Novel Chest Radiographic Biomarkers for COVID-19 Using Radiomic Features Associated with Diagnostics and Outcomes.

COVID-19 is a highly contagious disease that can cause severe pneumonia. Patients with pneumonia undergo chest X-rays (XR) to assess infiltrates that identify the infection. However, the radiographic characteristics of COVID-19 are similar to the other acute respiratory syndromes, hindering the imaging diagnosis. In this work, we proposed identifying quantitative/radiomic biomarkers for COVID-19 to support XR assessment of acute respiratory diseases. This retrospective study used different cohorts of 227 patients diagnosed with pneumonia; 49 of them had COVID-19. Automatically segmented images were characterized by 558 quantitative features, including gray-level histogram and matrices of co-occurrence, run-length, size zone, dependence, and neighboring gray-tone difference. Higher-order features were also calculated after applying square and wavelet transforms. Mann-Whitney U test assessed the diagnostic performance of the features, and the log-rank test assessed the prognostic value to predict Kaplan-Meier curves of overall and deterioration-free survival. Statistical analysis identified 51 independently validated radiomic features associated with COVID-19. Most of them were wavelet-transformed features; the highest performance was the small dependence matrix feature of "low gray-level emphasis" (area under the curve of 0.87, sensitivity of 0.85, [Formula: see text]). Six features presented short-term prognostic value to predict overall and deterioration-free survival. The features of histogram "mean absolute deviation" and size zone matrix "non-uniformity" yielded the highest differences on Kaplan-Meier curves with a hazard ratio of 3.20 ([Formula: see text]). The radiomic markers showed potential as quantitative measures correlated with the etiologic agent of acute infectious diseases and to stratify short-term risk of COVID-19 patients.

Multi-View Ensemble Convolutional Neural Network to Improve Classification of Pneumonia in Low Contrast Chest X-Ray Images.

Pneumonia is one of the leading causes of childhood mortality worldwide. Chest x-ray (CXR) can aid the diagnosis of pneumonia, but in the case of low contrast images, it is important to include computational tools to aid specialists. Deep learning is an alternative because it can identify patterns automatically, even in low-resolution images. We propose herein a convolutional neural network (CNN) architecture with different training strategies towards detecting pneumonia on CXRs and distinguishing its subforms of bacteria and virus. We also evaluated different image pre-processing methods to improve the classification. This study used CXRs from pediatric patients from a public pneumonia CXR dataset. The pre-processing methods evaluated were image cropping and histogram equalization. To classify the images, we adopted the VGG16 CNN and replaced its fully-connected layers with a customized multilayer perceptron. With this architecture, we proposed and evaluated four different training strategies: original CXR image (baseline), chest-cavity-cropped image (A), and histogram-equalized segmented image (B). The last strategy method (C) implemented is based on ensemble between strategies A and B. The performance was assessed by the area under the ROC curve (AUC) with 95% confidence interval (CI), accuracy, sensitivity, specificity, and F1-score. The ensemble model C yielded the highest performances: AUC of 0.97 (CI: 0.96-0.99) to classify pneumonia vs. normal, and AUC of 0.91 (CI: 0.88-0.94) to classify bacterial vs. viral cases. All models that used pre-processed images showed higher AUC than baseline, which used the original CXR image. Image cropping and histogram equalization reduced irrelevant information from the exam, enhanced contrast, and was able to identify fine CXR texture details. The proposed ensemble model increased the representation of inflammatory patterns from bacteria and viruses with few epochs to train the deep CNNs.Clinical relevance- Deep learning can identify complex radiographic patterns in low contrast images due to pneumonia and distinguish its subforms of bacteria and virus. The correlation of imaging with lab results could accelerate the adoption of complementary exams to confirm the disease's cause.

Patellar tracking after isolated medial patellofemoral ligament reconstruction: dynamic evaluation using computed tomography.

PURPOSE: Medial patellofemoral ligament (MPFL) reconstruction offers good clinical results with a very low rate of instability recurrence. However, its in vivo effect on patellar tracking is not clearly known. The aim of this study is to investigate the effects of MPFL reconstruction on patellar tracking using dynamic 320-detector-row CT. METHODS: Ten patients with patellofemoral instability referred to isolated MPFL reconstruction surgery were selected and subjected to dynamic CT before and ≥6 months after surgery. Patellar tilt angles and shift distance were analysed using computer software specifically designed for this purpose. Kujala and Tegner scores were applied, and the radiation of the CTs was recorded. Two protocols for imaging acquisition were compared: a tube potential of 80 kV and 50 mA versus a tube potential of 120 kV and 100 mA, both with a slice thickness of 0.5 mm and an acquisition duration of 10 s. RESULTS: There were no changes in patellar tracking after MPFL reconstruction. There was no instability relapse. Clinical scores improved from a mean of 51.9 (±15.6)-74.2 (±20.9) on the Kujala scale (p = 0.011) and from a median of 2 (range 0-4) to 4 (range 1-6) on the Tegner scale (p = 0.017). The imaging protocols produced a dose-length product (DLP) of 254 versus 1617 mGycm and a radiation effective estimated dose of 0.2 versus 1.3 mSv, respectively. Both protocols allowed the analysis of the studied parameters without loss of precision. CONCLUSIONS: Reconstruction of the MPFL produced no improvement in patellar tilt or shift in the population studied. The low-radiation protocol was equally effective in measuring changes in patellar tracking and is recommended. Although the procedure successfully stabilized the patella, knee surgeons should not expect patellar shift and tilt correction when performing isolated patellofemoral ligament reconstruction in patients with recurrent patellar instability. LEVEL OF EVIDENCE: IV.

Functional bull's eye based on three dimensional velocity information to quantify left ventricle motion in gated-SPECT.

The description and quantification of the regional function of the cardiac left ventricle (LV) involve making quantitative measurements of the heart movement. In this work we present a functional bull's eye or polar map that depicts three dimensional coded velocity information from gated-SPECT images. The polar map is built based on the standards defined by the AHA and comprises 17 segments. The use of the proposed map was tested in images from 5 normal subjects and 4 patients with intraventricular dyssynchrony submitted to cardiac resynchronization therapy. Preliminary results have shown good indications of potential application of the technique to the diagnosis and the follow up of such patients. The functional polar map is independent of the heart size, so it makes possible the creation of normal pattern standards. Such standards would allow the application of the method in a broad range of applications involving the analysis of the heart movement.

Medical Image distribution and visualization in a hospital using CORBA.

In this work it is presented the solution adopted by the Heart Institute (InCor) of Sao Paulo for medical image distribution and visualization inside the hospital's intranet as part of the PACS system. A CORBA-based image server was developed to distribute DICOM images across the hospital together with the images' report. The solution adopted allows the decoupling of the server implementation and the client. This gives the advantage of reusing the same solution in different implementation sites. Currently, the PACS system is being used on two different hospitals each one with three different environments: development, prototype and production.