RESUMEN
BACKGROUND & AIMS: Autoimmune gastritis (AIG), distinct from Helicobacter pylori-associated atrophic gastritis (HpAG), is underdiagnosed due to limited awareness. This multicenter study aims to develop a novel endoscopic artificial intelligence (AI) system assisting in AIG diagnosis. METHODS: Patients diagnosed with AIG, as well as HpAG and non-atrophic gastritis (NAG), were retrospectively enrolled from six centers. Endoscopic images with relevant demographic and medical data, were collected for the development of AI-assisted system, SEER-SCOPE AI, based on multi-site feature fusion model. The diagnostic performance of SEER-SCOPE AI was evaluated in the internal and external datasets. Endoscopists' performance with and without AI support was tested and compared using Mann-Whitney U test. Heatmap analysis was performed to interpret SEER-SCOPE AI. RESULTS: 1 070 patients (294 AIG, 386 HpAG, 390 NAG) with 18 828 endoscopy images were collected. SEER-SCOPE AI achieved strong performance for identifying AIG, with 96.9% sensitivity, 92.2% specificity and an AUROC of 0.990 internally, and 90.3% sensitivity, 93.1% specificity and an AUROC of 0.973 externally. The performance of SEER-SCOPE AI (sensitivity 91.3%) was comparable to experts (87.3%) and significantly outperformed non-experts (70.0%). With AI support, the overall performance of endoscopists was improved (sensitivity: 90.3% [95% CI 86.0%-93.2%] vs. 78.7% [95% CI 73.6%-83.2%], p=0.008). Heatmap analysis revealed consistent focus of SEER-SCOPE AI on regions corresponding to atrophic areas. CONCLUSIONS: SEER-SCOPE AI demonstrated expert-level performance in identifying AIG, and enhanced the diagnostic ability of endoscopists. Its application holds promise as a potent endoscopy-assisted tool for guiding biopsy sampling and early detection of AIG.
RESUMEN
The flexible strain sensor is an indispensable part in flexible integrated electronic systems and an important intermediate in external mechanical signal acquisition. The 3D printing technology provides a fast and cheap way to manufacture flexible strain sensors. In this paper, a MWCNTs/flexible resin composite for photocuring 3D printing was prepared using mechanical mixing method. The composite has a low percolation threshold (1.2%ωt). Based on the composite material, a flexible strain sensor with high performance was fabricated using digital light processing technology. The sensor has a GF of 8.98 under strain conditions ranging between 0% and 40% and a high elongation at break (48%). The sensor presents mechanical hysteresis under cyclic loading. With the increase of the strain amplitude, the mechanical hysteresis becomes more obvious. At the same time, the resistance response signal of the sensor shows double peaks during the unloading process, which is caused by the competition of disconnection and reconstruction of conductive network in the composite material. The test results show that the sensor has different response signals to different types of loads. Finally, its practicability is verified by applying it to balloon pressure detection.
RESUMEN
With the development of science and technology, flexible sensors play an indispensable role in body monitoring. Rapid prototyping of high-performance flexible sensors has become an important method to develop flexible sensors. The purpose of this study was to develop a flexible resin with multi-walled carbon nanotubes (MWCNTs) for the rapid fabrication of flexible sensors using digital light processing additive manufacturing. In this study, MWCNTs were mixed in thermoplastic polyurethane (TPU) photosensitive resin to prepare polymer-matrix composites, and a flexible strain sensor was prepared using self-developed additive equipment. The results showed that the 1.2 wt% MWCNTs/TPU composite flexible sensor had high gauge factor of 9.988 with a linearity up to 45% strain and high mechanical durability (1000 cycles). Furthermore, the sensor could be used for gesture recognition and monitoring and has good performance. This method is expected to provide a new idea for the rapid personalized forming of flexible sensors.