Semi-supervised Segmentation Algorithm Research Articles

Min-Max Similarity: A Contrastive Semi-Supervised Deep Learning Network for Surgical Tools Segmentation.

A common problem with segmentation of medical images using neural networks is the difficulty to obtain a significant number of pixel-level annotated data for training. To address this issue, we proposed a semi-supervised segmentation network based on contrastive learning. In contrast to the previous state-of-the-art, we introduce Min-Max Similarity (MMS), a contrastive learning form of dual-view training by employing classifiers and projectors to build all-negative, and positive and negative feature pairs, respectively, to formulate the learning as solving a MMS problem. The all-negative pairs are used to supervise the networks learning from different views and to capture general features, and the consistency of unlabeled predictions is measured by pixel-wise contrastive loss between positive and negative pairs. To quantitatively and qualitatively evaluate our proposed method, we test it on four public endoscopy surgical tool segmentation datasets and one cochlear implant surgery dataset, which we manually annotated. Results indicate that our proposed method consistently outperforms state-of-the-art semi-supervised and fully supervised segmentation algorithms. And our semi-supervised segmentation algorithm can successfully recognize unknown surgical tools and provide good predictions. Also, our MMS approach could achieve inference speeds of about 40 frames per second (fps) and is suitable to deal with the real-time video segmentation.

Semi-supervised identification and mapping of surface water extent using street-level monitoring videos

ABSTRACT Urban flooding is becoming a common and devastating hazard, which causes life loss and economic damage. Monitoring and understanding urban flooding in a highly localized scale is a challenging task due to the complicated urban landscape, intricate hydraulic process, and the lack of high-quality and resolution data. The emerging smart city technology such as monitoring cameras provides an unprecedented opportunity to address the data issue. However, estimating water ponding extents on land surfaces based on monitoring footage is unreliable using the traditional segmentation technique because the boundary of the water ponding, under the influence of varying weather, background, and illumination, is usually too fuzzy to identify, and the oblique angle and image distortion in the video monitoring data prevents georeferencing and object-based measurements. This paper presents a novel semi-supervised segmentation scheme for surface water extent recognition from the footage of an oblique monitoring camera. The semi-supervised segmentation algorithm was found suitable to determine the water boundary and the monoplotting method was successfully applied to georeference the pixels of the monitoring video for the virtual quantification of the local drainage process. The correlation and mechanism-based analysis demonstrate the value of the proposed method in advancing the understanding of local drainage hydraulics. The workflow and created methods in this study have a great potential to study other street-level and earth surface processes.

Adoption of Magnetic Resonance Image Features under Segmentation Algorithm in Effect Evaluation of Ginkgo Diterpenoid Lactone Glucamine Injection in Treatment of Cerebral Infarction.

Magnetic resonance imaging (MRI) image segmentation based on a segmentation algorithm was performed to assess neurological function in patients with acute cerebral infarction, to investigate the efficacy evaluation of Ginkgo diterpene lactones meglumine injection (GDLI) in the treatment of cerebral infarction and the efficiency of MRI image segmentation algorithm. First, the results of the fast semisupervised segmentation algorithm (algorithm group) and traditional processing (control group) were compared and analyzed. The recall rate, accuracy, recognition accuracy, and segmentation time of the two groups were compared. The control group was given conventional treatment, while the algorithm group was given GDLI based on conventional treatment. Finally, the difference in serum vascular endothelial growth factor (VEGF), hypoxia-inducible factor-la (HIF-la), angiotensin (Ang)-1, Ang-2, and interleukin (IL)-6 protein concentration was analyzed after treatment. The algorithm evaluation results showed that the accuracy and recall rate of MRI images recognized by the algorithm group fluctuate at 90%. In the control group, the accuracy and recall rate of MRI image results fluctuated at 80%, and the data were statistically different (p < 0.05). The clinical index test results showed that the serum VEGF content of the test group was higher than that of the control group, and the data was statistically different (p < 0.05). In addition, the cerebral blood flow (CBF) and cerebral blood volume (CBV) of the lesion side of the algorithm group were greatly higher than those of the control group on the 30th day, and the differences were significant (p < 0.05). There was little difference between the method presented in this study and the manual delineation by a physician. Compared with traditional manual segmentation, this method greatly reduced the time required for the segmentation of lesions. The diagnostic specificity, sensitivity, and accuracy of the images segmented by the fast semisupervised algorithm were higher than those of the conventional method, and the diagnostic accuracy of acute cerebral infarction was high. In addition, it was sensitive and accurate to detect acute cerebral infarction, which provided a reliable reference for early diagnosis and condition judgment of patients.

SemiSegSAR: A Semi-Supervised Segmentation Algorithm for Ship SAR Images

Automatic ship segmentation from high-resolution Synthetic Aperture Radar (SAR) remote sensing images has been a topic of interest that has gradually gained attention over the years due to the abundance of earth observation sensors. Recently, deep learning methods have provided a breakthrough increasing the performance greatly by using large amount of labeled data. Yet, the high cost related to the samples labeling and their scarcity result in significant limitation of their wide use. Therefore, it is crucial to overcome the unlabeled inputs challenge and develop semi-supervised learning approaches to enhance the machine learning models capacity. Our letter proposes a semi-supervised segmentation algorithm for SAR images named SemiSegSAR based on the use of Graph Signal Processing. This method includes instance segmentation; texture and statistical SAR features to represent the nodes of the graph; K-nearest neighbors to construct the graph; and Sobolev minimization algorithm to tackle the problem of semi-supervised semantic segmentation. The proposed algorithm is trained and tested using the publicly available SSDD and HRSID ship detection datasets. Experiments show that SemiSegSAR outperforms the current state-of-the-art semi-supervised and supervised methods while requiring only few labeled data.

Semi-Supervised Deep Learning for Multi-Tissue Segmentation from Multi-Contrast MRI

Segmentation of thigh tissues (muscle, fat, inter-muscular adipose tissue (IMAT), bone, and bone marrow) from magnetic resonance imaging (MRI) scans is useful for clinical and research investigations in various conditions such as aging, diabetes mellitus, obesity, metabolic syndrome, and their associated comorbidities. Towards a fully automated, robust, and precise quantification of thigh tissues, herein we designed a novel semi-supervised segmentation algorithm based on deep network architectures. Built upon Tiramisu segmentation engine, our proposed deep networks use variational and specially designed targeted dropouts for faster and robust convergence, and utilize multi-contrast MRI scans as input data. In our experiments, we have used 150 scans from 50 distinct subjects from the Baltimore Longitudinal Study of Aging (BLSA). The proposed system made use of both labeled and unlabeled data with high efficacy for training, and outperformed the current state-of-the-art methods with dice scores of 97.52%, 94.61%, 80.14%, 95.93%, and 96.83% for muscle, fat, IMAT, bone, and bone marrow tissues, respectively. Our results indicate that the proposed system can be useful for clinical research studies where volumetric and distributional tissue quantification is pivotal and labeling is a significant issue. To the best of our knowledge, the proposed system is the first attempt at multi-tissue segmentation using a single end-to-end semi-supervised deep learning framework for multi-contrast thigh MRI scans.

Ultrasonography Monitoring of Trauma-Induced Heterotopic Ossification: Guidance for Rehabilitation Procedures.

Traumatic injury is one of varying causes of heterotopic ossification (HO). After HO occurrence, rehabilitation training need alterations to avoid the aggravation of HO. Therefore, monitoring of HO development plays an important role in the rehabilitation procedure. The aims of this study are to evaluate the post-traumatic HO occurring at various joints, to describe the features of HO development in ultrasound images, and to provide a guidance for the orthopedist to make individualized rehabilitation therapy. Eight subjects with the post-traumatic HO were recruited in this study. The joints on the injured side was examined by plain radiography. The joints on the injured side and the corresponding sites on the uninjured sides were scanned by ultrsonography. The HO tissues were segmented automatically using a semi-supervised segmentation algorithm. Then the HO tissues were evaluated in comparison with the corresponding region of the uninjured side. During the development stage of immature HO, ultrasonography was sensitive to observe the involved soft tissue and the calcification of HO. The characteristics of HO tissues in ultrasound image included the hyperechoic mass occasionally accompanied with acoustic shadow and the irregular muscular architecture. It was found that the mean grayscale value of HO was significantly higher (p < 0.001) than that of the uninjured side at the middle and late stages. During the development period of HO, the HO grayscale value gradually increased and the mean grayscale of value of mature HO was significantly higher (p < 0.05) than that of immature HO. According to the information of HO provided by ultrasound, the orthopedist properly adjusted the rehabilitation treatment. The results demonstrated that the visualization of HO using ultrasonography revealed the development of HO in the muscle tissues around the injured joints and thus provide a guidance for the orthopedist to make individualized rehabilitation therapy. Ultrasound could be a useful imaging modality for quantitative evaluation of HO during the rehabilitation of traumatic injury.

A semi-supervised segmentation algorithm as applied to k-means using information value

Segmentation (or partitioning) of data for the purpose of enhancing predictive modelling is a well-established practice in the banking industry. Unsupervised and supervised approaches are the two main streams of segmentation and examples exist where the application of these techniques improved the performance of predictive models. Both these streams focus, however, on a single aspect (i.e. either target separation or independent variable distribution) and combining them may deliver better results in some instances. In this paper a semi-supervised segmentation algorithm is presented, which is based on k-means clustering and which applies information value for the purpose of informing the segmentation process. Simulated data are used to identify a few key characteristics that may cause one segmentation technique to outperform another. In the empirical study the newly proposed semi-supervised segmentation algorithm outperforms both an unsupervised and a supervised segmentation technique, when compared by using the Gini coecient as performance measure of the resulting predictive models. Key words : Banking, clustering, multivariate statistics, data mining

A semi-supervised fuzzy GrowCut algorithm to segment and classify regions of interest of mammographic images

According to the World Health Organization, breast cancer is the most common form of cancer in women. It is the second leading cause of death among women round the world, becoming the most fatal form of cancer. Despite the existence of several imaging techniques useful to aid at the diagnosis of breast cancer, x-ray mammography is still the most used and effective imaging technology. Consequently, mammographic image segmentation is a fundamental task to support image analysis and diagnosis, taking into account shape analysis of mammary lesions and their borders. However, mammogram segmentation is a very hard process, once it is highly dependent on the types of mammary tissues. The GrowCut algorithm is a relatively new method to perform general image segmentation based on the selection of just a few points inside and outside the region of interest, reaching good results at difficult segmentation cases when these points are correctly selected. In this work we present a new semi-supervised segmentation algorithm based on the modification of the GrowCut algorithm to perform automatic mammographic image segmentation once a region of interest is selected by a specialist. In our proposal, we used fuzzy Gaussian membership functions to modify the evolution rule of the original GrowCut algorithm, in order to estimate the uncertainty of a pixel being object or background. The main impact of the proposed method is the significant reduction of expert effort in the initialization of seed points of GrowCut to perform accurate segmentation, once it removes the need of selection of background seeds. Furthermore, the proposed method is robust to wrong seed positioning and can be extended to other seed based techniques. These characteristics have impact on expert and intelligent systems, once it helps to develop a segmentation method with lower required specialist knowledge, being robust and as efficient as state of the art techniques. We also constructed an automatic point selection process based on the simulated annealing optimization method, avoiding the need of human intervention. The proposed approach was qualitatively compared with other state-of-the-art segmentation techniques, considering the shape of segmented regions. In order to validate our proposal, we built an image classifier using a classical multilayer perceptron. We used Zernike moments to extract segmented image features. This analysis employed 685 mammograms from IRMA breast cancer database, using fat and fibroid tissues. Results show that the proposed technique could achieve a classification rate of 91.28% for fat tissues, evidencing the feasibility of our approach.

Applications of Hybrid Extreme Rotation Forests for image segmentation

This paper introduces the Hybrid Extreme Rotation Forest HERF classifier describing two succesful applications in the image segmentation domain. The HERF is an ensemble of classifiers composed of Extreme Learning Machines ELM and Decision Trees. Training of the HERF includes optimal rotation of random partitions of the feature set aimed to increase diversity. The first application is the segmentation of 3D Computed Tomography Angiography CTA following an Active Learning AL strategy for the optimal sample selection to minimize the number of data samples needed to obtain a required accuracy degree. AL is pertinent for interactive learning processes where a human operator is required to select training samples to enhance the classifier in an iterative process, therefore labeling samples for training may be a time consuming and expensive process. CTA image segmentation is one of such processes, due to the variability in CTA images which hinders the generalization of classifiers trained on one dataset to new datasets. Following an AL strategy, the human operator is presented with a visual selection of pixels whose labeling would be most informative for the classifier. After adding those labeled pixels to the training data, the classifier is retrained. This iteration is repeated until image segmentation quality meets the required level. The approach is applied to the segmentation of the thrombus in CTA imaging of Abdominal Aortic Aneurysm AAA patients, showing that the structures of interest can be accurately segmented after a few iterations using a small data sample. The second application is a new semisupervised segmentation algorithm for hyperspectral images. The algorithm steps are: 1 supervised training an initial classifier from a small balanced training set, 2 clustering of the image pixels, by a k-means algorithm 3 adding unlabeled pixels to the original trainning data set according to the spatial neighborhood and the cluster membership, 4 supervised training of the classifier with the enriched training data set, 6 classification of the hyperspectral image 4 spatial regularization of classification results consisting in selecting the most frequent class in each pixel neighborhood. Results on two well known benchmarking hyperspectral images improve over state of the art algorithms.

Defect Detection in Patterned Fabrics Using Wavelet Filter

This paper investigates the problem of automated defect detection for textile fabrics and proposes a new optimal filter design method for solving this problem. Wavelet is used to extract the texture features of textile fabrics. In view of this optimal filter, a news semi-supervised segmentation algorithm is then proposed. The performance of the scheme is evaluated by using a variety of homogeneous textile images with different types of common defects. The test results exhibit accurate defect detection with low false alarm, thus confirming the robustness and effectiveness of the proposed scheme.

Semisupervised Hyperspectral Image Segmentation Using Multinomial Logistic Regression With Active Learning

This paper presents a new semisupervised segmentation algorithm, suited to high-dimensional data, of which remotely sensed hyperspectral image data sets are an example. The algorithm implements two main steps: 1) semisupervised learning of the posterior class distributions followed by 2) segmentation, which infers an image of class labels from a posterior distribution built on the learned class distributions and on a Markov random field. The posterior class distributions are modeled using multinomial logistic regression, where the regressors are learned using both labeled and, through a graph-based technique, unlabeled samples. Such unlabeled samples are actively selected based on the entropy of the corresponding class label. The prior on the image of labels is a multilevel logistic model, which enforces segmentation results in which neighboring labels belong to the same class. The maximum a posteriori segmentation is computed by the α-expansion min-cut-based integer optimization algorithm. Our experimental results, conducted using synthetic and real hyperspectral image data sets collected by the Airborne Visible/Infrared Imaging Spectrometer system of the National Aeronautics and Space Administration Jet Propulsion Laboratory over the regions of Indian Pines, IN, and Salinas Valley, CA, reveal that the proposed approach can provide classification accuracies that are similar or higher than those achieved by other supervised methods for the considered scenes. Our results also indicate that the use of a spatial prior can greatly improve the final results with respect to a case in which only the learned class densities are considered, confirming the importance of jointly considering spatial and spectral information in hyperspectral image segmentation.