Real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinoma using a deep learning model (with videos).

BACKGROUND AND AIMS: We developed a system for computer-assisted diagnosis (CAD) for real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinomas (ESCCs) to assist the diagnosis of esophageal cancer. METHODS: A total of 6473 narrow-band imaging (NBI) images, including precancerous lesions, early ESCCs, and noncancerous lesions, were used to train the CAD system. We validated the CAD system using both endoscopic images and video datasets. The receiver operating characteristic curve of the CAD system was generated based on image datasets. An artificial intelligence probability heat map was generated for each input of endoscopic images. The yellow color indicated high possibility of cancerous lesion, and the blue color indicated noncancerous lesions on the probability heat map. When the CAD system detected any precancerous lesion or early ESCCs, the lesion of interest was masked with color. RESULTS: The image datasets contained 1480 malignant NBI images from 59 consecutive cancerous cases (sensitivity, 98.04%) and 5191 noncancerous NBI images from 2004 cases (specificity, 95.03%). The area under curve was 0.989. The video datasets of precancerous lesions or early ESCCs included 27 nonmagnifying videos (per-frame sensitivity 60.8%, per-lesion sensitivity, 100%) and 20 magnifying videos (per-frame sensitivity 96.1%, per-lesion sensitivity, 100%). Unaltered full-range normal esophagus videos included 33 videos (per-frame specificity 99.9%, per-case specificity, 90.9%). CONCLUSIONS: A deep learning model demonstrated high sensitivity and specificity for both endoscopic images and video datasets. The real-time CAD system has a promising potential in the near future to assist endoscopists in diagnosing precancerous lesions and ESCCs.

Ascariasis imaging: pictorial essay.

Ascariasis is not widespread in Europe, and the knowledge on how to diagnose and treat the disease is limited to some specialists. On the other hand, clinicians are facing an increasing number of immigrants from high-prevalence countries and are, therefore, challenged to update in this field of infectious diseases. Here we present current knowledge on this infection in 2 parts. The first part discusses clinical features and hot topics in ascariasis, and the second part presents imaging features of ascariasis as a pictorial essay.

EUS Needle Identification Comparison and Evaluation study (with videos).

BACKGROUND AND AIMS: EUS-guided FNA or biopsy sampling is widely practiced. Optimal sonographic visualization of the needle is critical for image-guided interventions. Of the several commercially available needles, bench-top testing and direct comparison of these needles have not been done to reveal their inherent echogenicity. The aims are to provide bench-top data that can be used to guide clinical applications and to promote future device research and development. METHODS: Descriptive bench-top testing and comparison of 8 commonly used EUS-FNA needles (all size 22 gauge): SonoTip Pro Control (Medi-Globe); Expect Slimline (Boston Scientific); EchoTip, EchoTip Ultra, EchoTip ProCore High Definition (Cook Medical); ClearView (Conmed); EZ Shot 2 (Olympus); and BNX (Beacon Endoscopic), and 2 new prototype needles, SonoCoat (Medi-Globe), coated by echogenic polymers made by Encapson. Blinded evaluation of standardized and unedited videos by 43 EUS endoscopists and 17 radiologists specialized in GI US examination who were unfamiliar with EUS needle devices. RESULTS: There was no significant difference in the ratings and rankings of these needles between endosonographers and radiologists. Overall, 1 prototype needle was rated as the best, ranking 10% to 40% higher than all other needles (P < .01). Among the commercially available needles, the EchoTip Ultra needle and the ClearView needle were top choices. The EZ Shot 2 needle was ranked statistically lower than other needles (30%-75% worse, P < .001). CONCLUSIONS: All FNA needles have their inherent and different echogenicities, and these differences are similarly recognized by EUS endoscopists and radiologists. Needles with polymeric coating from the entire shaft to the needle tip may offer better echogenicity.

Nasojejunal tube-assisted endoscopic ultrasound-guided gastrojejunostomy for the management of gastric outlet obstruction is safe and effective.

Background and aims: Endoscopic ultrasound-guided gastrojejunostomy (EUS-GJ) is a therapeutic option for patients with gastric outlet obstruction (GOO), which provides long-term luminal patency without the risk of tumor ingrowth and/or overgrowth and avoids surgical morbidity. The goal of this study was to assess technical success, clinical success, and adverse events associated with a nasojejunal tube-assisted EUS- GJ technique. Methods: This was a retrospective study conducted at a single tertiary care center. The nasojejunal tube (14F) was used to perform the EUS-GJ (device-assisted method). During the study period, consecutive GOO patients who underwent EUS-GJ between August 2018 and December 2021 were included. Technical success was defined as adequate positioning and deployment of the stent. The patient's ability to tolerate a normal oral diet without vomiting was defined as clinical success. Results: Thirty patients underwent EUS-GJ during this study period. Twenty-six patients had malignant GOO, while four had a benign obstruction. EUS-GJ was successfully performed in 29 patients, and technical success was 96.67% (29/30). Nasojejunal tube-assisted EUS-GJ technique was used in all patients. Clinical success was achieved in all patients who had technical success (29/29, 100%). The adverse events rate was 6.6%. During the procedure, the median procedure time was 25 min (interquartile range 15-42.5), and the average hospitalization was 4.4 days. Normal meals were tolerated by all patients. After 210 days of median follow-up (range 5-880 days), no recurrence of symptoms was observed. Conclusion: The nasojejunal tube-assisted EUS-GJ is a safe and effective technique to treat GOO symptoms.