64 research outputs found
Towards robust and effective shape prior modeling: sparse shape composition
No full textOrgan shape plays an important role in many clinical practices, including diagnosis, surgical planning and treatment evaluation. It is usually derived from medical images using low level appearance cues. However, due to diseases and imaging artifacts, low level appearance cues are often weak or misleading. In this situation, shape priors become critical to infer and refine the shape derived from image appearances. Effective modeling of shape priors is challenging because: 1) shape variations are complex and cannot always be modeled by parametric probability distributions; 2) a shape instance derived from image appearance cues (called an input shape) may have significant errors; and 3) local details of an input shape may be important for clinical purposes but difficult to preserve if they are not statistically significant in the training data. In this paper we propose a novel Sparse Shape Composition model (SSC) to address these three challenges in a unified framework. With our method, a sparse set of shapes is selected from the shape repository and composed together to infer and refine an input shape. This way, the prior information is implicitly incorporated on-the-fly. Our model leverages two sparsity observations of the input shape instance: 1) the input shape can be approximately represented by a sparse linear combination of shapes in the shape repository; 2) parts of the input shape may contain large errors but such errors are sparse. Our model is formulated as a sparse learning problem. Using norm relaxation, it can be solved by an efficient expectation-maximization (EM) framework. Furthermore, this model is extended to effectively handle multi-resolution, local shape priors and hierarchical priors. We also propose a framework to generate high quality training data in 3D. Our framework includes geometry processing methods and shape registration algorithms. The proposed shape prior model is extensively validated on five different medical applications: 2D lung localization in chest X-ray images, 3D liver segmentation in low-dose Computed Tomography (CT) scans, 3D segmentation of multiple rodent brain structures in Magnetic Resonance (MR) microscope, real time tracking of left ventricles in Magnetic Resonance Imaging (MRI), and high resolution CT reconstruction. Compared to state-of-the-art methods, our model exhibits better performance in all these studies.Ph. D.Includes bibliographical referencesIncludes vitaby Shaoting Zhan
Interannual and seasonal variability of glacier surface velocity in the parlung zangbo basin, tibetan plateau
No full textMonitoring glacier flow is vital to understand the response of mountain glaciers to environmental forcing in the context of global climate change. Seasonal and interannual variability of surface velocity in the temperate glaciers of the Parlung Zangbo Basin (PZB) has attracted significant attention. Detailed patterns in glacier surface velocity and its seasonal variability in the PZB are still uncertain, however. We utilized Landsat-8 (L8) OLI data to investigate in detail the variability of glacier velocity in the PZB by applying the normalized image cross-correlation method. On the basis of satellite images acquired from 2013 to 2020, we present a map of time-averaged glacier surface velocity and examined four typical glaciers (Yanong, Parlung No.4, Xueyougu, and Azha) in the PZB. Next, we explored the driving factors of surface velocity and of its variability. The results show that the glacier centerline velocity increased slightly in 2017–2020. The analysis of meteorological data at two weather stations on the outskirts of the glacier area provided some indications of increased precipitation during winter-spring. Such increase likely had an impact on ice mass accumulation in the up-stream portion of the glacier. The accumulated ice mass could have caused seasonal velocity changes in response to mass imbalance during 2017–2020. Besides, there was a clear winter-spring speedup of 40% in the upper glacier region, while a summer speedup occurred at the glacier tongue. The seasonal and interannual velocity variability was captured by the transverse velocity profiles in the four selected glaciers. The observed spatial pattern and seasonal variability in glacier surface velocity suggests that the winter-spring snow might be a driver of glacier flow in the central and upper portions of glaciers. Furthermore, the variations in glacier surface velocity are likely related to topographic setting and basal slip caused by the percolation of rainfall. The findings on glacier velocity suggest that the transfer of winter-spring accumulated ice triggered by mass conservation seems to be the main driver of changes in glacier velocity. The reasons that influence the seasonal surface velocity change need further investigation.Optical and Laser Remote Sensin
Changes in glacier albedo and the driving factors in the Western Nyainqentanglha Mountains from 2001 to 2020
No full textGlacier surface albedo dominates glacier energy balance, thus strongly affecting the glacier mass balance. Glaciers in the Western Nyainqentanglha Mountains (WNM) experienced large mass losses in the past two decades, but long-term changes of glacier albedo and its drivers are less understood. In this study, we retrieved glacier albedo with MODIS reflectance data to characterize the spatiotemporal variability of albedo from 2001 to 2020. Air temperature, rainfall, snowfall and deposition of light-absorbing impurities (LAIs) were evaluated as potential drivers of the observed variability in glacier albedo. The results showed that: (1) the glacier albedo experienced large inter-annual fluctuations, with the mean albedo being 0.552 ± 0.002 and a clear decreasing trend of 0.0443 ± 2 × 10-4 dec-1 in the WNM. The fastest decline was observed in autumn and in the vicinity of the equilibrium line altitude, indicating an extended melt season and an expansion of the ablation region to higher elevation; (2) local meteorology and LAIs deposition are the main drivers of glacier albedo change, but their effects on seasonal albedos are different due to different glacier processes. Both air temperature and the balance between liquid and solid precipitation affect summer and autumn albedos due to glacier ablation. Air temperature is the main driver of spring and winter albedos due to sublimation and metamorphism of snow, while snowfall carried by westerlies has limited influence on these two seasonal albedos due to less snowfall. LAIs mainly affect spring albedo due to high concentration coupled with the southerly wind in spring. These findings highlight the significance of changes in glacier albedo and the key role of local meteorology and LAIs deposition in determining such changes, which play an important role in glaciological and cryosphere processes. Optical and Laser Remote Sensin
Glacier area and snow cover changes in the range system surrounding tarim from 2000 to 2020 using google earth engine
No full textGlacier and snow are sensitive indicators of regional climate variability. In the early 21st century, glaciers in the West Kunlun and Pamir regions showed stable or even slightly positive mass budgets, and this is anomalous in a worldwide context of glacier recession. We studied the evolution of snow cover to understand whether it could explain the evolution of glacier area. In this study, we used the thresholding of the NDSI (Normalized Difference Snow Index) retrieved with MODIS data to extract annual glacier area and snow cover. We evaluated how the glacier trends related to snow cover area in five subregions in the Tarim Basin. The uncertainty in our retrievals was assessed by comparing MODIS results with the Landsat-5 TM in 2000 and Landsat-8 OLI in 2020 glacier delineation in five subregions. The glacier area in the Tarim Basin decreased by 1.32%/a during 2000–2020. The fastest reductions were in the East Tien Shan region, while the slowest relative reduction rate was observed in the West Tien Shan and Pamir, i.e., 0.69%/a and 1.08%/a, respectively, during 2000–2020. The relative glacier stability in Pamir may be related to the westerlies weather system, which dominates climate in this region. We studied the temporal variability of snow cover on different temporal scales. The analysis of the monthly snow cover showed that permanent snow can be reliably delineated in the months from July to September. During the summer months, the sequence of multiple snowfall and snowmelt events leads to intermittent snow cover, which was the key feature applied to discriminate snow and glacier.Optical and Laser Remote Sensin
Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train
No full textFoundation models have exhibited remarkable success in various applications,
such as disease diagnosis and text report generation. To date, a foundation
model for endoscopic video analysis is still lacking. In this paper, we propose
Endo-FM, a foundation model specifically developed using massive endoscopic
video data. First, we build a video transformer, which captures both local and
global long-range dependencies across spatial and temporal dimensions. Second,
we pre-train our transformer model using global and local views via a
self-supervised manner, aiming to make it robust to spatial-temporal variations
and discriminative across different scenes. To develop the foundation model, we
construct a large-scale endoscopy video dataset by combining 9 publicly
available datasets and a privately collected dataset from Baoshan Branch of
Renji Hospital in Shanghai, China. Our dataset overall consists of over 33K
video clips with up to 5 million frames, encompassing various protocols, target
organs, and disease types. Our pre-trained Endo-FM can be easily adopted for a
given downstream task via fine-tuning by serving as the backbone. With
experiments on 3 different types of downstream tasks, including classification,
segmentation, and detection, our Endo-FM surpasses the current state-of-the-art
(SOTA) self-supervised pre-training and adapter-based transfer learning methods
by a significant margin, such as VCL (3.1% F1, 4.8% Dice, and 5.5% F1 for
classification, segmentation, and detection) and ST-Adapter (5.9% F1, 9.6%
Dice, and 9.9% F1 for classification, segmentation, and detection). Code,
datasets, and models are released at https://github.com/med-air/Endo-FM.Comment: MICCAI 2023 camera-ready versio
Ultrasonographic characterization and prognostic follow-up of fetal cardiac involvement in maternal immune diseases
No full textObjectiveTo analyze the clinical characteristics, echocardiographic features, and prognosis of fetuses with maternal immune diseases.MethodsWe retrospectively evaluated 20 fetuses with cardiac manifestations due to maternal immune diseases from our center between 2019 and 2023 in China. Clinical and echocardiographic data of fetuses and maternal sero-immunity were collected. The pregnancy outcomes were followed up.ResultsThe cardiac manifestations seen in 20 fetuses were categorized into three types: type I: isolated-arrhythmia: seven cases (35%); type II: isolated endocardial fibroelastosis (EFE): four cases (20%); and type III: both arrhythmia and EFE: nine cases (45%). The arrhythmias in all cases were bradyarrhythmia, including sinus bradycardia and atrioventricular block. The results of maternal antibody test showed the following three types: (1) five cases were positive for anti-SSA antibody alone; (2) 10 cases of positive for both anti-SSA and anti-SSB antibody; (3) five cases of other special types of antibodies. Ultimately, four newborns were delivered and 16 fetuses were terminated. Of the mothers who chose to induce labor, three were treated and repregnant, two of which had normal fetuses, while one had a recurrence of arrhythmia, which was treated and monitored closely during the prenatal period, resulting in normalization of the fetal heart rhythm and eventual full-term delivery.ConclusionFetal cardiac involvement due to maternal immune diseases can be categorized into three types: the isolated-arrhythmia, isolated EFE, and both arrhythmia and EFE. In our study, all cases of arrhythmia were bradyarrhythmias, with sinus bradycardia being the most prevalent type. Given the strong association between maternal autoimmune diseases and fetal cardiac abnormalities such as bradyarrhythmias and EFE, prenatal ultrasound findings of these conditions should raise suspicion for maternal immune disorders. Consequently, prompt screening for maternal autoimmune antibodies is recommended
- …
