Joint correction of attenuation and scatter in image space using deep convolutional neural networks for dedicated brain 18F-FDG PET.

Dedicated brain positron emission tomography (PET) devices can provide higher-resolution images with much lower doses compared to conventional whole-body PET systems, which is important to support PET neuroimaging and particularly useful for the diagnosis of neurodegenerative diseases. However, when a dedicated brain PET scanner does not come with a combined CT or transmission source, there is no direct solution for accurate attenuation and scatter correction, both of which are critical for quantitative PET. To address this problem, we propose joint attenuation and scatter correction (ASC) in image space for non-corrected PET (PETNC) using deep convolutional neural networks (DCNNs). This approach is a one-step process, distinct from conventional methods that rely on generating attenuation maps first that are then applied to iterative scatter simulation in sinogram space. For training and validation, time-of-flight PET/MR scans and additional helical CTs were performed for 35 subjects (25/10 split for training and test dataset). A DCNN model was proposed and trained to convert PETNC to DCNN-based ASC PET (PETDCNN) directly in image space. For quantitative evaluation, uptake differences between PETDCNN and reference CT-based ASC PET (PETCT-ASC) were computed for 116 automated anatomical labels (AALs) across 10 test subjects (1160 regions in total). MR-based ASC PET (PETMR-ASC), a current clinical protocol in PET/MR imaging, was another reference for comparison. Statistical significance was assessed using a paired t test. The performance of PETDCNN was comparable to that of PETMR-ASC, in comparison to reference PETCT-ASC. The mean SUV differences (mean ± SD) from PETCT-ASC were 4.0% ± 15.4% (P < 0.001) and -4.2% ± 4.3% (P < 0.001) for PETDCNN and PETMR-ASC, respectively. The overall larger variation of PETDCNN (15.4%) was prone to the subject with the highest mean difference (48.5% ± 10.4%). The mean difference of PETDCNN excluding the subject was substantially improved to -0.8% ± 5.2% (P < 0.001), which was lower than that of PETMR-ASC (-5.07% ± 3.60%, P < 0.001). In conclusion, we demonstrated the feasibility of directly producing PET images corrected for attenuation and scatter using a DCNN (PETDCNN) from PETNC in image space without requiring conventional attenuation map generation and time-consuming scatter correction. Additionally, our DCNN-based method provides a possible alternative to MR-ASC for simultaneous PET/MRI.

The No-Prop algorithm: a new learning algorithm for multilayer neural networks.

A new learning algorithm for multilayer neural networks that we have named No-Propagation (No-Prop) is hereby introduced. With this algorithm, the weights of the hidden-layer neurons are set and fixed with random values. Only the weights of the output-layer neurons are trained, using steepest descent to minimize mean square error, with the LMS algorithm of Widrow and Hoff. The purpose of introducing nonlinearity with the hidden layers is examined from the point of view of Least Mean Square Error Capacity (LMS Capacity), which is defined as the maximum number of distinct patterns that can be trained into the network with zero error. This is shown to be equal to the number of weights of each of the output-layer neurons. The No-Prop algorithm and the Back-Prop algorithm are compared. Our experience with No-Prop is limited, but from the several examples presented here, it seems that the performance regarding training and generalization of both algorithms is essentially the same when the number of training patterns is less than or equal to LMS Capacity. When the number of training patterns exceeds Capacity, Back-Prop is generally the better performer. But equivalent performance can be obtained with No-Prop by increasing the network Capacity by increasing the number of neurons in the hidden layer that drives the output layer. The No-Prop algorithm is much simpler and easier to implement than Back-Prop. Also, it converges much faster. It is too early to definitively say where to use one or the other of these algorithms. This is still a work in progress.

A combined heartbeat detector based on individual BCG and IPG heartbeat detectors.

This paper presents a preliminary approach for heartbeat detection on a weighing scale, using a combined heartbeat detector and an ensemble method. First, two independent sub-detectors are implemented based on the BCG (Ballistocardiogram) and lower-body IPG (Impedance Plethysmogram) signals. Then, the results of these sub-detectors are combined using a higher level decision maker. The BCG, which describes the reaction of the body to cardiac ejection of blood, was measured using the strain gauges in a modified commercial weighing scale. For the lower-body IPG, a small amount of current was injected into the subject through the electrodes under the subject's toes, and the resulting differential voltage across the heels was measured. We tested our method on the first 30 seconds of the BCG and IPG signals collected from 8 subjects. The results show the combination significantly improved over individual detector, with a resulting interval accuracy of 97%.

Multi-signal electromechanical cardiovascular monitoring on a modified home bathroom scale.

A commercially available bathroom scale was modified to enable unobtrusive and robust cardiovascular monitoring in the home. Handlebar electrodes were interfaced to an ultra-low power, two-electrode electrocardiogram (ECG) acquisition circuit providing consistent and clean heartbeat timing information. In addition, the footpad electrodes were used to detect lower-body electromyogram (EMG) and lower-body impedance plethysmogram (IPG) signals using two parallel circuits. The lower-body EMG signal was used as an indication of excessive motion of the subject on the scale. The lower-body IPG signal is related to blood flow through the legs, and will be investigated further in future studies. Finally, the component of bodyweight that varies with time--the ballistocardiogram (BCG) signal--was amplified from the existing strain gauges built into the scale. A preliminary validation was completed on five healthy subjects of varying sizes. The average signal-to-noise ratio (SNR) values computed over all five subjects for the ECG, IPG, and BCG signals were 17.2, 12.0, and 9.0 dB, respectively.