JinHyeong Park

Iterative Multi-domain Regularized Deep Learning for Anatomical Structure Detection and Segmentation from Ultrasound Images

Accurate detection and segmentation of anatomical structures from ultrasound images are crucial for clinical diagnosis and biometric measurements. Although ultrasound imaging has been widely used with superiorities such as low cost and portability, the fuzzy border definition and existence of abounding artifacts pose great challenges for automatically detecting and segmenting the complex anatomical structures. In this paper, we propose a multi-domain regularized deep learning method to address this challenging problem. By leveraging the transfer learning from cross domains, the feature representations are effectively enhanced. The results are further improved by the iterative refinement. Moreover, our method is quite efficient by taking advantage of a fully convolutional network, which is formulated as an end-to-end learning framework of detection and segmentation. Extensive experimental results on a large-scale database corroborated that our method achieved a superior detection and segmentation accuracy, outperforming other methods by a significant margin and demonstrating competitive capability even compared to human performance.

Automatic Vertebra Labeling in Large-Scale 3D CT Using Deep Image-to-Image Network with Message Passing and Sparsity Regularization

Automatic localization and labeling of vertebra in 3D medical images plays an important role in many clinical tasks, including pathological diagnosis, surgical planning and postoperative assessment. However, the unusual conditions of pathological cases, such as the abnormal spine curvature, bright visual imaging artifacts caused by metal implants, and the limited field of view, increase the difficulties of accurate localization. In this paper, we propose an automatic and fast algorithm to localize and label the vertebra centroids in 3D CT volumes. First, we deploy a deep image-to-image network (DI2IN) to initialize vertebra locations, employing the convolutional encoder-decoder architecture together with multi-level feature concatenation and deep supervision. Next, the centroid probability maps from DI2IN are iteratively evolved with the message passing schemes based on the mutual relation of vertebra centroids. Finally, the localization results are refined with sparsity regularization. The proposed method is evaluated on a public dataset of 302 spine CT volumes with various pathologies. Our method outperforms other state-of-the-art methods in terms of localization accuracy. The run time is around 3 seconds on average per case. To further boost the performance, we retrain the DI2IN on additional 1000+ 3D CT volumes from different patients. To the best of our knowledge, this is the first time more than 1000 3D CT volumes with expert annotation are adopted in experiments for the anatomic landmark detection tasks. Our experimental results show that training with such a large dataset significantly improves the performance and the overall identification rate, for the first time by our knowledge, reaches 90%.

Supervised Action Classifier: Approaching Landmark Detection as Image Partitioning

In medical imaging, landmarks have significant clinical and scientific importance. Clinical measurements, derived from the landmarks, are used for diagnosis, therapy planning and interventional guidance in many cases. Automatic algorithms have been studied to reduce the need for manual placement of landmarks. Traditional machine learning techniques provide reasonable results; however, they have limitation of either robustness or precision given complexities and variabilities of the medical images. Recently, deep learning technologies have been emerging to tackle the problems. Among them, a deep reinforcement learning approach (DRL) has shown to successfully detect landmark locations by implicitly learning the optimized path from a starting location; however, its learning process can only include subsets of the almost infinite paths across the image context, and may lead to major failures if not trained with adequate dataset variations. Here, we propose a new landmark detection approach inspired from DRL. Instead of learning limited action paths in an image in a greedy manner, we construct a global action map across the whole image, which divides the image into four action regions (left, right, up and bottom) depending on the relative location towards the target landmark. The action map guides how to move to reach the target landmark from any location of the input image. This effectively translates the landmark detection problem into an image partition problem which enables us to leverage a deep image-to-image network to train a supervised action classifier for detection of the landmarks. We discuss the experiment results of two ultrasound datasets (cardiac and obstetric) by applying the proposed algorithm. It shows consistent improvement over traditional machine learning based and deep learning based methods.

Automatic Nuchal Translucency Measurement from Ultrasonography

This paper proposes a fully automatic approach for computing Nuchal Translucency (NT) measurement in an ultrasound scans of the mid-sagittal plane of a fetal head. This is an improvement upon current NT measurement methods which require manual placement of NT measurement points or user-guidance in semi-automatic segmentation of the NT region. The algorithm starts by finding the pose of the fetal head using discriminative learning-based detectors. The fetal head serves as a robust anchoring structure and the NT region is estimated from the statistical relationship between the fetal head and the NT region. Next, the pose of the NT region is locally refined and its inner and outer edge approximately determined via Dijkstras shortest path applied on the edge-enhanced image. Finally, these two region edges are used to define foreground and background seeds for accurate graph cut segmentation. The NT measurement is computed from the segmented region. Experiments show that the algorithm efficiently and effectively detects the NT region and provides accurate NT measurement which suggests suitability for clinical use.

Automatic computation of 2D cardiac measurements from B-mode echocardiography

We propose a robust and fully automatic algorithm which computes the 2D echocardiography measurements recommended by America Society of Echocardiography. The algorithm employs knowledge-based imaging technologies which can learn the experts knowledge from the training images and experts annotation. Based on the models constructed from the learning stage, the algorithm searches initial location of the landmark points for the measurements by utilizing heart structure of left ventricle including mitral valve aortic valve. It employs the pseudo anatomic M-mode image generated by accumulating the line images in 2D parasternal long axis view along the time to refine the measurement landmark points. The experiment results with large volume of data show that the algorithm runs fast and is robust comparable to expert.