PurposeTo show that a deep learning (DL)–based, automated model for Lipiodol (Guerbet Pharmaceuticals, Paris, France) segmentation on cone-beam computed tomography (CT) after conventional transarterial chemoembolization performs closer to the “ground truth segmentation” than a conventional thresholding-based model.Materials and MethodsThis post hoc analysis included 36 patients with a diagnosis of hepatocellular carcinoma or other solid liver tumors who underwent conventional transarterial chemoembolization with an intraprocedural cone-beam CT. Semiautomatic segmentation of Lipiodol was obtained. Subsequently, a convolutional U-net model was used to output a binary mask that predicted Lipiodol deposition. A threshold value of signal intensity on cone-beam CT was used to obtain a Lipiodol mask for comparison. The dice similarity coefficient (DSC), mean squared error (MSE), center of mass (CM), and fractional volume ratios for both masks were obtained by comparing them to the ground truth (radiologist-segmented Lipiodol deposits) to obtain accuracy metrics for the 2 masks. These results were used to compare the model versus the threshold technique.ResultsFor all metrics, the U-net outperformed the threshold technique: DSC (0.65 ± 0.17 vs 0.45 ± 0.22, P < .001) and MSE (125.53 ± 107.36 vs 185.98 ± 93.82, P = .005). The difference between the CM predicted and the actual CM was 15.31 mm ± 14.63 versus 31.34 mm ± 30.24 (P < .001), with lesser distance indicating higher accuracy. The fraction of volume present ([predicted Lipiodol volume]/[ground truth Lipiodol volume]) was 1.22 ± 0.84 versus 2.58 ± 3.52 (P = .048) for the current model’s prediction and threshold technique, respectively.ConclusionsThis study showed that a DL framework could detect Lipiodol in cone-beam CT imaging and was capable of outperforming the conventionally used thresholding technique over several metrics. Further optimization will allow for more accurate, quantitative predictions of Lipiodol depositions intraprocedurally. 相似文献
Partial differential equations (PDEs) play a dominant role in the mathematical modeling of many complex dynamical processes. Solving these PDEs often requires
prohibitively high computational costs, especially when multiple evaluations must be
made for different parameters or conditions. After training, neural operators can provide PDEs solutions significantly faster than traditional PDE solvers. In this work,
invariance properties and computational complexity of two neural operators are examined for transport PDE of a scalar quantity. Neural operator based on graph kernel network (GKN) operates on graph-structured data to incorporate nonlocal dependencies.
Here we propose a modified formulation of GKN to achieve frame invariance. Vector
cloud neural network (VCNN) is an alternate neural operator with embedded frame
invariance which operates on point cloud data. GKN-based neural operator demonstrates slightly better predictive performance compared to VCNN. However, GKN requires an excessively high computational cost that increases quadratically with the
increasing number of discretized objects as compared to a linear increase for VCNN. 相似文献
Objective: The main pathological change of Parkinson’s disease (PD) is progressive degeneration and necrosis of dopaminergic neurons in the midbrain, forming a Lewy body in many of the remaining neurons. Studies have found that in transgenic Drosophila, mutations in the PTEN-inducible kinase 1 (PINK1) gene may cause indirect flight muscle defects in Drosophila, and mitochondrial structural dysfunction as well.
Methods: In this study, Wnt4 gene overexpression and knockdown were performed in PINK1 mutant PD transgenic Drosophila, and the protective effect of Wnt4 gene on PD transgenic Drosophila and its possible mechanism were explored. The Wnt4 gene was screened in the previous experiment; And by using the PD transgenic Drosophila model of the MHC-Gal4/UAS system, the PINK1 gene could be specifically activated in the Drosophila muscle tissue.
Results: In PINK1 mutation transgenic fruit flies, the Wnt4 gene to study its implication on PD transgenic fruit flies’ wing normality and flight ability. We found that overexpression of Wnt4 gene significantly reduced abnormality rate of PD transgenic Drosophila and improved its flight ability, and then, increased ATP concentration, enhanced mitochondrial membrane potential and normalized mitochondrial morphology were found. All of these findings suggested Wnt4 gene may have a protective effect on PD transgenic fruit flies. Furthermore, in Wnt4 gene overexpression PD transgenic Drosophila, down-regulation autophagy and apoptosis-related proteins Ref(2)P, Pro-Caspase3, and up-regulation of Beclin1, Atg8a, Bcl2 protein were confirmed by Western Blotting.
Conclusion: The results imply that the restoring of mitochondrial function though Wnt4 gene overexpression in the PINK1 mutant transgenic Drosophila may be related to autophagy and/or apoptosis. 相似文献