Development of hybrid 3D printing approach for fabrication of high-strength hydroxyapatite bioscaffold using FDM and DLP techniques.

This study develops a hybrid 3D printing approach that combines fused deposition modeling (FDM) and digital light processing (DLP) techniques for fabricating bioscaffolds, enabling rapid mass production. The FDM technique fabricates outer molds, while DLP prints struts for creating penetrating channels. By combining these components, hydroxyapatite (HA) bioscaffolds with different channel sizes (600, 800, and 1000µm) and designed porosities (10%, 12.5%, and 15%) are fabricated using the slurry casting method with centrifugal vacuum defoaming for significant densification. This innovative method produces high-strength bioscaffolds with an overall porosity of 32%-37%, featuring tightly bound HA grains and a layered surface structure, resulting in remarkable cell viability and adhesion, along with minimal degradation rates and superior calcium phosphate deposition. The HA scaffolds show hardness ranging from 1.43 to 1.87 GPa, with increasing compressive strength as the designed porosity and channel size decrease. Compared to human cancellous bone at a similar porosity range of 30%-40%, exhibiting compressive strengths of 13-70 MPa and moduli of 0.8-8 GPa, the HA scaffolds demonstrate robust strengths ranging from 40 to 73 MPa, paired with lower moduli of 0.7-1.23 GPa. These attributes make them well-suited for cancellous bone repair, effectively mitigating issues like stress shielding and bone atrophy.

Hyperspectral Imaging Combined with Artificial Intelligence in the Early Detection of Esophageal Cancer.

This study uses hyperspectral imaging (HSI) and a deep learning diagnosis model that can identify the stage of esophageal cancer and mark the locations. This model simulates the spectrum data from the image using an algorithm developed in this study which is combined with deep learning for the classification and diagnosis of esophageal cancer using a single-shot multibox detector (SSD)-based identification system. Some 155 white-light endoscopic images and 153 narrow-band endoscopic images of esophageal cancer were used to evaluate the prediction model. The algorithm took 19 s to predict the results of 308 test images and the accuracy of the test results of the WLI and NBI esophageal cancer was 88 and 91%, respectively, when using the spectral data. Compared with RGB images, the accuracy of the WLI was 83% and the NBI was 86%. In this study, the accuracy of the WLI and NBI was increased by 5%, confirming that the prediction accuracy of the HSI detection method is significantly improved.

Identification of Skin Lesions by Using Single-Step Multiframe Detector.

An artificial intelligence algorithm to detect mycosis fungoides (MF), psoriasis (PSO), and atopic dermatitis (AD) is demonstrated. Results showed that 10 s was consumed by the single shot multibox detector (SSD) model to analyze 292 test images, among which 273 images were correctly detected. Verification of ground truth samples of this research come from pathological tissue slices and OCT analysis. The SSD diagnosis accuracy rate was 93%. The sensitivity values of the SSD model in diagnosing the skin lesions according to the symptoms of PSO, AD, MF, and normal were 96%, 80%, 94%, and 95%, and the corresponding precision were 96%, 86%, 98%, and 90%. The highest sensitivity rate was found in MF probably because of the spread of cancer cells in the skin and relatively large lesions of MF. Many differences were found in the accuracy between AD and the other diseases. The collected AD images were all in the elbow or arm and other joints, the area with AD was small, and the features were not obvious. Hence, the proposed SSD could be used to identify the four diseases by using skin image detection, but the diagnosis of AD was relatively poor.

Endoscopic Images by a Single-Shot Multibox Detector for the Identification of Early Cancerous Lesions in the Esophagus: A Pilot Study.

Diagnosis of early esophageal neoplasia, including dysplasia and superficial cancer, is a great challenge for endoscopists. Recently, the application of artificial intelligence (AI) using deep learning in the endoscopic field has made significant advancements in diagnosing gastrointestinal cancers. In the present study, we constructed a single-shot multibox detector using a convolutional neural network for diagnosing different histological grades of esophageal neoplasms and evaluated the diagnostic accuracy of this computer-aided system. A total of 936 endoscopic images were used as training images, and these images included 498 white-light imaging (WLI) and 438 narrow-band imaging (NBI) images. The esophageal neoplasms were divided into three classifications: squamous low-grade dysplasia, squamous high-grade dysplasia, and squamous cell carcinoma, based on pathological diagnosis. This AI system analyzed 264 test images in 10 s, and the sensitivity, specificity, and diagnostic accuracy of this system in detecting esophageal neoplasms were 96.2%, 70.4%, and 90.9%, respectively. The accuracy of this AI system in differentiating the histological grade of esophageal neoplasms was 92%. Our system showed better accuracy in diagnosing NBI (95%) than WLI (89%) images. Our results showed the great potential of AI systems in identifying esophageal neoplasms as well as differentiating histological grades.

Reducing signal loss of the parahippocampal gyrus improves imaging of the default-mode network in 3.0-T MRI: the effect of susceptibility-induced field gradients.

Previous investigations have indicated that the default-mode network (DMN) is highly involved in memory processing in the parahippocampal gyrus (PHC). However, because of susceptibility-related signal loss, parahippocampal activation in the DMN is difficult to detect in resting-state functional MRI experiments that are conducted using a 3.0-T MRI scanner. This study investigated the magnetic field gradients of various brain regions and attempted to compensate for signal loss in the PHC using an optimized slice orientation. The field gradients, signal intensities and DMN functional connectivity (FC) of the PHC were investigated using datasets acquired from 18 healthy volunteers. The results show that the field gradient component parallel to the main magnetic field dominates the PHC. The results indicate that the signal intensities and FC of the DMN are significantly low in the PHC when the slice orientation of the imaging plane is transversal. Whether the voxel dimension is isotropic or anisotropic exerts a minimal effect in altering the slice orientation dependence. In conclusion, the results of this study support the selection of the coronal or sagittal planes for imaging of the DMN.

Resting-state functional magnetic resonance imaging: the impact of regression analysis.

PURPOSE: To investigate the impact of regression methods on resting-state functional magnetic resonance imaging (rsfMRI). During rsfMRI preprocessing, regression analysis is considered effective for reducing the interference of physiological noise on the signal time course. However, it is unclear whether the regression method benefits rsfMRI analysis. MATERIALS AND METHODS: Twenty volunteers (10 men and 10 women; aged 23.4 ± 1.5 years) participated in the experiments. We used node analysis and functional connectivity mapping to assess the brain default mode network by using five combinations of regression methods. RESULTS: The results show that regressing the global mean plays a major role in the preprocessing steps. When a global regression method is applied, the values of functional connectivity are significantly lower (P ≤ .01) than those calculated without a global regression. This step increases inter-subject variation and produces anticorrelated brain areas. CONCLUSION: rsfMRI data processed using regression should be interpreted carefully. The significance of the anticorrelated brain areas produced by global signal removal is unclear.

Automatic calibration of trigger delay time for cardiac MRI.

This study aimed to automatically identify the cardiac rest period using a rapid free-breathing (FB) calibration scanning procedure, and to determine the optimal trigger delay for cardiac imaging. A standard deviation (SD) method was used to rapidly identify cardiac quiescent phases employing multiphase cine cardiac images. The accuracy of this method was investigated using 46 datasets acquired from 22 healthy volunteers. The possibility of using a low-resolution FB method to rapidly acquire cine images was also evaluated. The reproducibility and accuracy of the trigger delay obtained using the rapid calibration scanning process were assessed before its application to a real-time feedback system. The real-time trigger delay calibration system was then used to perform T1 -weighted, short-axis imaging at the end of the cardiac systolic period. Linear regression analysis of the trigger times obtained using the SD method and a reference method indicated that the SD algorithm accurately identified the cardiac rest period (linear regression: slope = 0.94-1, R(2) = 0.68-0.84). Group analysis showed that the number of pixels in the left ventricular blood pool in images acquired at the end-systolic time calculated in real time was significantly lower than in those acquired 50 ms in advance or later (p < 0.01, paired t-test). The low-resolution FB imaging method was reproducible for the calibration scanning of an image in a vertical long-axis slice position (average SD of trigger times, 16-39 ms). Combined with rapid FB calibration scanning, the real-time feedback system accurately adjusted the trigger delay for T1 -weighted short-axis imaging. The real-time feedback method is rapid and reliable for trigger time calibration, and could facilitate cardiac imaging during routine examination.