This paper studies the observer-based fault detection problem for a class of semi-Markov jump systems with conic-type nonlinearity and unknown transition rates by an event-impulse mixed triggered ...(EIMT) scheme. The EIMT scheme is used to obtain well-developed sampled data and save communication resources. In order to ensure the sensitivity to faults and the robustness against disturbances, a multi-target fault detection strategy is proposed based on the given H_/H∞ index. Then, sufficient conditions for the presence of fault detection observer are derived, and a fault detection optimization algorithm is employed to improve the H_/H∞ performance. Finally, the effectiveness and superiority of the proposed method are proved by a DC motor simulation experiment.
High performance of deep learning models on medical image segmentation greatly relies on large amount of pixel-wise annotated data, yet annotations are costly to collect. How to obtain high accuracy ...segmentation labels of medical images with limited cost (e.g. time) becomes an urgent problem. Active learning can reduce the annotation cost of image segmentation, but it faces three challenges: the cold start problem, an effective sample selection strategy for segmentation task and the burden of manual annotation. In this work, we propose a Hybrid Active Learning framework using Interactive Annotation (HAL-IA) for medical image segmentation, which reduces the annotation cost both in decreasing the amount of the annotated images and simplifying the annotation process. Specifically, we propose a novel hybrid sample selection strategy to select the most valuable samples for segmentation model performance improvement. This strategy combines pixel entropy, regional consistency and image diversity to ensure that the selected samples have high uncertainty and diversity. In addition, we propose a warm-start initialization strategy to build the initial annotated dataset to avoid the cold-start problem. To simplify the manual annotation process, we propose an interactive annotation module with suggested superpixels to obtain pixel-wise label with several clicks. We validate our proposed framework with extensive segmentation experiments on four medical image datasets. Experimental results showed that the proposed framework achieves high accuracy pixel-wise annotations and models with less labeled data and fewer interactions, outperforming other state-of-the-art methods. Our method can help physicians efficiently obtain accurate medical image segmentation results for clinical analysis and diagnosis.
•A hybrid active learning framework using interactive annotation for medical image segmentation.•A warm start initialization strategy to avoid the cold start problem.•Sample selection strategy that combines pixel entropy, region consistency and image diversity.•An interactive annotation module with suggesting superpixels.
3D coronary artery reconstruction (3D-CAR) in intravascular ultrasound (IVUS) sequences allows quantitative analyses of vessel properties. Existing methods treat two main tasks of the 3D-CAR ...separately, including the cardiac phase retrieval (CPR) and the membrane border extraction (MBE). They ignore the CPR-MBE connection that could achieve mutual promotions to both tasks. In this paper, we pioneer to achieve one-step 3D-CAR via a collaborative constraint generative adversarial network (GAN) named the AwCPM-Net. The AwCPM-Net consists of a dual-task collaborative generator and a dual-task constraint discriminator. The generator combines a self-supervised CPR branch with a semi-supervised MBE branch via a warming-up connection. The discriminator promotes dual-branch predictions simultaneously. The CPR branch requires no annotations and outputs inter-frame deformation fields used for identifying cardiac phases. Deformation fields are additionally constrained by the MBE branch and the discriminator. The MBE branch predicts membrane boundaries for each frame. Two aspects assist the semi-supervised segmentation: annotation augmentation by deformation fields of the CPR branch; information exploitation on unlabeled images enabled by GAN design. Trained and tested on an IVUS dataset acquired from atherosclerosis patients, the AwCPM-Net is effective in both CPR and MBE tasks, superior to state-of-the-art IVUS CPR or MBE methods. Hence, the AwCPM-Net reconstructs reliable 3D artery anatomy in the IVUS modality.
Inadequate generality across different organs and tasks constrains the application of ultrasound (US) image analysis methods in smart healthcare. Building a universal US foundation model holds the ...potential to address these issues. Nevertheless, the development of such foundation models encounters intrinsic challenges in US analysis, i.e., insufficient databases, low quality, and ineffective features. In this paper, we present a universal US foundation model, named USFM, generalized to diverse tasks and organs towards label efficient US image analysis. First, a large-scale Multi-organ, Multi-center, and Multi-device US database was built, comprehensively containing over two million US images. Organ-balanced sampling was employed for unbiased learning. Then, USFM is self-supervised pre-trained on the sufficient US database. To extract the effective features from low-quality US images, we proposed a spatial-frequency dual masked image modeling method. A productive spatial noise addition-recovery approach was designed to learn meaningful US information robustly, while a novel frequency band-stop masking learning approach was also employed to extract complex, implicit grayscale distribution and textural variations. Extensive experiments were conducted on the various tasks of segmentation, classification, and image enhancement from diverse organs and diseases. Comparisons with representative US image analysis models illustrate the universality and effectiveness of USFM. The label efficiency experiments suggest the USFM obtains robust performance with only 20% annotation, laying the groundwork for the rapid development of US models in clinical practices.
•The inadequate generalizability limits the downstream application of ultrasound models.•These models suffer from limited dataset, low image quality, and ineffective features.•USFM provides the prior knowledge of ultrasound images facilitating downstream tasks.•The knowledge is adequate by learning from a large-scale and multi-organ database.•USFM can extend the development of US models with high performance and label efficiency.
•A novel vessel membrane segmentation method that combines a region detector and an effective selection strategy is proposed.•Vessel membrane extraction in different IVUS frames and calcific region ...location in high-frequency IVUS images are simultaneously achieved by the proposed method.•The computational time of the proposed method is competitive, and few parameters need to be initialized.
Segmenting vessel membranes and locating the calcific region in intravascular ultrasound (IVUS) images aid physicians in the diagnosis of atherosclerosis. However, the manual extraction of the media adventitia (MA)/lumen border and calcification location are cumbersome due to the excessive number of IVUS frames. Moreover, most existing (semi-)automatic detection methods cannot achieve both vessel membrane extraction and calcification location simultaneously, and they are unable to detect vessel membranes in IVUS frames from different acquisition systems.
A fully automatic approach is proposed based on extremal regions and a flexible selection strategy to extract vessel membranes in different IVUS frames and locate the calcific region in high-frequency ones. Three main steps are included in the algorithm. First, a region detector is employed to extract extremal regions from an IVUS image. Then, according to the selection strategy, a part of the extracted regions is selected. At the same time, the calcification is located according to its special acoustic properties. Next, approximate MA and lumen border segmentation is achieved based on the selected extremal regions and the located calcification in polar coordinates. Finally, the final segmentation results are obtained by smoothing the approximate values.
To demonstrate the feasibility of the method, it was evaluated based on a standard public dataset. Furthermore, to quantitatively evaluate the segmentation performance, the Hausdorff distance (HD), Jaccard measure (JM) and percentage of area difference (PAD) were used. The results show that a mean HD of 1.13/1.21 mm, a mean JM of 0.83/0.77 and a mean PAD of 0.11/0.23 are achieved for MA/lumen border detection in 77 40-MHz IVUS images. For MA/lumen border extraction in 435 20-MHz IVUS frames, the average HD, JM and PAD values are 0.47/0.28 mm, 0.84/0.89 and 0.13/0.10, respectively. In addition, the approach successfully achieves calcification location in 40-MHz IVUS frames. In comparison with other published methods, the method proposed in this study is competitive.
According to these results, our strategy can extract MA/lumen borders in different IVUS frames and effectively locate calcification in high-frequency IVUS frames.
ABSTRACTIt is unusual to observe I accumulation in the gallbladder and high-grade serous ovarian adenocarcinoma during posttherapeutic I scan. We report the case of a 55-year-old woman with papillary ...thyroid cancer, who received total thyroidectomy and then 3 courses of I therapy. The posttherapeutic whole-body scan after the third dose of I therapy revealed abnormal I uptake in the right upper abdomen, overlapping the liver, and the pelvis. Further SPECT/CT imaging found that they were from an enlarged gallbladder and a large pelvic complex solid and cystic mass, which was pathologically confirmed as bilateral high-grade serous ovarian adenocarcinoma.
The detection of the lumen and media-adventitia (MA) borders in intravascular ultrasound (IVUS) images is crucial for quantifying plaque burdens. The challenge of the segmentation work mainly roots ...in various artifacts in the image. Most of the published methods involve the establishment of complex models but do not behave well on images with artifacts. In this study, aiming at automatically delineating borders in IVUS frames acquired by 20 MHz ultrasound probes, we present a fuzzy clustering-initialized hierarchical level set evolution (FC-HLSE) method. A cluster selection strategy based on the spatial fuzzy c-means (FCM) is proposed to generate the initial value and regularization term of the level set evolution (LSE). The contour convergence splits into two LSE steps between which an ingenious contour extraction (consisting of the morphological processing, the seek and linear interpolation, the gradient-based and circular fitting-based refinement) is carried out. We evaluate the proposed methodology on the publicly available 435 images by comparing auto-segmented results with the ground truth. The performance of the method is quantified using the Jaccard measure (JM), the Hausdorff distance (HD), the percentage of area difference (PAD), the linear regression and Bland-Altman analysis. Results reveal that our method can handle images with or without artifacts. The algorithm is able to extract the lumen/MA border with the JM of 0.90/0.89, the HD of 0.31/0.40 mm, the PAD of 0.07/0.08 in average, which is better in some cases compared with several state-of-the-art methods.
•The proposed method has admirable results on both non-artifact and artifact images.•Performance of the proposed method judged by the Jaccard measure is better than the other nine recent methods in most cases.•Resulting metrics of the proposed method are close to intra- and inter-observer variabilities.
The passive controller design issue for conic-type nonlinear Markov jump systems with unmeasurable states and mode-dependent uncertainties is considered in this paper. Firstly, we construct a ...appropriate observer and state feedback controller and design an error dynamic system. Then, an suitable Lyapunov-Krasovskii function is selected to guarantee the error dynamic system be stochastic stable and fulfills the given passive performance indicator. In the end, the validity of the presented approach is demonstrated by a numerical simulation.
Automatic extraction of the lumen-intima border (LIB) and the media-adventitia border (MAB) in intravascular ultrasound (IVUS) images is of high clinical interest. Despite the superior performance ...achieved by deep neural networks (DNNs) on various medical image segmentation tasks, there are few applications to IVUS images. The complicated pathological presentation and the lack of enough annotation in IVUS datasets make the learning process challenging. Several existing networks designed for IVUS segmentation train two groups of weights to detect the MAB and LIB separately. In this paper, we propose a multi-scale feature aggregated U-Net (MFAU-Net) to extract two membrane borders simultaneously. The MFAU-Net integrates multi-scale inputs, the deep supervision, and a bi-directional convolutional long short-term memory (BConvLSTM) unit. It is designed to sufficiently learn features from complicated IVUS images through a small number of training samples. Trained and tested on the publicly available IVUS datasets, the MFAU-Net achieves both 0.90 Jaccard measure (JM) for the MAB and LIB detection on 20 MHz dataset. The corresponding metrics on 40 MHz dataset are 0.85 and 0.84 JM respectively. Comparative evaluations with state-of-the-art published results demonstrate the competitiveness of the proposed MFAU-Net.
Positron Emission Tomography (PET) is an important clinical imaging tool but inevitably introduces radiation hazards to patients and healthcare providers. Reducing the tracer injection dose and ...eliminating the CT acquisition for attenuation correction can reduce the overall radiation dose, but often results in PET with high noise and bias. Thus, it is desirable to develop 3D methods to translate the non-attenuation-corrected low-dose PET (NAC-LDPET) into attenuation-corrected standard-dose PET (AC-SDPET). Recently, diffusion models have emerged as a new state-of-the-art deep learning method for image-to-image translation, better than traditional CNN-based methods. However, due to the high computation cost and memory burden, it is largely limited to 2D applications. To address these challenges, we developed a novel 2.5D Multi-view Averaging Diffusion Model (MADM) for 3D image-to-image translation with application on NAC-LDPET to AC-SDPET translation. Specifically, MADM employs separate diffusion models for axial, coronal, and sagittal views, whose outputs are averaged in each sampling step to ensure the 3D generation quality from multiple views. To accelerate the 3D sampling process, we also proposed a strategy to use the CNN-based 3D generation as a prior for the diffusion model. Our experimental results on human patient studies suggested that MADM can generate high-quality 3D translation images, outperforming previous CNN-based and Diffusion-based baseline methods.
