应用Micro-CT对小鼠全身脂肪扫描成像研究

目的  探讨扫描电压和X射线滤光片对小鼠全身脂肪扫描图像质量和对小鼠辐射剂量的影响。方法  选取C57BL/6小鼠6只,3只为正常对照小鼠,3只为高脂喂养的肥胖小鼠。应用Micro-CT对小鼠全身进行成像扫描,统计不同扫描条件下对小鼠的辐射剂量;使用Analyze12.0分析软件对小鼠皮下和内脏脂肪进行提取,然后评价扫描图像质量以及脂肪分布。结果  正常小鼠和肥胖小鼠的扫描结果表明,在扫描电压为70 kV和Al 1.0 mm X射线滤光片扫描条件下,小鼠皮下脂肪和内脏脂肪边界清晰且无伪影,图像质量高,辐射剂量小。使用Analyze 12.0软件分离的小鼠皮下脂肪和内脏脂肪连续且平滑,脂肪显示完整。结论  本研究为临床研究患者皮下脂肪和内脏脂肪提供了理论依据,对CT扫描电压和X射线滤光片的选择提供了数据参考。在降低扫描电压和保证图像质量的前提下,最大限度的降低患者受到的辐射剂量。     

Atlas-based prostate segmentation using an hybrid registration

Purpose  This paper presents the preliminary results of a semi-automatic method for prostate segmentation of magnetic resonance images (MRI) which aims to be incorporated in a navigation system for prostate brachytherapy. Methods  The method is based on the registration of an anatomical atlas computed from a population of 18 MRI exams onto a patient image. An hybrid registration framework which couples an intensity-based registration with a robust point-matching algorithm is used for both atlas building and atlas registration. Results  The method has been validated on the same dataset that the one used to construct the atlas using the leave-one-out method. Results gives a mean error of 3.39 mm and a standard deviation of 1.95 mm with respect to expert segmentations. Conclusions  We think that this segmentation tool may be a very valuable help to the clinician for routine quantitative image exploitation.     

Atlas-based fiber reconstruction from diffusion tensor MRI data

Purpose

Develop a neural fiber reconstruction method based on diffusion tensor imaging, which is not as sensitive to user-defined regions of interest as streamline tractography.

Methods

A simulated annealing approach is employed to find a non-rigid transformation to map a fiber bundle from a fiber atlas to another fiber bundle, which minimizes a specific energy functional. The energy functional describes how well the transformed fiber bundle fits the patient??s diffusion tensor data.

Results

The feasibility of the method is demonstrated on a diffusion tensor software phantom. We analyze the behavior of the algorithm with respect to image noise and number of iterations. First results on the datasets of patients are presented.

Conclusions

The described method maps fiber bundles based on diffusion tensor data and shows high robustness to image noise. Future developments of the method should help simplify inter-subject comparisons of fiber bundles.     

Improved segmentation of low-contrast lesions using sigmoid edge model

Purpose

The intensity profile of an image in the vicinity of a tissue’s boundary is modeled by a step/ramp function. However, this assumption does not hold in cases of low-contrast images, heterogeneous tissue textures, and where partial volume effect exists. We propose a hybrid algorithm for segmentation of CT/MR tumors in low-contrast, noisy images having heterogeneous/homogeneous or hyper-/hypo-intense abnormalities. We also model a smoothed noisy intensity profile by a sigmoid function and employ it to find the true location of boundary more accurately.

Methods

A novel combination of the SVM, watershed, and scattered data approximation algorithms is employed to initially segment a tumor. Small and large abnormalities are treated distinctly. Next, the proposed sigmoid edge model is fitted to the normal profile of the border. The estimated parameters of the model are then utilized to find true boundary of a tissue.

Results

We extensively evaluated our method using synthetic images (contaminated with varying levels of noise) and clinical CT/MR data. Clinical images included 57 CT/MR volumes consisting of small/large tumors, very low-/high-contrast images, liver/brain tumors, and hyper-/hypo-intense abnormalities. We achieved a Dice measure of \(0.83\,(\pm 0.07)\) and average symmetric surface distance of \(2.56\,(\pm 6.31)\) mm. Regarding IBSR dataset, we fulfilled Jaccard index of \(0.85\,(\pm 0.07)\). The average run-time of our code was \(154\,(\pm 71)\) s.

Conclusion

Individual treatment of small and large tumors and boundary correction using the proposed sigmoid edge model can be used to develop a robust tumor segmentation algorithm which deals with any types of tumors.

     

Atlas-based hippocampus segmentation in Alzheimer's disease and mild cognitive impairment

This study assesses the performance of public-domain automated methodologies for MRI-based segmentation of the hippocampus in elderly subjects with Alzheimer's disease (AD) and mild cognitive impairment (MCI). Structural MR images of 54 age- and gender-matched healthy elderly individuals, subjects with probable AD, and subjects with MCI were collected at the University of Pittsburgh Alzheimer's Disease Research Center. Hippocampi in subject images were automatically segmented by using AIR, SPM, FLIRT, and the fully deformable method of Chen to align the images to the Harvard atlas, MNI atlas, and randomly selected, manually labeled subject images ("cohort atlases"). Mixed-effects statistical models analyzed the effects of side of the brain, disease state, registration method, choice of atlas, and manual tracing protocol on the spatial overlap between automated segmentations and expert manual segmentations. Registration methods that produced higher degrees of geometric deformation produced automated segmentations with higher agreement with manual segmentations. Side of the brain, presence of AD, choice of reference image, and manual tracing protocol were also significant factors contributing to automated segmentation performance. Fully automated techniques can be competitive with human raters on this difficult segmentation task, but a rigorous statistical analysis shows that a variety of methodological factors must be carefully considered to insure that automated methods perform well in practice. The use of fully deformable registration methods, cohort atlases, and user-defined manual tracings are recommended for highest performance in fully automated hippocampus segmentation.     

Atlas-based fiber bundle segmentation using principal diffusion directions and spherical harmonic coefficients

PurposeTo develop an automatic atlas-based method for segmentation of fiber bundles using High Angular Resolution Diffusion Imaging (HARDI) data.HypothesisQuantitative evaluation of diffusion characteristics inside specific fiber bundles provides new insights into disease developments, evolutions, therapy effects, and surgical interventions.BackgroundMost of previous segmentation methods use similarity measures and strategies that do not lead to accurate segmentation results. They also suffer from subjectivity of initial seeds and regions of interest (ROI) defined by operator.Materials and methodsWe propose a novel method that uses Spherical Harmonic Coefficients (SHC) of HARDI diffusion signals to compute Orientation Distribution Function (ODF) and to extract Principal Diffusion Directions (PDDs). The proposed method selects most collinear PDD of neighbors of each voxel. Then, based on SHC and selected PDD, a similarity measure is proposed and used as a speed function in the level set framework that segments fiber bundles. To automate the process, an atlas-based method is used to select initial seeds for fiber bundles. To generate data for evaluation of the proposed method, an artificial pattern consisting of three crossing bundles intersected by a circular bundle is created. Also, two normal controls are imaged by two different HARDI protocols.ResultsSegmentation results for different fiber bundles in simulated data and normal control data are presented. Influence of threshold selection on the proposed segmentation method is evaluated using Dice coefficient. Also, effect of increasing the number of gradient directions on accuracy of extracted PDDs is evaluated.ConclusionThe proposed segmentation method has advantages over previous methods especially those that use similarity measures based on diffusion tensor imaging (DTI) data. These advantages are achieved by proper propagation of a hyper-surface in fiber crossing areas without making assumptions about diffusivity profile and selection of initial seeds or ROI.     

Atlas-based segmentation of 3D cerebral structures with competitive level sets and fuzzy control

We propose a novel approach for the simultaneous segmentation of multiple structures with competitive level sets driven by fuzzy control. To this end, several contours evolve simultaneously toward previously defined anatomical targets. A fuzzy decision system combines the a priori knowledge provided by an anatomical atlas with the intensity distribution of the image and the relative position of the contours. This combination automatically determines the directional term of the evolution equation of each level set. This leads to a local expansion or contraction of the contours, in order to match the boundaries of their respective targets. Two applications are presented: the segmentation of the brain hemispheres and the cerebellum, and the segmentation of deep internal structures. Experimental results on real magnetic resonance (MR) images are presented, quantitatively assessed and discussed.     

Comparison of atlas-based techniques for whole-body bone segmentation

We evaluate the accuracy of whole-body bone extraction from whole-body MR images using a number of atlas-based segmentation methods. The motivation behind this work is to find the most promising approach for the purpose of MRI-guided derivation of PET attenuation maps in whole-body PET/MRI. To this end, a variety of atlas-based segmentation strategies commonly used in medical image segmentation and pseudo-CT generation were implemented and evaluated in terms of whole-body bone segmentation accuracy. Bone segmentation was performed on 23 whole-body CT/MR image pairs via leave-one-out cross validation procedure. The evaluated segmentation techniques include: (i) intensity averaging (IA), (ii) majority voting (MV), (iii) global and (iv) local (voxel-wise) weighting atlas fusion frameworks implemented utilizing normalized mutual information (NMI), normalized cross-correlation (NCC) and mean square distance (MSD) as image similarity measures for calculating the weighting factors, along with other atlas-dependent algorithms, such as (v) shape-based averaging (SBA) and (vi) Hofmann's pseudo-CT generation method. The performance evaluation of the different segmentation techniques was carried out in terms of estimating bone extraction accuracy from whole-body MRI using standard metrics, such as Dice similarity (DSC) and relative volume difference (RVD) considering bony structures obtained from intensity thresholding of the reference CT images as the ground truth. Considering the Dice criterion, global weighting atlas fusion methods provided moderate improvement of whole-body bone segmentation (DSC = 0.65 ± 0.05) compared to non-weighted IA (DSC = 0.60 ± 0.02). The local weighed atlas fusion approach using the MSD similarity measure outperformed the other strategies by achieving a DSC of 0.81 ± 0.03 while using the NCC and NMI measures resulted in a DSC of 0.78 ± 0.05 and 0.75 ± 0.04, respectively. Despite very long computation time, the extracted bone obtained from both SBA (DSC = 0.56 ± 0.05) and Hofmann's methods (DSC = 0.60 ± 0.02) exhibited no improvement compared to non-weighted IA. Finding the optimum parameters for implementation of the atlas fusion approach, such as weighting factors and image similarity patch size, have great impact on the performance of atlas-based segmentation approaches. The voxel-wise atlas fusion approach exhibited excellent performance in terms of cancelling out the non-systematic registration errors leading to accurate and reliable segmentation results. Denoising and normalization of MR images together with optimization of the involved parameters play a key role in improving bone extraction accuracy.     

Atlas-based segmentation of white matter tracts of the human brain using diffusion tensor tractography and comparison with classical dissection

The technique of diffusion tensor tractography is gaining increasing prominence as a non-invasive method for studying the architecture of the white matter pathways in the human brain. Numerous studies have been published that attempt to identify or reconstruct particular pathways of interest. An atlas or map of all the pathways in the white matter would be particularly useful for providing detailed anatomical data that is not available in studies based on conventional MRI data. In this paper we present a method for constructing a white matter atlas to define structures from diffusion tensor tractography by making use of the locations of the anatomical terminations of individual streamlines that pass through white matter. We show how a map of unique seed regions can be used to generate tracts of interest. This approach provides anatomical information that can be rapidly applied to MRI datasets for the clear identification of white matter tracts. We show close correspondence of the tracts generated from the atlas with tracts isolated with classical dissection of post-mortem brain tissue.     

Automatic detection of aorto-femoral vessel trajectory from whole-body computed tomography angiography data sets

Extraction of the aorto-femoral vessel trajectory is important to utilize computed tomography angiography (CTA) in an integrated workflow of the image-guided work-up prior to trans-catheter aortic valve replacement (TAVR). The aim of this study was to develop a new, fully-automated technique for the extraction of the entire arterial access route from the femoral artery to the aortic root. An automatic vessel tracking algorithm was first used to find the centerline that connected the femoral accessing points and the aortic root. Subsequently, a deformable 3D-model fitting method was used to delineate the lumen boundary of the vascular trajectory in the whole-body CTA dataset. A validation was carried out by comparing the automatically obtained results with semi-automatically obtained results from two experienced observers. The whole framework was validated on whole body CTA datasets of 36 patients. The average Dice similarity indexes between the segmentations of the automatic method and observer 1 for the left ilio-femoral artery, the right ilio-femoral artery and the aorta were 0.977?±?0.030, 0.980?±?0.019, 0.982?±?0.016; the average Dice similarity indexes between the segmentations of the automatic method and observer 2 were 0.950?±?0.040, 0.954?±?0.031 and 0.965?±?0.019, respectively. The inter-observer variability resulted in a Dice similarity index of 0.954?±?0.038, 0.952?±?0.031 and 0.969?±?0.018 for the left ilio-femoral artery, the right ilio-femoral artery and the aorta. The average minimal luminal diameters (MLDs) of the ilio-femoral artery were 6.03?±?1.48, 5.70?±?1.43 and 5.52?±?1.32 mm for the automatic method, observer 1 and observer 2 respectively. The MLDs of the aorta were 13.43?±?2.54, 12.40?±?2.93 and 12.08?±?2.40 mm for the automatic method, observer 1 and observer 2 respectively. The automatic measurement overestimated the MLD slightly in the ilio-femoral artery at the average by 0.323 mm (SD?=?0.49 mm, p?<?0.001) compared to observer 1 and by 0.51 mm (SD?=?0.71 mm, p?<?0.001) compared to observer 2. The proposed segmentation approach can automatically provide reliable measurements of the entire arterial accessing route that can be used to support TAVR procedures. To the best of our knowledges, this approach is the first fully automatic segmentation method of the whole aorto-femoral vessel trajectory in CTA images.     

Automatic segmentation of the wire frame of stent grafts from CT data

Endovascular aortic replacement (EVAR) is an established technique, which uses stent grafts to treat aortic aneurysms in patients at risk of aneurysm rupture. Late stent graft failure is a serious complication in endovascular repair of aortic aneurysms. Better understanding of the motion characteristics of stent grafts will be beneficial for designing future devices. In addition, analysis of stent graft movement in individual patients in vivo can be valuable for predicting stent graft failure in these patients.To be able to gather information on stent graft motion in a quick and robust fashion, we propose an automatic method to segment stent grafts from CT data, consisting of three steps: the detection of seed points, finding the connections between these points to produce a graph, and graph processing to obtain the final geometric model in the form of an undirected graph.Using annotated reference data, the method was optimized and its accuracy was evaluated. The experiments were performed using data containing the AneuRx and Zenith stent grafts. The algorithm is robust for noise and small variations in the used parameter values, does not require much memory according to modern standards, and is fast enough to be used in a clinical setting (65 and 30 s for the two stent types, respectively). Further, it is shown that the resulting graphs have a 95% (AneuRx) and 92% (Zenith) correspondence with the annotated data.The geometric model produced by the algorithm allows incorporation of high level information and material properties. This enables us to study the in vivo motions and forces that act on the frame of the stent. We believe that such studies will provide new insights into the behavior of the stent graft in vivo, enables the detection and prediction of stent failure in individual patients, and can help in designing better stent grafts in the future.     

Automatic morphology-based brain segmentation (MBRASE) from MRI-T1 data

A method called morphology-based brain segmentation (MBRASE) has been developed for fully automatic segmentation of the brain from T1-weighted MR image data. The starting point is a supervised segmentation technique, which has proven highly effective and accurate for quantitation and visualization purposes. The proposed method automates the required user interaction, i.e., defining a seed point and a threshold range, and is based on the simple operations thresholding, erosion, and geodesic dilation. The thresholds are detected in a region growing process and are defined by connections of the brain to other tissues. The method is first evaluated on three computer simulated datasets by comparing the automated segmentations with the original distributions. The second evaluation is done on a total of 30 patient datasets, by comparing the automated segmentations with supervised segmentations carried out by a neuroanatomy expert. The comparison between two binary segmentations is performed both quantitatively and qualitatively. The automated segmentations are found to be accurate and robust. Consequently, the proposed method can be used as a default segmentation for quantitation and visualization of the human brain from T1-weighted MR images in routine clinical procedures.     

Automatic detection, segmentation and assessment of snoring from ambient acoustic data

Snoring is a prevalent condition with a variety of negative social effects and associated health problems. Treatments, both surgical and therapeutic, have been developed, but the objective non-invasive monitoring of their success remains problematic. We present a method which allows the automatic monitoring of snoring characteristics, such as intensity and frequency, from audio data captured via a freestanding microphone. This represents a simple and portable diagnostic alternative to polysomnography. Our system is based on methods that have proved effective in the field of speech recognition. Hidden Markov models (HMMs) were employed as basic elements with which to model different types of sound by means of spectrally based features. This allows periods of snoring to be identified, while rejecting silence, breathing and other sounds. Training and test data were gathered from six subjects, and annotated appropriately. The system was tested by requiring it to automatically classify snoring sounds in new audio recordings and then comparing the result with manually obtained annotations. We found that our system was able to correctly identify snores with 82-89% accuracy, despite the small size of the training set. We could further demonstrate how this segmentation can be used to measure the snoring intensity, snoring frequency and snoring index. We conclude that a system based on hidden Markov models and spectrally based features is effective in the automatic detection and monitoring of snoring from audio data.     

Learned iterative segmentation of highly variable anatomy from limited data: Applications to whole heart segmentation for congenital heart disease

Training deep learning models that segment an image in one step typically requires a large collection of manually annotated images that captures the anatomical variability in a cohort. This poses challenges when anatomical variability is extreme but training data is limited, as when segmenting cardiac structures in patients with congenital heart disease (CHD). In this paper, we propose an iterative segmentation model and show that it can be accurately learned from a small dataset. Implemented as a recurrent neural network, the model evolves a segmentation over multiple steps, from a single user click until reaching an automatically determined stopping point. We develop a novel loss function that evaluates the entire sequence of output segmentations, and use it to learn model parameters. Segmentations evolve predictably according to growth dynamics encapsulated by training data, which consists of images, partially completed segmentations, and the recommended next step. The user can easily refine the final segmentation by examining those that are earlier or later in the output sequence. Using a dataset of 3D cardiac MR scans from patients with a wide range of CHD types, we show that our iterative model offers better generalization to patients with the most severe heart malformations.     

Brain tissue segmentation based on DTI data

We present a method for automated brain tissue segmentation based on the multi-channel fusion of diffusion tensor imaging (DTI) data. The method is motivated by the evidence that independent tissue segmentation based on DTI parametric images provides complementary information of tissue contrast to the tissue segmentation based on structural MRI data. This has important applications in defining accurate tissue maps when fusing structural data with diffusion data. In the absence of structural data, tissue segmentation based on DTI data provides an alternative means to obtain brain tissue segmentation. Our approach to the tissue segmentation based on DTI data is to classify the brain into two compartments by utilizing the tissue contrast existing in a single channel. Specifically, because the apparent diffusion coefficient (ADC) values in the cerebrospinal fluid (CSF) are more than twice that of gray matter (GM) and white matter (WM), we use ADC images to distinguish CSF and non-CSF tissues. Additionally, fractional anisotropy (FA) images are used to separate WM from non-WM tissues, as highly directional white matter structures have much larger fractional anisotropy values. Moreover, other channels to separate tissue are explored, such as eigenvalues of the tensor, relative anisotropy (RA), and volume ratio (VR). We developed an approach based on the Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm that combines these two-class maps to obtain a complete tissue segmentation map of CSF, GM, and WM. Evaluations are provided to demonstrate the performance of our approach. Experimental results of applying this approach to brain tissue segmentation and deformable registration of DTI data and spoiled gradient-echo (SPGR) data are also provided.     

Detection of myeloma in skeleton of mice by whole-body optical fluorescence imaging

Development of new therapies for myeloma has been hindered by the lack of suitable preclinical animal models of the disease in which widespread tumor foci in the skeleton can be detected reliably. Traditional means of detecting skeletal tumor infiltration such as histopathology are cumbersome and labor-intensive and do not allow temporal monitoring of tumor progression or regression in response to therapy. To resolve this problem, we modified the Radl 5TGM1 model of myeloma bone disease such that fluorescent myeloma tumors can be optically imaged in situ. Here, we show that murine myeloma 5TGM1 tumor cells, engineered to express enhanced green fluorescent protein (eGFP; 5TGM1-eGFP cells), can be imaged in a temporal fashion using a fluorescence illuminator and a charge-coupled device camera in skeletons of live C57BL/KaLwRij mice. High-resolution, whole-body images of tumor-bearing mice revealed that myeloma cells homed almost exclusively to the skeleton, with multiple focal tumor foci in the axial skeleton, consistent with myeloma tumor distribution in humans. Finally, the tested antitumor treatment effect of Velcade (bortezomib), a proteasome inhibitor used clinically in myeloma, was readily detected by GFP imaging, suggesting the power of the technique in combination with the Radl 5TGM1-eGFP model for rapid preclinical assessment and sensitive monitoring of novel and potential therapeutics. Whole-body GFP imaging is practical, convenient, inexpensive, and rapid, and these advantages should enable a high throughput when evaluating in vivo efficacy of new potential antimyeloma therapeutics and assessing response to treatment.     

Semi-supervised task-driven data augmentation for medical image segmentation

Supervised learning-based segmentation methods typically require a large number of annotated training data to generalize well at test time. In medical applications, curating such datasets is not a favourable option because acquiring a large number of annotated samples from experts is time-consuming and expensive. Consequently, numerous methods have been proposed in the literature for learning with limited annotated examples. Unfortunately, the proposed approaches in the literature have not yet yielded significant gains over random data augmentation for image segmentation, where random augmentations themselves do not yield high accuracy. In this work, we propose a novel task-driven data augmentation method for learning with limited labeled data where the synthetic data generator, is optimized for the segmentation task. The generator of the proposed method models intensity and shape variations using two sets of transformations, as additive intensity transformations and deformation fields. Both transformations are optimized using labeled as well as unlabeled examples in a semi-supervised framework. Our experiments on three medical datasets, namely cardiac, prostate and pancreas, show that the proposed approach significantly outperforms standard augmentation and semi-supervised approaches for image segmentation in the limited annotation setting.The code is made publicly available at https://github.com/krishnabits001/task_driven_data_augmentation.     

Volume segmentation and reconstruction from freehand three-dimensional ultrasound data with application to ovarian follicle measurement

This article presents a semi-automatic method for segmentation and reconstruction of freehand three-dimensional (3D) ultrasound data. The method incorporates a number of interesting features within the level-set framework: First, segmentation is carried out using region competition, requiring multiple distinct and competing regions to be encoded within the framework. This region competition uses a simple dot-product based similarity measure to compare intensities within each region. In addition, segmentation and surface reconstruction is performed within the 3D domain to take advantage of the additional spatial information available. This means that the method must interpolate the surface where there are gaps in the data, a feature common to freehand 3D ultrasound reconstruction. Finally, although the level-set method is restricted to a voxel grid, no assumption is made that the data being segmented will conform to this grid and may be segmented in its world-reference position. The volume reconstruction method is demonstrated in vivo for the volume measurement of ovarian follicles. The 3D reconstructions produce a lower error variance than the current clinical measurement based on a mean diameter estimated from two-dimensional (2D) images. However, both the clinical measurement and the semi-automatic method appear to underestimate the true follicular volume.     

Preleukemic change in the bone marrow of whole-body irradiated RFM/up mice

In the whole-body irradiated mouse, various late effects of radiation are observed after the recovery from acute radiation injury. Some of these account for the familiar proneness of certain mouse strains to develop leukemias. The two experiments described below were designed to (a) identify such preleukemic changes in blood-forming tissues and (b) to find ways to manipulate them experimentally with the purpose of preventing leukemia. Preleukemic change of the bone marrow appears to be a mere quantitative departure from normal in a qualitatively non-malignant tissue. It entails increased proneness of immature (precursor) cells to react with latent virus. Our data are consistent with the assumption that this proneness is enhanced (or brought about) by removal of a controlling influence exerted by the mature cells over their precursors (feed-back inhibition). Re-irradiation combined with intravenous bone marrow substitution offsets the leukemogenic influence of an earlier radiation exposure. The effect of re-irradiation on bone marrow displaying preleukemic lesions corroborates conclusions from earlier experiments on the nature of these lesions.     

Anomaly segmentation in retinal images with poisson-blending data augmentation

Diabetic retinopathy (DR) is one of the most important complications of diabetes. Accurate segmentation of DR lesions is of great importance for the early diagnosis of DR. However, simultaneous segmentation of multi-type DR lesions is technically challenging because of 1) the lack of pixel-level annotations and 2) the large diversity between different types of DR lesions. In this study, first, we propose a novel Poisson-blending data augmentation (PBDA) algorithm to generate synthetic images, which can be easily utilized to expand the existing training data for lesion segmentation. We perform extensive experiments to recognize the important attributes in the PBDA algorithm. We show that position constraints are of great importance and that the synthesis density of one type of lesion has a joint influence on the segmentation of other types of lesions. Second, we propose a convolutional neural network architecture, named DSR-U-Net++ (i.e., DC-SC residual U-Net++), for the simultaneous segmentation of multi-type DR lesions. Ablation studies showed that the mean area under precision recall curve (AUPR) for all four types of lesions increased by >5% with PBDA. The proposed DSR-U-Net++ with PBDA outperformed the state-of-the-art methods by 1.7%-9.9% on the Indian Diabetic Retinopathy Image Dataset (IDRiD) and 67.3% on the e-ophtha dataset with respect to mean AUPR. The developed method would be an efficient tool to generate large-scale task-specific training data for other medical anomaly segmentation tasks.