DL-based Method Research Articles

Usefulness of dictionary learning-based processing for improving image quality of sub-millisievert low-dose chest CT: initial experience.

To develop a dictionary learning (DL)-based processing technique for improving the image quality of sub-millisievert chest computed tomography (CT). Standard-dose and sub-millisievert chest CT were acquired in 12 patients. Dictionaries including standard- and low-dose image patches were generated from the CT datasets. For each patient, DL-based processing was performed for low-dose CT using the dictionaries generated from the remaining 11 patients. This procedure was repeated for all 12 patients. Image quality of normal thoracic structures on the processed sub-millisievert CT images was assessed with a 5-point scale (5 = excellent, 1 = very poor). Lung lesion conspicuity was also assessed on a 5-point scale. Image noise on sub-millisievert CT was significantly decreased with DL-based image processing (48.5 ± 13.7 HU vs 20.4 ± 7.9 HU, p = 0.0005). Image quality of lung structures was significantly improved with DL-based method (middle level of lung, 2.25 ± 0.75 vs 2.92 ± 0.79, p = 0.0078). Lung lesion conspicuity was also significantly improved with DL-based technique (solid nodules, 3.4 ± 0.6 vs 2.7 ± 0.6, p = 0.0273). Image quality and lesion conspicuity on sub-millisievert chest CT images may be improved by DL-based post-processing.

Partial-ring PET image restoration using a deep learning based method

PET scanners with partial-ring geometry have been proposed for various imaging purposes. The incomplete projection data obtained from this design cause undesirable artifacts in the reconstructed images. In this study, we investigated the performance of a deep learning (DL) based method for the recovery of partial-ring PET images. Twenty digital brain phantoms were used in the Monte Carlo simulation toolkit, SimSET, to simulate 15 min full-ring PET scans. Partial-ring PET data were generated from full-ring PET data by removing coincidence events that hit these specific detector blocks. A convolutional neural network based on the residual U-Net architecture was trained to predict full-ring data from partial-ring data in either the projection or image domain. The performance of the proposed DL-based method was evaluated by comparing with the PET images reconstructed using the full-ring projection data in terms of the mean squared error (MSE), structural similarity (SSIM) index and recovery coefficient (RC). The MSE results showed the superiority of the image-domain approach in reduction of 91.7% in contrast to 14.3% for the projection-domain approach. Therefore, the image-domain approach was used to study the influence of the number of detector block removal. The SSIM results were 0.998, 0.996 and 0.993 for 3, 5 and 7 detector block removals, respectively. The activity of gray and white matters could be fully recovered even with 7 detector block removal, while the RCs of two artificially inserted small lesions (3 pixels in diameter) in the testing data were 94%, 89% and 79% for 3, 5, and 7 detector block removals, respectively. Our simulation results suggest that DL has the potential to recover partial-ring PET images.

Sparse-View Reconstruction in Dental Computed Tomography by Using a Dictionary-Learning Based Method

In this study, we investigated sparse-view reconstruction in dental computed tomography (DCT) by using a dictionary-learning (DL)-based method to reduce excessive radiation dose to patients. In sparse-view DCT, only a small number (< 100) of projections, far less than what is required by the Nyquist sampling theory, are acquired from the imaging system and used for image reconstruction. DL is a representation learning theory that aims to find a sparse representation of the input signal in the form of a linear combination of basic elements (or atoms). We implemented a DL-based reconstruction algorithm and performed a systematic simulation and an experiment to evaluate the algorithm’s effectiveness for sparse-view reconstruction in DCT. DCT images were reconstructed using the three sparse-view projections of P30, P40, and P60, and their image qualities were quantitatively evaluated in terms of the intensity profile, the universal quality index, and the peak signal-to-noise ratio. The hardware system used in the experiment consisted of an X-ray tube, which was run at 90 kVp and 40 mA, and a flat-panel detector with a 388-μm pixel size. Our simulation and experimental results indicate that the DL-based method significantly reduced streak artifacts in the sparse-view DCT reconstruction when using P40, thus maintaining image quality.

Deep learning based classification of breast tumors with shear-wave elastography

This study aims to build a deep learning (DL) architecture for automated extraction of learned-from-data image features from the shear-wave elastography (SWE), and to evaluate the DL architecture in differentiation between benign and malignant breast tumors. We construct a two-layer DL architecture for SWE feature extraction, comprised of the point-wise gated Boltzmann machine (PGBM) and the restricted Boltzmann machine (RBM). The PGBM contains task-relevant and task-irrelevant hidden units, and the task-relevant units are connected to the RBM. Experimental evaluation was performed with five-fold cross validation on a set of 227 SWE images, 135 of benign tumors and 92 of malignant tumors, from 121 patients. The features learned with our DL architecture were compared with the statistical features quantifying image intensity and texture. Results showed that the DL features achieved better classification performance with an accuracy of 93.4%, a sensitivity of 88.6%, a specificity of 97.1%, and an area under the receiver operating characteristic curve of 0.947. The DL-based method integrates feature learning with feature selection on SWE. It may be potentially used in clinical computer-aided diagnosis of breast cancer.

Face Behind Makeup

In this work, we propose a novel automatic makeup detector and remover framework. For makeup detector, a locality-constrained low-rank dictionary learning algorithm is used to determine and locate the usage of cosmetics. For the challenging task of makeup removal, a locality-constrained coupled dictionary learning (LC-CDL) framework is proposed to synthesize non-makeup face, so that the makeup could be erased according to the style. Moreover, we build a stepwise makeup dataset (SMU) which to the best of our knowledge is the first dataset with procedures of makeup. This novel technology itself carries many practical applications, e.g. products recommendation for consumers; user-specified makeup tutorial; security applications on makeup face verification. Finally, our system is evaluated on three existing (VMU, MIW, YMU) and one own-collected makeup datasets. Experimental results have demonstrated the effectiveness of DL-based method on makeup detection. The proposed LC-CDL shows very promising performance on makeup removal regarding on the structure similarity. In addition, the comparison of face verification accuracy with presence or absence of makeup is presented, which illustrates an application of our automatic makeup remover system in the context of face verification with facial makeup.