season than those in the wet season, and the d-excess values of surface water and groundwater were lower than the global average, indicating strong local evaporation. Spatially, the δ18O value of the rivers had the same change characteristics in the wet and dry seasons, showing gradual enrichment from the upstream to the downstream, and the groundwater δ18O high value area was unevenly distributed in space, with groundwater δ18O values becoming more depleted with the increase in burial depth. The highest slope of the groundwater water line was 7.87 in the wet season, which was very close to the slope of the local atmospheric precipitation line and river water line, indicating that there was a complex hydraulic connection between the "three waters" in the wet season. The surface water in the study area was mainly supplied by precipitation during the wet season and then by groundwater runoff. These results can provide a theoretical basis for revealing the hydrological cycle in arid and semi-arid areas.

Effect of vacuum sealing drainage in dermatoplasty of large area of cutaneous defects.

OBJECTIVES: To investigate the clinical effect of vacuum sealing drainage in dermatoplasty of large area of cutaneous defects in comparison to conventional treatment. METHODS: 80 patients with large area of cutaneous defects were enrolled in this study, and they had received superficial thickness dermatoplasty. Then these patients were randomly divided into two groups based on follow-up treatments: vacuum sealing drainage (defined as group A, 40 cases) and conventional treatment (defined as group B, 40 cases). After operation, all the patients received similar hospital stay, antibiotics administration, swelling elimination and wound closure in these two groups. RESULTS: No significant difference was observed in terms of the baseline characteristics between the two groups, including areas of cutaneous defects. Compared with conventional treatment group, the healing time of dermatoplasty was reduced significantly in vacuum sealing drainage group. Meanwhile, the rate of survival of dermatoplasty was better, and the rate of wound infection was lower in vacuum sealing drainage group than conventional treatment group. CONCLUSION: Vacuum sealing drainage is effective in treatment with large area of cutaneous defects combined with dermatoplasty, which had better clinical outcomes than conventional therapy.