A systematic review on diagnosis and treatment of gastrointestinal diseases by magnetically controlled capsule endoscopy and artificial intelligence.

Background: Magnetically controlled capsule endoscopy (MCCE) is a non-invasive, painless, comfortable, and safe equipment to diagnose gastrointestinal diseases (GID), partially overcoming the shortcomings of conventional endoscopy and wireless capsule endoscopy (WCE). With advancements in technology, the main technical parameters of MCCE have continuously been improved, and MCCE has become more intelligent. Objectives: The aim of this systematic review was to summarize the research progress of MCCE and artificial intelligence (AI) in the diagnosis and treatment of GID. Data Sources and Methods: We conducted a systematic search of PubMed and EMBASE for published studies on GID detection of MCCE, physical factors related to MCCE imaging quality, the application of AI in aiding MCCE, and its additional functions. We synergistically reviewed the included studies, extracted relevant data, and made comparisons. Results: MCCE was confirmed to have the same performance as conventional gastroscopy and WCE in detecting common GID, while it lacks research in detecting early gastric cancer (EGC). The body position and cleanliness of the gastrointestinal tract are the main factors affecting imaging quality. The applications of AI in screening intestinal diseases have been comprehensive, while in the detection of common gastric diseases such as ulcers, it has been developed. MCCE can perform some additional functions, such as observations of drug behavior in the stomach and drug damage to the gastric mucosa. Furthermore, it can be improved to perform a biopsy. Conclusion: This comprehensive review showed that the MCCE technology has made great progress, but studies on GID detection and treatment by MCCE are in the primary stage. Further studies are required to confirm the performance of MCCE.

Efficient Passive Daytime Radiative Cooling by Hierarchically Designed Films Integrating Robust Durability.

Surfaces with efficient passive daytime radiative cooling (PDRC) are underpinned by maximizing both solar reflection and thermal radiation to the outer space at no additional energy cost. Despite notable progress, their practical applications are of great challenge due to their complicated fabrication processes, easy contamination and damage, and high costs. Herein, we fabricate a hierarchically designed passive daytime radiative cooling film (HPRF) comprising cost-effective Al2O3 particles and poly(dimethylsiloxane) (PDMS) via a simple phase separation method. The designed film possesses a high solar spectrum reflectance of ∼0.96 and a mid-infrared emittance of ∼0.95, achieving a ∼12.4 °C subambient cooling under direct solar irradiation. This excellent PDRC is due to the efficient Mie scattering of sunlight by hierarchical micro-/nanostructures and selected molecular vibrations of PDMS combined with the phonon polariton resonance of Al2O3 particles, respectively. Moreover, the designed HPRF is accompanied with robust durability endowed by superior self-cleaning, flexibility, and anti-ultraviolet radiation that can present substantial application promises of thermal management in various electronic devices and wearable products.

Early gastric cancer segmentation in gastroscopic images using a co-spatial attention and channel attention based triple-branch ResUnet.

BACKGROUND AND OBJECTIVE: The artificial segmentation of early gastric cancer (EGC) lesions in gastroscopic images remains a challenging task due to reasons including the diversity of mucosal features, irregular edges of EGC lesions and nuances between EGC lesions and healthy background mucosa. Hence, this study proposed an automatic segmentation framework: co-spatial attention and channel attention based triple-branch ResUnet (CSA-CA-TB-ResUnet) to achieve accurate segmentation of EGC lesions for aiding clinical diagnosis and treatment. METHODS: The input gastroscopic image sequences of the triple-branch segmentation network CSA-CA-TB-ResUnet is firstly generated by the designed multi-branch input preprocessing (MBIP) module in order to fully utilize massive correlation information among multiple gastroscopic images of the same a lesion. Then, the proposed CSA-CA-TB-ResUnet performs the segmentation of EGC lesion, in which the co-spatial attention (CSA) mechanism is designed to activate the spatial location of EGC lesions by leveraging on the correlations among multiple gastroscopic images of the same EGC lesion, and the channel attention (CA) mechanism is introduced to extract subtle discriminative features of EGC lesions by capturing the interdependencies between channel features. Finally, two gastroscopic images datasets from different digestive endoscopic centers in the southwest and northeast regions of China respectively were collected to validate the performances of proposed segmentation method. RESULTS: The correlation information among gastroscopic images was confirmed to be able to improve the accuracy of EGC segmentation. On another unseen dataset, our EGC segmentation method achieves Jaccard similarity index (JSI) of 84.54% (95% confidence interval (CI), 83.49%-85.56%), threshold Jaccard index (TJI) of 81.73% (95% CI, 79.70%-83.61%), Dice similarity coefficient (DSC) of 91.08% (95% CI, 90.40%-91.76%) and pixel-wise accuracy (PA) of 91.18% (95% CI, 90.43%-91.87%), which is superior to other state-of-the-art methods. Even on the challenging small lesions, the segmentation results of our CSA-CA-TB-ResUnet-based method are consistently and significantly better than other state-of-the-art methods. We also compared the segmentation result of our model with the diagnostic accuracy with junior/senior expert. The comparison results indicated that our model performed better than the junior expert. CONCLUSIONS: This study proposed a novel CSA-CA-TB-ResUnet-based EGC segmentation method and it has a potential for real-time application in improving EGC clinical diagnosis and minimally invasive surgery.

Improving the Classification Performance of Esophageal Disease on Small Dataset by Semi-supervised Efficient Contrastive Learning.

The classification of esophageal disease based on gastroscopic images is important in the clinical treatment, and is also helpful in providing patients with follow-up treatment plans and preventing lesion deterioration. In recent years, deep learning has achieved many satisfactory results in gastroscopic image classification tasks. However, most of them need a training set that consists of large numbers of images labeled by experienced experts. To reduce the image annotation burdens and improve the classification ability on small labeled gastroscopic image datasets, this study proposed a novel semi-supervised efficient contrastive learning (SSECL) classification method for esophageal disease. First, an efficient contrastive pair generation (ECPG) module was proposed to generate efficient contrastive pairs (ECPs), which took advantage of the high similarity features of images from the same lesion. Then, an unsupervised visual feature representation containing the general feature of esophageal gastroscopic images is learned by unsupervised efficient contrastive learning (UECL). At last, the feature representation will be transferred to the down-stream esophageal disease classification task. The experimental results have demonstrated that the classification accuracy of SSECL is 92.57%, which is better than that of the other state-of-the-art semi-supervised methods and is also higher than the classification method based on transfer learning (TL) by 2.28%. Thus, SSECL has solved the challenging problem of improving the classification result on small gastroscopic image dataset by fully utilizing the unlabeled gastroscopic images and the high similarity information among images from the same lesion. It also brings new insights into medical image classification tasks.

High-Precision Machining Method of Weak-Stiffness Mirror Based on Fast Tool Servo Error Compensation Strategy.

Weak-stiffness mirrors are widely used in various fields such as aerospace and optoelectronic information. However, it is difficult to achieve micron-level precision machining because weak-stiffness mirrors are hard to clamp and are prone to deformation. The machining errors of these mirrors are randomly distributed and non-rotationally symmetric, which is difficult to overcome by common machining methods. Based on the fast tool servo system, this paper proposes a high-precision machining method for weak-stiffness mirrors. Firstly, the clamping error and cutting error compensation strategy is obtained by analyzing the changing process of the mirror surface morphology. Then, by combining real-time monitoring and theoretical simulation, the elastic deformation of the weak-stiffness mirror is accurately extracted to achieve the compensation of the clamping error, and the compensation of the cutting error is achieved by iterative machining. Finally, a weak-stiffness mirror with a thickness of 2.5 mm was machined twice, and the experimental process produced a clamping error with a peak to valley (PV) value of 5.2 µm and a cutting error with a PV value of 1.6 µm. The final machined surface after compensation had a PV value of 0.7 µm. The experimental results showed that the compensation strategy proposed in this paper overcomes the clamping error of the weak-stiffness mirror and significantly reduces cutting errors during the machining process, achieving the high precision machining of a weak-stiffness mirror.

Fabrication and evaluation of complicated microstructures on cylindrical surface.

Various items of roll molds are popularly used to fabricate different kinds of optical films for optoelectronic information and other new and high-tech fields, while the fabrication and evaluation of optical microstructures on a cylindrical roller surface is more difficult than ecumenically manufactured products. In this study, the machinability of microstructures on the roll based on a fast tool servo (FTS) system is investigated. First, the flexible hinge holder for a FTS is designed and its structural parameters are optimized with finite-element analysis and fatigue reliability theory. The tool radius compensation algorithm for complicated microstructures is then deduced based on the surface fitting and bilinear interpolation algorithm of discrete data. Meanwhile, the evaluation index and method are proposed by the medium section method. Finally, a machining test of aspheric arrays on a cylindrical aluminum surface is carried out, and the high quality of the microstructure indicates that the proposed method is able to be used to fabricate optical microstructures.

High-precision processing method for an aluminum mirror assisted with a femtosecond laser.

At present, aluminum-based optical payloads are widely used in the aviation and aerospace field, and the demand for aluminum mirrors has become increasingly urgent in the visible light region. The main processing of an aluminum alloy mirror involves single-point diamond turning followed by a combined polishing process. Among these processes, magnetorheological finishing (MRF) is an important method for improving a surface figure. During the MRF process, excessive impurity contaminants are introduced into the surface of the aluminum mirror, thereby reducing surface reflectivity. In this paper, theoretical analysis and time-of-flight secondary ion mass spectrometry depth profiling were used to obtain the cause of pollution, and the process scheme of femtosecond laser cleaning was proposed. After verifying the feasibility, a new, to the best of our knowledge, process route was implemented on a Φ50mm aluminum mirror. Finally, the surface figure of RMS 0.022λ and the surface roughness of Ra 3.24 nm were obtained. In addition, reflectance in the visible light and near-infrared bands has increased by about 50%.

Study on the surface crystallization mechanism and inhibition method in the CMP process of aluminum alloy mirrors.

Owing to its material properties, aluminum-based optical loads are widely used in the aerospace field. At present, the main processing of an aluminum alloy mirror is single-point diamond turning followed by the combined polishing process. The surface will generate some white crystals during the chemical mechanical polishing process (CMP). These crystals can affect the improvement of surface quality and seriously reduce the processing efficiency of the whole process. In view of the above problems, four main factors of crystallization are obtained by interface theoretical analysis, Visual MINTEQ simulation of chemical morphological distribution, and experimental analysis. They are temperature, PH value of polishing fluid, solid-liquid contact angle, and impurity content of aluminum alloy. The crystallization phenomenon in the polishing process is successfully suppressed by improving the polishing process and selecting new materials. The experimental results showed that the surface roughness decreased from 7.21 to 2.98 nm without crystallization using the new method.