AIM: To evaluate the ability of contrast-enhanced computerized tomography (CECT) to characterize the nature of peripancreatic collections.METHODS: Twenty five patients with peripancreatic collections on CECT and who u...AIM: To evaluate the ability of contrast-enhanced computerized tomography (CECT) to characterize the nature of peripancreatic collections.METHODS: Twenty five patients with peripancreatic collections on CECT and who underwent operative intervention for severe acute pancreatitis were retrospectively studied. The collections were classified into (1) necrosis without frank pus; (2) necrosis with pus; and (3) fluid without necrosis. A blinded radiologist assessed the preoperative CTs of each patient for necrosis and peripancreatic fluid collections. Peripancreatic collections were described in terms of volume, location, number, heterogeneity, fluid attenuation, wall perceptibility, wall enhancement, presence of extraluminal gas, and vascular compromise.RESULTS: Fifty-four collections were identif ied at operation, of which 45 (83%) were identif ied on CECT. Of these, 25/26 (96%) had necrosis without pus, 16/19 (84%) had necrosis with pus, and 4/9 (44%) had fluid without necrosis. Among the study characteristics, fluid heterogeneity was seen in a greater proportion of collections in the group with necrosis and pus, compared to the other two groups (94% vs 48% and 25%, P = 0.002 and 0.003, respectively). Among the wall characteristics, irregularity was seen in a greater proportion of collections in the groups with necrosis with and without pus, when compared to the group with fluid without necrosis (88% and 71% vs 25%, P = 0.06 and P < 0.01, respectively). The combination of heterogeneity and presence of extraluminal gas had a specif icity and positive likelihood ratio of 92% and 5.9, respectively, in detecting pus. CONCLUSION: Most of the peripancreatic collections seen on CECT in patients with severe acute pancreatitis who require operative intervention contain necrotic tissue. CECT has a somewhat limited role in differentiating the different types of collections.展开更多
文摘AIM: To evaluate the ability of contrast-enhanced computerized tomography (CECT) to characterize the nature of peripancreatic collections.METHODS: Twenty five patients with peripancreatic collections on CECT and who underwent operative intervention for severe acute pancreatitis were retrospectively studied. The collections were classified into (1) necrosis without frank pus; (2) necrosis with pus; and (3) fluid without necrosis. A blinded radiologist assessed the preoperative CTs of each patient for necrosis and peripancreatic fluid collections. Peripancreatic collections were described in terms of volume, location, number, heterogeneity, fluid attenuation, wall perceptibility, wall enhancement, presence of extraluminal gas, and vascular compromise.RESULTS: Fifty-four collections were identif ied at operation, of which 45 (83%) were identif ied on CECT. Of these, 25/26 (96%) had necrosis without pus, 16/19 (84%) had necrosis with pus, and 4/9 (44%) had fluid without necrosis. Among the study characteristics, fluid heterogeneity was seen in a greater proportion of collections in the group with necrosis and pus, compared to the other two groups (94% vs 48% and 25%, P = 0.002 and 0.003, respectively). Among the wall characteristics, irregularity was seen in a greater proportion of collections in the groups with necrosis with and without pus, when compared to the group with fluid without necrosis (88% and 71% vs 25%, P = 0.06 and P < 0.01, respectively). The combination of heterogeneity and presence of extraluminal gas had a specif icity and positive likelihood ratio of 92% and 5.9, respectively, in detecting pus. CONCLUSION: Most of the peripancreatic collections seen on CECT in patients with severe acute pancreatitis who require operative intervention contain necrotic tissue. CECT has a somewhat limited role in differentiating the different types of collections.
文摘在正电子发射断层(Positron emission tomography,PET)重建算法中,正则项常被用来抑制噪声。现将Mumford-Shah(MS)正则项,构造出一种新的变分结构用以进行PET图像重建。采用了Ambrosio和Tortorelli提出的Γ-收敛逼近方法,将MS函式对边界积分转化为一类合适的辅助光滑函数的区域积分。在仿真测试中,将算法与传统滤波反投影(Filtered back projection,FBP)算法、最大似然估计方法(MLEM)和最大后验概率估计方法作比较。通过实验对算法的效率和可行性进行了分析。实验结果表明,本文算法在噪声抑制和边界保留上均有较好的表现。
