Ping Chen

Abstract: Segmentation of fetal left ventricle (LV) in echocardiographic sequences is important for further quantitative analysis of fetal cardiac function. However, image gross inhomogeneities and fetal random movements make the segmentation a challenging problem. In this paper, a dynamic convolutional neural networks (CNN) based on multiscale information and fine-tuning is proposed for fetal LV segmentation. The CNN is pretrained by amount of labeled training data. In the segmentation, the first frame of each echocardiographic sequence is delineated manually. The dynamic CNN is fine-tuned by deep tuning with the first frame and shallow tuning with the rest of frames, respectively, to adapt to the individual fetus. Additionally, to separate the connection region between LV and left atrium (LA), a matching approach, which consists of block matching and line matching, is used for mitral valve (MV) base points tracking. Advantages of our proposed method are compared with an active contour model (ACM), a dynamical appearance model (DAM), and a fixed multiscale CNN method. Experimental results in 51 echocardiographic sequences show that the segmentation results agree well with the ground truth, especially in the cases with leakage, blurry boundaries, and subject-to-subject variations. The CNN architecture can be simple, and the dynamic fine-tuning is efficient.

Abstract: A novel method is developed for the fetal abdominal contour extraction and measurement in ultrasound images. Fetal abdominal circumference (AC) is one of the standardized measurements in the antepartum ultrasound monitoring. Among several standardized measurements, AC is best correlated with fetal growth but is also the most difficult to be accurately measured. To overcome the difficulties in the abdominal contour extraction, the proposed method is a four-step procedure that integrates several image segmentation techniques. The proposed method is able to make the best use of the strength of different segmentation algorithms, while avoiding their deficiencies. An enhanced instantaneous coefficient of variation (ICOV) edge detector is first developed to detect edges of the abdominal contour and alleviate the effects of most speckle noise. Then, the Fuzzy C-Means clustering is employed to distinguish salient edges attributable to the abdominal contour from weak edges due to the other texture. Subsequently, the iterative Hough transform is applied to determine an elliptical contour and obtain an initial estimation of the AC. Finally, the gradient vector field (GVF) snake adapts the initial ellipse to the real edges of the abdominal contour. Quantitative validation of the proposed method on synthetic images under different imaging conditions achieves satisfactory segmentation accuracy (98.78% ± 0.16%). Experiments on 150 clinical images are carried out in three aspects: comparisons between inter-observer and inter-run variation, the fitness analysis between the automatically detected ellipse and the manual delineation, and the accuracy comparisons between automatic measurements and manual measurements in estimation of fetal weight (EFW). Experimental results show that the proposed method can provide consistent and accurate measurements. The reductions of the mean absolute difference and the standard deviation of EFW based on automatic measurements are about 1.2% and 2.1%, respectively, which indicate its potential in clinical antepartum monitoring application. (E-mail: yywang@fudan.edu.cn )

Abstract: A semi-automated fetal ultrasound image segmentation system is developed to improve the estimation of fetal weight (EFW). Four standardized fetal parameters are measured by the proposed segmentation system: biparietal diameter, head circumference, abdominal circumference and femur length. Computerized measurements of 215 fetuses are compared with manual measurements in term of fitness analysis and difference analysis. Among 215 cases, computerized measurements of 103 fetuses within 3 days of delivery are utilized in the fetal weight estimation. The EFW based on computerized measurements and manual measurements are compared by using regression analysis, artificial neural network and support vector regression. By using different estimation methods, the computerized measurements decrease the EFW errors about 40-70 g. The lowest mean absolute percentage error of EFW decrease from 6.71% for manual measurements to 4.66% for computerized measurements. The proposed fetal ultrasound image segmentation system can provide more accurate EFW in antepartum examination.

Abstract: Polycystic Ovary Syndrome (PCOS) is a complex endocrine disorder which seriously impacts women's health. The disorder is characterized by the formation of many follicular cysts in the ovary. Nowadays the diagnosis performed by doctors is to manually count the number of follicular cysts, which may lead to problems of the variability, reproducibility and low efficiency. To overcome these problems, an automated scheme is proposed to detect the PCOS. Firstly the input ovary ultrasound image is filtered by an adaptive morphological filter. Then a modified labeled watershed algorithm is used to extract contours of targets. Finally a clustering method is applied to identify expected follicular cysts. The experimental application verifies the effectivity of this proposed scheme, which achieves the accuracy rate of 84%.

Abstract: The structure detection of the first-trimester fetal heart is important for the diagnosis of fetuses, which is difficult due to the small size of the first-trimester fetal heart and the low signal-to-noise ratio of the ultrasound imaging. In the paper, a novel method is proposed for the automated detection of the fetal cardiac structure from first-trimester ultrasound images. First the region of interest for the fetal heart is automatically selected based on the established motion summation image. Then a despeckle method is proposed to simultaneously suppress the speckle noise according to its statistical property and emphasize the motion information which is important for the next detection. Finally an active appearance model is designed for the fetal heart and accomplishes the structure detection. Experiments on 258 ultrasound images verify the effectivity of our proposed method.

Abstract: Deep learning algorithms, in particular convolutional networks, have rapidly become a methodology of choice for analyzing medical images. This paper reviews the major deep learning concepts pertinent to medical image analysis and summarizes over 300 contributions to the field, most of which appeared in the last year. We survey the use of deep learning for image classification, object detection, segmentation, registration, and other tasks. Concise overviews are provided of studies per application area: neuro, retinal, pulmonary, digital pathology, breast, cardiac, abdominal, musculoskeletal. We end with a summary of the current state-of-the-art, a critical discussion of open challenges and directions for future research.

Abstract: Secret History: Return of the Black Death Channel 4, 7-8pm In 1348 the Black Death swept through London, killing people within days of the appearance of their first symptoms. Exactly how many died, and why, has long been a mystery. This Secret History documentary follows experts as they pick through the evidence and reveal why the plague killed on such a scale. And they ask, what might be coming next?

Abstract: The goals of this review paper on deep learning (DL) in medical imaging and radiation therapy are to (a) summarize what has been achieved to date; (b) identify common and unique challenges, and strategies that researchers have taken to address these challenges; and (c) identify some of the promising avenues for the future both in terms of applications as well as technical innovations. We introduce the general principles of DL and convolutional neural networks, survey five major areas of application of DL in medical imaging and radiation therapy, identify common themes, discuss methods for dataset expansion, and conclude by summarizing lessons learned, remaining challenges, and future directions.

Abstract: Ultrasound (US) has become one of the most commonly performed imaging modalities in clinical practice. It is a rapidly evolving technology with certain advantages and with unique challenges that include low imaging quality and high variability. From the perspective of image analysis, it is essential to develop advanced automatic US image analysis methods to assist in US diagnosis and/or to make such assessment more objective and accurate. Deep learning has recently emerged as the leading machine learning tool in various research fields, and especially in general imaging analysis and computer vision. Deep learning also shows huge potential for various automatic US image analysis tasks. This review first briefly introduces several popular deep learning architectures, and then summarizes and thoroughly discusses their applications in various specific tasks in US image analysis, such as classification, detection, and segmentation. Finally, the open challenges and potential trends of the future application of deep learning in medical US image analysis are discussed.