Knowledge-Guided Multiview Deep Curriculum Learning for Elbow Fracture Classification.

Elbow fracture diagnosis often requires patients to take both frontal and lateral views of elbow X-ray radiographs. In this paper, we propose a multiview deep learning method for an elbow fracture subtype classification task. Our strategy leverages transfer learning by first training two single-view models, one for frontal view and the other for lateral view, and then transferring the weights to the corresponding layers in the proposed multiview network architecture. Meanwhile, quantitative medical knowledge was integrated into the training process through a curriculum learning framework, which enables the model to first learn from "easier" samples and then transition to "harder" samples to reach better performance. In addition, our multiview network can work both in a dual-view setting and with a single view as input. We evaluate our method through extensive experiments on a classification task of elbow fracture with a dataset of 1,964 images. Results show that our method outperforms two related methods on bone fracture study in multiple settings, and our technique is able to boost the performance of the compared methods. The code is available at https://github.com/ljaiverson/multiview-curriculum.

Tenascin-C may be a predictor of acute pulmonary thromboembolism.

AIM: Numerous studies have shown an increase in NT-pro BNP, troponin I and D-dimer levels with right ventricular dysfunction on echocardiography in patients with acute pulmonary thromboembolism (PTE). We found no data about the relation between tenascin-C and acute PTE in the litera-ture. The aim of this study was to evaluate tenascin-C levels in acute PTE and correlate them with NT-pro BNP, troponin I and D-dimer. METHOD: Thirty-four patients who have massive or submassive PTE on spiral thorax CT (PTE group) and twenty healthy volunteers (non-PTE group) were evaluated. In all patients, right ventricular functions were obtained on transthoracic echocardiography and plasma tenascin-C, NT-pro BNP, troponin I, and D-dimer levels were measured. RESULTS: The left ventricular systolic diameter, left ventricular diastolic diameter and left ventricular ejection fraction were similar in the two groups. The right heart chamber sizes and main pulmonary artery diameter were significantly larger in the PTE group and systolic pulmonary artery pressures were also significantly higher in this group. Tenascin-C, NT-pro BNP, and D-dimer levels were also significantly higher in the PTE group than in the non-PTE group (p< 0.001). The troponin I levels did not differ between the two groups (p=0.4). Tenascin-C was found to be highly correlated with sPAP and NT-pro BNP and correlated with D-dimer; however, troponin I was not correlated with tenascin-C. CONCLUSION: This study demonstrates that tenascin-C may be an indicator of acute PTE.