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

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

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

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

BACKGROUND/AIMS: Chronic atrophic gastritis (CAG) and metaplastic gastritis (MG) are precancerous conditions of Helicobacter pylori (H. pylori)-related gastric cancer. This study aimed to identify the characteristics of nodular gastritis (NG) showing CAG or MG after nodule regression. METHODS: H. pylori-infected patients with NG were included after upper gastrointestinal endoscopy. Patients were excluded if their latest endoscopy had been performed ≤36 months after the initial diagnosis of NG. Small-granular-type NG was defined as the condition with 1–2 mm regular subepithelial nodules. Large-nodular-type NG was defined as those with 3–4 mm, irregular subepithelial nodules. The endoscopic findings after nodule regression were recorded. RESULTS: Among the 97 H. pylori-infected patients with NG, 61 showed nodule regression after a mean follow-up of 73.0±22.0 months. After nodule regression, 16 patients showed a salt-and-pepper appearance and/or transparent submucosal vessels, indicating CAG. Twenty-nine patients showed diffuse irregular elevations and/or whitish plaques, indicating MG. Sixteen patients with other endoscopic findings (14 normal, one erosive gastritis, and one chronic superficial gastritis) showed a higher proportion of H. pylori eradication (12/16, 75.0%) than those in the CAG group (5/16, 31.3%) and MG group (6/29, 20.7%; p=0.001). Patients with small-granular-type NG tended to progress toward CAG (14/27, 51.9%), whereas those with large-nodular-type NG tended to progress toward MG (25/34, 73.5%; p<0.001). CONCLUSIONS: In patients with a persistent H. pylori infection, NG tended to progress to CAG or MG when the nodules regressed. Small-granular-type NG tended to progress to CAG, whereas large-nodular-type NG tended to progress to MG.
Atrophy ; Diagnosis ; Endoscopy ; Endoscopy, Gastrointestinal ; Follow-Up Studies ; Gastritis ; Gastritis, Atrophic ; Helicobacter pylori ; Humans ; Lymphoid Tissue ; Metaplasia ; Precancerous Conditions ; Stomach Neoplasms

Barrett's esophagus (BE) is one of the most prominent diseases in Western countries because of its potential to progress to dysplasia or adenocarcinoma. Recently, the American College of Gastroenterology (ACG), American Gastroenterology Association (AGA), and European Society of Gastrointestinal Endoscopy (ESGE) developed clinical guidelines for the diagnosis and management of BE. All three guidelines commonly stressed the necessity of the endoscopic eradication of confirmed, nonnodular low grade dysplasia or high grade dysplasia, as well as the endoscopic elimination of the remaining BE after an endoscopic resection of visible mucosal abnormalities. An endoscopic resection is also considered for the optimal management of esophageal adenocarcinoma confined to the mucosa (T1a), and even in selective cases of submucosal invasion (T1b). As endoscopic therapy becomes the mainstay for the treatment of BE and its complications, the eligibility of pathologic or endoscopic experts and the BE expert center are being set and strengthened. This paper introduces the statements of the ACG, AGA and ESGE guidelines and compares the similarities and differences between them.
Adenocarcinoma ; Barrett Esophagus ; Diagnosis ; Endoscopy, Gastrointestinal ; Esophageal Neoplasms ; Gastroenterology ; Mucous Membrane

Advances in diagnosis and therapeutic technologies have brought increased life expectancy for most cancers, but paradoxically it also has increased the risk of second primary malignancies. Cancer survivors have a higher risk of developing cancer than the general population. This suggests that more studies are needed to develop screen and management programs for cancer survivors, especially patients with gastrointestinal cancers, which are the most common cancers in Korea.
Diagnosis ; Gastrointestinal Neoplasms ; Humans ; Korea ; Life Expectancy ; Neoplasms, Second Primary ; Survivors