A Multimodal Multipath Artificial Intelligence System for Diagnosing Gastric Protruded Lesions on Endoscopy and Endoscopic Ultrasonography Images

Laparoscopic resection and endoscopic submucosal dissection for treating gastric ectopic pancreas

BACKGROUND

Gastric ectopic pancreas (GEP) is a rare developmental abnormality that refers to the existence of pancreatic tissue in the stomach with no anatomical relationship with the main pancreas. It is usually difficult to diagnose through histological examination, and the choice of treatment method is crucial.

AIM

To describe the endoscopic ultrasound characteristics of GEP and evaluate the value of laparoscopic resection (LR) and endoscopic submucosal dissection (ESD).

METHODS

Forty-nine patients with GEP who underwent ESD and LR in the Second Affiliated Hospital of Fujian Medical University from May 2018 to July 2023 were retrospectively included. Data on clinical characteristics, endoscopic ultrasonography (EUS), ESD, and LR were collected and analyzed. The characteristics of EUS and the efficacy of the two treatments were analyzed.

RESULTS

The average age of the patients was 43.31 ± 13.50 years, and the average maximum diameter of the lesions was 1.55 ± 0.70 cm. The lesion originated from the mucosa in one patient (2.04%), from the submucosa in 42 patients (85.71%), and from the muscularis propria in 6 patients (12.25%). Twenty-nine patients (59.20%) with GEP showed umbilical depression on endoscopy. The most common initial symptom of GEP was abdominal pain (40.82%). Tumor markers, including carcinoembryonic antigen (CEA) and carbohydrate antigen 19-9 (CA-19-9), were generally within the normal range. One patient (2.04%) with GEP had increased CEA and CA-19-9 levels. However, no cancer tissue was found on postoperative pathological examination, and tumor markers returned to normal levels after resecting the lesion. There was no significant difference in surgery duration (72.42 ± 23.84 vs 74.17 ± 12.81 min) or hospital stay (3.70 ± 0.91 vs 3.83 ± 0.75 d) between the two methods. LR was more often used for patients with larger tumors and deeper origins. The amount of bleeding was significantly higher in LR than in ESD (11.28 ± 16.87 vs 16.67 ± 8.76 mL, P < 0.05). Surgery was associated with complete resection of the lesion without any serious complications; there were no cases of recurrence during the follow-up period.

CONCLUSION

GEP has unique characteristics in EUS. LR and ESD seem to be good choices for treating GEP. LR is better for large GEP with a deep origin. However, due to the rarity of GEP, multicenter large-scale studies are needed to describe its characteristics and evaluate the safety of LR and ESD.

General Multiscenario Ultrasound Image Tumor Diagnosis Method Based on Unsupervised Domain Adaptation

OBJECTIVE

The utilization of computer-aided diagnosis (CAD) in breast ultrasound image classification has been limited by small sample sizes and domain shift. Current ultrasound classification methods perform inadequately when exposed to cross-domain scenarios, as they struggle with data sets from unobserved domains. In the medical field, there are situations in which all images must share the same networks as they capture the same symptom of the same participant, implying that they share identical structural content. Nevertheless, most domain adaptation methods are not suitable for medical images as they overlook the common features among the images.

METHODS

To overcome these challenges, we propose a novel diverse-domain 2-D feature selection network (FSN), which uses the similarities among medical images and extracts features with a reconstruction network with shared weights. Additionally, it penalizes the feature domain distance through two adversarial learning modules that align the feature space and select common features. Our experiments illustrate that the proposed method is robust and can be applied to ultrasound images of various diseases.

RESULTS

Compared with the latest domain adaptive methods, 2-D FSN markedly enhances the accuracy of classification of breast, thyroid and endoscopic ultrasound images, achieving accuracies of 82.4%, 96.4% and 89.7%, respectively. Furthermore, the model was evaluated on an unsupervised domain adaptation task using ultrasound images from multiple sources and achieved an average accuracy of 77.3% across widely varying domains.

CONCLUSION

In general, 2-D FSN improves the classification ability of the model on multidomain ultrasound data sets through the learning of common features and the combination of multimodule intelligence. The algorithm has good clinical guidance value.

Endoscopic Ultrasound Advanced Techniques for Diagnosis of Gastrointestinal Stromal Tumours

Gastrointestinal Stromal Tumors (GISTs) are subepithelial lesions (SELs) that commonly develop in the gastrointestinal tract. GISTs, unlike other SELs, can exhibit malignant behavior, so differential diagnosis is critical to the decision-making process. Endoscopic ultrasound (EUS) is considered the most accurate imaging method for diagnosing and differentiating SELs in the gastrointestinal tract by assessing the lesions precisely and evaluating their malignant risk. Due to their overlapping imaging characteristics, endosonographers may have difficulty distinguishing GISTs from other SELs using conventional EUS alone, and the collection of tissue samples from these lesions may be technically challenging. Even though it appears to be less effective in the case of smaller lesions, histology is now the gold standard for achieving a final diagnosis and avoiding unnecessary and invasive treatment for benign SELs. The use of enhanced EUS modalities and elastography has improved the diagnostic ability of EUS. Furthermore, recent advancements in artificial intelligence systems that use EUS images have allowed them to distinguish GISTs from other SELs, thereby improving their diagnostic accuracy.