Breast cancer is the most prevalent cancer with a high mortality rate in women over the age of 40. Many studies have shown that the detection of cancer at earlier stages significantly reduces patients' mortality and morbidity rages. Ultrasound computer tomography (USCT) is considered as a promising screening tool for diagnosing early-stage breast cancer as it is cost-effective and produces 3D images without radiation exposure. However, USCT is not a popular choice mainly due to its prolonged imaging time. USCT is time-consuming because it needs to transmit a number of ultrasound waves and record them one by one to acquire a high-quality image. We propose FastUSCT, a method to acquire a high-quality image faster than traditional methods for USCT. FastUSCT consists of three steps. First, it transmits multiple ultrasound waves at the same time to reduce the imaging time. Second, it separates the overlapping waves recorded by the receiving elements into each wave with UNet. Finally, it reconstructs an ultrasound image with a synthetic aperture method using the separated waves. We evaluated FastUSCT on simulation on breast digital phantoms. We trained the UNet on simulation using natural images and transferred the model for the breast digital phantoms. The empirical result shows that FastUSCT significantly improves the quality of the image under the same imaging time to the conventional USCT method, especially when the imaging time is limited.

A new on-line learning algorithm which minimizes a statistical de(cid:173) pendency among outputs is derived for blind separation of mixed signals. The dependency is measured by the average mutual in(cid:173) formation (MI) of the outputs. The source signals and the mixing matrix are unknown except for the number of the sources. The Gram-Charlier expansion instead of the Edgeworth expansion is used in evaluating the MI. The natural gradient approach is used to minimize the MI.

We present an algorithm which compensates for the mismatches between characteristics of real-world problems and assumptions of independent component analysis algorithm. To provide additional information to the ICA network, we incorporate top-down selective attention. An MLP classifier is added to the separated signal channel and the error of the classifier is backpropagated to the ICA network. This backpropagation process results in estimation of expected ICA output signal for the top-down attention. Then, the unmixing matrix is retrained according to a new cost function representing the backpropagated error as well as independence.

We present an algorithm which compensates for the mismatches between characteristics of real-world problems and assumptions of independent component analysis algorithm. To provide additional information to the ICA network, we incorporate top-down selective attention. An MLP classifier is added to the separated signal channel and the error of the classifier is backpropagated to the ICA network. This backpropagation process results in estimation of expected ICA output signal for the top-down attention. Then, the unmixing matrix is retrained according to a new cost function representing the backpropagated error as well as independence.

Independent Component Analysis (ICA) is a method for blind signal separation.

A new online learning algorithm which minimizes a statistical dependency amongoutputs is derived for blind separation of mixed signals. The dependency is measured by the average mutual information (MI)of the outputs. The source signals and the mixing matrix are unknown except for the number of the sources. The Gram-Charlier expansion instead of the Edgeworth expansion is used in evaluating the MI. The natural gradient approach is used to minimize the MI. A novel activation function is proposed for the online learning algorithm which has an equivariant property and is easily implemented on a neural network like model. The validity of the new learning algorithm are verified by computer simulations.