Objective: To construct the diagnostic model of superficial esophageal squamous cell carcinoma (ESCC) and precancerous lesions in endoscopic images based on the YOLOv5l model by using deep learning method of artificial intelligence to improve the diagnosis of early ESCC and precancerous lesions under endoscopy. Methods: 13, 009 endoscopic esophageal images of white light imaging (WLI), narrow band imaging (NBI) and lugol chromoendoscopy (LCE) were collected from June 2019 to July 2021 from 1, 126 patients at the Cancer Hospital, Chinese Academy of Medical Sciences, including low-grade intraepithelial neoplasia, high-grade intraepithelial neoplasia, ESCC limited to the mucosal layer, benign esophageal lesions and normal esophagus. By computerized random function method, the images were divided into a training set (11, 547 images from 1, 025 patients) and a validation set (1, 462 images from 101 patients). The YOLOv5l model was trained and constructed with the training set, and the model was validated with the validation set, while the validation set was diagnosed by two senior and two junior endoscopists, respectively, to compare the diagnostic results of YOLOv5l model and those of the endoscopists. Results: In the validation set, the accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of the YOLOv5l model in diagnosing early ESCC and precancerous lesions in the WLI, NBI and LCE modes were 96.9%, 87.9%, 98.3%, 88.8%, 98.1%, and 98.6%, 89.3%, 99.5%, 94.4%, 98.2%, and 93.0%, 77.5%, 98.0%, 92.6%, 93.1%, respectively. The accuracy in the NBI model was higher than that in the WLI model (P<0.05) and lower than that in the LCE model (P<0.05). The diagnostic accuracies of YOLOv5l model in the WLI, NBI and LCE modes for the early ESCC and precancerous lesions were similar to those of the 2 senior endoscopists (96.9%, 98.8%, 94.3%, and 97.5%, 99.6%, 91.9%, respectively; P>0.05), but significantly higher than those of the 2 junior endoscopists (84.7%, 92.9%, 81.6% and 88.3%, 91.9%, 81.2%, respectively; P<0.05). Conclusion: The constructed YOLOv5l model has high accuracy in diagnosing early ESCC and precancerous lesions in endoscopic WLI, NBI and LCE modes, which can assist junior endoscopists to improve diagnosis and reduce missed diagnoses.
Artificial Intelligence ; Endoscopy/methods* ; Esophageal Neoplasms/pathology* ; Esophageal Squamous Cell Carcinoma/diagnostic imaging* ; Humans ; Narrow Band Imaging ; Precancerous Conditions/diagnostic imaging* ; Sensitivity and Specificity

Esophageal Neoplasms/diagnostic imaging* ; Humans ; Laryngeal Neoplasms/diagnostic imaging* ; Laryngoscopes ; Narrow Band Imaging ; Neoplasms, Multiple Primary

The accurate judgement of the upper and lower borders of the adenocarcinoma of esophagogastric junction (AEG) by radiology can facilitate the decisions on surgical approach and staging criteria. X-ray double contrast radiography, CT and MRI are the common modalities. The accuracy of X-ray double contrast radiography in determining the invasion length of esophagus and the central point of gastric infiltration can be improved by standardized pretreatment, combination of multiple contrast methods such as double contrast and flow-coating procedure, and combination of multi-angle observations such as conventional frontal, left /right anterior oblique and supine right posterior oblique position. Abdominal enhanced CT is the imaging method recommended by clinical guidelines for the radiological examination of AEG. The relative position of the central point of the tumor from 2 cm line can be determined through the combination of measurement and formula calculation on multi-planar reconstructed CT images. The "three-layer four-type" classification can provide reference for the selection of abdominothoracic incision. The direct demonstration of the tumor extension can be achieved through the CT curved planar reconstruction by drawing lines along esophagus to stomach. The combination of multiple sequences of MRI is helpful to determine the extension of the lesions. In the future, more radiological studies are needed to establish criteria with high accuracy, repeatability and convenient operation,and to assist clinical evaluation of AEG invasion.
Adenocarcinoma ; classification ; diagnostic imaging ; pathology ; surgery ; Contrast Media ; Esophageal Neoplasms ; classification ; diagnostic imaging ; pathology ; surgery ; Esophagogastric Junction ; diagnostic imaging ; pathology ; surgery ; Humans ; Magnetic Resonance Imaging ; Neoplasm Invasiveness ; Neoplasm Staging ; Stomach Neoplasms ; classification ; diagnostic imaging ; pathology ; surgery ; Tomography, X-Ray Computed

Esophageal Neoplasms ; surgery ; Esophagectomy ; adverse effects ; Humans ; Mediastinum ; diagnostic imaging ; Surgical Wound Infection ; diagnostic imaging ; etiology

OBJECTIVETo investigate the accuracy of CT in preoperative discrimination of cT3 from cT4 in patients with Siewert II esophagogastric junction (EGJ) adenocarcinoma according to UICC/AJCC 8th edition and IGCA 4th edition.

METHODSCT imaging data of 43 consecutive patients with Siewert II EGJ adenocarcinoma who underwent preoperative CT and were diagnosed as pT3 or pT4 by postoperative pathology were retrospectively analyzed. Inclusion criteria were as follows:(1)no previous history of gastric operation, radiochemotherapy, targeted treatment; no contraindications of CT enhanced scanning; (2) good filling of gastric cavity by CT, clear image without artifacts, all axial-coronal-sagittal 3-plane reconstruction images obtained by abdominal stage 3 enhanced scan; (3) operation within 1 week after CT examination; (4) Siewert II EGJ adenocarcinoma confirmed by operation, pT3 and pT4 by postoperative pathology. Transverse and multiplanar reconstruction images were reviewed by two radiologists in double-blind method. Distance between cancer epicenter and esophagogastric junction line, and the contour of the serosa were retrospectively measured on CT scans. The cT staging judgment was performed according to the UICC/AJCC 8th edition (Siewert II EGJ adenocarcinoma should be staged as esophageal cancer) and IGCA 4th edition (Siewert II EGJ adenocarcinoma should be staged as gastric cancer) respectively. Consistency of cT staging and pathological pT staging was compared between UICC/AJCC and IGCA.

RESULTSPreoperative CT revealed that the mean length between tumor epicenter and esophagogastric junction line was(1.5±0.4) cm (0.7-2.5 cm), and such length was ≤2 cm in 41 cases, whose concordance with surgical judgment was 95.3%(41/43). IGCA staging: 18 cases were preoperatively assessed as cT3 and 25 cases as cT4a. UICC/AJCC staging: 41 cases with cancer epicenter locating within 2 cm below esophagogastric junction line were staged as cT3 according to esophageal cancer staging; 2 cases with cancer epicenter locating > 2 cm below esophagogastric junction line were staged according to gastric cancer staging, of whom one was staged as cT3 due to regular serosa and the other was staged as cT4a due to irregular serosa. Postoperative pathology: 33 cases were pT3 and 10 cases were pT4a. The accuracy of preoperative CT in discrimination of T3 from T4a was 74.4%(32/43) with UICC/AJCC criteria and 65.1%(28/43) with IGCA criteria, whose difference was significant(P<0.01).

CONCLUSIONSPreoperative CT can accurately localize the 2 cm threshold line of Siewert II esophagogastric junction adenocarcinoma, which is beneficial to the discrimination of cT3 from cT4a EGJ adenocarcinoma. Application of the UICC/AJCC 8th edition criteria to above discrimination has higher accuracy as compared to IGCA 4th edition in cT-staging by CT.

Adenocarcinoma ; Double-Blind Method ; Esophageal Neoplasms ; diagnostic imaging ; Esophagogastric Junction ; Humans ; Neoplasm Staging ; Retrospective Studies ; Stomach Neoplasms ; diagnostic imaging ; Tomography, X-Ray Computed

Objective To assess the diagnostic accuracy of multidetector CT (MDCT) for restaging of patients with esophageal squamous cell carcinoma (SCC) after neoadjuvant chemotherapy and determine the feasibility of CT for assessing the treatment response and evaluating the prognosis. Methods Totally 135 patients with esophageal SCC who had received neoadjuvant treatment and surgery in Beijing Cancer Hospital from September 2005 to December 2011 were enrolled in this study. TN staging was performed using CT for lesions before and after neoadjuvant treatment by two radiologists,and the tumor regression grade (TRG) and pathological TRG were also assessed. Based on preoperative CT TN restaging results,the patients were defined as responders with TNafter therapy,non-responders with T3-4N+,and patients with undefined response (TN0 or TNN). Results The accuracy of T and N restaging using CT was 50%,54% (κ=0.718,P <0.001) and 59%,56% (κ=0.753,P <0.001) by two radiologists,respectively. TRG from CT was predicted correctly in 27% of patients. Pathological TRG was an accurate predictor of survival (χ=8.13,P=0.04). There was no significant trend toward better survival for lower CT TRG (χ=1.17,P=0.286). Among 135 patients with esophageal cancer,19 patients(14.07%) were responders ,46 patients(34.07%) were non-responders,and 70 patients (50.37%)were patients with undefined response . The overall survival rates of responders,non-responders and patients with undefined response were 71.5%,47.3%,and 18.5%,respectively. The overall survival of responders was better than that of patients with undefined response (χ=1.518,P=0.63) and non-responders(χ=12.04,P=0.0016),but the overall survival of patients with undefined response was better than that of non-responders (χ=14.468,P=0.0003). Conclusion sMDCT restaging after neoadjuvant treatment can not accurately predict pathological stage in esophageal SCC. The CT T and N restaging has certain clinical value in assessing the response to neoadjuvant chemotherapy in patients with esophageal cancer and predicting the prognosis.
Carcinoma, Squamous Cell ; diagnostic imaging ; drug therapy ; Esophageal Neoplasms ; diagnostic imaging ; drug therapy ; Humans ; Neoadjuvant Therapy ; Neoplasm Staging ; Prognosis ; Survival Rate ; Tomography, X-Ray Computed

Adenocarcinoma ; surgery ; Candidiasis ; etiology ; Cardiac Tamponade ; diagnosis ; etiology ; Echocardiography ; Electrocardiography ; Esophageal Fistula ; complications ; diagnostic imaging ; Fever ; etiology ; Gastrectomy ; Haemophilus Infections ; etiology ; Heart Diseases ; complications ; diagnostic imaging ; Humans ; Male ; Middle Aged ; Pericardial Effusion ; diagnostic imaging ; etiology ; Pericarditis ; diagnostic imaging ; etiology ; Postoperative Complications ; diagnostic imaging ; Staphylococcal Infections ; etiology ; Stomach Neoplasms ; surgery ; Streptococcal Infections ; etiology ; Tomography, X-Ray Computed

BACKGROUND/AIMS: Unexpected diagnosis of synchronous second primary cancers (SPC) complicates physicians' decision-making because clinical details of squamous esophageal cancer (EC) patients with SPC have been limited. We evaluated clinical features and treatment outcomes of patients with synchronous SPC detected during the initial staging of squamous EC. METHODS: We identified a total of 317 consecutive patients diagnosed with squamous EC. Relevant clinical and cancer-specific information were reviewed retrospectively. RESULTS: EC patients with synchronous SPC were identified in 21 patients (6.6%). There were significant differences in median age (70 years vs. 63 years, p = 0.01), serum albumin level (3.3 g/dL vs. 3.9 g/dL, p < 0.01) and body mass index (20.4 kg/m2 vs. 22.8 kg/m2, p = 0.01) between EC patients with and without SPC. Head and neck, lung and gastric cancers accounted for 18.2%, 22.7%, and 18.2% of SPC, respectively. Positron emission tomography-computed tomography (PET-CT) detected four cases (18.2%) of SPC that were missed on CT. Management plans were altered in 13 of 21 patients (61.9%) with detected SPC. Curative esophagectomy was attempted in 28.6% of EC patients with SPC (vs. 59.1% of patients without SPC; p = 0.006). EC patients with SPC had significantly lower 5-year survival than patients without SPC (10.6% vs. 36.7%, p = 0.008). CONCLUSIONS: Synchronous SPC were found in 6.6% of squamous EC patients, and PET-CT contributed substantially to the detection of synchronous SPC. EC patients with SPC had poor survival due to challenges of providing stage-appropriate treatment.
Aged ; Carcinoma, Squamous Cell/diagnostic imaging/mortality/*pathology/therapy ; Esophageal Neoplasms/diagnostic imaging/mortality/*pathology/therapy ; Esophagectomy ; Esophagoscopy ; Female ; Humans ; Kaplan-Meier Estimate ; Male ; Middle Aged ; Neoplasm Staging ; Neoplasms, Multiple Primary/diagnostic imaging/mortality/*pathology/therapy ; Positron Emission Tomography Computed Tomography ; Predictive Value of Tests ; Retrospective Studies ; Risk Factors ; Time Factors ; Treatment Outcome

Barrett's esophagus (BE) is the only known precursor to esophageal adenocarcinoma (EAC), whose incidence has increased sharply in the last 4 decades. The annual conversion rate of BE to cancer is significant, but small. The identification of patients at a higher risk of cancer therefore poses a clinical conundrum. Currently, endoscopic surveillance is recommended in BE patients, with the aim of diagnosing either dysplasia or cancer at early stages, both of which are curable with minimally invasive endoscopic techniques. There is a large variation in clinical practice for endoscopic surveillance, and dysplasia as a marker of increased risk is affected by sampling error and high interobserver variability. Screening programs have not yet been formally accepted, mainly due to the economic burden that would be generated by upper gastrointestinal endoscopy. Screening programs have not yet been formally accepted, mainly due to the economic burden that would be generated by widespread indication to upper gastrointestinal endoscopy. In fact, it is currently difficult to formulate an accurate algorithm to confidently target the population at risk, based on the known clinical risk factors for BE and EAC. This review will focus on the clinical and molecular factors that are involved in the development of BE and its conversion to cancer and on how increased knowledge in these areas can improve the clinical management of the disease.
Adenocarcinoma/*etiology ; Animals ; Barrett Esophagus/*complications/diagnosis ; Diagnostic Imaging/methods ; Disease Models, Animal ; Epigenesis, Genetic/physiology ; Esophageal Neoplasms/diagnosis/*etiology ; Esophagoscopy/methods ; Forecasting ; Genetic Markers/physiology ; Humans ; Mice ; Practice Guidelines as Topic ; Risk Factors

The presence of lymph node metastasis is an important prognostic factor for patients with esophageal cancer. Accurate assessment of lymph nodes in thoracic esophageal carcinoma is essential for selecting appropriate treatment and forecasting disease progression. Positron emission tomography combined with computed tomography (PET/CT) is becoming an important tool in the workup of esophageal carcinoma. Here, we evaluated the effectiveness of the maximum standardized uptake value (SUVmax) in assessing lymph node metastasis in esophageal squamous cell carcinoma (ESCC) prior to surgery. Fifty-nine surgical patients with pathologically confirmed thoracic ESCC were retrospectively studied. These patients underwent radical esophagectomy with pathologic evaluation of lymph nodes. They all had (18)F-FDG PET/CT scans in their preoperative staging procedures. None had a prior history of cancer. The pathologic status and PET/CT SUVmax of lymph nodes were collected to calculate the receiver operating characteristic (ROC) curve and to determine the best cutoff value of the PET/CT SUVmax to distinguish benign from malignant lymph nodes. Lymph node data from 27 others were used for the validation. A total of 323 lymph nodes including 39 metastatic lymph nodes were evaluated in the training cohort, and 117 lymph nodes including 32 metastatic lymph nodes were evaluated in the validation cohort. The cutoff point of the SUVmax for lymph nodes was 4.1, as calculated by ROC curve (sensitivity, 80%; specificity, 92%; accuracy, 90%). When this cutoff value was applied to the validation cohort, a sensitivity, a specificity, and an accuracy of 81%, 88%, and 86%, respectively, were obtained. These results suggest that the SUVmax of lymph nodes predicts malignancy. Indeed, when an SUVmax of 4.1 was used instead of 2.5, FDG-PET/CT was more accurate in assessing nodal metastasis.
Carcinoma, Squamous Cell ; diagnostic imaging ; Esophageal Neoplasms ; diagnostic imaging ; Fluorodeoxyglucose F18 ; Humans ; Lymph Nodes ; Lymphatic Metastasis ; diagnostic imaging ; Multimodal Imaging ; methods ; Positron-Emission Tomography ; Radiopharmaceuticals ; Retrospective Studies ; Sensitivity and Specificity