Background: Detection of malignant liver mass is very important for the treatment modalities. Objective: The purpose of the present study was to establish the usefulness of CT scan in the diagnosis of malignant hepati...Background: Detection of malignant liver mass is very important for the treatment modalities. Objective: The purpose of the present study was to establish the usefulness of CT scan in the diagnosis of malignant hepatic mass. Methodology: This cross sectional study was carried out in the Department of Radiology and Imaging at Mymensingh Medical College Hospital (MMCH), Mymensingh, Banghabandhu Sheikh Mujib Medical University (BSMMU), Dhaka and Dhaka Medical College Hospital (DMCH), Dhaka during the period of 1st January 2006 to 31st December 2007. Patients admitted in the Department of Medicine and Department of Hepatobiliary of MMCH, BSMMU, and DMCH with the clinical diagnosis of fever, abdominal pain, anorexia, nausea/vomiting, loss of appetite, jaundice, weight loss and ascites were selected as study population. CT scan and histopathology were performed to all the patients. Result: A total number of 50 patients were recruited for this study. Mean age of all patients was 51.28 ± 14 years with a range of 17 year to 78 years. Among all patients 28 had multiple lesion, of them 71.4% was malignant and 28.6% was benign. On the other side 22 patients had solitary lesion, of them 36.4% was malignant and 63.6% was benign展开更多
In recent days,Deep Learning(DL)techniques have become an emerging transformation in the field of machine learning,artificial intelligence,computer vision,and so on.Subsequently,researchers and industries have been hi...In recent days,Deep Learning(DL)techniques have become an emerging transformation in the field of machine learning,artificial intelligence,computer vision,and so on.Subsequently,researchers and industries have been highly endorsed in the medical field,predicting and controlling diverse diseases at specific intervals.Liver tumor prediction is a vital chore in analyzing and treating liver diseases.This paper proposes a novel approach for predicting liver tumors using Convolutional Neural Networks(CNN)and a depth-based variant search algorithm with advanced attention mechanisms(CNN-DS-AM).The proposed work aims to improve accuracy and robustness in diagnosing and treating liver diseases.The anticipated model is assessed on a Computed Tomography(CT)scan dataset containing both benign and malignant liver tumors.The proposed approach achieved high accuracy in predicting liver tumors,outperforming other state-of-the-art methods.Additionally,advanced attention mechanisms were incorporated into the CNN model to enable the identification and highlighting of regions of the CT scans most relevant to predicting liver tumors.The results suggest that incorporating attention mechanisms and a depth-based variant search algorithm into the CNN model is a promising approach for improving the accuracy and robustness of liver tumor prediction.It can assist radiologists in their diagnosis and treatment planning.The proposed system achieved a high accuracy of 95.5%in predicting liver tumors,outperforming other state-of-the-art methods.展开更多
Purpose:Abdominal CT scan using oral and intravenous(IV)contrast is helpful in the diagnosis of intra-abdominal injuries.However,the use of oral and IV contrast delays the process of diagnosis and increases the risk o...Purpose:Abdominal CT scan using oral and intravenous(IV)contrast is helpful in the diagnosis of intra-abdominal injuries.However,the use of oral and IV contrast delays the process of diagnosis and increases the risk of aspiration.It has also been shown that CT scan with IV contrast alone is as helpful as CT scan with oral and IV contrast and rectal CT scan in detecting abdominal injuries.Therefore,the present study aims to prospectively compare the diagnostic value of CT scan with oral and IV contrast versus CT scan with IV contrast alone in the diagnosis of blunt abdominal trauma(BAT).Methods:Altogether 123 BAT patients,60(48.8%)women and 63(51.2%)men with the mean age of(40.4±18.7)years who referred to the emergency department of Imam Khomeini Educational and Medical Center in Sari,Iran(a tertiary trauma center in north of Iran)from November 2014 to March 2017 and underwent abdominal CT scans+laparotomy were investigated.Those with penetrating trauma or hemodynamically unstable patients were excluded.The participants were randomly allocated to two groups:abdominal CT scan with oral and IV contrast(n=63)and CT scan with IV contrast alone(n=60).No statistically significant difference was found between two groups regarding the hemodynamic parameters,age,gender,injury mechanisms(all p>0.05).The results of CT scan were compared with that of laparotomy results.The collected data were recorded in SPSS version 22.0 for Windows.Quantitative data were presented as mean and SD.Results:The sensitivity and specificity of CT scan using oral and IV contrast in the diagnosis of BAT were estimated at 96.48(95%CI:90.73-99.92)and 92.67(95% CI:89.65-94.88),respectively;while CT scan with IV contrast alone achieved a comparable sensitivity and specificity of 96.6(95% CI:87.45-99),42 and 92.84(95% CI:89.88-95.00),respectively.Conclusion:CT scan with IV contrast alone can be used to assess visceral injuries in BAT patients with normal hemodynamics to avoid diagnostic delay.展开更多
Background: Maxillofacial trauma affects young adults more. The injury assessment is difficult to establish in low-income countries because of the imaging means, particularly the scanner, which is poorly available and...Background: Maxillofacial trauma affects young adults more. The injury assessment is difficult to establish in low-income countries because of the imaging means, particularly the scanner, which is poorly available and less financially accessible. The aim of this study is to describe the epidemiological profile and the various tomodensitometric aspects of traumatic lesions of the face in patients received in the Radiology department of Kira Hospital. Patients and methods: This is a descriptive retrospective study involving 104 patients of all ages over a period of 2 years from December 2018 to November 2019 in the medical imaging department of KIRA HOSPITAL. We included in our study any patient having undergone a CT scan of the head and presenting at least one lesion of the facial mass, whether associated with other cranioencephalic lesions. Results: Among the 384 patients received for head trauma, 104 patients (27.1% of cases) presented facial damage. The average age of our patients was 32.02 years with extremes of 8 months and 79 years. In our study, 87 of the patients (83.6%) were male. The road accident was the circumstance in which facial trauma occurred in 79 patients (76% of cases). These injuries were accompanied by at least one bone fracture in 97 patients (93.3%). Patients with fractures of more than 3 facial bones accounted for 40.2% of cases and those with fractures of 2 to 3 bones accounted for 44.6% of cases. The midface was the site of the fracture in 85 patients (87.6% of cases). Orbital wall fractures were noted in 57 patients (58.8% of cases) and the jawbone was the site of a fracture in 50 patients (51.5% of cases). In the vault, the fractures involved the extra-facial frontal bone (36.1% of cases) and temporal bone (18.6% of cases). Cerebral contusion was noted in 41.2% of patients and pneumoencephaly in 15.5% of patients. Extradural hematoma was present in 16 patients and subdural hematoma affected 13 patients. Conclusion: Computed tomography is a diagnostic tool of choice in facial trauma patients. Most of these young patients present with multiple fractures localizing to the mid-level of the face with concomitant involvement of the brain.展开更多
目的观察肝硬化(HC)合并原发性肝癌(PLC)患者CT动态增强扫描变化,分析其诊断价值。方法回顾性分析2020年4月—2022年7月我院125例HC患者资料,所有受试者均行病理组织学检测及CT动态增强扫描,统计所有患者病灶大小及分布情况,CT动态增强...目的观察肝硬化(HC)合并原发性肝癌(PLC)患者CT动态增强扫描变化,分析其诊断价值。方法回顾性分析2020年4月—2022年7月我院125例HC患者资料,所有受试者均行病理组织学检测及CT动态增强扫描,统计所有患者病灶大小及分布情况,CT动态增强扫描动脉期、静脉期、延迟期病灶检出情况,以病理检查为金标准,分析CT动态增强扫描对HC患者PLC的诊断价值、HC患者与HC并PLC患者血流灌注参数大小及不同肝功能CTP分级下血流灌注参数变化。结果125例HC患者共检出161个病灶,其中直径<1 cm 8个,1~3 cm 53个,4~5 cm 63个,>5 cm 37个,肝右前叶、肝右后叶者居多,分别为45及69个;CT动态增强扫描动脉期检出病灶149个,检出率92.55%;门脉期检出病灶134个,检出率83.23%;延迟期检出病灶142个,检出率88.20%;125例HC患者中病理学检查显示75例PLC阳性,50例PLC阴性,CT动态增强扫检测HC并PLC的敏感度为94.67%,特异度为94.00%,准确率为94.40%,阳性预测值为95.95%,阴性预测值为92.16%,Kappa值为0.884,具有较高的一致性;HC组HAP、HPI值均显著低于HC并PLC组,PVP、TLP值均显著高于HC并PLC组(P<0.05);125例HC并PLC患者中CTP A级41例,CTP B级46例,CTP C级38例,CTP A级HAP、HPI值显著低于CTP B、C级(P<0.05),PVP、TLP值均显著高于CTP B、C级(P<0.05),CTP B级HPI值与CTP C级比较,差异均无统计学意义(P>0.05)。结论CT动态增强扫描可多方位多角度显示HC病灶情况,且对PLC具有较好的诊断价值,其中肝脏血流灌注参数具有一定的特征性,可为PLC诊断和肝功能分级提供参考。展开更多
One of the leading causes of mortality worldwide is liver cancer.The earlier the detection of hepatic tumors,the lower the mortality rate.This paper introduces a computer-aided diagnosis system to extract hepatic tumo...One of the leading causes of mortality worldwide is liver cancer.The earlier the detection of hepatic tumors,the lower the mortality rate.This paper introduces a computer-aided diagnosis system to extract hepatic tumors from computed tomography scans and classify them into malignant or benign tumors.Segmenting hepatic tumors from computed tomography scans is considered a challenging task due to the fuzziness in the liver pixel range,intensity values overlap between the liver and neighboring organs,high noise from computed tomography scanner,and large variance in tumors shapes.The proposed method consists of three main stages;liver segmentation using Fast Generalized Fuzzy C-Means,tumor segmentation using dynamic thresholding,and the tumor’s classification into malignant/benign using support vector machines classifier.The performance of the proposed system was evaluated using three liver benchmark datasets,which are MICCAI-Sliver07,LiTS17,and 3Dircadb.The proposed computer adided diagnosis system achieved an average accuracy of 96.75%,sensetivity of 96.38%,specificity of 95.20%and Dice similarity coefficient of 95.13%.展开更多
文摘Background: Detection of malignant liver mass is very important for the treatment modalities. Objective: The purpose of the present study was to establish the usefulness of CT scan in the diagnosis of malignant hepatic mass. Methodology: This cross sectional study was carried out in the Department of Radiology and Imaging at Mymensingh Medical College Hospital (MMCH), Mymensingh, Banghabandhu Sheikh Mujib Medical University (BSMMU), Dhaka and Dhaka Medical College Hospital (DMCH), Dhaka during the period of 1st January 2006 to 31st December 2007. Patients admitted in the Department of Medicine and Department of Hepatobiliary of MMCH, BSMMU, and DMCH with the clinical diagnosis of fever, abdominal pain, anorexia, nausea/vomiting, loss of appetite, jaundice, weight loss and ascites were selected as study population. CT scan and histopathology were performed to all the patients. Result: A total number of 50 patients were recruited for this study. Mean age of all patients was 51.28 ± 14 years with a range of 17 year to 78 years. Among all patients 28 had multiple lesion, of them 71.4% was malignant and 28.6% was benign. On the other side 22 patients had solitary lesion, of them 36.4% was malignant and 63.6% was benign
文摘In recent days,Deep Learning(DL)techniques have become an emerging transformation in the field of machine learning,artificial intelligence,computer vision,and so on.Subsequently,researchers and industries have been highly endorsed in the medical field,predicting and controlling diverse diseases at specific intervals.Liver tumor prediction is a vital chore in analyzing and treating liver diseases.This paper proposes a novel approach for predicting liver tumors using Convolutional Neural Networks(CNN)and a depth-based variant search algorithm with advanced attention mechanisms(CNN-DS-AM).The proposed work aims to improve accuracy and robustness in diagnosing and treating liver diseases.The anticipated model is assessed on a Computed Tomography(CT)scan dataset containing both benign and malignant liver tumors.The proposed approach achieved high accuracy in predicting liver tumors,outperforming other state-of-the-art methods.Additionally,advanced attention mechanisms were incorporated into the CNN model to enable the identification and highlighting of regions of the CT scans most relevant to predicting liver tumors.The results suggest that incorporating attention mechanisms and a depth-based variant search algorithm into the CNN model is a promising approach for improving the accuracy and robustness of liver tumor prediction.It can assist radiologists in their diagnosis and treatment planning.The proposed system achieved a high accuracy of 95.5%in predicting liver tumors,outperforming other state-of-the-art methods.
基金The present study was based on a doctoral dissertation in the Emergency Medicine,School of Medicine,Mazandaran University of Medical Sciences,Iran(grant number 1404)。
文摘Purpose:Abdominal CT scan using oral and intravenous(IV)contrast is helpful in the diagnosis of intra-abdominal injuries.However,the use of oral and IV contrast delays the process of diagnosis and increases the risk of aspiration.It has also been shown that CT scan with IV contrast alone is as helpful as CT scan with oral and IV contrast and rectal CT scan in detecting abdominal injuries.Therefore,the present study aims to prospectively compare the diagnostic value of CT scan with oral and IV contrast versus CT scan with IV contrast alone in the diagnosis of blunt abdominal trauma(BAT).Methods:Altogether 123 BAT patients,60(48.8%)women and 63(51.2%)men with the mean age of(40.4±18.7)years who referred to the emergency department of Imam Khomeini Educational and Medical Center in Sari,Iran(a tertiary trauma center in north of Iran)from November 2014 to March 2017 and underwent abdominal CT scans+laparotomy were investigated.Those with penetrating trauma or hemodynamically unstable patients were excluded.The participants were randomly allocated to two groups:abdominal CT scan with oral and IV contrast(n=63)and CT scan with IV contrast alone(n=60).No statistically significant difference was found between two groups regarding the hemodynamic parameters,age,gender,injury mechanisms(all p>0.05).The results of CT scan were compared with that of laparotomy results.The collected data were recorded in SPSS version 22.0 for Windows.Quantitative data were presented as mean and SD.Results:The sensitivity and specificity of CT scan using oral and IV contrast in the diagnosis of BAT were estimated at 96.48(95%CI:90.73-99.92)and 92.67(95% CI:89.65-94.88),respectively;while CT scan with IV contrast alone achieved a comparable sensitivity and specificity of 96.6(95% CI:87.45-99),42 and 92.84(95% CI:89.88-95.00),respectively.Conclusion:CT scan with IV contrast alone can be used to assess visceral injuries in BAT patients with normal hemodynamics to avoid diagnostic delay.
文摘Background: Maxillofacial trauma affects young adults more. The injury assessment is difficult to establish in low-income countries because of the imaging means, particularly the scanner, which is poorly available and less financially accessible. The aim of this study is to describe the epidemiological profile and the various tomodensitometric aspects of traumatic lesions of the face in patients received in the Radiology department of Kira Hospital. Patients and methods: This is a descriptive retrospective study involving 104 patients of all ages over a period of 2 years from December 2018 to November 2019 in the medical imaging department of KIRA HOSPITAL. We included in our study any patient having undergone a CT scan of the head and presenting at least one lesion of the facial mass, whether associated with other cranioencephalic lesions. Results: Among the 384 patients received for head trauma, 104 patients (27.1% of cases) presented facial damage. The average age of our patients was 32.02 years with extremes of 8 months and 79 years. In our study, 87 of the patients (83.6%) were male. The road accident was the circumstance in which facial trauma occurred in 79 patients (76% of cases). These injuries were accompanied by at least one bone fracture in 97 patients (93.3%). Patients with fractures of more than 3 facial bones accounted for 40.2% of cases and those with fractures of 2 to 3 bones accounted for 44.6% of cases. The midface was the site of the fracture in 85 patients (87.6% of cases). Orbital wall fractures were noted in 57 patients (58.8% of cases) and the jawbone was the site of a fracture in 50 patients (51.5% of cases). In the vault, the fractures involved the extra-facial frontal bone (36.1% of cases) and temporal bone (18.6% of cases). Cerebral contusion was noted in 41.2% of patients and pneumoencephaly in 15.5% of patients. Extradural hematoma was present in 16 patients and subdural hematoma affected 13 patients. Conclusion: Computed tomography is a diagnostic tool of choice in facial trauma patients. Most of these young patients present with multiple fractures localizing to the mid-level of the face with concomitant involvement of the brain.
文摘目的观察肝硬化(HC)合并原发性肝癌(PLC)患者CT动态增强扫描变化,分析其诊断价值。方法回顾性分析2020年4月—2022年7月我院125例HC患者资料,所有受试者均行病理组织学检测及CT动态增强扫描,统计所有患者病灶大小及分布情况,CT动态增强扫描动脉期、静脉期、延迟期病灶检出情况,以病理检查为金标准,分析CT动态增强扫描对HC患者PLC的诊断价值、HC患者与HC并PLC患者血流灌注参数大小及不同肝功能CTP分级下血流灌注参数变化。结果125例HC患者共检出161个病灶,其中直径<1 cm 8个,1~3 cm 53个,4~5 cm 63个,>5 cm 37个,肝右前叶、肝右后叶者居多,分别为45及69个;CT动态增强扫描动脉期检出病灶149个,检出率92.55%;门脉期检出病灶134个,检出率83.23%;延迟期检出病灶142个,检出率88.20%;125例HC患者中病理学检查显示75例PLC阳性,50例PLC阴性,CT动态增强扫检测HC并PLC的敏感度为94.67%,特异度为94.00%,准确率为94.40%,阳性预测值为95.95%,阴性预测值为92.16%,Kappa值为0.884,具有较高的一致性;HC组HAP、HPI值均显著低于HC并PLC组,PVP、TLP值均显著高于HC并PLC组(P<0.05);125例HC并PLC患者中CTP A级41例,CTP B级46例,CTP C级38例,CTP A级HAP、HPI值显著低于CTP B、C级(P<0.05),PVP、TLP值均显著高于CTP B、C级(P<0.05),CTP B级HPI值与CTP C级比较,差异均无统计学意义(P>0.05)。结论CT动态增强扫描可多方位多角度显示HC病灶情况,且对PLC具有较好的诊断价值,其中肝脏血流灌注参数具有一定的特征性,可为PLC诊断和肝功能分级提供参考。
文摘One of the leading causes of mortality worldwide is liver cancer.The earlier the detection of hepatic tumors,the lower the mortality rate.This paper introduces a computer-aided diagnosis system to extract hepatic tumors from computed tomography scans and classify them into malignant or benign tumors.Segmenting hepatic tumors from computed tomography scans is considered a challenging task due to the fuzziness in the liver pixel range,intensity values overlap between the liver and neighboring organs,high noise from computed tomography scanner,and large variance in tumors shapes.The proposed method consists of three main stages;liver segmentation using Fast Generalized Fuzzy C-Means,tumor segmentation using dynamic thresholding,and the tumor’s classification into malignant/benign using support vector machines classifier.The performance of the proposed system was evaluated using three liver benchmark datasets,which are MICCAI-Sliver07,LiTS17,and 3Dircadb.The proposed computer adided diagnosis system achieved an average accuracy of 96.75%,sensetivity of 96.38%,specificity of 95.20%and Dice similarity coefficient of 95.13%.
