Automatic Segmentation of Anatomical Areas in X-ray Images Based on Fully Convolutional Networks / 中国医疗器械杂志

OBJECTIVE@#Medical image segmentation is a key step in medical image processing. An architecture of fully convolutional networks was proposed to realize automatic segmentation of anatomical areas in X-ray images.@*METHODS@#Enlightened by the advantages of convolutional neural networks on features extraction, fully convolutional networks consisting of 9 layers were designed to segment medical images. The networks used convolution kernels of various sizes to extract multi-dimensional image features in the images, meanwhile, eliminated pooling layers to avoid the loss of image details during downsampling procedures.@*RESULTS@#The experiment was conducted in accordance with the specific scene of X-ray images segmentation. Compared with traditional segmentation methods, this approach achieved more accurate segmentation of anatomical areas.@*CONCLUSIONS@#Fully convolutional networks can extract representative and multidimensional features of medical images, avoid the loss of image details during downsampling procedures, and complete automatic segmentation of anatomical areas accurately in X-ray images.

Using Parallel Convolutional Neural Networks for Treatment Position Recognition in X-ray Images / 中国医疗器械杂志

Treatment position recognition in medical images is a key technique in medical image processing. Due to the excellent performance of convolutional neural networks on features extraction and classification, an architecture of parallel convolutional neural networks is proposed to recognize treatment positions in X-ray images, which uses convolution kernels of different sizes to extract local features of different sizes in these images. The experimental analysis shows that parallel convolution neural networks, which can extract representative image features with more dimensions, are competent to classify and recognize treatment positions in medical images.

Radiomics:clinical application and progress / 中华放射肿瘤学杂志

Radiomics is an emerging tumor diagnosis and auxiliary detection technique that has undergone rapid development in the past few decades.The availability of new imaging equipment and reagents, as well as the use of standardized imaging protocol, has made quantitative and standardized imaging analysis possible.Radiomics is a field of study that involves the extraction of a large number of quantitative features from areas of interest in medical images using data-characterization algorithms, and transformation of these data into first-order or high-order data.The accuracy of clinical diagnosis and prognostic value of radiomics can be further improved by analyzing the relationship between data layers.Although radiomics has many advantages and has made great progress, its standardization, reliability, and application in large data and multicenter studies will need to be further optimized.

Placental transmogrification of the lung: two case report and systematic review of the literature / 中华胸心血管外科杂志

Objective Placental transmogrification of the lung(PTL) is rare;summarizes the reported cases and add our two cases, to explore the best diagnosis and treatment strategy.Methods Review of the cases reported in the literature, combined with the 2 cases described in this article, summarizes the characteristics of PTL and analyzed the best diagnosis and treatment strategy.Results We reported two cases of placental transmogrification of the lung, both presented in the right lower lobe, imaging performance as a giant bulla with a cystic nodule.VATS lobectomy was performed in both cases, no complication after operation.Combined with literature review of 34 cases of patients to analyze the best diagnosis and treatment strategy.Conclusion Grossly and microscopically, the lesion resembles placental tissue, with formation of placental villus-like papillary structures covered by epithelial cells.The most common imaging manifestation of PTL is a bullous emphysema pattern or with a mixed pattern of thin-walled cystic lesions and nodules.Early diagnosis and surgical operation should be performed as soon as possible, these lesions are best treated by minimally invasive surgery, leaving as much normal lung tissue and avoiding pneumonectomy if possible.Surgical treatment is usually curable and leads to successful improvement of symptoms and quality of life.

Prediction of near-term breast cancer risk based on virtual optical density image / 中国医学影像技术

Objective To investigate the value of improving the prediction accuracy of near-term risk for developing breast cancer by transforming the original mammography image and fusing the different types of image features using the algorithm of machine learning.Methods The craniocaudal (CC) full-field digital mammography (FFDM) of 185 women were downloaded from the clinical database at the university of Pittsburgh medical center.Firstly,the original gray images were segmented and transformed into virtual optical density images.Then the asymmetry features were separately extracted from original gray images and virtual optical density images.Two decision tree classifiers of the first stage were trained based on the features extracted from two types of image.And the scores output from the two classifiers were used as input to train the second stage of one decision tree classifier.Leave-one-case-out method was used to validate the prediction performance of near-term risk of breast cancer.Results Using two-stage decision tree fusion method to predict breast cancer,the area under the ROC curve (AUC) was 0.9612±0.0132.And the sensitivity,specificity and prediction accuracy were 96.63％(86/89),91.67％(88/96) and 94.05％(174/185).Conclusion The features extracted from virtual optical density image have higher discriminatory power of predicting breast cancer.Fusing the two kinds of image features twice by two-stage decision tree method can help to improve the prediction accuracy of near-term risk of breast cancer.