Detecting pill defection remains challenging, despite recent extensive studies, because of the lack of defective data. In this paper, we propose a pipeline composed of a pill detection module and an autoencoder-based defect detection module to detect defective pills in pill packages. Furthermore, we created a new dataset to test our model. The pill detection module segments pills in an aluminumplastic package into individual pills. To segment pills, we used a shallow segmentation network that is then divided into individual pills using the watershed algorithm. The defect detection module identifies defects in individual pills. It is trained only on the normal data. Thus, it is expected that the module will be unable to reconstruct defective data correctly. However, in reality, the conventional autoencoder reconstructs defective data better than expected, even if the network is trained only on normal data. Hence, we introduce a patch division method to prevent this problem. The patch division involves dividing the output of the convolutional encoder network into patch-wise features, and then applying path-wise encoder layer. In this process, each latent patch has its independent weight and bias. This can be interpreted as reconstructing the input image using multiple local autoencoders. The patch division makes the network concentrate only on reconstructing local regions, thereby reducing the overall capacity. This prohibits the proposed network reconstructing unseen data well. Experiments show that the proposed patch division technique indeed improves the defect detection performance and outperforms existing deep learning based anomaly detection methods. The ablation study shows the efficacy of patch division and compression following the concatenation of patch-wise features.
Pancreatic carcinosarcoma is a very rare malignancy with a poor prognosis. Because of these characteristics, a treatment strategy for it has not been established yet. The aim of this study was to establish a therapeutic strategy for pancreatic carcinosarcoma. We reviewed data of a 65-year-old female patient who was diagnosed with pancreatic carcinosarcoma through endoscopic ultrasound-guided fine needle aspiration biopsy before surgery. For literature review, we searched PubMed using terms of "Pancreatic" or "Pancreas" and "carcinosarcoma" or "carcinosarcomatous". The patient received 11 cycles of neoadjuvant treatment with leucovorin, fluorouracil, irinotecan, oxaliplatin and pembrolizumab because the tumor was borderline resectable. She underwent stereotactic ablative body radiotherapy (SABR) with 35 Gy in 5 fractions, followed by robotic pylorus-preserving pancreaticoduodenectomy. After surgery, the patient received adjuvant chemotherapy in the same regimen as before surgery. She is alive without any recurrence. Among 48 patients within 33 available papers, the median survival time was 15 months. The survival rate of patients who received adjuvant chemotherapy tended to be higher than that of those who did not receive adjuvant chemotherapy, although the difference was not statistically significant (median survival, 47 vs. 15 months; p = 0.485). Three patients who received neoadjuvant chemotherapy had a survival period of 13-23.5 months. Surgery with lymphadenectomy, adjuvant therapy, and neoadjuvant therapy are thought to help improve survival outcomes. Modern treatment approaches for conventional pancreatic ductal adenocarcinoma could be applied to pancreatic carcinosarcoma.
Purpose Postoperative pancreatic fistula (POPF) is the most troublesome complication after pancreaticojejunostomy (PJ). This study aimed to compare the short-term outcomes of 2 different methods of duct-to-mucosa PJ; out-layer continuous suture anastomosis (OCA) and the modified Blumgart method (mBM). Methods This retrospective cohort study enrolled patients who underwent curative-intent, open PD between 2015 and 2020. In mBM, 2 transpancreatic U-sutures were performed between the pancreatic margin and jejunum, with reinforced sutures in the central region. Patient demographics, diagnosis, intraoperative factors, postoperative complications, and POPF defined by the International Study Group on Pancreatic Fistula were investigated. Clinically relevant POPF (CR-POPF) included grades B and C POPF. Results A total of 184 patients underwent OCA, and 96 patients underwent mBM. The mBM group had more patients who underwent neoadjuvant therapy. The fistula risk scores were comparable between the 2 groups. Both groups showed no significant differences in CR-POPF and overall surgical complication rates. The total operation time was comparable, although the operation time for PJ was shorter in mBM. Conclusion No significant differences were observed in the postoperative outcomes between each group; the operation time for PJ in mBM was shorter. Therefore, mBM may be considered for utilization in duct-to-mucosa PJ.
Background: Carbohydrate antigen 19-9 (CA 19-9) is a representative tumor marker used for the diagnosis of pancreatic and biliary tract cancers. There are few published research results that can be applied to actual clinical practice for ampullary cancer (AC) alone. This study aimed to demonstrate the relationship between the prognosis of AC and the level of CA 19-9, and to determine the optimal thresholds. Methods: Patients who underwent curative resection (pancreaticoduodenectomy (PD) or pylorus preserving pancreaticoduodenectomy (PPPD)) for AC at the Seoul National University Hospital between January 2000 and December 2017 were enrolled. To determine the optimal cutoff values that could clearly stratify the survival outcome, the conditional inference tree (C-tree) method was used. After obtaining the optimal cutoff values, they were compared to the upper normal clinical limit of 36 U/mL for CA 19-9. Results In total, 385 patients were enrolled in this study. The median value of the tumor marker CA 19-9 was 18.6 U/mL. Using the C-tree method, 46 U/mL was determined to be the optimal cutoff value for CA 19-9. Histological differentiation, N stage, and adjuvant chemotherapy were significant predictors. CA 19-9 36 U/mL had marginal significance as a prognostic factor. In contrast, the new cutoff value, CA 19-9 46 U/mL, was found to be a statistically significant prognostic factor (HR: 1.37, p = 0.048). Conclusions: The new cutoff value of CA 19-9 46 U/mL may be used for evaluating the prognosis of AC. Therefore, it may be an effective indicator for determining treatment strategies such as surgical treatments and adjuvant chemotherapy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.