Search

The identification of surface texture images from machining surfaces using image processing techniques has been a prominent research area in the recent decades. The aim of this paper is to identify various machined surface texture images using machine learning techniques. Charge coupled device is used to capture images of machined components. Based on captured images, twelve statistical features are extracted and feature vector is formed. Grey Level Co-occurrence Matrix is used to extract statistical features from the machined surface images. Four Machine learning algorithms such as Random Forest, Support Vector Machine, Artificial Neural Network and J48 were utilized to characterize machined surfaces. Training and Ten-fold cross validation process is utilized for identification of machined component images. It is found that Artificial Neural Network and Random forest give 100 % training accuracy and 99% cross validation accuracy. Results obtained demonstrate the efficiency of proposed methodology, which is useful for identifying texture images. more...

Abstract: A 70-year-old man who was scheduled for surgery because of the recurrence of gastric cancer was referred to our clinic preoperatively. The patient underwent a comprehensive evaluation through 18 F-FDG and 68 Ga-FAPI ( 68 Ga-labeled FAP inhibitors) PET/CT scans. The 68 Ga-FAPI PET/CT scan was particularly valuable in this case because of its ability to detect recurrent mass lesions and identify unusual metastatic sites compared with the 18 F-FDG PET/CT scan., (Copyright © 2024 Wolters Kluwer Health, Inc. All rights reserved.) more...

Abstract: A 60-year-old woman diagnosed with clear cell endometrial carcinoma received neoadjuvant chemotherapy. However, the patient was inoperable and referred to our clinic to evaluate the extent of the disease. The patient underwent 18FDG PET/CT and 68Ga-FAPI (fibroblast activated protein inhibitor)-04 PET/CT scans. 68Ga-FAPI-04 PET/CT outperformed 18FDG PET/CT demonstrating higher uptake in the metastatic lesions., Competing Interests: Conflicts of interest and sources of funding: none declared., (Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved.) more...

Purpose: Split renal function (SRF) can be measured by using several methods in 99m Tc-DMSA scintigraphy. Geometric mean (GM) based methods derived from planar images(2D) have been used for several years, besides; 3D-methods were also reported as an option for assessment of SRF. The purpose of this study to compare 2D and 3D methods for calculation of SRF in pediatric and adult patients., Methods: We evaluated 212 patients, underwent both planar and SPECT 99m Tc-DMSA scintigraphy.2D-SRFs were calculated by GM without background correction (SRFnobcg), GM with background correction in crescent formation from lower lateral borders (SRFcres), and GM with background correction in circumferential formation, including the whole kidney surroundings (SRFcirc). In 3D settings, SRF was measured with SPECT (SRFspect). Paired t-test was used to compare the mean SRFs of each group. Bland-Altman method was used as an agreement method for each method. Analyses were performed based on left kidney SRFs., Results: In comparison of 2D and 3D methods, SRFspect was significantly different from SRFnobcg and SRFcres (p=<0.001) but not from SRFcirc (p = 0.155) in all patients. Similar results were found for patients with high creatinine level, SRFcirc and SRFspect were not significantly different (p = 0.317), while significant differences were found between SRFspect and SRFnobcg/SRFcres (p=<0.001).On the other hand, all 2D-methods showed statistical differences (p=<0.001-0.026) from 3D-method in pediatric patients. Bland-Altman-plot demonstrated that SRFcirc underestimated the poor functioning kidneys., Conclusion: SRFcirc can be used in measurement of SRF in adult patients with normal functioning kidneys in busy clinics. However, SRFspect provides more accurate results and suggested particularly for pediatric patients and poor functioning kidneys., (Copyright © 2022 Associazione Italiana di Fisica Medica e Sanitaria. Published by Elsevier Ltd. All rights reserved.) more...

Abstract: 68Ga-Pentixafor is a novel radiotracer for imaging chemokine receptor subtype 4 (CXCR4) receptors, which are expressed exceptionally high in several hematologic malignancies, including various types of lymphoma. Herein we report a case of a 64-year-old man patient with suspected hematologic malignancy who underwent 18F-FDG and 68Ga-pentixafor PET/CT. Both scans demonstrated diffusely increased activity related to bone marrow involvement. 68Ga-Pentixafor PET/CT demonstrated CXCR4-expressing intra-abdominal lymph nodes that were not detected by 18F-FDG PET/CT. The patient was highly suspicious of lymphoma; however, histopathological examination of the bone marrow revealed systemic mastocytosis with associated myelofibrosis., Competing Interests: Conflicts of interest and sources of funding: none declared., (Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.) more...