Search

Accurate target detection in complex orchard environments is the basis for automatic picking and pollination. The characteristics of small, clustered and complex interference greatly increase the difficulty of detection. Toward this end, we explore a detector in the orchard and improve the detection ability of complex targets. Our model includes two core designs to make it suitable for reducing the risk of error detection due to small and camouflaged object features. Multi-scale texture enhancement design focuses on extracting and enhancing more distinguishable features for each level with multiple parallel branches. Our adaptive region-aware feature fusion module extracts the dependencies between locations and channels, potential cross-relations among different levels and multi-types information to build distinctive representations. By combining enhancement and fusion, experiments on various real-world datasets show that the proposed network can outperform previous state-of-the-art methods, especially for detection in complex conditions. [ABSTRACT FROM AUTHOR]

Background: We conducted a meta-analysis and trial sequential analysis (TSA) to compare the therapeutic efficacy and adverse events (AEs) between the following treatment strategies for patients with hepatocellular carcinoma (HCC): TACE plus tyrosine kinase inhibitors (TKIs) and immune checkpoint inhibitors (ICIs) (TACE + T + I) versus TACE plus TKIs (TACE + T). Methods: We systematically searched PubMed, the Web of Science, the Cochrane Library, and Embase for studies comparing TACE + T + I and TACE + T for the treatment of BCLC intermediate- or advanced-stage HCC. The objective response rate (ORR), progression-free survival (PFS), overall survival (OS), and AEs were included as outcomes. We used a fixed- or random-effects model based on the results of a heterogeneity evaluation and performed a meta-analysis using Review Manager 5.3 and Stata 16.0. We then carried out the TSA. Results: Five studies examining a total of 425 patients were included in this study. Our meta-analysis revealed that, compared to TACE + T, TACE + T + I significantly improved the ORR (risk ratio [RR] = 1.53, 95% confidence interval [CI] = 1.27–1.85, p < 0.01) and extended both the median PFS (mean difference [MD] = 4.51 months, 95% CI = 2.16–6.87, p < 0.01) and median OS (MD = 5.75 months, 95% CI = 4.03–7.48, p < 0.01). These results were tested to be true by the TSA without requiring a larger information size. Among AEs, hypertension tended to occur more often in patients treated with TACE + T + I than in those treated with TACE + T (RR = 1.58, 95% CI = 1.05–2.40, p < 0.05). However, the TSA suggested that additional cases are necessary to confirm this difference. Regarding the other AEs, no significant differences were detected between the two groups. Conclusion: TACE + T + I showed better effects on the ORR, PFS, and OS than TACE + T as a treatment for BCLC stages B and C HCC, without an obvious increase in the AEs. Based on these findings, well-designed, large RCTs are suggested. [ABSTRACT FROM AUTHOR]

Background: We aimed to construct and validate a deep learning (DL) radiomics nomogram using baseline and restage enhanced computed tomography (CT) images and clinical characteristics to predict the response of metastatic lymph nodes to neoadjuvant chemotherapy (NACT) in locally advanced gastric cancer (LAGC). Methods: We prospectively enrolled 112 patients with LAGC who received NACT from January 2021 to August 2022. After applying the inclusion and exclusion criteria, 98 patients were randomized 7:3 to the training cohort (n = 68) and validation cohort (n = 30). We established and compared three radiomics signatures based on three phases of CT images before and after NACT, namely radiomics-baseline, radiomics-delta, and radiomics-restage. Then, we developed a clinical model, DL model, and a nomogram to predict the response of LAGC after NACT. We evaluated the predictive accuracy and clinical validity of each model using the receiver operating characteristic curve and decision curve analysis, respectively. Results: The radiomics-delta signature was the best predictor among the three radiomics signatures. So, we developed and validated a DL delta radiomics nomogram (DLDRN). In the validation cohort, the DLDRN produced an area under the receiver operating curve of 0.94 (95% confidence interval, 0.82–0.96) and demonstrated adequate differentiation of good response to NACT. Furthermore, the DLDRN significantly outperformed the clinical model and DL model (p < 0.001). The clinical utility of the DLDRN was confirmed through decision curve analysis. Conclusions: In patients with LAGC, the DLDRN effectively predicted a therapeutic response in metastatic lymph nodes, which could provide valuable information for individualized treatment. [ABSTRACT FROM AUTHOR]

Background: Some studies have demonstrated the short-term recovery course for patients who underwent laparoscopic gastrectomy according to preoperative computed tomography angiography (CTA) assessment. However, reports of the long-term oncological outcomes are still limited. Methods: The data of 988 consecutive patients who underwent laparoscopic or robotic radical gastrectomy between January 2014 and September 2018 were analyzed retrospectively at our center, and propensity score matching was used to eliminate bias. Study cohorts were divided into the CTA group (n = 498) and the non-CTA group (n = 490) depending on whether preoperative CTA was available. The primary and secondary endpoints were the 3-year overall survival (OS) and disease-free survival (DFS) rates and the intraoperative course and short-term outcomes, respectively. Results: 431 patients were included in each group after PSM. Compared with the non-CTA group, the CTA group had more harvested lymph nodes and less operative time, blood loss, intraoperative vascular injury and total cost, especially in the subgroup analysis with BMI ≥ 25 kg/m2 patients. There was no difference in the 3 year OS and DFS between the CTA group and the non-CTA group. When further stratified by BMI < 25 or ≥ 25 kg/m2, the 3-year OS and DFS were significantly higher in the CTA group than in the non-CTA group in terms of BMI ≥ 25 kg/m2. Conclusions: Laparoscopic or robotic radical gastrectomy based on preoperative perigastric artery CTA surgical decision-making has the possibility of improving short-term outcomes. However, there is no difference in the long-term prognosis, except for a subgroup of patients with BMI ≥ 25 kg/m2. [ABSTRACT FROM AUTHOR]

Background: This study was performed to evaluate the safety and efficacy of laparoscopic gastrectomy (LG) in patients with locally advanced gastric cancer (LAGC) who received neoadjuvant chemotherapy (NACT). Methods: We retrospectively analyzed patients who underwent gastrectomy for LAGC (cT2-4aN+M0) after NACT from January 2015 to December 2019. The patients were divided into a LG group and an open gastrectomy (OG) group. The short- and long-term outcomes in both groups were examined following propensity score matching. Results: We retrospectively reviewed 288 patients with LAGC who underwent gastrectomy following NACT. Of these 288 patients, 218 were enrolled; after 1:1 propensity score matching, each group comprised 81 patients. The LG group had significantly lower estimated blood loss than the OG group [80 (50–110) vs. 280 (210–320) mL, P < 0.001) but a longer operation time [205 (186.5–222.5) vs. 182 (170–190) min, P < 0.001], a lower postoperative complication rate (24.7% vs. 42.0%, P = 0.002), and a shorter postoperative hospitalization period [8 (7–10) vs. 10 (8–11.5) days, P = 0.001]. Subgroup analysis revealed that patients who underwent laparoscopic distal gastrectomy had a lower rate of postoperative complications than patients in the OG group (18.8% vs. 38.6%, P = 0.034); however, such a pattern was not seen in patients who underwent total gastrectomy (32.3% vs. 45.9%, P = 0.251). The 3-year matched cohort analysis showed no significant difference in overall survival or recurrence-free survival (log-rank P = 0.816 and P = 0.726, respectively) (71.3% and 65.0% in OG vs. 69.1% and 61.7% in LG, respectively). Conclusion: In the short term, LG following NACT is safer and more effective than OG. However, the long-term results are comparable. [ABSTRACT FROM AUTHOR]

Background: Research on short-term outcomes and oncology results after robotic gastrectomy (RG) is still limited, especially from a single surgical team. The purpose of this study was to compare the short-term and long-term outcomes of robotic and laparoscopic gastrectomy (LG). Methods: Between October 2014 and September 2019, 1686 consecutive patients who underwent MIS gastrectomy were enrolled. The patients were divided into RG and LG groups according to surgical type. Groups were matched at a 1:1 ratio using propensity scores based on the following variables: age, sex, ASA score, primary tumor location, histologic type, pathological stage, and neoadjuvant chemotherapy. The primary outcomes were 3-year overall survival (OS) and relapse-free survival (RFS). The secondary outcomes were postoperative short-term outcomes. Results: Demographic and baseline characteristics were similar between the two groups after matching. Compared to the LG group, the RG group had a significantly higher retrieved lymph node (LN) number (32.15 vs 30.82, P = 0.040), more retrieved supra-pancreatic LNs (12.45 vs 11.61, P = 0.028), lower estimated blood loss (73.67 vs 98.08 ml, P < 0.001), but longer operation time (205.18 vs 185.27 min, P < 0.001) and higher hospitalization costs ($13,607 vs $10,928, P < 0.001) in the matched cohort. In the subgroup analysis, we observed that compared with LG, patients with advanced gastric cancer benefitted more from RG surgery. The matched cohort analysis demonstrated no statistically significant differences for 3-year OS or RFS (log-rank, P = 0.648 and P = 0.951, respectively): 80.3% and 77.0% in LG vs. 81.2% and 76.6% in RG, respectively. Conclusion: RG has certain technical advantages over LG, especially in patients with advanced gastric cancer. However, RG does not improve long-term oncology outcomes. [ABSTRACT FROM AUTHOR]