Surgical Second Opinion for Pancreatic Cancer Patients.

Background: Due to the complexity of pancreatic surgery, patients diagnosed with pancreatic ductal adenocarcinoma (PDAC) may seek out the opinion of more than one surgeon. Little is known regarding how second surgical opinions impact the likelihood of pancreatectomy and perioperative outcomes. Our study aimed to determine the impact of obtaining second surgical opinions on pancreatectomy rates and to assess its impact on surgical outcomes.

Unsupervised learning-enabled pulsed infrared thermographic microscopy of subsurface defects in stainless steel.

Metallic structures produced with laser powder bed fusion (LPBF) additive manufacturing method (AM) frequently contain microscopic porosity defects, with typical approximate size distribution from one to 100 microns. Presence of such defects could lead to premature failure of the structure. In principle, structural integrity assessment of LPBF metals can be accomplished with nondestructive evaluation (NDE).

The shirker's dilemma and the prospect of cooperation in large groups.

Cooperation usually becomes harder to sustain as groups become larger because incentives to shirk increase with the number of potential contributors to collective action. But is this always the case? Here we study a binary-action cooperative dilemma where a public good is provided as long as not more than a given number of players shirk from a costly cooperative task. We find that at the stable polymorphic equilibrium, which exists when the cost of cooperation is low enough, the probability of cooperating increases with group size and reaches a limit of one when the group size tends to infinity.

Multi-Task Learning of Scanning Electron Microscopy and Synthetic Thermal Tomography Images for Detection of Defects in Additively Manufactured Metals.

One of the key challenges in laser powder bed fusion (LPBF) additive manufacturing of metals is the appearance of microscopic pores in 3D-printed metallic structures. Quality control in LPBF can be accomplished with non-destructive imaging of the actual 3D-printed structures. Thermal tomography (TT) is a promising non-contact, non-destructive imaging method, which allows for the visualization of subsurface defects in arbitrary-sized metallic structures.

Physics-informed neural network with transfer learning (TL-PINN) based on domain similarity measure for prediction of nuclear reactor transients.

Nuclear reactor safety and efficiency can be enhanced through the development of accurate and fast methods for prediction of reactor transient (RT) states. Physics informed neural networks (PINNs) leverage deep learning methods to provide an alternative approach to RT modeling. Applications of PINNs in monitoring of RTs for operator support requires near real-time model performance.