arXiv subjects

Yirui Wang

Publications and source records attributed to Yirui Wang.

26 records · Page 2Linked to original sources

arXiv2021

Knowledge Distillation with Adaptive Asymmetric Label Sharpening for Semi-supervised Fracture Detection in Chest X-rays

Exploiting available medical records to train high performance computer-aided diagnosis (CAD) models via the semi-supervised learning (SSL) setting is emerging to tackle the prohibitively high labor costs involved in large-scale medical image annotations. Despite the extensive attentions received on SSL, previous methods failed to 1) account for the low disease prevalence in medical records and 2) utilize the image-level diagnosis indicated from the medical records. Both issues are unique to SSL for CAD models. In this work, we propose a new knowledge distillation method that effectively exploits large-scale image-level labels extracted from the medical records, augmented with limited expert annotated region-level labels, to train a rib and clavicle fracture CAD model for chest X-ray (CXR). Our method leverages the teacher-student model paradigm and features a novel adaptive asymmetric label sharpening (AALS) algorithm to address the label imbalance problem that specially exists in medical domain. Our approach is extensively evaluated on all CXR (N = 65,845) from the trauma registry of anonymous hospital over a period of 9 years (2008-2016), on the most common rib and clavicle fractures. The experiment results demonstrate that our method achieves the state-of-the-art fracture detection performance, i.e., an area under receiver operating characteristic curve (AUROC) of 0.9318 and a free-response receiver operating characteristic (FROC) score of 0.8914 on the rib fractures, significantly outperforming previous approaches by an AUROC gap of 1.63% and an FROC improvement by 3.74%. Consistent performance gains are also observed for clavicle fracture detection.

cs.CV↗

arXiv2021

A New Window Loss Function for Bone Fracture Detection and Localization in X-ray Images with Point-based Annotation

Object detection methods are widely adopted for computer-aided diagnosis using medical images. Anomalous findings are usually treated as objects that are described by bounding boxes. Yet, many pathological findings, e.g., bone fractures, cannot be clearly defined by bounding boxes, owing to considerable instance, shape and boundary ambiguities. This makes bounding box annotations, and their associated losses, highly ill-suited. In this work, we propose a new bone fracture detection method for X-ray images, based on a labor effective and flexible annotation scheme suitable for abnormal findings with no clear object-level spatial extents or boundaries. Our method employs a simple, intuitive, and informative point-based annotation protocol to mark localized pathology information. To address the uncertainty in the fracture scales annotated via point(s), we convert the annotations into pixel-wise supervision that uses lower and upper bounds with positive, negative, and uncertain regions. A novel Window Loss is subsequently proposed to only penalize the predictions outside of the uncertain regions. Our method has been extensively evaluated on 4410 pelvic X-ray images of unique patients. Experiments demonstrate that our method outperforms previous state-of-the-art image classification and object detection baselines by healthy margins, with an AUROC of 0.983 and FROC score of 89.6%.

cs.CV↗

arXiv2020

Contour Transformer Network for One-shot Segmentation of Anatomical Structures

Accurate segmentation of anatomical structures is vital for medical image analysis. The state-of-the-art accuracy is typically achieved by supervised learning methods, where gathering the requisite expert-labeled image annotations in a scalable manner remains a main obstacle. Therefore, annotation-efficient methods that permit to produce accurate anatomical structure segmentation are highly desirable. In this work, we present Contour Transformer Network (CTN), a one-shot anatomy segmentation method with a naturally built-in human-in-the-loop mechanism. We formulate anatomy segmentation as a contour evolution process and model the evolution behavior by graph convolutional networks (GCNs). Training the CTN model requires only one labeled image exemplar and leverages additional unlabeled data through newly introduced loss functions that measure the global shape and appearance consistency of contours. On segmentation tasks of four different anatomies, we demonstrate that our one-shot learning method significantly outperforms non-learning-based methods and performs competitively to the state-of-the-art fully supervised deep learning methods. With minimal human-in-the-loop editing feedback, the segmentation performance can be further improved to surpass the fully supervised methods.

cs.CV↗

arXiv2020

Assembled Kinetic Impactor for Deflecting Asteroids via Combining the Spacecraft with the Launch Vehicle Final Stage

Asteroid Impacts pose a major threat to all life on the Earth. Deflecting the asteroid from the impact trajectory is an important way to mitigate the threat. A kinetic impactor remains to be the most feasible method to deflect the asteroid. However, due to the constraint of the launch capability, an impactor with the limited mass can only produce a very limited amount of velocity increment for the asteroid. In order to improve the deflection efficiency of the kinetic impactor strategy, this paper proposed a new concept called the Assembled Kinetic Impactor (AKI), which is combining the spacecraft with the launch vehicle final stage. By making full use of the mass of the launch vehicle final stage, the mass of the impactor will be increased, which will cause the improvement of the deflection efficiency. According to the technical data of Long March 5 (CZ-5) launch vehicle, the missions of deflecting Bennu are designed to demonstrate the power of the AKI concept. Simulation results show that, compared with the Classic Kinetic Impactor (CKI, performs spacecraft-rocket separation), the addition of the mass of the launch vehicle final stage can increase the deflection distance to more than 3 times, and reduce the launch lead-time by at least 15 years. With the requirement of the same deflection distance, the addition of the mass of the launch vehicle final stage can reduce the number of launches to 1/3 of that of the number of CKI launches. The AKI concept makes it possible to defend Bennu-like large asteroids by a no-nuclear technique within 10-year launch lead-time. At the same time, for a single CZ-5, the deflection distance of a 140 m diameter asteroid within 10-year launch lead-time, can be increased from less than 1 Earth radii to more than 1 Earth radii.

astro-ph.IM↗

arXiv2020

Anatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection in X-ray Images

Visual cues of enforcing bilaterally symmetric anatomies as normal findings are widely used in clinical practice to disambiguate subtle abnormalities from medical images. So far, inadequate research attention has been received on effectively emulating this practice in CAD methods. In this work, we exploit semantic anatomical symmetry or asymmetry analysis in a complex CAD scenario, i.e., anterior pelvic fracture detection in trauma PXRs, where semantically pathological (refer to as fracture) and non-pathological (e.g., pose) asymmetries both occur. Visually subtle yet pathologically critical fracture sites can be missed even by experienced clinicians, when limited diagnosis time is permitted in emergency care. We propose a novel fracture detection framework that builds upon a Siamese network enhanced with a spatial transformer layer to holistically analyze symmetric image features. Image features are spatially formatted to encode bilaterally symmetric anatomies. A new contrastive feature learning component in our Siamese network is designed to optimize the deep image features being more salient corresponding to the underlying semantic asymmetries (caused by pelvic fracture occurrences). Our proposed method have been extensively evaluated on 2,359 PXRs from unique patients (the largest study to-date), and report an area under ROC curve score of 0.9771. This is the highest among state-of-the-art fracture detection methods, with improved clinical indications.

cs.CV↗

arXiv2020

Learning to Segment Anatomical Structures Accurately from One Exemplar

Accurate segmentation of critical anatomical structures is at the core of medical image analysis. The main bottleneck lies in gathering the requisite expert-labeled image annotations in a scalable manner. Methods that permit to produce accurate anatomical structure segmentation without using a large amount of fully annotated training images are highly desirable. In this work, we propose a novel contribution of Contour Transformer Network (CTN), a one-shot anatomy segmentor including a naturally built-in human-in-the-loop mechanism. Segmentation is formulated by learning a contour evolution behavior process based on graph convolutional networks (GCNs). Training of our CTN model requires only one labeled image exemplar and leverages additional unlabeled data through newly introduced loss functions that measure the global shape and appearance consistency of contours. We demonstrate that our one-shot learning method significantly outperforms non-learning-based methods and performs competitively to the state-of-the-art fully supervised deep learning approaches. With minimal human-in-the-loop editing feedback, the segmentation performance can be further improved and tailored towards the observer desired outcomes. This can facilitate the clinician designed imaging-based biomarker assessments (to support personalized quantitative clinical diagnosis) and outperforms fully supervised baselines.

cs.CV↗

arXiv2020

Enhanced Kinetic Impactor for Deflecting Large Potentially Hazardous Asteroids via Maneuvering Space Rocks

Asteroid impacts pose a major threat to all life on Earth. The age of the dinosaurs was abruptly ended by a 10-km-diameter asteroid. Currently, a nuclear device is the only means of deflecting large Potentially Hazardous Asteroids (PHAs) away from an Earth-impacting trajectory. The Enhanced Kinetic Impactor (EKI) concept is proposed to deflect large PHAs via maneuvering space rocks. First, an unmanned spacecraft is launched to rendezvous with an intermediate Near-Earth Asteroid (NEA). Then, more than one hundred tons of rocks are collected from the NEA as the EKI. The NEA can also be captured as the EKI if the NEA is very small. Finally, the EKI is maneuvered to impact the PHA at a high speed, resulting in a significant deflection of the PHA. For example, to deflect Apophis, as much as 200 t of rocks could be collected from a NEA as the EKI based on existing engineering capabilities. The EKI can produce a velocity increment (delta-v) of 39.81 mm/s in Apophis, thereby increasing the minimum geocentric distance during the close encounter in 2029 by 1,866.93 km. This mission can be completed in 3.96 years with a propellant cost of 2.98 t. Compared with a classic kinetic impactor, the deflection distance can be increased one order of magnitude. The EKI concept breaks through the limitation of the ground-based launch capability, which can significantly increase the mass of the impactor. We anticipate that our research will be a starting point for efficient planetary defense against large PHAs.

physics.space-ph↗

arXiv2019

Weakly Supervised Universal Fracture Detection in Pelvic X-rays

Hip and pelvic fractures are serious injuries with life-threatening complications. However, diagnostic errors of fractures in pelvic X-rays (PXRs) are very common, driving the demand for computer-aided diagnosis (CAD) solutions. A major challenge lies in the fact that fractures are localized patterns that require localized analyses. Unfortunately, the PXRs residing in hospital picture archiving and communication system do not typically specify region of interests. In this paper, we propose a two-stage hip and pelvic fracture detection method that executes localized fracture classification using weakly supervised ROI mining. The first stage uses a large capacity fully-convolutional network, i.e., deep with high levels of abstraction, in a multiple instance learning setting to automatically mine probable true positive and definite hard negative ROIs from the whole PXR in the training data. The second stage trains a smaller capacity model, i.e., shallower and more generalizable, with the mined ROIs to perform localized analyses to classify fractures. During inference, our method detects hip and pelvic fractures in one pass by chaining the probability outputs of the two stages together. We evaluate our method on 4 410 PXRs, reporting an area under the ROC curve value of 0.975, the highest among state-of-the-art fracture detection methods. Moreover, we show that our two-stage approach can perform comparably to human physicians (even outperforming emergency physicians and surgeons), in a preliminary reader study of 23 readers.

cs.CV↗