Neural network-based computer-aided diagnosis in distinguishing malignant from benign solitary pulmonary nodules by computed tomography / 中华医学杂志(英文版)

<p><b>BACKGROUND</b>Computer-aided diagnosis (CAD) of lung cancer is the subject of many current researches. Statistical methods and artificial neural networks have been applied to more quantitatively characterize solitary pulmonary nodules (SPNs). In this study, we developed a CAD scheme based on an artificial neural network to distinguish malignant from benign SPNs on thin-section computed tomography (CT) images, and investigated how the CAD scheme can help radiologists with different levels of experience make diagnostic decisions.</p><p><b>METHODS</b>Two hundred thin-section CT images of SPNs with proven diagnoses (135 small peripheral lung cancers and 65 benign nodules) were analyzed. Three clinical features and nine CT signs of each case were studied by radiologists, and the indices of qualitative diagnosis were quantified. One hundred and forty nodules were selected randomly to form training samples, on which the neural network model was built. The remaining 60 nodules, forming test samples, were presented to 9 radiologists with 3 - 20 years of clinical experience, accompanied by standard reference images. The radiologists were asked to determine whether a nodule was malignant or benign first without and then with CAD output. Diagnostic performance was evaluated by receiver operating characteristic (ROC) analysis.</p><p><b>RESULTS</b>CAD outputs on test samples had higher agreement with pathological diagnoses (Kappa = 0.841, P < 0.001). Compared with diagnostic results without CAD output, the average area under the ROC curve with CAD output was 0.96 (P < 0.001) for junior radiologists, 0.94 (P = 0.014) for secondary radiologists and 0.96 (P = 0.221) for senior radiologists, respectively. The differences in diagnostic performance with CAD output among the three levels of radiologists were not statistically significant (P = 0.584, 0.920 and 0.707, respectively).</p><p><b>CONCLUSIONS</b>This CAD scheme based on an artificial neural network could improve diagnostic performance and assist radiologists in distinguishing malignant from benign SPNs on thin-section CT images.</p>

Survival analysis on liver failure patients treated with an artificial liver support system / 中华肝脏病杂志

<p><b>OBJECTIVE</b>To evaluate the efficacy of artificial liver support system (ALSS) in the treatment of liver failure patients.</p><p><b>METHODS</b>This is a prospective, multi-center, controlled, large sample clinic trial. 518 patients with liver failure from 5 hospitals were studied and followed. All the patients received similar pharmacological manipulation according to one and the same protocol but were divided into an ALSS treatment group and a control group without ALSS treatment. The ALSS treatment procedures included plasma exchange, molecular adsorbent recirculating system (MARS), plasma exchange plus hemofiltration and other combined nonbioartificial methods. The analysis of survival time was computed using the Kaplain-Maier method, and comparison among groups was done using Log-Rank, Breslow and/or the Tarone-Ware test.</p><p><b>RESULTS</b>Survival time of acute liver failure patients was prolonged from 4.0+/-0.2 days to 8.0+/-0.4 days (P=0.004). ALSS was shown to be two times more effective. ALSS increased the survival time of acute on chronic (A on C) liver failure patients from 27.0+/-1.6 days to 39.0+/-4.0 days (P less than 0.01). In addition, it increased the survival time of the patients in the middle and end stage of subacute liver failure and A on C liver failure, but had no significant effects on early stage patients. The survival time of middle stage patients was 38.0+/-17.5 days in the control group vs 66.0+/-18.6 days in the ALSS group (P less than 0.05). The survival time of end stage patients of the control group and the ALSS group was 18.0+/-4.0 days vs 26.0+/-2.5 days (P less than 0.01).</p><p><b>CONCLUSIONS</b>Multi ALSS treatment is more effective than the standard medicinal liver care treatment. Multi-ALSS treatment could increase survival time of patients suffering from acute liver failure or A on C liver failure, especially in their middle and end stages. It is important and necessary to treat these patients with ALSS.</p>