A Fully Deep Learning Paradigm for Pneumoconiosis Staging on Chest Radiographs.

Pneumoconiosis staging has been a very challenging task, both for certified radiologists and computer-aided detection algorithms. Although deep learning has shown proven advantages in the detection of pneumoconiosis, it remains challenging in pneumoconiosis staging due to the stage ambiguity of pneumoconiosis and noisy samples caused by misdiagnosis when they are used in training deep learning models. In this article, we propose a fully deep learning pneumoconiosis staging paradigm that comprises a segmentation procedure and a staging procedure. The segmentation procedure extracts lung fields in chest radiographs through an Asymmetric Encoder-Decoder Network (AED-Net) that can mitigate the domain shift between multiple datasets. The staging procedure classifies the lung fields into four stages through our proposed deep log-normal label distribution learning and focal staging loss. The two cascaded procedures can effectively solve the problem of model overfitting caused by stage ambiguity and noisy labels of pneumoconiosis. Besides, we collect a clinical chest radiograph dataset of pneumoconiosis from the certified radiologist's diagnostic reports. The experimental results on this novel pneumoconiosis dataset confirm that the proposed deep pneumoconiosis staging paradigm achieves an Accuracy of 90.4%, a Precision of 84.8%, a Sensitivity of 78.4%, a Specificity of 95.6%, an F1-score of 80.9% and an Area Under the Curve (AUC) of 96%. In particular, we achieve 68.4% Precision, 76.5% Sensitivity, 95% Specificity, 72.2% F1-score and 89% AUC on the early pneumoconiosis 'stage-1'.

Clinical Application of Artificial Ascites in assisting CT-guided Percutaneous Cryoablation of Hepatic Tumors Adjacent to the Gastrointestinal Tract.

This study was to assess the safety and efficacy of artificial ascitetes in assisting CT-guided cryoablation of hepatic tumors adjacent to the gastrointestinal (GI) tract. A total of 84 patients with peripheral hepatic tumors adjacent to the GI tract, who were treated cryoablation, were included in this retrospective study. Of these 84 patients, cryoablation had been performed in 39 patients with 41 peripheral hepatic tumors. These were assisted by induction artificial ascites while 40 patients with 43 peripheral hepatic tumors underwent cryoablation without induction of ascites. The artificial ascites separation success rate, the cryoablation technique effectiveness, local tumor progression and complications were all evaluated. The results showed that the artificial ascites separation success rate for 41 hepatic tumors adjacent to the GI tract was 95% (39/41). Technique effectiveness of group I was achieved in 35 of 43 tumors (81.3%) after follow-up imaging three months after cryoablation. In group II, technique effectiveness was achieved in 39 of 41 tumors after follow-up imaging three months following cryoablation. No major complications were encountered in either of the two groups. Artificial ascites assisting in CT-guided percutaneous cryoablation is a reliable and effective method for the treatment of hepatic tumors adjacent to the GI tract, and it can achieve a fine local control of such tumors.

Computed tomography-guided catheter drainage with urokinase and ozone in management of empyema.

AIM: To retrospectively compare the outcomes of catheter drainage, urokinase and ozone in management of empyema. METHODS: Retrospective study included 209 patients (111 males and 98 females; age range 19 to 72 years) who were diagnosed with empyema. The patients were divided into 3 groups based on the therapy instituted: catheter drainage only (group I); catheter drainage and urokinase (group II); catheter drainage, urokinase and ozone (group III). Drainage was considered successful if empyema was resolved with closure of cavity, clinical symptoms were resolved, and need for any further surgical procedure was avoided. Success rate, length of stay (LOS), need for further surgery and hospital costs were compared between the three groups using the Kruskall-Wallis nonparametric test, with P < 0.05 considered significant. RESULTS: Of the 209 patients with empyema, all catheters were placed successfully under CT guidance. Sixty-three patients were treated with catheters alone (group I), 64 with catheters and urokinase (group II), and 82 with catheters, urokinase and ozone (group III). Group I, group II and group III had success rates of 62%, 83% and 95% respectively (P < 0.05). Group I and group II had statistically longer LOS (P < 0.05) and higher hospital costs (P < 0.05) compared to group III. There were statistically significant differences between the three groups when comparing patients who converted into further surgery. CONCLUSION: The combination of chest tube drainage, urokinase and ozone is a safe and effective therapeutic modality in thoracic empyema.