The application of artificial neural network algorithm in pathological diagnosis of gastrointestinal malignant tumors has become a research hotspot. In the previous studies, the algorithm research mainly focused on the model development based on convolutional neural networks, while only a few studies used the combination of convolutional neural networks and recurrent neural networks. The research contents included classical histopathological diagnosis and molecular typing of malignant tumors, and the prediction of patient prognosis by utilizing artificial neural networks. This article reviews the research progress on artificial neural network algorithm in the pathological diagnosis and prognosis prediction of digestive tract malignant tumors.
Humans ; Neural Networks, Computer ; Algorithms ; Prognosis ; Gastrointestinal Neoplasms/diagnosis*

Objective: To analyze the clinicopathological characteristics and prognosis of patients with small bowel tumors. Methods: This was a retrospective, observational study. We collected clinicopathological data of patients with primary jejunal or ileal tumors who had undergone small bowel resection in the Department of Gastrointestinal Surgery, West China Hospital, Sichuan University between January 2012 and September 2017. The inclusion criteria included: (1) older than 18 years; (2) had undergone small bowel resection; (3) primary location at jejunum or ileum; (4) postoperative pathological examination confirmed malignancy or malignant potential; and (5) complete clinicopathological and follow-up data. Patients with a history of previous or other concomitant malignancies and those who had undergone exploratory laparotomy with biopsy but no resection were excluded. The clinicopathological characteristics and prognoses of included patients were analyzed. Results: The study cohort comprised 220 patients with small bowel tumors, 136 of which were classified as gastrointestinal stromal tumors (GISTs), 47 as adenocarcinomas, and 35 as lymphomas. The median follow-up for all patient was 81.0 months (75.9-86.1). GISTs frequently manifested as gastrointestinal bleeding (61.0%, 83/136) and abdominal pain (38.2%, 52/136). In the patients with GISTs, the rates of lymph node and distant metastasis were 0.7% (1/136) and 11.8% (16/136), respectively. The median follow-up time was 81.0 (75.9-86.1) months. The 3-year overall survival (OS) rate was 96.3%. Multivariate Cox regression-analysis results showed that distant metastasis was the only factor associated with OS of patients with GISTs (HR=23.639, 95% CI: 4.564-122.430, P<0.001). The main clinical manifestations of small bowel adenocarcinoma were abdominal pain (85.1%, 40/47), constipation/diarrhea (61.7%, 29/47), and weight loss (61.7%, 29/47). Rates of lymph node and distant metastasis in patients with small bowel adenocarcinoma were 53.2% (25/47) and 23.4% (11/47), respectively. The 3-year OS rate of patients with small bowel adenocarcinoma was 44.7%. Multivariate Cox regression-analysis results showed that distant metastasis (HR=4.018, 95%CI: 2.108-10.331, P<0.001) and adjuvant chemotherapy (HR=0.291, 95% CI: 0.140-0.609, P=0.001) were independently associated with OS of patients with small bowel adenocarcinoma. Small bowel lymphoma frequently manifested as abdominal pain (68.6%, 24/35) and constipation/diarrhea (31.4%, 11/35); 77.1% (27/35) of small bowel lymphomas were of B-cell origin. The 3-year OS rate of patients with small bowel lymphomas was 60.0%. T/NK cell lymphomas (HR= 6.598, 95% CI: 2.172-20.041, P<0.001) and adjuvant chemotherapy (HR=0.119, 95% CI: 0.015-0.925, P=0.042) were independently associated with OS of patients with small bowel lymphoma. Small bowel GISTs have a better prognosis than small intestinal adenocarcinomas (P<0.001) or lymphomas (P<0.001), and small bowel lymphomas have a better prognosis than small bowel adenocarcinomas (P=0.035). Conclusions: The clinical manifestations of small intestinal tumor are non-specific. Small bowel GISTs are relatively indolent and have a good prognosis, whereas adenocarcinomas and lymphomas (especially T/NK-cell lymphomas) are highly malignant and have a poor prognosis. Adjuvant chemotherapy would likely improve the prognosis of patients with small bowel adenocarcinomas or lymphomas.
Humans ; Prognosis ; Intestinal Neoplasms/diagnosis* ; Duodenal Neoplasms ; Gastrointestinal Stromal Tumors ; Lymphoma ; Adenocarcinoma/surgery* ; Constipation ; Abdominal Pain ; Retrospective Studies

Humans ; Dendritic Cell Sarcoma, Follicular/diagnosis* ; Granuloma, Plasma Cell/diagnosis* ; Biopsy, Needle ; Gastrointestinal Neoplasms ; Hepatitis

Asian Continental Ancestry Group ; Consensus ; Gastrointestinal Neoplasms/diagnosis* ; Gastrointestinal Tract ; Humans ; Neuroendocrine Tumors/diagnosis* ; Pancreatic Neoplasms/diagnosis*

Due to the lack of typical symptoms and imaging findings, gastric gastrointestinal stromal tumor (GIST) is easy to be misdiagnosed as other gastric tumors clinically. In clinical practice, clinicians should adopt the multidisciplinary team model, fully understand the characteristics of gastric GIST, grasp the key points of its differential diagnosis from other gastric tumors to achieve precise diagnosis and treatment. This paper analyzes the causes of misdiagnosis and elucidates the differential diagnosis of gastric GIST, aiming to improve the accuracy of preoperative diagnosis, reduce the misdiagnosis, and improve treatment outcomes.
Diagnosis, Differential ; Diagnostic Errors ; Gastrointestinal Stromal Tumors/diagnosis* ; Humans ; Stomach Neoplasms/diagnosis* ; Treatment Outcome

Objective: Contrast-enhanced CT is an important method of preoperative diagnosis and evaluation for the malignant potential of gastric submucosal tumor (SMT). It has a high diagnostic accuracy rate in differentiating gastric gastrointestinal stromal tumor (GIST) with a diameter greater than 5 cm from gastric benign SMT. This study aimed to use deep learning algorithms to establish a diagnosis model (GISTNet) based on contrast-enhanced CT and evaluate its diagnostic value in distinguishing gastric GIST with a diameter ≤ 5 cm and other gastric SMT before surgery. Methods: A diagnostic test study was carried out. Clinicopathological data of 181 patients undergoing resection with postoperative pathological diagnosis of gastric SMT with a diameter ≤ 5 cm at Department of Gastrointestinal Surgery of Renji Hospital from September 2016 to April 2021 were retrospectively collected. After excluding 13 patients without preoperative CT or with poor CT imaging quality, a total of 168 patients were enrolled in this study, of whom, 107 were GIST while 61 were benign SMT (non-GIST), including 27 leiomyomas, 24 schwannomas, 6 heterotopic pancreas and 4 lipomas. Inclusion criteria were as follows: (1) gastric SMT was diagnosed by contrast-enhanced CT before surgery; (2) preoperative gastroscopic examination and biopsy showed no abnormal cells; (3) complete clinical and pathological data. Exclusion criteria were as follows: (1) patients received anti-tumor therapy before surgery; (2) without preoperative CT or with poor CT imaging quality due to any reason; (3) except GIST, other gastric malignant tumors were pathologically diagnosed after surgery. Based on the hold-out method, 148 patients were randomly selected as the training set and 20 patients as the test set of the GISTNet diagnosis model. After the GISTNet model was established, 5 indicators were used for evaluation in the test set, including sensitivity, specificity, positive predictive value, negative predictive value and the area under the receiver operating curve (AUC). Then GISTNet diagnosis model was compared with the GIST-risk scoring model based on traditional CT features. Besides, in order to compare the accuracy of the GISTNet diagnosis model and the imaging doctors in the diagnosis of gastric SMT imaging, 3 radiologists with 3, 9 and 19 years of work experience, respectively, blinded to clinical and pathological information, tested and judged the samples. The accuracy rate between the three doctors and the GISTNet model was compared. Results: The GISTNet model yielded an AUC of 0.900 (95% CI: 0.827-0.973) in the test set. When the threshold value was 0.345, the sensitivity specificity, positive and negative predictive values of the GISTNet diagnosis model was 100%, 67%, 75% and 100%, respectively. The accuracy rate of the GISTNet diagnosis model was better than that of the GIST-risk model and the manual readings from two radiologists with 3 years and 9 years of work experience (83% vs. 75%, 60%, 65%), and was close to the manual reading of the radiologist with 19 years of work experience (83% vs. 80%). Conclusion: The deep learning algorithm based on contrast-enhanced CT has favorable and reliable diagnostic accuracy in distinguishing gastric GIST with a diameter ≤ 5 cm and other gastric SMT before operation.
Deep Learning ; Diagnosis, Differential ; Gastrointestinal Stromal Tumors/diagnostic imaging* ; Humans ; Retrospective Studies ; Stomach Neoplasms/diagnostic imaging* ; Tomography, X-Ray Computed

gastrointestinal cancer as work-related disease during their evaluation. However, in 2018 OSHRI recognized gastric and rectal cancers as work-related disease in asbestos-exposed workers. We present 2 such cases along supportive evidence of causation.CASE PRESENTATION: Patient A: A 57-year-old man had worked for about 40 years since 1978 as an oxygen cutter at workplaces that dismantle ships, buildings, boilers, and thermal power plants. In November 2016, endoscopy and biopsy confirmed the diagnosis of advanced gastric cancer, for which he underwent subtotal gastrectomy and chemotherapy; however, he later died of the cancer. Patient B: A 71-year-old man had worked in shipbuilding and repair workplaces for approximately 49 years, being employed in pipe laying, asbestos insulation installation, grinding, and other ship repair work. In 2003, he was diagnosed of rectal cancer by abdominal computed tomography. He accordingly underwent surgical removal of the cancer. Based on the occupational history of the 2 patients and our review of the relevant literature addressing the occupational environment, we concluded that both patients had continuous exposure to high levels of asbestos while performing their jobs for 40 and 49 years, respectively.CONCLUSION: Both patients had a history of smoking and drinking (non-occupational personal risk factors). However, the possibility of an increased risk of gastric and rectal cancers from asbestos exposure cannot be excluded. Therefore, we considered that occupational exposure to asbestos had contributed to the cancer diagnosis in these cases. Workers exposed to asbestos should be made aware of the possibility of gastric or rectal cancer, and should undergo monitoring and medical examinations. Appropriate compensation for gastric and rectal cancers that occur in workers exposed to asbestos are anticipated in future.]]>
Academies and Institutes ; Aged ; Asbestos ; Biopsy ; Compensation and Redress ; Diagnosis ; Drinking ; Drug Therapy ; Endoscopy ; Gastrectomy ; Gastrointestinal Neoplasms ; Humans ; Korea ; Middle Aged ; Occupational Exposure ; Occupational Health ; Oxygen ; Power Plants ; Rectal Neoplasms ; Ships ; Smoke ; Smoking ; Stomach Neoplasms

Obesity is associated with various comorbidities, such as type II diabetes, hypertension, dyslipidemia, and cardiovascular disease. Gastrointestinal complications are also frequent and obesity is a direct cause of nonalcoholic fatty liver disease, and are risk factors for gastroesophageal reflux disease, pancreatitis, gallstone disease, diarrhea, dyssynergic defection, and various gastrointestinal cancers. Diagnosis is usually made by measuring body mass index (BMI). Although BMI is correlated with body fat mass, it may overestimate subjects with high muscle mass and underestimate subjects with low muscle mass. Co-measurement of waist circumference as a reflection of abdominal obesity for subjects with BMIs ranging from 25 to 35 kg/m2 has been recommended; however, it is still an anthropometric diagnosis that does not clearly discriminate subjects at risk for developing comorbidities. Biomarkers reflect the underlying biological mechanisms of obesity and can be used to characterize the obesity phenotype (i.e., at high risk for disease development) as well as a target for disease-causing factors. In this article, we describe the conventional diagnosis, biomarkers of obesity, and current challenges.
Adipose Tissue ; Biomarkers ; Body Mass Index ; Cardiovascular Diseases ; Comorbidity ; Diagnosis ; Diarrhea ; Dyslipidemias ; Gallstones ; Gastroesophageal Reflux ; Gastrointestinal Diseases ; Gastrointestinal Neoplasms ; Hypertension ; Non-alcoholic Fatty Liver Disease ; Obesity ; Obesity, Abdominal ; Pancreatitis ; Phenotype ; Risk Factors ; Waist Circumference

The incidence of gastric mucosa-associated lymphoid tissue (MALT) lymphoma is increasing worldwide, but the diagnosis is difficult. Most patients are asymptomatic or complain of nonspecific gastrointestinal symptoms. As the endoscopic features of gastric MALT lymphoma are variable and nonspecific, the possibility of this condition may be overlooked during esophagogastroduodenoscopy, and it remain undiagnosed. Therefore, this condition needs to be considered when an abnormal mucosa is observed during this procedure. Biopsy performed during endoscopy is the primary diagnostic test, but false negative results are possible; large numbers of samples should be collected from both normal and abnormal mucosae. Endoscopic ultrasonography is useful to assess the depth of invasion and to predict the treatment response. After treatment, follow-up tests are required every 3 months until complete remission is achieved, and annually thereafter. Early diagnosis of gastric MALT lymphoma is difficult, and its diagnosis and follow-up require wide experience and competent endoscopic technique.
Biopsy ; Diagnosis ; Diagnostic Tests, Routine ; Early Diagnosis ; Endoscopy ; Endoscopy, Digestive System ; Endoscopy, Gastrointestinal ; Endosonography ; Follow-Up Studies ; Humans ; Incidence ; Lymphoid Tissue ; Lymphoma ; Lymphoma, B-Cell, Marginal Zone ; Mucous Membrane ; Stomach Neoplasms

Gastric schwannoma, a rare mesenchymal tumor originating from the schwann cells of peripheral nerves, rarely occurs in the gastrointestinal tract. It accounts for only 0.2% of all gastric tumors and 2~6% of gastric mesenchymal tumors. Gastric schwannoma is observed as a subepithelial tumor on endoscopy; it is covered with normal mucosa, rendering its preoperative differential diagnosis difficult. An asymptomatic 43-year-old woman visited our hospital after a 7-cm ulcerofungating mass was detected in the lesser curvature of the gastric body on gastroscopy. Abdominal CT revealed multiple enlarged lymph nodes, and ¹⁸F-fluorodeoxyglucose (FDG) PET demonstrated a subtle uptake of FDG, suggestive of advanced gastric cancer. After three failed attempts of endoscopic biopsy, the patient underwent total gastrectomy with lymphadenectomy and was subsequently diagnosed with gastric schwannoma. Herein, we report this case with a literature review.
Adult ; Biopsy ; Diagnosis, Differential ; Endoscopy ; Female ; Gastrectomy ; Gastrointestinal Tract ; Gastroscopy ; Humans ; Lymph Node Excision ; Lymph Nodes ; Mucous Membrane ; Neurilemmoma ; Peripheral Nerves ; Schwann Cells ; Stomach Neoplasms ; Tomography, X-Ray Computed