Toward an Expert Level of Lung Cancer Detection and Classification Using a Deep Convolutional Neural Network.

BACKGROUND: Computed tomography (CT) is essential for pulmonary nodule detection in diagnosing lung cancer. As deep learning algorithms have recently been regarded as a promising technique in medical fields, we attempt to integrate a well-trained deep learning algorithm to detect and classify pulmonary nodules derived from clinical CT images. MATERIALS AND METHODS: Open-source data sets and multicenter data sets have been used in this study. A three-dimensional convolutional neural network (CNN) was designed to detect pulmonary nodules and classify them into malignant or benign diseases based on pathologically and laboratory proven results. RESULTS: The sensitivity and specificity of this well-trained model were found to be 84.4% (95% confidence interval [CI], 80.5%-88.3%) and 83.0% (95% CI, 79.5%-86.5%), respectively. Subgroup analysis of smaller nodules (<10 mm) have demonstrated remarkable sensitivity and specificity, similar to that of larger nodules (10-30 mm). Additional model validation was implemented by comparing manual assessments done by different ranks of doctors with those performed by three-dimensional CNN. The results show that the performance of the CNN model was superior to manual assessment. CONCLUSION: Under the companion diagnostics, the three-dimensional CNN with a deep learning algorithm may assist radiologists in the future by providing accurate and timely information for diagnosing pulmonary nodules in regular clinical practices. IMPLICATIONS FOR PRACTICE: The three-dimensional convolutional neural network described in this article demonstrated both high sensitivity and high specificity in classifying pulmonary nodules regardless of diameters as well as superiority compared with manual assessment. Although it still warrants further improvement and validation in larger screening cohorts, its clinical application could definitely facilitate and assist doctors in clinical practice.

[Variation characteristics of farmland soil pH in the past 30 years of Enshi Autonomous Prefecture, Hubei, China]. / 恩施州耕地土壤pH近30年变化特征.

In order to explore temporal-spatial variability of farmland soil pH at Enshi Antonomous Prefecture, Hubei, China, soil pH during the past three decades was analyzed, using the datasets of the Second National Soil Survey (1980-1983) and the Cultivated Land Quality Evaluation (2010-2013). The natural and human factors inducing the change of soil pH were evaluated to provide theoretical guidance for further soil acidification management. Results showed that acidic soil (i.e., pH＜6.5) and neutral and alkaline soil (i.e., pH 6.5-8.5) were accounted for 98.4% and 1.6% in the farmland during the period of 2010-2013, respectively. The ratio increased 61.4% for the acidic soil but decreased 61.2% for the neutral and alkaline soil as compared with the period of 1980-1983. In addition, there was no alkaline soil (pH>8.5) in the region in 2010-2013. According to the dataset of the Second National Soil Survey (1980-1983), acidic soil was mainly distributed at Laifeng, Lichuan, Xuanen and Xianfeng counties, with the area ratio of 74.4%, 63.5%, 61.3% and 60.7%, respectively. For the period of 2010-2013, the ratio of acidic soil enhanced widely which was above 96% for each county. At Enshi Autonomous Prefecture, farmland soil showed an obvious acidification trend during the past three decades, with spatial variation of higher in the eastern part and lower in the western part of the region. Furthermore, soil pH decline occurred among different land use types in different areas. Overall, farmland soil pH declined 0.90 on average, with 1.14 decrease for upland and 0.87 for paddy soil, respectively. Clearly, upland soil acidification was severe than paddy soil. Factors related to soil acidification in the Enshi Autonomous Prefecture were mainly human factors such as unreasonable fertilizer combination, fertilizer ratio change, and more base cations taking away by high crop yield.

Efficient, Edge-Aware, Combined Color Quantization and Dithering.

In this paper, we present a novel algorithm to simultaneously accomplish color quantization and dithering of images. This is achieved by minimizing a perception-based cost function, which considers pixel-wise differences between filtered versions of the quantized image and the input image. We use edge aware filters in defining the cost function to avoid mixing colors on the opposite sides of an edge. The importance of each pixel is weighted according to its saliency. To rapidly minimize the cost function, we use a modified multi-scale iterative conditional mode (ICM) algorithm, which updates one pixel a time while keeping other pixels unchanged. As ICM is a local method, careful initialization is required to prevent termination at a local minimum far from the global one. To address this problem, we initialize ICM with a palette generated by a modified median-cut method. Compared with previous approaches, our method can produce high-quality results with a fewer visual artifacts but also requires significantly less computational effort.