Aiming at the problem that traditional lung nodules detection method can only get low sensitivities with a lot of false positives, we propose a new framework of ensemble of convolutional neural networks (E-CNNs), and use it to significantly reduce the number of false-positive on lung nodules detection in chest radiographs (CXRs). Firstly Unsharp Mask technique is used to enhance the nodules in the CXRs. Then we cut patches in the 229×229 image containing or not containing nodule from the enhanced CXRs, which correspond to the positive and negative samples. Thirdly, 3 optimized CNNs of different input sizes and different depths, namely CNN1, CNN2 and CNN3, are constructed to detect lung nodule separately, and their input sizes are 12×12, 32×32 and 60×60, and the number of layer is 5, 7 and 9, separately. Finally, a logical AND operator is used to fuse the results of CNN1, CNN2 and CNN3, and an ensemble of convolutional neural networks (E-CNNs) are constructed for detecting lung nodules. Our experimental results on the JSRT database show our proposed E-CNNs attain a sensitivity of 94% and 84% with an average of 5.0 false-positives (FPs) per image and 2.0 FPs per image, respectively, in a 5-fold cross-validation test, which far outperforms the state of art.

Recently, most dehazed image quality assessment (DQA) methods mainly focus on the estimation of remaining haze, omitting the impact of distortions from the side effect of dehazing algorithms, which lead to their limited performance. Addressing this problem, we proposed a learning both Visibility and Distortion Aware features no-reference (NR) Dehazed image Quality Assessment method (VDA-DQA). Visibility aware features are exploited to characterize clarity optimization after dehazing, including the brightness, contrast, and sharpness aware feature extracted by complex contourlet transform (CCT). Then, distortion aware features are employed to measure the distortion artifacts of images, including the normalized histogram of local binary pattern (LBP) from the reconstructed dehazed image and the statistics of the CCT sub-bands corresponding to chroma and saturation map. Finally, all the above features are mapped into the quality scores by the support vector regression (SVR). Extensive experimental results on six public DQA datasets verify the superiority of proposed VDA-DQA in terms of the consistency with subjective visual perception, and outperforms the state-of-the-art methods.The source code of VDA-DQA is available at https://github.com/li181119/VDA-DQA.

Effectively evaluating the perceptual quality of dehazed images remains an under-explored research issue. In this paper, we propose a no-reference complex-valued convolutional neural network (CV-CNN) model to conduct automatic dehazed image quality evaluation. Specifically, a novel CV-CNN is employed that exploits the advantages of complex-valued representations, achieving better generalization capability on perceptual feature learning than real-valued ones. To learn more discriminative features to analyze the perceptual quality of dehazed images, we design a dual-stream CV-CNN architecture. The dual-stream model comprises a distortion-sensitive stream that operates on the dehazed RGB image, and a haze-aware stream on a novel dark channel difference image. The distortion-sensitive stream accounts for perceptual distortion artifacts, while the haze-aware stream addresses the possible presence of residual haze. Experimental results on three publicly available dehazed image quality assessment (DQA) databases demonstrate the effectiveness and generalization of our proposed CV-CNN DQA model as compared to state-of-the-art no-reference image quality assessment algorithms.