Generalizable synthetic MRI with physics-informed convolutional networks.

BACKGROUND: Magnetic resonance imaging (MRI) provides state-of-the-art image quality for neuroimaging, consisting of multiple separately acquired contrasts. Synthetic MRI aims to accelerate examinations by synthesizing any desirable contrast from a single acquisition. PURPOSE: We developed a physics-informed deep learning-based method to synthesize multiple brain MRI contrasts from a single 5-min acquisition and investigate its ability to generalize to arbitrary contrasts. METHODS: A dataset of 55 subjects acquired with a clinical MRI protocol and a 5-min transient-state sequence was used. The model, based on a generative adversarial network, maps data acquired from the five-minute scan to "effective" quantitative parameter maps (q*-maps), feeding the generated PD, T1 , and T2 maps into a signal model to synthesize four clinical contrasts (proton density-weighted, T1 -weighted, T2 -weighted, and T2 -weighted fluid-attenuated inversion recovery), from which losses are computed. The synthetic contrasts are compared to an end-to-end deep learning-based method proposed by literature. The generalizability of the proposed method is investigated for five volunteers by synthesizing three contrasts unseen during training and comparing these to ground truth acquisitions via qualitative assessment and contrast-to-noise ratio (CNR) assessment. RESULTS: The physics-informed method matched the quality of the end-to-end method for the four standard contrasts, with structural similarity metrics above 0.75 ± 0.08 (±std), peak signal-to-noise ratios above 22.4 ± 1.9, representing a portion of compact lesions comparable to standard MRI. Additionally, the physics-informed method enabled contrast adjustment, and similar signal contrast and comparable CNRs to the ground truth acquisitions for three sequences unseen during model training. CONCLUSIONS: The study demonstrated the feasibility of physics-informed, deep learning-based synthetic MRI to generate high-quality contrasts and generalize to contrasts beyond the training data. This technology has the potential to accelerate neuroimaging protocols.

Tens of images can suffice to train neural networks for malignant leukocyte detection.

Convolutional neural networks (CNNs) excel as powerful tools for biomedical image classification. It is commonly assumed that training CNNs requires large amounts of annotated data. This is a bottleneck in many medical applications where annotation relies on expert knowledge. Here, we analyze the binary classification performance of a CNN on two independent cytomorphology datasets as a function of training set size. Specifically, we train a sequential model to discriminate non-malignant leukocytes from blast cells, whose appearance in the peripheral blood is a hallmark of leukemia. We systematically vary training set size, finding that tens of training images suffice for a binary classification with an ROC-AUC over 90%. Saliency maps and layer-wise relevance propagation visualizations suggest that the network learns to increasingly focus on nuclear structures of leukocytes as the number of training images is increased. A low dimensional tSNE representation reveals that while the two classes are separated already for a few training images, the distinction between the classes becomes clearer when more training images are used. To evaluate the performance in a multi-class problem, we annotated single-cell images from a acute lymphoblastic leukemia dataset into six different hematopoietic classes. Multi-class prediction suggests that also here few single-cell images suffice if differences between morphological classes are large enough. The incorporation of deep learning algorithms into clinical practice has the potential to reduce variability and cost, democratize usage of expertise, and allow for early detection of disease onset and relapse. Our approach evaluates the performance of a deep learning based cytology classifier with respect to size and complexity of the training data and the classification task.

Significantly Elevated C-Reactive Protein Levels After Epicardial Clipping of the Left Atrial Appendage.

OBJECTIVE: Besides mechanical and anatomical changes of the left atrium, epicardial closure of the left atrial appendage has also possible homeostatic effects. The aim of this study was to assess whether epicardial clipping of the left atrial appendage has different biochemical effects compared with complete removal of the left atrial appendage. METHODS: Eighty-two patients were included and underwent a totally thoracoscopic AF ablation procedure. As part of the procedure, the left atrial appendage was excluded with an epicardial clip (n = 57) or the left atrial appendage was fully amputated with an endoscopic vascular stapler (n = 25). From all patients' preprocedural and postprocedural blood pressure, electrolytes and inflammatory parameters were collected. RESULTS: The mean age and left atrial volume index were comparable between the epicardial clip and stapler group (64 ± 8 years vs. 60 ± 9 years, P = non-significant; 44 ± 15 mL/m vs. 40 ± 13 mL/m, P = non-significant). Patients receiving left atrial appendage clipping had significantly elevated C-reactive protein levels compared with patients who had left atrial appendage stapling at the second, third, and fourth postoperative day (225 ± 84 mg/L vs. 149 ± 76 mg/L, P = 0.002, 244 ± 78 vs. 167 ± 76, P = 0.004, 190 ± 74 vs. 105 ± 48, P < 0.001, respectively). Patients had a significant decrease in sodium levels, systolic, and diastolic blood pressure at 24 and 72 hours after left atrial appendage closure. However, this was comparable for both the left atrial appendage clipping and stapling group. CONCLUSIONS: Increased activation of the inflammatory response was observed after left atrial appendage clipping compared with left atrial appendage stapling. Furthermore, a significant decrease in blood pressure was observed after surgical removal of the left atrial appendage. Whether the inflammatory response affects the outcome of arrhythmia surgery needs to be further evaluated.