Printability for additive manufacturing with machine learning: Hybrid intelligent Gaussian process surrogate-based neural network model for Co-Cr alloy.

AM has revolutionized the manufacturing industry, involving several operating parameters that may affect the properties of the final manufactured part. In AM, LPBF has proved its reliability in producing dense components; however, process development for every material necessitates extensive testing. Even the tiniest change can negate all the data for the same material. It is vital to have a P-P correlation that can train itself following a change in powder or machine to achieve defects-free parts and optimal properties. These goals cannot be met alone by multi-physics. One of the ways to address this issue is to apply ML, but it requires a huge data set for training and testing purposes. A framework has been developed for Co-Cr S-S curves to resolve this issue. Twenty-two experimental S-S curves have been generated to produce YS, TS, and EL data points. In combination with DNN, these data points have been applied to the validated and tested GPS-surrogate model to develop a smart processing window to achieve desired YS, TS, and EL. LP, LSS, HD, and PLT have been selected during the whole framework as inputs, while YS, TS, and EL have been classified as outputs. The output of the smart window was verified experimentally. It is found that the highest YS (1110.91 MPa) is attained using LP = 180 W, LSS = 600 mm/s and HD = 70 µm, while least YS (645.05 MPa) is identified using LP = 160 W, LSS = 900 mm/s and HD = 70 µm. For TS, the maximum (165.91 MPa) and minimum (689.73 MPa) values have been achieved using LP = 180 W, LSS = 900 mm/s and HD = 70 µm, and LP = 180 W, LSS = 1000 mm/s and HD = 70 µm, respectively. In the case of EL, LP = 180 W, LSS = 700 mm/s and HD = 70 µm, and LP = 180 W, LSS = 600 mm/s and HD = 70 µm, resulted 23.04% and 0.789% EL, respectively. Using CC, LP and HD did not significantly affect the TS, YS, and EL, while a negative relationship has been found for LSS with TS, YS, and EL. The smart processing window showed that the YS and TS could be achieved at low-high LP and low LSS at the cost of EL. This study provides a technique for framework development in the case of P-P relation based on the provided inputs and the corresponding outputs, leading toward process smartification.

Assessment of total placenta previa by magnetic resonance imaging and ultrasonography to detect placenta accreta and its variants.

OBJECTIVE: To evaluate the importance of ultrasonography (US) and magnetic resonance imaging (MRI) in detecting placental adherence defects. MATERIAL AND METHODS: Patients diagnozed with total placenta previa (n = 40) in whom hysterectomy was performed due to placental adherence defects (n = 20) or in whom the placenta detached spontaneously after a Cesarean delivery (n = 20) were included into the study between June 2008 and January 2011, at the Department of Obstetrics and Gynecology Ege University (lzmir Turkey). Gray-scale US was used to check for any placental lacunae, sub-placental sonolucent spaces or a placental mass invading the vesicouterine plane and bladder Intra-placental lacunar turbulent blood flow and an increase in vascularization in the vesicouterine plane were evaluated with color Doppler mode. Subsequently all patients had MRI and the results were compared with the histopathologic examinations. RESULTS: The sensitivity of MRI for diagnosis of placental adherence defects before the operation was 95%, with a specificity of 95%. In the presence of at least one diagnostic criterion, the sensitivity and specificity of US were 87.5% and 100% respectively, while the sensitivity of color Doppler US was 62.5% with a specificity of 100%. CONCLUSIONS: Currently MRI appears to be the gold standard for the diagnosis of placenta accreta. None of the ultrasonographic criteria is solely sufficient to diagnose placental adherence defects, however they assist in the diagnostic process.

Role of contrast-enhanced 3D magnetic resonance portography in evaluating portal venous system compared with color Doppler ultrasonography.

AIM: The purpose of this study was to evaluate the capability of contrast-enhanced three-dimensional (3D) MR portography in detecting abnormal findings associated with the portal venous system compared with the results of color Doppler ultrasonography (CDUS). MATERIALS AND METHODS: MR portography findings were retrospectively compared with the results of CDUS examinations in 161 patients, who were suspected of having portal venous system abnormalities. Portal venous vessels were divided into main 5 groups including the main portal vein, its left and right intrahepatic branches, splenic vein and superior mesenteric vein. Imaging findings were classified as normal, occluded, or partially thrombosed. Results of clinical and imaging follow-up examinations including CDUS, MR portography or angiography, if available, were used as a proof of final diagnosis. The potential sites of varicose veins and collateral vessels were also examined by both imaging methods. RESULTS: Vascular abnormalities were identified in 79 of 161 patients. There was a statistically significant agreement between the results of MR portography and CDUS in evaluating portal venous system (kappa = 0.871, P < 0.05). The sensitivity of MR portography was slightly superior to CDUS in detecting partially thrombosis and occlusion in the main portal venous vessels. In addition, MR portograms were superior to CDUS in the management of patients with portal hypertension by identifying portosystemic collaterals more adequately, and clearly demonstrated portal venous vessels that cannot be visualized at CDUS. CONCLUSION: Results of present study indicates that contrast-enhanced 3D MR portography is well suited and superior to CDUS in the management of patients with portal hypertension.

Hydatid disease involving some rare locations in the body: a pictorial essay.

Hydatid disease (HD) is an endemic illness in many countries, and it poses an important public health problem that's influenced by peoples' socioeconomic status and migration that spreads this disease. Although rare, it may occur in any organ or tissue. The most common site is the liver (59-75%), followed in frequency by lung (27%), kidney (3%), bone (1-4%) and brain (1-2%). Other sites such as the heart, spleen, pancreas and muscles are very rarely affected. Unusual sites for this disease can cause diagnostic problems. This pictorial essay illustrates various radiological findings of HD in the liver, spleen, kidney, pancreas, peritoneal cavity, omentum, adrenal, ovary, lung, mediastinum and retroperitoneum. Familiarity with the imaging findings of HD may be helpful in making an accurate diagnosis and preventing potential complications.

CT findings of abdominal tuberculosis in 12 patients.

Our purpose was to evaluate the Computed Tomography (CT) findings of the abdominal tuberculosis (TBC) retrospectively which was diagnosed histopatologically. This study included 12 patients. All patients were evaluated by abdominal CT study. Most findings of CT studies were mesenteric calcified or noncalcified lymphadenopathies, ascites, thickened intestinal wall located on the right lower quadrant of abdomen, thickening of peritoneum, mottled soft-tissue densities in omentum and mesenterium. In addition, one of the patients had bilateral calcified adrenal glands and one of them had calcified mass in adrenal gland. If peritoneal thickening, ascites, abdominal lymphadenophaties and thickened intestinal walls are obtained, TBC should be considered in differential diagnosis in developing countries.