ABSTRACT
<p><b>OBJECTIVE</b>To evaluate the feasibility of using radiomic features for differential diagnosis of hepatocellular carcinoma (HCC) and hepatic cavernous hemangioma (HHE).</p><p><b>METHODS</b>Gadoxetate disodium-enhanced magnetic resonance imaging data were collected from a total of 135 HCC and HHE lesions. The radiomic texture features of each lesion were extracted on the hepatobiliary phase images, and the performance of each feature was assessed in differentiation and classification of HCC and HHE. In multivariate analysis, the performance of 3 feature selection algorithms (namely minimum redundancy-maximum relevance, mRmR; neighborhood component analysis, NCA; and sequence forward selection, SFS) was compared. The optimal feature subset was determined according to the optimal feature selection algorithm and used for testing the 3 classifier algorithms (namely the support vector machine, RBF-SVM; linear discriminant analysis, LDA; and logistic regression). All the tests were repeated 5 times with 10-fold cross validation experiments.</p><p><b>RESULTS</b>More than 50% of the radiomic features exhibited strong distinguishing ability, among which gray level co-occurrence matrix feature S (3, -3) SumEntrp showed a good classification performance with an AUC of 0.72 (P<0.01), a sensitivity of 0.83 and a specificity of 0.57. For the multivariate analysis, 15 features were selected based on the SFS algorithm, which produced better results than the other two algorithms. Testing of these 15 selected features for their average cross-validation performance with RBF-SVM classifier yielded a test accuracy of 0.82∓0.09, an AUC of 0.86∓0.12, a sensitivity of 0.88∓0.11, and a specificity of 0.76∓0.18.</p><p><b>CONCLUSION</b>The radiomic features based on gadoxetate disodium-enhanced magnetic resonance images allow efficient differential diagnosis of HCC and HHE, and can potentially provide important assistance in clinical diagnosis of the two diseases.</p>
ABSTRACT
<p><b>OBJECTIVE</b>To observe the clinical effectiveness of a topical application of Xiaozheng Zhitong: Paste (, XZP) in alleviating the cancerous pain of patients with middle/late stage cancer</p><p><b>METHODS</b>By: adopting a random number table, 124 patients enrolled were randomized into the treatment group (64 patients) and the control group (60 patients). In addition to the basic therapy [including the three-ladder (3L) analgesia] used in both groups, topical application of XZP was given to patients in the treatment group for pain alleviation. The analgesic efficacy was recorded in terms of pain intensity, analgesia initiating time and sustaining time, and the optimal analgesic effect revealing time. Meanwhile, the quality of life (QOL) and adverse reactions that occurred in patients were recorded as well.</p><p><b>RESULTS</b>The total effective rate in the treatment group was: 84.38% (54/64), and in the control group it was 88.33% (53/60), showing no significant difference between them (P>0.05), but the analgesia initiating time and the optimal analgesia effect revealing time in the treatment group were significantly shorter (both P<0.01). Moreover, XZP was better in improving patients' QOL, showing more significant improvements in the treatment group than those in the control group in aspects of mental condition, walking capacity, working capacity, social acceptability, sleep and joy of living (P<0.05 or P<0.01). Lower incidence of adverse reactions, such as nausea, vomiting, mouth dryness, dizziness, etc., especially constipation, was noted in the treatment group (P<0.05 or P<0.01).</p><p><b>CONCLUSION</b>Applying an external compress: of XZP showed a synergistic action with 3L analgesia for shortening the initiating time and the optimal effect revealing time, and could evidently enhance patients' QOL with fewer adverse reactions.</p>