Browsing by Author "Kovac, Jelena (52563972900)"

Background: This study analyzed different classifier models for differentiating pancreatic adenocarcinoma from surrounding healthy pancreatic tissue based on radiomic analysis of magnetic resonance (MR) images. Methods: We observed T2W-FS and ADC images obtained by 1.5T-MR of 87 patients with histologically proven pancreatic adenocarcinoma for training and validation purposes and then tested the most accurate predictive models that were obtained on another group of 58 patients. The tumor and surrounding pancreatic tissue were segmented on three consecutive slices, with the largest area of interest (ROI) of tumor marked using MaZda v4.6 software. This resulted in a total of 261 ROIs for each of the observed tissue classes in the training–validation group and 174 ROIs in the testing group. The software extracted a total of 304 radiomic features for each ROI, divided into six categories. The analysis was conducted through six different classifier models with six different feature reduction methods and five-fold subject-wise cross-validation. Results: In-depth analysis shows that the best results were obtained with the Random Forest (RF) classifier with feature reduction based on the Mutual Information score (all nine features are from the co-occurrence matrix): an accuracy of 0.94/0.98, sensitivity of 0.94/0.98, specificity of 0.94/0.98, and F1-score of 0.94/0.98 were achieved for the T2W-FS/ADC images from the validation group, retrospectively. In the testing group, an accuracy of 0.69/0.81, sensitivity of 0.86/0.82, specificity of 0.52/0.70, and F1-score of 0.74/0.83 were achieved for the T2W-FS/ADC images, retrospectively. Conclusions: The machine learning approach using radiomics features extracted from T2W-FS and ADC achieved a relatively high sensitivity in the differentiation of pancreatic adenocarcinoma from healthy pancreatic tissue, which could be especially applicable for screening purposes. © 2025 by the authors.

Background: This study analyzed different classifier models for differentiating pancreatic adenocarcinoma from surrounding healthy pancreatic tissue based on radiomic analysis of magnetic resonance (MR) images. Methods: We observed T2W-FS and ADC images obtained by 1.5T-MR of 87 patients with histologically proven pancreatic adenocarcinoma for training and validation purposes and then tested the most accurate predictive models that were obtained on another group of 58 patients. The tumor and surrounding pancreatic tissue were segmented on three consecutive slices, with the largest area of interest (ROI) of tumor marked using MaZda v4.6 software. This resulted in a total of 261 ROIs for each of the observed tissue classes in the training–validation group and 174 ROIs in the testing group. The software extracted a total of 304 radiomic features for each ROI, divided into six categories. The analysis was conducted through six different classifier models with six different feature reduction methods and five-fold subject-wise cross-validation. Results: In-depth analysis shows that the best results were obtained with the Random Forest (RF) classifier with feature reduction based on the Mutual Information score (all nine features are from the co-occurrence matrix): an accuracy of 0.94/0.98, sensitivity of 0.94/0.98, specificity of 0.94/0.98, and F1-score of 0.94/0.98 were achieved for the T2W-FS/ADC images from the validation group, retrospectively. In the testing group, an accuracy of 0.69/0.81, sensitivity of 0.86/0.82, specificity of 0.52/0.70, and F1-score of 0.74/0.83 were achieved for the T2W-FS/ADC images, retrospectively. Conclusions: The machine learning approach using radiomics features extracted from T2W-FS and ADC achieved a relatively high sensitivity in the differentiation of pancreatic adenocarcinoma from healthy pancreatic tissue, which could be especially applicable for screening purposes. © 2025 by the authors.

[No abstract available]

Objective: The purpose of this study was to evaluate whether magnetic resonance (MR) imaging can accurately predict invasion of the preepiglottic and paraglottic space in patients with laryngeal carcinoma. Identification of these fat filling spaces is important for surgical treatment and prognosis. Materials and methods: The study was based on the prospective analysis of MRI images in a series of 40 patients (90% males), overall average age 60.1 ± 7.3 years, (49-70 years), with histopathologically diagnosed laryngeal squamous cell carcinoma. Unenhanced T2w, T2w FS, T1w, and contrast-enhanced T1w FS scans were analyzed for the presence of preepiglottic and paraglottic neoplastic invasion and were compared to postoperative histopathologic analysis. Results: In 28 patients (70%) the tumor was glottic and in 12 patients (30%) supraglottic. No statistical difference was found in the number of patients with positive MRI findings in comparison to postsurgical patohistology for infiltration of the preepiglottic space (23% vs 20%, respectively). Sensitivity for infiltration of preepiglottic space was 89% and specificity was 97%. However, infiltration of the paraglottic spaces was observed more frequently on MRI than on postsurgical patohistology analysis (60% vs 40%, respectively; p< 0.05), with a sensitivity of 67% and a specificity 50%. According to MRI findings, 26 (65%) patients were classified as T3, 14 (35%) patients as T2 while according to histopathologic analysis of specimens after surgery, 19 patients were classified as T3 (48%) and 21 as T2 (52%). Conclusion: MRI has been shown to be a reliable method for assessment of preepiglottic space while the diagnostic accuracy in patients with infiltration of the paraglottic space is limited. © 2014 Elsevier Ireland Ltd.

Isolated hydatid cysts of the pancreas are rare lesions, even in endemic regions. In this report, we present the case of a 76-year-old patient who was admitted to our clinic with a diagnosis of a cystic lesion in the tail of the pancreas. On preoperative computed tomography (CT) and magnetic resonance (MR) examination, the cyst was characterized as a mucinous cystadenoma. A laparoscopic distal pancreatectomy followed. A histopathological examination revealed a large hydatid cyst in the tail of the pancreas. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.

Background: The objective of this study is to determine the morphological computed tomography features of the tumor and texture analysis parameters, which may be a useful diagnostic tool for the preoperative prediction of high-risk gastrointestinal stromal tumors (HR GISTs). Methods: This is a prospective cohort study that was carried out in the period from 2019 to 2022. The study included 79 patients who underwent CT examination, texture analysis, surgical resection of a lesion that was suspicious for GIST as well as pathohistological and immunohistochemical analysis. Results: Textural analysis pointed out min norm (p = 0.032) as a histogram parameter that significantly differed between HR and LR GISTs, while min norm (p = 0.007), skewness (p = 0.035) and kurtosis (p = 0.003) showed significant differences between high-grade and low-grade tumors. Univariate regression analysis identified tumor diameter, margin appearance, growth pattern, lesion shape, structure, mucosal continuity, enlarged peri- and intra-tumoral feeding or draining vessel (EFDV) and max norm as significant predictive factors for HR GISTs. Interrupted mucosa (p < 0.001) and presence of EFDV (p < 0.001) were obtained by multivariate regression analysis as independent predictive factors of high-risk GISTs with an AUC of 0.878 (CI: 0.797–0.959), sensitivity of 94%, specificity of 77% and accuracy of 88%. Conclusion: This result shows that morphological CT features of GIST are of great importance in the prediction of non-invasive preoperative metastatic risk. The incorporation of texture analysis into basic imaging protocols may further improve the preoperative assessment of risk stratification. © 2023 by the authors.

Background: The objective of this study is to determine the morphological computed tomography features of the tumor and texture analysis parameters, which may be a useful diagnostic tool for the preoperative prediction of high-risk gastrointestinal stromal tumors (HR GISTs). Methods: This is a prospective cohort study that was carried out in the period from 2019 to 2022. The study included 79 patients who underwent CT examination, texture analysis, surgical resection of a lesion that was suspicious for GIST as well as pathohistological and immunohistochemical analysis. Results: Textural analysis pointed out min norm (p = 0.032) as a histogram parameter that significantly differed between HR and LR GISTs, while min norm (p = 0.007), skewness (p = 0.035) and kurtosis (p = 0.003) showed significant differences between high-grade and low-grade tumors. Univariate regression analysis identified tumor diameter, margin appearance, growth pattern, lesion shape, structure, mucosal continuity, enlarged peri- and intra-tumoral feeding or draining vessel (EFDV) and max norm as significant predictive factors for HR GISTs. Interrupted mucosa (p < 0.001) and presence of EFDV (p < 0.001) were obtained by multivariate regression analysis as independent predictive factors of high-risk GISTs with an AUC of 0.878 (CI: 0.797–0.959), sensitivity of 94%, specificity of 77% and accuracy of 88%. Conclusion: This result shows that morphological CT features of GIST are of great importance in the prediction of non-invasive preoperative metastatic risk. The incorporation of texture analysis into basic imaging protocols may further improve the preoperative assessment of risk stratification. © 2023 by the authors.

Background: We compare the health-related quality of life (QoL) of patients with incision hernias before and after surgery with two different techniques. Methods: In this prospective randomized study, the study population consisted of all patients who underwent the first surgical incisional hernias repair during the 1-year study period. Patients who met the criteria for inclusion in the study were randomized into two groups: the first group consisted of patients operated by an open Rives sublay technique, and the second group included patients operated by a segregation component technique. The change in the quality of life before and 6 months after surgery was assessed using two general (Short form of SF-36 questionnaires and European Quality of Life Questionnaire—EQ-5D-3L), and three specific hernia questionnaires (Hernia Related Quality of Life Survey-HerQles, Eura HS Quality of Life Scale—EuraHS QoL, and Carolinas Comfort Scale—CCS). Results: A total of 93 patients were included in the study. Patients operated on by the Rives technique had a better role physical score before surgery, according to the SF-36 tool, although this was not found after surgery. The postoperative QoL measured with each scale of all questionnaires was significantly better after surgery. Comparing two groups of patients after surgery, only the pain domain of the EuraHS Qol questionnaire was worse in patients operated by a segregation component technique. Conclusion: Both techniques improve the quality of life after surgery. Generic QoL questionnaires showed no difference in the quality of life compared to repair technique but specific hernia-related questionnaires showed differences. © 2022, The Author(s).

Pancreatic pseudoaneurysm is a rare but life-threatening clinical entity. In this paper, we present a case of a 74-year-old man, who was admitted to our clinic with a diagnosis of an acute on chronic pancreatitis complicated by walled-off-pancreatic-necrosis, with subsequent development of peripancreatic pseudoaneurysm. After initial conservative management, the patient recovered and was discharged from the hospital. However, he soon returned feeling anxious due to a pulsatile abdominal mass. Abdominal Color–Doppler examination, CT scan, and angiography revealed large pancreatic necrotic collection in the total size of 9 cm, with centrally enhancing area of 3.5 cm that corresponded to pseudoaneurysm originating from the posterior pancreaticoduodenal vascular arcade. Considering the size, location of the pseudoaneurysm, feeding vessel, and poor general patients condition, we opted for minimally invasive treatment. Pseudoaneurysm was successfully managed by endovascular coil embolization, i.e., “sandwich technique”. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.