ABSTRACT
@#Esophageal cancer is an aggressive malignancy with high morbidity and poor prognosis. Symptoms of early esophageal cancer are insidious and difficult to detect, while advanced esophageal obstruction, lesion infiltration and metastasis seriously affect patients’ quality of life. Early detection and treatment can help to increase the survival chance of patients. Recently, artificial intelligence (AI) has shown remarkable success in diagnosis of esophageal cancer, highlighting the great potential of new AI-assisted diagnostic modalities. This paper aims to review recent progress of AI in the diagnosis of esophageal cancer and to prospect its clinical application.
ABSTRACT
@#Endoscopic resection and surgical resection are the two major therapeutic methods for early esophageal cancer. Endoscopic resection is safe and minimally invasive, but lymph node dissection can not be performed. Although surgery provides a rather thorough resection of the lesions and affected lymph nodes, surgical trauma brings certain negative impact on patients' long-term life quality. A comprehensive assessment of the patient's general condition, the risk of diseased lymph node metastasis, and the risk of the treatment itself is an important measure to optimize treatment decisions and formulate personalized treatment plans.
ABSTRACT
Objective:To develop an diagnostic equipment with artificial intelligence (AI) real-time assistance under endoscopy (endoscopic AI equipment) for the detection of gastrointestinal protruding lesions, and to evaluate its performance and safety.Methods:From January to December 2017, at Endoscopy Center of West China Hospital, Sichuan University, the endoscopic images of individuals who underwent routine gastroscopy and colonoscopy were collected. The model was established based on convolutional neural network and the endoscopic AI equipment was developed. From June to December 2019, a prospective, single center, blinded and parallel controlled study was conducted to compare the differences in evaluation of protruding lesions of the same patient under gastroscopy or colonoscopy between endoscopist and the endoscopic AI equipment and to evaluated the impact of lesion size (lesions <5 mm and ≥5 mm) on the detection of endoscopic AI equipment. The main outcome measure was the detection time difference in reporting the protruding lesion between endoscopic AI equipment and endoscopist; and the secondary indicator was the accuracy of endoscopic AI equipment in detecting the protruding lesion. Wilcoxon rank sum test and chi-square test were used for statistical analysis.Results:A total of 71 582 white light endoscopy images were used for endoscopic AI equipment training, which included 41 376 images of protruding lesions. The endoscopic AI equipment was successfully developed and obtained the registration certificate of medical devices of the People′s Republic of China (Sichuan Instrument Standard, 20202060049). The accuracy, sensitivity, and specificity of endoscopic AI equipment in detecting protruding lesions were 96.4%, 95.1% and 92.8%, respectively. The detection time of each protruding lesions under gastroscopy of endoscopic AI equipment was 1.524 seconds faster than that of endoscopist; but the detection time of each protruding lesions under colonoscopy was 0.070 seconds slower than that of endoscopist, and the differences were statistically significant ( Z=-5.505 and -4.394, both P<0.01). The detection time of each protruding lesions under gastroscopy or colonoscopy of endoscopic AI equipment was not inferior to that of endoscopist. The detection rate of protruding lesions under colonoscopy by endoscopic AI equipment was 89.9% (249/277) and the sensitivity was 89.9%; the detection rate of protruding lesions under colonoscopy was 87.0% (450/517) and the sensitivity was 86.9%. There were no statistically significant differences in the detection time difference, sensitivity and missed diagnostic rate between the lesions <5 mm and ≥5 mm detected by endoscopic AI equipment under gastroscopy (all P>0.05). The sensitivity of endoscopic AI equipment in detecting the lesions ≥5 mm under colonoscopy was higher than that of lesions <5 mm (96.8% vs. 84.9%), and the missed diagnostic rate was lower than that of lesions <5 mm (3.2%, 3/94 vs. 15.1%, 61/405), and the differences were statistically significant ( χ2=9.615 and 9.612, both P=0.002). No adverse events on patients and medical staffs occurred, and there were no cases of equipment electricity leakage, and abnormal work reported during the use of endoscopic AI equipment. Conclusions:The endoscopic AI equipment can report the protruding lesions simultaneously with endoscopists, and the accuracy is close to 90%, which is expected to be a practical assistant for endoscopists to avoid missed detection of protruding lesions.
ABSTRACT
Diarrhea is a common intestinal symptom in macaque.The corresponding intestinal lesions of macaque are mainly described at autopsy but less observed by colonoscopy.The aim of this study was to develop a colonoscopic technique and to obtain endoscopic images of the entire colon in macaques.Eight healthy adult macaques ( 5 males and 3 females) without diarrhea for 2 months, were fed Glauber’ s salt through nasogastric tubes.The colon cleanliness was well matched to the endoscopic observation of macaque colon.The procedure took 10-20 min for each animal.There was no obvious abnormality in the colon of four animals except some slight differences of mucosal structure from that of human beings.Small pieces of erosion and ulcer in the colons were observed in four macaques which presented mild diarrhea for less than 1 day, while a severe stenosis was observed in one of those four macaques.No animal died during and one week after the endoscopic procedure.Colonoscopy may safely performed in macaques.The images taken by colonoscopy may be important to establish diagnosis and treatment of colitis in macaques in time and to evaluate the efficacy of drug intervention as well.This technique is also helpful to provide qualified macaques for scientific researches.