scholarly journals A Novel Model Based on Deep Convolutional Neural Network Improves Diagnostic Accuracy of Intramucosal Gastric Cancer (With Video)

2021 ◽  
Vol 11 ◽  
Author(s):  
Dehua Tang ◽  
Jie Zhou ◽  
Lei Wang ◽  
Muhan Ni ◽  
Min Chen ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Diagnostic Accuracy ◽  
Diagnostic Performance ◽  
Training Dataset ◽  
Deep Convolutional Neural Networks ◽  
Testing Dataset ◽  
Kappa Value ◽  
The Mean ◽  
Gastric Cancer Patients ◽  
Novel Model

Background and AimsPrediction of intramucosal gastric cancer (GC) is a big challenge. It is not clear whether artificial intelligence could assist endoscopists in the diagnosis.MethodsA deep convolutional neural networks (DCNN) model was developed via retrospectively collected 3407 endoscopic images from 666 gastric cancer patients from two Endoscopy Centers (training dataset). The DCNN model’s performance was tested with 228 images from 62 independent patients (testing dataset). The endoscopists evaluated the image and video testing dataset with or without the DCNN model’s assistance, respectively. Endoscopists’ diagnostic performance was compared with or without the DCNN model’s assistance and investigated the effects of assistance using correlations and linear regression analyses.ResultsThe DCNN model discriminated intramucosal GC from advanced GC with an AUC of 0.942 (95% CI, 0.915–0.970), a sensitivity of 90.5% (95% CI, 84.1%–95.4%), and a specificity of 85.3% (95% CI, 77.1%–90.9%) in the testing dataset. The diagnostic performance of novice endoscopists was comparable to those of expert endoscopists with the DCNN model’s assistance (accuracy: 84.6% vs. 85.5%, sensitivity: 85.7% vs. 87.4%, specificity: 83.3% vs. 83.0%). The mean pairwise kappa value of endoscopists was increased significantly with the DCNN model’s assistance (0.430–0.629 vs. 0.660–0.861). The diagnostic duration reduced considerably with the assistance of the DCNN model from 4.35s to 3.01s. The correlation between the perseverance of effort and diagnostic accuracy of endoscopists was diminished using the DCNN model (r: 0.470 vs. 0.076).ConclusionsAn AI-assisted system was established and found useful for novice endoscopists to achieve comparable diagnostic performance with experts.

Clinical features, treatments and survival of HER2 positive gastric cancer with elevated alpha-fetoprotein: An analysis of 16 cases.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e16000-e16000
Author(s):  
Shaohua Ge ◽  
Yi Ba ◽  
Ting Deng ◽  
Yuchong Yang ◽  
Tao Ning ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Cancer Patients ◽  
Immune Checkpoint ◽  
Clinical Characteristics ◽  
Immune Checkpoint Inhibitors ◽  
Checkpoint Inhibitors ◽  
Elevated Serum ◽  
Her2 Positive ◽  
The Mean ◽  
Gastric Cancer Patients

e16000 Background: Gastric cancer with elevated alpha-fetoprotein (AFP) is a special type of gastric cancer with elevated serum AFP. It is often misdiagnosed as primary hepatic cancer due to abnormal AFP and liver metastasis. The AFP level is related to the prognosis of these patients in whom there is prone to high HER2 positive rate. Therefore, anti-HER2 treatment is optional, as well as the emerging immunotherapy with immune checkpoint inhibitors. Methods: Gastric cancer patients with HER2 and serum AFP examination were collected in our hospital from May 2017 till now. Serum AFP level over 7 ng/ml was defined as elevated AFP. The clinical characteristics, treatments and survival of the patients with HER2 positive and elevated AFP were picked and analyzed. Results: Among 135 gastric cancer patients with elevated AFP, 16 (11.9%) were HER-2 positive (12 with HER2 3+, 3 with HER2 2+/FISH+ and 1 with HER2 gene amplification in NGS). The mean serum AFP is 201.4± 476.7ng/ml (range: 7.74 -1335). There were 9 males and 7 females. The mean age was 55 years (range: 38-90). The tumors were located in stomach cardia and fundus in 5 cases, body in 5 cases, antrum in 4 cases, body and antrum in 1 case and whole stomach in 1 case. There were 2 patients in stage III and 14 patients in stage IV with metastasis to lymph node metastasis in 15, liver in 9, abdominal cavity in 3 and peritoneum in 3. As for the treatments, three patients underwent surgery, one of whom with exploratory laparotomy (no antitumor treatment after surgery, died from infection). In 13 advanced patients, 12 patients received systemic antitumor therapies (8 with chemotherapy+Trastuzumab+ immunotherapy, 2 with chemotherapy+Trastuzumab, 1 with chemotherapy+ immunotherapy and 1 with chemotherapy). The chemotherapy regimens were XELOX in 5 cases, SOX in 4 cases and FLOT in 2 cases. The response rate was 50% (6 in 12 patients) and the disease control rate was 100%. The median PFS was 7.5 months in first line therapy with six patients without progression disease yet. The longest PFS with PR lasted for 16.5 months with chemotherapy, trastuzumab and immune checkpoint inhibitor. Conclusions: Gastric cancer with HER2 positive and elevated serum AFP is a disease with special clinical characteristics. Patients with advanced diseases can be treated with chemotherapy, trastuzumab +/- immune checkpoint inhibitors. This combination is expected to become a new regimen to improve survival of such special patients.

scholarly journals Repeated Combined Chemotherapy with Cisplatin Lowers Carnitine Levels in Gastric Cancer Patients

2017 ◽  
Vol 71 (3-4) ◽  
pp. 261-265 ◽  
Author(s):  
Akimasa Kawai ◽  
Hideo  Matsumoto ◽  
Youko Endou ◽  
Yui Honda ◽  
Hisako Kubota ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Organic Cation ◽  
Organic Cation Transporter ◽  
Combined Chemotherapy ◽  
Carnitine Level ◽  
Upper Gastrointestinal Cancer ◽  
The Mean ◽  
Total Carnitine ◽  
Gastric Cancer Patients ◽  
Upper Gastrointestinal

Background/Aims: Carnitine plays an important role in the metabolism of fatty acids. It has also been reported that the administration of anticancer drugs may lead to reductions in serum carnitine levels due to decreased activity of organic cation transporter novel 2, which plays a role in the reabsorption of carnitine in the tubules of the kidney. We therefore studied the change in carnitine levels when chemotherapy was administered repeatedly to patients with gastric cancer. Methods: Ten patients with upper gastrointestinal cancer were enrolled in this study between December 2014 and August 2015. All patients were administered chemotherapy consisting of TS-1 and cisplatin every 3 weeks: 3 received it as adjuvant therapy post resection, the remaining 7 received it as treatment for unresectable tumors. Before the start of each chemotherapy cycle, serum was collected. Results: The mean total carnitine level was 54.5 ± 13.7 μmol/L prior to commencing chemotherapy; it was 46.7 ± 13.5 and 41.4 ± 14.8 μmol/L at the second and third cycles respectively. The total carnitine level was decreased in a statistically significant manner (p = 0.0039). The serum level of total protein and cholinesterase was also decreased significantly (p = 0.0218 and p = 0.0418). Conclusion: Carnitine levels decreased during repeated chemotherapy in patients with gastric cancer, and they are associated with the nutritional status.

scholarly journals Development of U-Net Breast Density Segmentation Method for Fat-Sat MR Images Using Transfer Learning Based on Non-Fat-Sat Model

2021 ◽  
Author(s):  
Yang Zhang ◽  
Siwa Chan ◽  
Jeon-Hor Chen ◽  
Kai-Ting Chang ◽  
Chin-Yao Lin ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Breast Tissue ◽  
Ground Truth ◽  
Training Dataset ◽  
Breast Volume ◽  
Segmentation Method ◽  
Tissue Segmentation ◽  
Testing Dataset ◽  
The Mean

AbstractTo develop a U-net deep learning method for breast tissue segmentation on fat-sat T1-weighted (T1W) MRI using transfer learning (TL) from a model developed for non-fat-sat images. The training dataset (N = 126) was imaged on a 1.5 T MR scanner, and the independent testing dataset (N = 40) was imaged on a 3 T scanner, both using fat-sat T1W pulse sequence. Pre-contrast images acquired in the dynamic-contrast-enhanced (DCE) MRI sequence were used for analysis. All patients had unilateral cancer, and the segmentation was performed using the contralateral normal breast. The ground truth of breast and fibroglandular tissue (FGT) segmentation was generated using a template-based segmentation method with a clustering algorithm. The deep learning segmentation was performed using U-net models trained with and without TL, by using initial values of trainable parameters taken from the previous model for non-fat-sat images. The ground truth of each case was used to evaluate the segmentation performance of the U-net models by calculating the dice similarity coefficient (DSC) and the overall accuracy based on all pixels. Pearson’s correlation was used to evaluate the correlation of breast volume and FGT volume between the U-net prediction output and the ground truth. In the training dataset, the evaluation was performed using tenfold cross-validation, and the mean DSC with and without TL was 0.97 vs. 0.95 for breast and 0.86 vs. 0.80 for FGT. When the final model developed with and without TL from the training dataset was applied to the testing dataset, the mean DSC was 0.89 vs. 0.83 for breast and 0.81 vs. 0.81 for FGT, respectively. Application of TL not only improved the DSC, but also decreased the required training case number. Lastly, there was a high correlation (R2 > 0.90) for both the training and testing datasets between the U-net prediction output and ground truth for breast volume and FGT volume. U-net can be applied to perform breast tissue segmentation on fat-sat images, and TL is an efficient strategy to develop a specific model for each different dataset.

scholarly journals Diagnostic Performance of Artificial Intelligence-Centred Systems in the Diagnosis and Postoperative Surveillance of Upper Gastrointestinal Malignancies Using Computed Tomography Imaging: A Systematic Review and Meta-Analysis of Diagnostic Accuracy

2021 ◽  
Author(s):  
Swathikan Chidambaram ◽  
Viknesh Sounderajah ◽  
Nick Maynard ◽  
Sheraz R. Markar
Keyword(s):  
Artificial Intelligence ◽  
Gastric Cancer ◽  
Systematic Review ◽  
Esophageal Cancer ◽  
Diagnostic Accuracy ◽  
Diagnostic Performance ◽  
Meta Analysis ◽  
Diagnostic Methods ◽  
Gastrointestinal Malignancies ◽  
Upper Gastrointestinal

Abstract Background Upper gastrointestinal cancers are aggressive malignancies with poor prognosis, even following multimodality therapy. As such, they require timely and accurate diagnostic and surveillance strategies; however, such radiological workflows necessitate considerable expertise and resource to maintain. In order to lessen the workload upon already stretched health systems, there has been increasing focus on the development and use of artificial intelligence (AI)-centred diagnostic systems. This systematic review summarizes the clinical applicability and diagnostic performance of AI-centred systems in the diagnosis and surveillance of esophagogastric cancers. Methods A systematic review was performed using the MEDLINE, EMBASE, Cochrane Review, and Scopus databases. Articles on the use of AI and radiomics for the diagnosis and surveillance of patients with esophageal cancer were evaluated, and quality assessment of studies was performed using the QUADAS-2 tool. A meta-analysis was performed to assess the diagnostic accuracy of sequencing methodologies. Results Thirty-six studies that described the use of AI were included in the qualitative synthesis and six studies involving 1352 patients were included in the quantitative analysis. Of these six studies, four studies assessed the utility of AI in gastric cancer diagnosis, one study assessed its utility for diagnosing esophageal cancer, and one study assessed its utility for surveillance. The pooled sensitivity and specificity were 73.4% (64.6–80.7) and 89.7% (82.7–94.1), respectively. Conclusions AI systems have shown promise in diagnosing and monitoring esophageal and gastric cancer, particularly when combined with existing diagnostic methods. Further work is needed to further develop systems of greater accuracy and greater consideration of the clinical workflows that they aim to integrate within.

scholarly journals Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Kaori Ishii ◽  
Ryo Asaoka ◽  
Takashi Omoto ◽  
Shingo Mitaki ◽  
Yuri Fujino ◽  
...  
Keyword(s):  
Deep Learning ◽  
Intraocular Pressure ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Fundus Photography ◽  
Training Dataset ◽  
Support Vector ◽  
Testing Dataset ◽  
The Mean ◽  
Systemic Variables

AbstractThe purpose of the current study was to predict intraocular pressure (IOP) using color fundus photography with a deep learning (DL) model, or, systemic variables with a multivariate linear regression model (MLM), along with least absolute shrinkage and selection operator regression (LASSO), support vector machine (SVM), and Random Forest: (RF). Training dataset included 3883 examinations from 3883 eyes of 1945 subjects and testing dataset 289 examinations from 289 eyes from 146 subjects. With the training dataset, MLM was constructed to predict IOP using 35 systemic variables and 25 blood measurements. A DL model was developed to predict IOP from color fundus photographs. The prediction accuracy of each model was evaluated through the absolute error and the marginal R-squared (mR2), using the testing dataset. The mean absolute error with MLM was 2.29 mmHg, which was significantly smaller than that with DL (2.70 dB). The mR2 with MLM was 0.15, whereas that with DL was 0.0066. The mean absolute error (between 2.24 and 2.30 mmHg) and mR2 (between 0.11 and 0.15) with LASSO, SVM and RF were similar to or poorer than MLM. A DL model to predict IOP using color fundus photography proved far less accurate than MLM using systemic variables.

scholarly journals Mast Cells Positive to Tryptase and c-Kit Receptor Expressing Cells Correlates with Angiogenesis in Gastric Cancer Patients Surgically Treated

2013 ◽  
Vol 2013 ◽  
pp. 1-5 ◽  
Author(s):  
Michele Ammendola ◽  
Rosario Sacco ◽  
Giuseppe Sammarco ◽  
Giuseppe Donato ◽  
Valeria Zuccalà ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Mast Cells ◽  
Cancer Patients ◽  
Tumour Tissue ◽  
7Th Edition ◽  
Complex Process ◽  
Kit Receptor ◽  
The Mean ◽  
Gastric Cancer Patients ◽  
Tryptase Inhibitors

Background. Angiogenesis is a complex process involved in both growth and progression of several human and animal tumours. Tryptase is a serin protease stored in mast cells granules, which plays a role in tumour angiogenesis. Mast cells (MCs) can release tryptase following c-Kit receptor (c-KitR) activation.Method. In a series of 25 gastric cancer patients with stage T3N2-3M0(by AJCC for Gastric Cancer 7th Edition), immunohistochemistry and image analysis methods were employed to evaluate in the tumour tissue the correlation between the number of mast cells positive to tryptase (MCPT), c-KitR expressing cells (c-KitR-EC), and microvascular density (MVD).Results. Data demonstrated a positive correlation between MCPT, c-KitR-EC, and MVD to each other. In tumour tissue the mean number of MCPT was 15, the mean number of c-KitR-EC was 20, and the mean number of MVD was 20. The Pearson test correlating MCPT and MVD, c-KitR-EC and MVD was significantly (r=0.64,P=0.001;r=0.66,P=0.041, resp.).Conclusion. In this pilot study, we suggest that MCPT and c-KitR-EC play a role in gastric cancer angiogenesis, so we think that several c-KitR or tryptase inhibitors such as gabexate mesilate and nafamostat mesilate might be evaluated in clinical trials as a new antiangiogenetic approach.

Chemotherapy (CT) treatment patterns and neutropenia management in gastric cancer patients (pts) receiving myelosuppressive chemotherapy in Europe.

2013 ◽  
Vol 31 (4_suppl) ◽  
pp. 128-128
Author(s):  
Ewa Kalinka-Warzocha ◽  
Javier Gallego Plazas ◽  
Laurent Mineur ◽  
Tomas Salek ◽  
Alain Hendlisz ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
High Risk ◽  
Risk Estimation ◽  
Primary Prophylaxis ◽  
Myelosuppressive Chemotherapy ◽  
Chemotherapy Administration ◽  
Treatment Naïve ◽  
Drug Regimens ◽  
The Mean ◽  
Gastric Cancer Patients

128 Background: Granulocyte-colony stimulating factor (G-CSF) primary prophylaxis (PP) is recommended for pts undergoing CT who are at overall high risk for febrile neutropenia (FN). No single CT regimen is recognized as standard in gastric cancer and few regimens are represented in G-CSF guidelines. We therefore evaluated neutropenia management in pts receiving CT for gastric cancer. Methods: This was a multicentre prospective observational study that enrolled pts sequentially from 11/2009 to 06/2011. Adult gastric cancer pts (any stage) with ≥3 cycles of myelosuppressive CT scheduled and an investigator-assessed overall FN risk ≥20% were eligible. The primary outcome was the proportion of pts who received PP G-CSF (G-CSF in days 1-7 of cycle 1). Secondary outcomes included FN incidence, chemotherapy administration, and G-CSF use. Posthoc analyses investigated the subgroup who received DCF, including modifications from standard DCF (Van Cutsem. JCO. 2006), and the G-CSF support given up to the first FN (G-CSF prophylaxis given per label in each cycle up to that in which FN occurred). Results: Of 209 pts enrolled, 199 were eligible and their data analyzed. The mean (±SD) age was 62 (±12) years, 76% were male, 17% were ECOG 2 and none ECOG 3-4; 47% were treatment naïve. Planned CT was palliative in 74% of pts; overall, 27 different backbone regimens were planned (10 triplet, 12 doublet, 5 single drug regimens). The most common regimen used was DCF (54 pts, 27%), predominantly given as modified DCF (41 pts). Despite being assessed as high risk for FN, G-CSF PP was administered to only 35% of pts overall (n=70; 54 pegfilgrastim, 16 daily G-CSF) and to 69% of pts who received DCF. FN occurred in 14 pts (10%), 9 of whom received DCF. A large majority of FN pts (12/14, 86%) had not received prophylactic G-CSF per label up to the first FN occurrence; furthermore, 86% of FN pts did not receive G-CSF prophylaxis in the cycle following the FN event. Conclusions: The variety of CT used, frequent modifications to standard CT, and presence of pt risk factors makes FN risk estimation difficult in gastric cancer. Improved risk assessment and appropriate targeting of G-CSF PP to high risk pts is needed.

scholarly journals Additive Effects of Evaluating Micro-Surface and Microvascular Patterns Using Magnifying Endoscopy with Narrow-Band Imaging for Gastric Cancer

2021 ◽  
Author(s):  
Yusuke Horiuchi ◽  
Toshiaki Hirasawa ◽  
Naoki Ishizuka ◽  
Junki Tokura ◽  
Mitsuaki Ishioka ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Diagnostic Accuracy ◽  
Diagnostic Performance ◽  
Evaluation Method ◽  
Narrow Band ◽  
Narrow Band Imaging ◽  
Magnifying Endoscopy ◽  
Additive Effects ◽  
Surface Patterns ◽  
Microvascular Pattern

Abstract No studies have compared the performance of microvascular and micro-surface patterns alone with their combination in magnifying endoscopy with narrow-band imaging for diagnosing gastric cancer. This study aimed to clarify the difference in diagnostic performance between these methods. Thirty-three participating endoscopists underwent specialized training in magnifying endoscopy evaluated microvascular and micro-surface patterns for images of 106 cancerous and 106 non-cancerous cases. If classified as “irregular”, the lesion was diagnosed as cancerous. To evaluate diagnostic performance, we compared the diagnostic accuracy, sensitivity, and specificity among the methods. Performance-related items did not significantly differ between the microvascular and micro-surface patterns. However, the diagnostic accuracy and sensitivity were significantly higher when using the combination of these methods than when using the microvascular pattern alone (percentage [95% confidence interval]: 82.1% [76.4–86.7] vs. 76.4% [70.3–81.6], P = 0.0005; and 69.8% [60.5–77.8] vs. 63.2% [53.7–71.8], P = 0.0082, respectively). The additive effects on diagnostic accuracy and sensitivity were 5.7% and 6.6%, respectively. The combination of micro-surface and microvascular patterns has superior diagnostic accuracy and sensitivity for diagnosing gastric cancer than the evaluation method using microvascular pattern alone. Our results may contribute to improving the diagnosis of gastric cancers.

scholarly journals AN ANALYTICAL STUDY TO ASSESS AND COMPARE OUTCOME OF CLIPPING VERSUS SUTURE LIGATION OF THE CYSTIC DUCT IN LAPAROSCOPIC CHOLECYSTECTOMY

2021 ◽  
Vol 5 (8) ◽  
Author(s):  
Lakhami Chand Sinsinwar ◽  
Rajvala Choudhary ◽  
Sanjeev Singh Choudhary ◽  
Jeevan Kankaria
Keyword(s):  
Gastric Cancer ◽  
Cancer Patients ◽  
Total Gastrectomy ◽  
Laparoscopic Total Gastrectomy ◽  
Oral Feeding ◽  
Feeding Time ◽  
Early Oral Feeding ◽  
The Mean ◽  
Gastric Cancer Patients

Background: The early oral feeding after the laparoscopic total gastrectomy contributes to the enhanced treatment efficiency and improved quality of life of gastric cancer patients. To evaluate the efficiency of early oral feeding after laparoscopic total gastrectomy in gastric cancer patients at the Nghe An General Friendship Hospital. Methods: A retrospective observational study, performed in patients who underwent laparoscopic total gastrectomy from 2014 to 2020. Results: 126 patients were recruited. The mean age was 60.6 ± 11.1 years. The male/female ratio was 2.8/1. 15.9% of patients had the tumor at the one-third upper stomach, 81.7% at the middle of the stomach. 70.6% of patients contracted adenocarcinoma and ductal carcinoma, 24.6% of patients had ring cell carcinoma. The percent of tumor at stages I, II, III were respectively 19.0%, 49.2%, 31.7%. There were 71.4% of cases underwent laparoscopic total gastrectomy and were made the anastomosis by linear staplers. No case presented complications relating to the anastomosis after the surgery. The mean oral feeding time was 4.4 ± 1.9 (2 – 8 days), 27.8% of cases started at the second postoperative date, 8.7% of cases at the third postoperative date, 29.4% of cases from the fourth and fifth date, and 34.1% of cases started from the sixth date and further. The later the oral feeding time was, the slower recovery of the peristalsis was and vice versa (p < 0.05). There was no difference between the feeding time and the complications (p > 0.05). The more early the feeding time was, the shorter duration of antibiotic therapy observed and vice versa (p < 0.05). The more early the feeding time was, the short duration of hospital stay was and vice versa (p < 0.05). Conclusions: The early oral feeding after laparoscopic total gastrectomy was safe and contributed to improving the efficiency of the treatment, the quality of life in gastric cancer patients. Keywords: Early oral feeding, gastric cancer.

Sign in / Sign up

Export Citation Format

Share Document