Early and automatic detection of pulmonary nodules from CT lung screening is the prerequisite for precise management of lung cancer. However, a large number of false positives appear in order to increase the sensitivity, especially for detecting micro-nodules (diameter < 3 mm), which increases the radiologists’ workload and causes unnecessary anxiety for the patients. To decrease the false positive rate, we propose to use CNN models to discriminate between pulmonary micro-nodules and non-nodules from CT image patches. A total of 13,179 micro-nodules and 21,315 non-nodules marked by radiologists are extracted with three different patch sizes (16 × 16, 32 × 32 and 64 × 64) from LIDC/IDRI database and used in the experiments. Three CNN models with different depths (1, 2 or 4 convolutional layers) are designed; their performances are evaluated by the fivefold cross-validation in term of the accuracy, area under the curve (AUC), F-score and sensitivity. The network parameters are also optimized. It is found that the performance of the CNN models is greatly dependent on the patches size and the number of convolutional layers. The CNN model with two convolutional layers presented the best performance in case of 32 × 32 patches size, achieving an accuracy of 88.28%, an AUC of 0.87, a F-score of 83.45% and a sensitivity of 83.82%. The CNN models with appropriate depth and size of image patches can effectively discriminate between pulmonary micro-nodules and non-nodules, and reduce the false positives and help manage lung cancer precisely.

Full waveform inversion (FWI) is a powerful tool for estimating the underground velocity model. However, it is computationally expensive and the resulting models tend to be not accurate enough. Thus, to improve the efficiency and accuracy of FWI, we propose a super-resolution (SR) method based on deep learning to enhance the resolution of the seismic velocity model. Since the edge images of the seismic velocity model are also widely used in geophysics, a multitask learning (MTL) network with hard parameter sharing is applied to perform the SR of the seismic velocity model and its edge images. The proposed MTL model dubbed M-RUDSR includes a global residual skip connection, an encoder-decoder structure of U-Net, and a dense skip connection structure. Besides, two networks for comparison, namely, RUDSR and M-RUSR, are proffered. RUDSR is a single-task version of M-RUDSR, whereas M-RUSR is a simplified version of M-RUDSR without a dense skip connection structure. Compared with RUDSR and M-RUSR, M-RUDSR produced the best results for all kinds of blurring levels and achieved better visual details. We found that FWI followed by SR can help reduce the computational cost of FWI in the high-frequency part of the spectrum, as well as achieve better high-frequency details recovery. The experimental results show that M-RUDSR is a practical recovery scheme in SR of the seismic velocity model and can be applied to a real data set efficiently.

Structural curvatures are widely used seismic attributes that help interpreters to understand both structural and stratigraphic features. Traditional structural curvature extractions are mainly calculated from dip estimations through lateral scanning of seismic events, which is not only a very time-costing approach but also influenced by parameter settings, seismic frequency, and data quality. In this article, we propose a deep learning-based volumetric curvature extraction approach that directly derives structural curvature volumes from the seismic response. To realize the above approach, we develop a suite of sample generation and augmentation methods to synthesize seismic samples with accurate curvature labels. Then, a multitask end-to-end convolutional neural network architecture and a geometric loss function are proposed to establish the volume mapping model from complex seismic responses to the most positive and negative curvature volumes. The performance of the proposed curvature extraction approach is evaluated on both the synthetic data and the Netherlands F3 field seismic data. Extensive experiments demonstrate that curvature volumes extracted with the proposed approach are not only more accurate and less influenced by the noises of poststack seismic data but also more friendly for structure interpretation. Therefore, we believe that our proposed deep learning curvature extraction approach can be a useful tool for further seismic structure interpretation practices.

The outcome of endoscopic tasks can be significantly affected by the presence of specular reflections. Although numerous methods have been proposed for specular reflection detection and suppression from endoscopic images, they are inefficient, usually require tedious empirical parameters selection, and perform poorly when handling large specular regions. To this end, we propose a robust and efficient deep learning framework termed EasySpec for identifying and suppressing specular reflections from endoscopic images. Our proposed EasySpec consists of two stages: a detection stage and a suppression stage. The former stage is performed using a lightweight UNet-variant dubbed Scaled-UNet, which is trained exploiting a novel hybrid strategy that integrates the advantages of both transfer learning and weakly supervised techniques. The latter stage is achieved utilizing the concept of deep image inpainting. Specifically, a new and fast end-to-end approach for inpainting multi-size specular reflection regions in endoscopic images is developed. Our proposed approach termed GatedResUNet, takes advantage of the gated convolution to accurately differentiate specular pixels from non-specular pixels, and the U-Net architecture to learn multi-level semantic representative features, which helps reconstruct more realistic and semantically plausible images. Extensive qualitative and quantitative experiments on several endoscopic datasets acquired from different MIS scenes reveal that our proposed EasySpec outperforms state-of-the-art endoscopic specular reflection suppression approaches. Specifically, EasySpec generalizes well on various MIS scenes, and can properly reconstruct blood vessels and fine details in a reasonable processing time, which validates its practical significance.