Breast cancer is one of the most common and deadliest types of cancer among women and early detection is of major importance to decrease mortality rates. Microcalcification clusters and masses are two major indicators...Breast cancer is one of the most common and deadliest types of cancer among women and early detection is of major importance to decrease mortality rates. Microcalcification clusters and masses are two major indicators of malignancy in the early stages of this disease, when mammography is typically used as the screening technology. Computer-Aided Diagnosis (CAD) systems can support the radiologists’ work, by performing a double-reading process, which provides a second opinion that the physician can take into account in the detection process. This paper presents a CAD model based on computer vision procedures for locating suspicious regions that are later analyzed by artificial neural networks, support vector machines and linear discriminant analysis, to classify them into benign or malignant, based on a set of features that are extracted from lesions to characterize their visual content. A genetic algorithm is used to find the subset of features that provide the greatest discriminant power. Our results show that the SVM presented the highest overall accuracy and specificity for classifying microcalcification clusters, while the NN outperformed the rest for mass-classification in the same parameters. Overall accuracy, sensitivity and specificity were measured.展开更多
AIM: To prospectively analyse the clinical, biochemical and radiological characteristics of the mass lesions arising in a background of chronic calcific pancreatitis (CCP). METHODS: Eighty three patients, who presente...AIM: To prospectively analyse the clinical, biochemical and radiological characteristics of the mass lesions arising in a background of chronic calcific pancreatitis (CCP). METHODS: Eighty three patients, who presented with chronic pancreatitis (CP) and a mass lesion in the head of pancreas between February 2005 and December 2011, were included in the study. Patients who were identified to have malignancy underwent Whipple' s procedure and patients whose investigations were suggestive of a benign lesion underwent Frey's procedure. Student t-test was used to compare the mean values of imaging findings [common bile duct (CBD), main pancreatic duct (MPD) size] and laboratory data [Serum bilirubin, carbohydrate antigen 19-9 (CA 19-9)] between the groups. Receiver operating characteristic curve (ROC curve) analysis was done to calculate the cutoff valves of serum bilirubin, CA 19-9, MPD and CBD size. The sensitivity, specificity, positive predictive valve (PPV) and negative predictive value (NPV) were calculated using these cut off points. Multivariate analysis was performed using logistic regression model. RESULTS: The study included 56 men (67.5%) and 27 women (32.5%). Sixty (72.3%) patients had tropical calcific pancreatitis and 23 (27.7%) had alcohol related CCP. Histologically, it was confirmed that 55 (66.3%) of the 83 patients had an inflammatory head mass and 28 (33.7%) had a malignant head mass. The mean age of individuals with benign inflammatory mass and those with malignant mass was 38.4 years and 45 years respectively. Significant clinical features that predicted a malignant head mass in CP were presence of a head mass in CCP of tropics, old age, jaundice, sudden worsening abdominal pain, gastric outlet obstruction and significant weight loss (P ≤ 0.05). The ROC curve analysis showed a cut off value of 5.8 mg/dL for serum bilirubin, 127 U/mL for CA 19-9, 11.5 mm for MPD size and 14.5 mm for CBD size. CONCLUSION: Elevated Serum bilirubin and CA 19-9, and dilated MPD and CBD were useful in predicting malignancy in patients with CCP and head mass.展开更多
Background: CT-scan is a very useful diagnostic tool for the detection of hepatic mass. Objective: The present study was undertaken to determine the CT-scan findings of benign and malignant hepatic mass patients. Meth...Background: CT-scan is a very useful diagnostic tool for the detection of hepatic mass. Objective: The present study was undertaken to determine the CT-scan findings of benign and malignant hepatic mass patients. Methodology: This was a cross sectional study conducted in Radiology and Imaging Department at Mymensingh Medical College Hospital (MMCH), Mymensingh;Dhaka Medical College Hospital (DMCH), Dhaka and Banghabandhu Sheikh Mujib Medical University (BSMMU), Dhaka with the collaboration of Pathology Department of the same institute for histopathological confirmation. This study was carried out from January 2006 to December 2007 for a period of 2 years. The patients who were clinically suspected of having hepatic mass attended in the Radiology and Imaging Department in the above mentioned institutes were included as study population. All the CT-scan findings were recorded. Result: A total number of 50 patients were enrolled for this study. CT-scan was done among 40 males and 10 females with a mean age of 51.28 years old. Hypodensity was found in 17 (60.7%) and 18 (81.8%) cases in malignant and benign hepatic lesions respectively. Ill-defined margin was detected in 12 (42.9%) and 6 (27.3%) cases respectively. Calcification was present on 11 (39.3%) malignant lesion and 6 (27.3%) benign lesions. Pressure effect on biliary apparatus was found in 11 (39.3%) malignant lesions and 1 (4.5%) benign lesions (p < 0.05). Lymphadenopathy was found in 10 (35.7%) malignant lesions and 1 (4.5%) benign lesions (p < 0.05). Conclusion: In conclusion, CT-scan findings of malignant and benign hepatic mass show hypodensity with more contrast enhancement in malignant lesions with more calcification in malignant lesion;however, significant difference is detected in pressure effect on biliary apparatus and lymphadenopathy.展开更多
文摘Breast cancer is one of the most common and deadliest types of cancer among women and early detection is of major importance to decrease mortality rates. Microcalcification clusters and masses are two major indicators of malignancy in the early stages of this disease, when mammography is typically used as the screening technology. Computer-Aided Diagnosis (CAD) systems can support the radiologists’ work, by performing a double-reading process, which provides a second opinion that the physician can take into account in the detection process. This paper presents a CAD model based on computer vision procedures for locating suspicious regions that are later analyzed by artificial neural networks, support vector machines and linear discriminant analysis, to classify them into benign or malignant, based on a set of features that are extracted from lesions to characterize their visual content. A genetic algorithm is used to find the subset of features that provide the greatest discriminant power. Our results show that the SVM presented the highest overall accuracy and specificity for classifying microcalcification clusters, while the NN outperformed the rest for mass-classification in the same parameters. Overall accuracy, sensitivity and specificity were measured.
文摘AIM: To prospectively analyse the clinical, biochemical and radiological characteristics of the mass lesions arising in a background of chronic calcific pancreatitis (CCP). METHODS: Eighty three patients, who presented with chronic pancreatitis (CP) and a mass lesion in the head of pancreas between February 2005 and December 2011, were included in the study. Patients who were identified to have malignancy underwent Whipple' s procedure and patients whose investigations were suggestive of a benign lesion underwent Frey's procedure. Student t-test was used to compare the mean values of imaging findings [common bile duct (CBD), main pancreatic duct (MPD) size] and laboratory data [Serum bilirubin, carbohydrate antigen 19-9 (CA 19-9)] between the groups. Receiver operating characteristic curve (ROC curve) analysis was done to calculate the cutoff valves of serum bilirubin, CA 19-9, MPD and CBD size. The sensitivity, specificity, positive predictive valve (PPV) and negative predictive value (NPV) were calculated using these cut off points. Multivariate analysis was performed using logistic regression model. RESULTS: The study included 56 men (67.5%) and 27 women (32.5%). Sixty (72.3%) patients had tropical calcific pancreatitis and 23 (27.7%) had alcohol related CCP. Histologically, it was confirmed that 55 (66.3%) of the 83 patients had an inflammatory head mass and 28 (33.7%) had a malignant head mass. The mean age of individuals with benign inflammatory mass and those with malignant mass was 38.4 years and 45 years respectively. Significant clinical features that predicted a malignant head mass in CP were presence of a head mass in CCP of tropics, old age, jaundice, sudden worsening abdominal pain, gastric outlet obstruction and significant weight loss (P ≤ 0.05). The ROC curve analysis showed a cut off value of 5.8 mg/dL for serum bilirubin, 127 U/mL for CA 19-9, 11.5 mm for MPD size and 14.5 mm for CBD size. CONCLUSION: Elevated Serum bilirubin and CA 19-9, and dilated MPD and CBD were useful in predicting malignancy in patients with CCP and head mass.
文摘Background: CT-scan is a very useful diagnostic tool for the detection of hepatic mass. Objective: The present study was undertaken to determine the CT-scan findings of benign and malignant hepatic mass patients. Methodology: This was a cross sectional study conducted in Radiology and Imaging Department at Mymensingh Medical College Hospital (MMCH), Mymensingh;Dhaka Medical College Hospital (DMCH), Dhaka and Banghabandhu Sheikh Mujib Medical University (BSMMU), Dhaka with the collaboration of Pathology Department of the same institute for histopathological confirmation. This study was carried out from January 2006 to December 2007 for a period of 2 years. The patients who were clinically suspected of having hepatic mass attended in the Radiology and Imaging Department in the above mentioned institutes were included as study population. All the CT-scan findings were recorded. Result: A total number of 50 patients were enrolled for this study. CT-scan was done among 40 males and 10 females with a mean age of 51.28 years old. Hypodensity was found in 17 (60.7%) and 18 (81.8%) cases in malignant and benign hepatic lesions respectively. Ill-defined margin was detected in 12 (42.9%) and 6 (27.3%) cases respectively. Calcification was present on 11 (39.3%) malignant lesion and 6 (27.3%) benign lesions. Pressure effect on biliary apparatus was found in 11 (39.3%) malignant lesions and 1 (4.5%) benign lesions (p < 0.05). Lymphadenopathy was found in 10 (35.7%) malignant lesions and 1 (4.5%) benign lesions (p < 0.05). Conclusion: In conclusion, CT-scan findings of malignant and benign hepatic mass show hypodensity with more contrast enhancement in malignant lesions with more calcification in malignant lesion;however, significant difference is detected in pressure effect on biliary apparatus and lymphadenopathy.
