Search

Background: This study aims to show the impact of imbalanced data and the typical evaluation methods in developing and misleading assessments of machine learning-based models for preoperative thyroid nodules screening. Study design: A retrospective study. Methods: The ultrasonography features for 431 thyroid nodules cases were extracted from medical records of 313 patients in Babol, Iran. Since thyroid nodules are commonly benign, the relevant data are usually unbalanced in classes. It can lead to the bias of learning models toward the majority class. To solve it, a hybrid resampling method called the Smote-was used to creating balance data. Following that, the support vector classification (SVC) algorithm was trained by balance and unbalanced datasets as Models 2 and 3, respectively, in Python language programming. Their performance was then compared with the logistic regression model as Model 1 that fitted traditionally. Results: The prevalence of malignant nodules was obtained at 14% (n = 61). In addition, 87% of the patients in this study were women. However, there was no difference in the prevalence of malignancy for gender. Furthermore, the accuracy, area under the curve, and geometric mean values were estimated at 92.1%, 93.2%, and 76.8% for Model 1, 91.3%, 93%, and 77.6% for Model 2, and finally, 91%, 92.6% and 84.2% for Model 3, respectively. Similarly, the results identified Micro calcification, Taller than wide shape, as well as lack of ISO and hyperechogenicity features as the most effective malignant variables. Conclusion: Paying attention to data challenges, such as data imbalances, and using proper criteria measures can improve the performance of machine learning models for preoperative thyroid nodules screening. [ABSTRACT FROM AUTHOR]

Background: When the first wave of COVID-19 outbreak occurred, the infrastructure for definitive detection of the disease through real-time polymerase chain reaction (RT-PCR) was not yet available in many regions, and a large proportion of suspected patients were inevitably referred to radiology centers to provide a chest CT scan. This research was conducted to describe chest CT characteristics in patients who underwent chest CT during the first weeks of COVID-19 outbreak in Babol, Iran. Methods: All non-hospitalized suspected COVID-19 patients referred to the state radiologic clinic to perform chest CT from March 8, 2020 to March 28, 2020 have been enrolled in this observational study. All CT scans were reviewed by a faculty member radiologist with approximately 20 years of experience. Results: Totally, 2,207 (52.3%) men and 2016 (47.7%) women have been examined. Imaging characteristics in 2292 (54.3%) individuals illustrated a highly suggestive sign of COVID-19 infection while 1869 (44.3%) had a normal chest CT scan. 1813 cases (77.00%) had bilateral involvement and 541 cases (23.00%) were infected unilaterally; Also, 1727 (73.36%) patients had left-sided involvement. Lung field involvement in 2036 (86.49%) patients was less than 20%. Ground glass opacity had a sensitivity, specificity, PPV, NPV, LR+ and LR- of 99%, 96%, 96%, 98%, 22 and 0.01, respectively, for categorization of a patient as a COVID-19 case. These values were 99%, 73%, 70%, 99%, 3.72% and 0.01%, respectively for consolidations. Conclusion: Although, RT-PCR is still introduced as the gold standard method for definite diagnosis, diagnostic accuracy of chest CT in COVID-19 detection is considerable. [ABSTRACT FROM AUTHOR]

Background: We aimed to compare the diagnostic accuracy of mammography and ultrasonography and their breast imaging-reporting and data system (BI-RADS) classification versus breast core needle biopsy (CNB) findings in distinguishing the breast masses. Methods: This cross-sectional study was conducted during 2016-2018 on female patients who were referred to a radiology center in Babol, northern Iran, for routine screening and/or for CNB. Patients underwent sonography and mammography by a senior radiologist. The breast lesions were also evaluated according to BI-RADS classification. CNB was performed on the breast masses by the same radiologist and pathological procedures were performed by an expert pathologist. Descriptive statistics were used to analyze the data. Results: In total, 213 breast masses were finally assessed, of which 107 (50.2 %) masses were benign and 106 (49.8 %) masses were malignant. The sensitivity for mammography and ultrasound alone was 72.6% and 68.9%, respectively. This rate for combined mammography and ultrasound was 84.9%. About BI-RADS classification, 28 masses were classified as BI-RADS 3, 99 as BI-RADS 4A, 4 as BI-RADS 4B, 18 as BI-RADS 4C, and 64 as BI-RADS 5. BI-RADS 4A had the highest sensitivity (70.1%) among BI-RADS categories. The highest specificity pertained to BI-RADS 3 and 5 (100%) among BI-RADS categories. Also, the highest accuracy was related to BI-RADS 5 (80.3%). Conclusion: The results of the present study showed that combined mammography and ultrasound had a higher rate of accuracy than mammography or ultrasound alone. Furthermore, the imaging methods BI-RADS classification had an acceptable positive predictive value. [ABSTRACT FROM AUTHOR]

Background: Computed tomography (CT) is a routine procedure for diagnosing using ionization radiation which has hazardous effects especially on sensitive organs. Objective: The aim of this study was to quantify the dose reduction effect of lead apron shielding on the testicular region during routine chest CT scans. Material and Methods: In this measurement study, the routine chest CT examinations were performed for 30 male patients with common lead aprons folded and positioned in testis regions. The patient's mean body mass index (BMI) was 26.2 ± 4.6 kg/m². To calculate the doses at testis region, three thermoluminescent dosimeters (TLD-100) were attached at the top surface of the apron as an indicator of the doses without shielding, and three TLDs under the apron for doses with shielding. The TLD readouts were compared using SPSS software (Wilcoxon test) version 16. Results: The radiation dose in the testicular regions was reduced from 0.46 ± 0.04 to 0.20 ± 0.04 mGy in the presence of lead apron shielding (p < 0.001), the reduction was equal to 56%. Furthermore, the heritable risk probability was obtained at 2.0 ×10-5 % and 4.6 ×10-5 % for the patients using the lead apron shield versus without shield, respectively. Conclusion: Applying common lead aprons as shielding in the testis regions of male patients undergoing chest CT scans can reduce the radiation doses significantly. Therefore, this shield can be recommended for routine chest CT examinations. [ABSTRACT FROM AUTHOR]

Purpose: To investigate the association of peripheral calcification, as well as its sonographic features, with thyroid nodule malignancy. Material and methods: This study was prospectively conducted during 2015-2020 on patients diagnosed with thyroid nodule undergoing ultrasound-guided fine-needle aspiration in Shahid Beheshti teaching hospital or private offices in Babol, northern Iran. The ultrasonographic characteristics of the nodules, as well as the cytological findings, were recorded. Regression analysis was used to assess the relationship between sonographic results and malignancy. We also used receiver operator characteristics (ROC) analysis to estimate the ability of ultrasound to predict the characteristic features of malignancy, as estimated by the area under the curve (AUC). Results: A total of 1857 thyroid nodules were finally included, of which 84 were peripherally calcified nodules. There was a significant positive association between the nodule malignancy and peripheral calcification (OR = 2.23, 95% CI: 1.13-4.35). In the nodules with peripheral calcification, significant positive associations were seen between malignancy and lobulated margin (OR = 3.85, 95% CI: 1.02-14.54) and solid composition (OR = 4.05, 95% CI: 0.99-16.53). The ROC analysis indicated that AUC for lobulated margin and solid composition was 63.8% and 66.5%, respectively, in predicting malignant thyroid nodules. Conclusion: The findings showed that peripheral calcification on sonography can be a potential indicator of malignant thyroid nodules. Also, the presence of lobulated margin and/or solid composition, besides peripheral calcification, can be helpful in better distinguishing malignant from benign nodules. [ABSTRACT FROM AUTHOR]

Introduction The main purpose of this study was to determine the diagnostic reference level (DRL) for routine digital radiography examinations in Mazandaran province. Materials and methods Thirteen digital radiographic examinations at 18 high-patient-load radiography centres were investigated. The indirect dosimetry method was performed based on the IAEA report. Average entrance skin dose (ESD) and the third quartile of ESD as the DRL were evaluated from the measurement made by a semiconductor dosemeter. Results DRL for the examinations of digital radiography was obtained as: Skull (postero-anterior [PA]): 2.2, skull (lateral [LAT]): 2.4, cervical spine (antero-posterior [AP]): 1.6, cervical spine (LAT): 1.7, thoracic spine (AP): 3.6, thoracic spine (LAT): 9.9, lumbar spine (AP): 5.3, lumbar spine (LAT): 11.8, chest (PA): 1.4, chest (LAT): 2.1, abdomen (AP): 4.3, pelvis (AP): 3.2 and hip (AP): 2.1 mGy. Conclusion Although DRL was not higher compared with the international organisations' levels, it can be reduced by adequate training of radiographers. [ABSTRACT FROM AUTHOR]

Background: Bladder cancer ranks ninth in world-wide cancer incidence and is 2.5-4 times more common in men, and painless gross hematuria is its typical clinical symptom. Cystoscopy is used to evaluate the cause of hematuria in bladder while the use and reliability of ultrasonography is questionable for this purpose. Therefore, the aim of this study was to compare abdominal ultrasonography and rigid cystoscopy in the diagnosis of bladder tumors in Babol Shahid Beheshti Hospital. Methods: In this cross-sectional study, 60 patients who were candidate for cystoscopy referred to Babol Shahid Beheshti Hospital in Iran in 2017-2018. In this study, rigid cystoscope was used to view the bladder after doing sonography. The numbers, demographic information (age, gender and residence) and clinical characteristics (indication of cystoscopy, history of chronic disease, sonographic and cystoscopic results) of patients were recorded in the checklist. Results: The mean age of patients (37 (61.7%)=males) was 58.65±14.26 (19-85) years and 48 (80%) of them were >50 years old. The sensitivity and specificity of sonography was 71.43 (95% CI: 29.4, 96.33) and 96.23% (95% CI: 87.02, 99.54) in detecting bladder tumors, respectively. The negative predictive and positive predictive values in sonography were 96.23 (95% CI: 88.76, 98.8) and 71.43% (95% CI: 37.25, 91.33) respectively. Conclusion: The results of this study indicate that since sonography has high negative predictive values in evaluating hematuria; therefore it can be replaced with rigid cystoscopy for patients with lower risk of malignancy. [ABSTRACT FROM AUTHOR]

Background and Objectives: Breast cancer is the most common malignancy among women in the world. The aim of this study was to assess estrogen receptor (ER), progesterone receptor (PR) and HER-2/neu of infiltrating ductal carcinoma (IDC) with tumor size, histologic grade, lymph node metastasis and age. Methods: This study was carried out on 300 tissue blocks of patients with IDC who underwent mastectomy from 2007 to 2011 in Shahid Beheshti Hospital, affiliated to Babol University of Medical Sciences, Babol, Iran. Data including age, tumor size, and histologic grade and lymph node status retrieved from pathology department. Result: The mean age of the patients was 40.2±2.3 (ranged 19-82 years). ER and PR were positively correlated with each other (P= 0.001) and they inversely correlated with HER-2/neu(P=0.001). We observed correlation between ER and PR expression and low histologic grade (P= 0.001) and HER-2/neu expression and high histologic grade (P= 0.003). There was correlation between HER-2/neu expression and lymph node involvement (P=0.03). None of these makers showed correlation with age and tumor size (P> 0.05). Conclusion: Our findings indicate the importance of ER, PR and HER-2/neu expression asprognostic factors for therapeutic decision. [ABSTRACT FROM AUTHOR]

Background: When the first wave of COVID-19 outbreak occurred, the infrastructure for definitive detection of the disease through real-time polymerase chain reaction (RT-PCR) was not yet available in many regions, and a large proportion of suspected patients were inevitably referred to radiology centers to provide a chest CT scan. This research was conducted to describe chest CT characteristics in patients who underwent chest CT during the first weeks of COVID-19 outbreak in Babol, Iran., Methods: All non-hospitalized suspected COVID-19 patients referred to the state radiologic clinic to perform chest CT from March 8, 2020 to March 28, 2020 have been enrolled in this observational study. All CT scans were reviewed by a faculty member radiologist with approximately 20 years of experience., Results: Totally, 2,207 (52.3%) men and 2016 (47.7%) women have been examined. Imaging characteristics in 2292 (54.3%) individuals illustrated a highly suggestive sign of COVID-19 infection while 1869 (44.3%) had a normal chest CT scan. 1813 cases (77.00%) had bilateral involvement and 541 cases (23.00%) were infected unilaterally; Also, 1727 (73.36%) patients had left-sided involvement. Lung field involvement in 2036 (86.49%) patients was less than 20%. Ground glass opacity had a sensitivity, specificity, PPV, NPV, LR+ and LR- of 99%, 96%, 96%, 98%, 22 and 0.01, respectively, for categorization of a patient as a COVID-19 case. These values were 99%, 73%, 70%, 99%, 3.72% and 0.01%, respectively for consolidations., Conclusion: Although, RT-PCR is still introduced as the gold standard method for definite diagnosis, diagnostic accuracy of chest CT in COVID-19 detection is considerable., Competing Interests: The authors declare that there is no conflict of interest.

Introduction: The main purpose of this study was to determine the diagnostic reference level (DRL) for routine digital radiography examinations in Mazandaran province., Materials and Methods: Thirteen digital radiographic examinations at 18 high-patient-load radiography centres were investigated. The indirect dosimetry method was performed based on the IAEA report. Average entrance skin dose (ESD) and the third quartile of ESD as the DRL were evaluated from the measurement made by a semiconductor dosemeter., Results: DRL for the examinations of digital radiography was obtained as: Skull (postero-anterior [PA]): 2.2, skull (lateral [LAT]): 2.4, cervical spine (antero-posterior [AP]): 1.6, cervical spine (LAT): 1.7, thoracic spine (AP): 3.6, thoracic spine (LAT): 9.9, lumbar spine (AP): 5.3, lumbar spine (LAT): 11.8, chest (PA): 1.4, chest (LAT): 2.1, abdomen (AP): 4.3, pelvis (AP): 3.2 and hip (AP): 2.1 mGy., Conclusion: Although DRL was not higher compared with the international organisations' levels, it can be reduced by adequate training of radiographers., (© The Author(s) 2020. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.)