Segmentation Identification Research Articles

Artificial Intelligence in Musculoskeletal Radiology: Past, Present, and Future

Musculoskeletal radiology is an important tool for the diagnosis of muscle damage, bone fractures, bone tumors, musculoskeletal infection, and other diseases. However, all currently used radiological techniques, including radiography, ultrasonography, computed tomography, and magnetic resonance imaging are associated with their own challenges. With its ability to address these challenges, artificial intelligence (AI) holds the promise to transform a musculoskeletal radiologist’s job in several areas. In the past, AI-based approaches in musculoskeletal radiology were primarily used for measuring bone mineral density or identifying bone tumors. However, recent studies have expanded the application of AI in several other areas, such as image segmentation, resolution enhancement, and fracture identification as well automatic diagnosis of other forms of musculoskeletal damage. This review article discusses numerous older as well as more recent studies to highlight how the development and application of AI-based approaches have evolved in the field of musculoskeletal radiology and how the applicability of these approaches may be improved in the future.

Grape leaf segmentation for disease identification through adaptive Snake algorithm model

Fruits are the eminent export agriculture product for any country, especially grape, it is used for making wines and developing raisins. Moreover, Viticulture has proven to be one of the highly profitable industry from the economic point of view. However, in viticulture grape quality should be of top-notch quality, moreover throughout the research it is observed that grape quality is degraded mainly due to the plant disease. In past several researcher have tried their efforts to detect the early identification of disease. Segmentation plays bigger role identifying the disease, Hence in this paper we propose an Adaptive Snake Model for segmentation and region identification. ASA (Adaptive Snake Model) is two phase segmentation model namely common segmentation and absolute segmentation. Through common segmentation, we achieve the fast segmentation and through the absolute segmentation, we achieve the better accuracy. Moreover for evaluation of Adaptive Snake Algorithm two standard dataset i.e. PlantLevel and PlantVillage dataset, for further evaluation we have compared with various state-of-art technique in terms of various performance metric such as PSNR, Dice, Manhattan, Recall and Jaccard. Adaptive Snake Algorithm performs better than the other existing methodology.

Scalable Hash From Triplet Loss Feature Aggregation For Video De-duplication

The producing, sharing and consuming life cycle of video content creates massive amount of duplicates in video segments due to variable bit rate representation and fragmentation in the playbacks. The inefficiency of this duplicates to storage and communication motivate researchers in both academia and industry to come up with computationally efficient video deduplication solutions for storage and CDN providers. Moreover, the increasing demands of high resolution and quality aggravate the status of heavy burden of cluster storage side and restricted bandwidth resources. Hence, video de-duplication in storage and transmission is becoming an important feature for video cloud storage and Content Delivery Network (CDN) service providers. Despite of the necessity of optimizing the multimedia data de-duplication approach, it is a challenging task because we should match as many as possible duplicated videos under not removing videos by mistake. The current video de-duplication schemes mostly relies on the URL based solution, which is not able to deal with non-cacheable content like video, which the same piece of content may have totally different URL identification and fragmentation and different quality representations further complicate the problem. In this paper, we propose a novel content based video segmentation identification scheme that is invariant to the underlying codec and operational bit rates, it computes robust features from a triplet loss deep learning network that captures the invariance of the same content under different coding tools and strategy, while a scalable hashing solution is developed based on Fisher Vector aggregation of the convolutional features from the Triplet loss network. Our simulation results demonstrate the great improvement in terms of large scale video repository de-duplication compared with state-of-the-art methods.

Efficient Multi-Object Detection and Smart Navigation Using Artificial Intelligence for Visually Impaired People

Visually impaired people face numerous difficulties in their daily life, and technological interventions may assist them to meet these challenges. This paper proposes an artificial intelligence-based fully automatic assistive technology to recognize different objects, and auditory inputs are provided to the user in real time, which gives better understanding to the visually impaired person about their surroundings. A deep-learning model is trained with multiple images of objects that are highly relevant to the visually impaired person. Training images are augmented and manually annotated to bring more robustness to the trained model. In addition to computer vision-based techniques for object recognition, a distance-measuring sensor is integrated to make the device more comprehensive by recognizing obstacles while navigating from one place to another. The auditory information that is conveyed to the user after scene segmentation and obstacle identification is optimized to obtain more information in less time for faster processing of video frames. The average accuracy of this proposed method is 95.19% and 99.69% for object detection and recognition, respectively. The time complexity is low, allowing a user to perceive the surrounding scene in real time.

An efficient method for PET image denoising by combining multi-scale transform and non-local means

The diagnosis of dementia, particularly in the early stages is very much helpful with Positron emission tomography (PET) image processing. The most important challenges in PET image processing are noise removal and region of interests (ROIs) segmentation. Although denoising and segmentation are performed independently, but the performance of the denoising process significantly affects the performance of the segmentation process. Due to the low signals to noise ratio and low contrast, PET image denoising is a challenging task. Individual wavelet, curvelet and non-local means (NLM) based methods are not well suited to handle both isotropic (smooth details) and anisotropic (edges and curves) features due to its restricted abilities. To address these issues, the present work proposes an efficient denoising framework for reducing the noise level of brain PET images based on the combination of multi-scale transform (wavelet and curvelet) and tree clustering non-local means (TNLM). The main objective of the proposed method is to extract the isotropic features from a noisy smooth PET image using tree clustering based non-local means (TNLM). Then curvelet-based denoising is applied to the residual image to extract the anisotropic features such as edges and curves. Finally, the extracted anisotropic features are inserted back into the isotropic features to obtain an estimated denoised image. Simulated phantom and clinical PET datasets have been used in this proposed work for testing and measuring the performance in the medical applications, such as gray matter segmentation and precise tumor region identification without any interaction with other structural images like MRI or CT. The results in the experimental section show that the proposed denoising method has obtained better performance than existing wavelet, curvelet, wavelet-curvelet, non-local means (NLM) and deep learning methods based on the preservation of the edges. Qualitatively, a notable gain is achieved in the proposed denoised PET images in terms of contrast enhancement than other existing denoising methods.

A Method of Identifying Rust Status of Dampers Based on Image Processing

As one of the important antivibration fittings in transmission lines, the damper's accurate location, the quick detection of damper rust defect, and the timely remedial measures are all of great significance to ensure the reliable transmission of electric energy. Considering the background complexity of the damper image and harmfulness of its rust defect, a method for identifying the rust status of damper based on image processing is proposed in this article. First, the damper image acquired by the image acquisition device is grayed, and the feature enhancement of the damper region is completed by the local difference processing, the edge strength mapping based on the anisotropic Gaussian kernel directional derivative and the image fusion, and so on. Second, the segmentation of damper is completed by the threshold segmentation and the morphological treatment. Finally, the rust parameters of the damper area, which are the rusty area ratio (RAR) and the color shade index (CSI) are presented, by which the identification of the rust status can be defined as the rust-free, slight rust, medium rust, and severe rust. The results show that the segmentation and accurate identification of the rusted dampers can be completed by the proposed method. The total identification rate of the rusted dampers can reach 93% even under the complex background. The method is new and effective for identifying the rust status of damper.

Applications of Artificial Intelligence in Orthodontics

Artificial intelligence (AI) technology is a tool for finding insights in different kind of information in medical field. The purpose of this article was giving a brief introduction to applications of AI in orthodontic treatment. The reviewed literatures were further categorized into (1) extraction or non-extraction therapy in orthodontic treatment, (2) orthognathic surgery, (3) segmentation and landmark identification, (4) growth prediction, (5) cleft related studies, and (6) TMD classification.

2112-P: Sarco/Endoplasmic Reticulum ATPase (SERCA2) Deficiency in the Nonobese Diabetic (NOD) Mouse Accelerates Type 1 Diabetes Development

Recent evidence has implicated pathways intrinsic to the β cell, such as endoplasmic reticulum (ER) stress, as potential triggers of T1D. ER stress is increased by the loss of ER Ca2+, leading to decreased β cell function and increased β cell apoptosis. Maintenance of intraluminal ER Ca2+ stores is primarily regulated by the sarco/endoplasmic reticulum Ca2+ ATPase (SERCA2) pump, and we have shown that β cell SERCA2 expression is reduced in islets from mouse models of T1D prior to, and after, disease onset. Thus, we hypothesized that SERCA2-mediated ER Ca2+ dyshomeostasis could be a major contributor to T1D development. To test this, we generated a mouse model haploinsufficient for SERCA2 on the NOD background (NOD-S2+/-). Compared to wild type littermates (NOD-WT), NOD-S2+/- mice had a higher incidence of diabetes (p<0.0001) and incidence was accelerated (14.5 wks vs. 19 wks, p<0.0001). Prior to diabetes onset, NOD-S2+/- islets also had increased MHC-I expression, which has been reported to follow increased ER stress and lead to increased β cell immunogenicity. To test whether SERCA2 activation may have beneficial therapeutic effects, we treated NOD-WT and NOD-S2+/- mice with CDN1163, an allosteric activator of SERCA2, from 6-8 wks of age and observed a two week delay in NOD-S2+/- average onset (p<0.05). To characterize patterns of islet immune infiltration in response to SERCA2 loss, we are utilizing the CODEX multiplexed tissue imaging platform. Our pilot study used a ten antibody panel to label and image spleen, pancreatic lymph nodes, and islets from NOD-WT. Using Indiana University-developed software, Volumetric Tissue Exploration Analysis, our preliminary analysis yields a high fidelity of nuclear segmentation and low (∼10%) false positive identification of markers. Taken together, our data suggest that loss of SERCA2 exacerbates T1D development and indicates SERCA2 may be a novel T1D therapeutic target. Disclosure R.N. Bone: None. C.A. Reissaus: None. T. Kono: None. C. Evans-Molina: Consultant; Self; Bristol-Myers Squibb.

“Visual Affluence” in Social Photography: Applicability of Image Segmentation as a Visually Oriented Approach to Study Instagram Hashtags

The aim of the study is to examine the applicability of image segmentation—identification of objects/regions by partitioning images—to examine online social photography. We argue that the need for a meaning-independent reading of online social photography within social markers, such as hashtags, arises due to two characteristics of social photography: (1) internal incongruence resulting from user-driven construction and (2) variability of content in terms of visual attributes, such as color combinations, brightness, and details in backgrounds. We suggest visual affluence—plenitude of visual stimuli, such as objects and surfaces containing a variety of color regions, present in visual imagery—as a basis for classifying visual content and image segmentation as a technique to measure affluence. We demonstrate that images containing objects with complex texture and background patterns are more affluent, while images that include blurry backgrounds are less affluent than others. Moreover, images that contain letters and dark, single-color backgrounds are less affluent than images that include subtle shades. Mann–Whitney U test results for ten pairs of hashtags showed that eight pairs had significant differences in visual affluence. The proposed measure can be used to encourage a “visually oriented” turn in online social photography research that can benefit from hybrid methods that are able to extrapolate micro-level findings to macro-level effects.

Anatomical region segmentation method from dermoscopic images of pigmented skin lesions

AbstractMelanoma tumor can cause a serious life threatening problem in humans, if left untreated for a long time without early diagnosis. For early diagnosis of melanoma, it is more significant to develop novel methods based on biophysics analyses, molecular targets recognitions, and new image analysis criteria. In this article, anatomical region segmentation and diameter identification is proposed to detect melanoma from dermoscopic images. Four main steps of the proposed system are as follows: In the first step, the preprocessing is performed to smooth the melanoma extraction process. The region segmentation is done in the second step using watershed segmentation and Sobel operator. In the third step, the postprocessing procedures like as morphological open, canny edge detection also applied to improve the region of interest. Finally, the melanoma region is identified using color symmetry features. The proposed method is tested with two data sets to prove the performance proposed method. The proposed method achieved an accuracy of 95.31% and specificity of 98.3%, which is better than other methods. Experimental results show that the effectiveness of the proposed method and illustrate viability of real‐time clinical applications.

Grayscale distribution of maize canopy based on HLS-SVM method

ABSTRACT It is a crucial step locating the maize plant or even its target location precisely during the intelligent agricultural equipment working in farmland. Therefore, the segmentation of plants from the background image is one of the important research contents of agricultural machine vision. Under the background of significant color difference, the current method can effectively complete maize canopy segmentation and plant location identification. However, under the background of no-significant color difference, there is no robust and high-precision method for maize canopy segmentation and plant location identification. In this study, it was found that the grayscale of maize canopy had gradient distribution trend along the radial direction. The Hue Saturation Value color space and Support Vector Machine method was used to segment 600 maize canopy images, then the polynomial regression method was used to find out the functional relationship between grayscale gradient and canopy diameter. The functional relationship gave identification results of canopy central region under different gray gradient distribution. The result provided a theoretical basis for accurate identification and rapid location of maize plant center at seedling stage, and provided accurate position coordinate and yaw information for field navigation of agricultural intelligent equipment such as plant protection UAV.

Review of Clustering Techniques in Control System

Abstract Data clustering is an important tool in data mining, that helps to retrieve useful data from large amount of available data. In this digital era data is available in abundance, but finding useful data has become a challenging task. For this, data clustering is an effective and common approach where we can group data by seeing some pattern or inherent data similarity in one group. Clustering is an unsupervised learning method of linearly separable and nonlinearly separable clusters widely used for different nature of application [1]. Data clustering finds application in classification of patterns in different areas such as artificial intelligence, summarization, learning, segmentation, speech recognition, pattern recognition, image segmentation, biology, marketing, data mining, modelling and system identification etc [5][24][25]. No one clustering technique can be said as best or better than other, because different clustering algorithms co-exists and are application specific. This paper majorly emphasises on critical review of clustering algorithms used in control systems, but a brief overview is also given about all major algorithms.

Stage Identification and Classification of Lung Cancer using Deep Convolutional Neural Network

The performance of lung segmentation is highly dependent on disease prediction task. Challenges for prediction and segmentation raise the need of using multiple learning techniques. Current models initially perform image segmentation in all CT scan images and then classify it as malicious or benign. This consumes more time since it segments both normal and abnormal CT’s. So, due to improper segmentation of images the region of interest will be inaccurate and results in false classification of images. Therefore, by initially checking the CT which has malignancy and then segmenting those lesions will provide more accuracy in segmentation of cancerous nodules thereby helps to identify the stage of cancer the patient is suffering from. The aim is to improve the current cancer detection techniques using DCNN by filtering out malignant CT scan from the medical dataset and segmenting those images for stage identification. Segmentation is done using UNET++ architecture and stage identification is done by considering the “size” (T) parameter from the globally recognized standard named “TNM staging” for classifying the spread of each malignant nodule as T1-T4. 99.83 % accuracy is achieved in lung cancer classification using VGG-16 which yields better results for both segmentation and stage identification too.

Research on Imbalanced Microscopic Image Classification of Harmful Algae

Image analysis based on biological morphological differences is an important development direction for classification and determination of planktonic algae. However, it has some shortages, such as high degree of sample imbalance and difficult to have formalized description of local physiological features. To overcome these shortages, this study decomposed recognition of harmful algae microscopic images into sample supplementation, accurate segmentation, feature extraction and classification and identification. Firstly, sample imbalance is solved by Kernel-ADASYN method to generate enough samples. Target cells are separated through integration of multi-directional projections. Refined segmentation between the spine and cingulum detail regions is further realized. Later, effective feature extraction and description of global and local features were performed one by one by matching physiological features of algae with machine recognition features. Finally, the SVM model was applied for multi-class recognition. Results demonstrated that the proposed method can reduce imbalance rate of sample size and realize multi-class recognition of microscopic images of 15 categories of algae cells.

Breast Segmentation and Probable Region Identification for Breast Cancer using DL-CNN

Mammography is one of the key method used for detecting the breast cancer, several researcher has proposed the detection and segmentation method, however absolute solution has not developed till now and they have certain limitation and still it is one of the major challenge for finding the region in masses. Hence in this research work we have developed and design a novel method named as DL-CNN (Dual Layered) architecture CNN. The main intention of the model is segmentation and probable region identification. DL-CNN is based on the Convolution Neural Network. It has two layer first layer is applied for identifying the probable region whereas the second layer is used for segmentation and minimizing the false positive Reduction. In order to evaluate the DL-CNN algorithm by using the In Breast Dataset. Moreover the proposed model is compared against the various model in terms of ROI(Region of Interest), Dice_Index and False positive per Image. Result analysis shows that our model outperforms the existing

Detection of early decay on citrus using hyperspectral transmittance imaging technology coupled with principal component analysis and improved watershed segmentation algorithms

Abstract Decay caused by Penicillium spp. fungi is one of the main problems affecting marketing of citrus fruit after harvest because the fungal infection can spread fast from a small number of decayed fruit to the whole consignment. However, the automatic detection of decayed citrus is still a challenge. Early decay of citrus happen on surface peel and present a obvious symptom of water-soaked with cell tissue collapse, which may offer the feasibility of transmittance imaging mode to detect decayed region of citrus. In this study, image processing methods including principal component analysis (PCA), pseudo-color image transformation technology and improved watershed segmentation algorithms (IWSA) were employed to analyze the feasibility of decay detection based on the scanned hyperspectral transmittance images (325−1098 nm) of sound and decayed oranges. The results show that PC3 image is promising for decay segmentation. G components extracted from pseudo-color images of PC3 were selected to enhance image contrasts between decayed and sound tissues, and then decayed regions were segmented perfectly by IWSA whether the defects located on the edge or center position of oranges. However, stem-end tissue had similar features with decayed tissue and therefore were easily misidentified as decayed tissues for those decayed samples with stem-end tissue, and so stem-end identification was carried out. PC2 image and R components extracted from pseudo-color images of PC2 were promising for stem-end identification, then IWSA and morphological parameters were used to extract stem-end region. The stem-end was marked in both operations of decay segmentation and stem-end identification, hence decayed region were further determined for eliminating the misclassification interference of stem-end tissue on decay detection by removing the stem-end region from the operation of decay segmentation. For a validation set including of 84 decayed and 66 sound fruit, the success rates were 93 % and 96 %, respectively, and 94 % for decayed, sound and all fruit. Hyperspectral transmittance imaging offers a novel method for automatic detection of early decayed orange caused by fungus.

Crop Organ Segmentation and Disease Identification Based on Weakly Supervised Deep Neural Network

Object segmentation and classification using the deep convolutional neural network (DCNN) has been widely researched in recent years. On the one hand, DCNN requires large data training sets and precise labeling, which bring about great difficulties in practical application. On the other hand, it consumes a large amount of computing resources, so it is difficult to apply it to low-cost terminal equipment. This paper proposes a method of crop organ segmentation and disease recognition that is based on weakly supervised DCNN and lightweight model. While considering the actual situation in the greenhouse, we adopt a two-step strategy to reduce the interference of complex background. Firstly, we use generic instance segmentation architecture—Mask R-CNN to realize the instance segmentation of tomato organs based on weakly supervised learning, and then the disease recognition of tomato leaves is realized by depth separable multi-scale convolution. Instance segmentation algorithms usually require accurate pixel-level supervised labels, which are difficult to collect, so we propose a weakly supervised instance segmentation assignment to solve this problem. The lightweight model uses multi-scale convolution to expand the network width, which makes the extracted features richer, and depth separable convolution is adopted to reduce model parameters. The experimental results showed that our method reached higher recognition accuracy when compared with other methods, at the same time occupied less memory space, which can realize the real-time recognition of tomato diseases on low-performance terminals, and can be applied to the recognition of crop diseases in other similar application scenarios.

Aplikasi self-organizing mapping sebagai alat deteksi anemia pada citra sel darah merah

Application of self-organizing mapping as anemia detection using an image of red blood cellsBackground: Anemia is a nutritional problem characterized by changes in blood cell size, especially in microcytic or macrocytic anemia. Iron deficiency anemia is included in hypochromic microcytic anemia because it has a smaller than normal size red blood cell and has a lower than normal hemoglobin (Hb) arising from reduced supply of iron for erythropoiesis (cell maturation process red blood). Analysis based on red blood cell image is a tool to detect anemia using technology applications. Self-organizing mapping (SOM) is one of the artificial neural networks by dividing the input pattern into several groups, so the network output is in the form of groups that are most similar to the input.Objective: To measure the accuracy of SOM for detecting the size of red blood cells in anemia condition.Methods: The type of research was an observational laboratory. The study was conducted at the Electrobiomedical Laboratory of Universitas Respati Yogyakarta from January to August 2018. The sample consisted of anemia and non-anemia red blood cells which had been tested in a laboratory of 92 blood preparations. Stage of measuring red blood cells consisted of pre-processing (cropping, gray scaling, contrast enhancement, and screening), segmentation, feature extraction, and image identification with SOM. The image identification results were concluded by calculating the accuracy of the anemia detection system based on laboratory examination results.Results: The characteristic that distinguishes anemia and non-anemia was in the size of red blood cells. Anemic red blood cells had different pixel intensities than non-anemic red blood cells. The image of non-anemia red blood cells had a full round or oval image. From as many as 92 detections of blood images, five blood images were not by the target results of laboratory tests. The accuracy achieved by the system was 94.57%.Conclusions: The accuracy value of anemia detection using SOM can be used to identify the type of anemia based on red blood cell size.

An efficient wavelet and curvelet-based PET image denoising technique.

Positron emission tomography (PET) image denoising is a challenging task due to the presence of noise and low spatial resolution compared with other imaging techniques such as magnetic resonance imaging (MRI) and computed tomography (CT). PET image noise can hamper further processing and analysis, such as segmentation and disease screening. The wavelet transform-based techniques have often been proposed for PET image denoising to handle isotropic (smooth details) features. The curvelet transform-based PET image denoising techniques have the ability to handle multi-scale and multi-directional properties such as edges and curves (anisotropic features) as compared with wavelet transform-based denoising techniques. The wavelet denoising method is not optimal for anisotropic features, whereas the curvelet denoising method sometimes has difficulty in handling isotropic features. In order to handle the weaknesses of individual wavelet and curvelet-based methods, the present research proposes an efficient PET image denoising technique based on the combination of wavelet and curvelet transforms, along with a new adaptive threshold selection to threshold the wavelet coefficients in each subband (except last level low pass (LL) residual). The proposed threshold utilizes the advantages of adaptive threshold taken from BayesShrink along with the neighborhood window concept. The present method was tested on both simulated phantom and clinical PET datasets. Experimental results show that our method has achieved better results than the existing methods such as VisuShrink, BayesShrink, NeighShrink, ModineighShrink, curvelet, and an existing wavelet curvelet-based method with respect to different noise measurement metrics, such as mean squared error (MSE), signal-to-noise ratio (SNR), peak signal-to-noise ratio (PSNR), and image quality index (IQI). Furthermore, notable performance is achieved in the case of medical applications such as gray matter segmentation and precise tumor region identification. Graphical Abstract Block diagram of the proposed method. (a) Steps of the proposed denoising method and (b) image information generated by each step of (a).

A Survey on Medical Image Analysis in Capsule Endoscopy.

Capsule Endoscopy (CE) is a non-invasive, patient-friendly alternative to conventional endoscopy procedure. However, CE produces 6 to 8 hrs long video posing a tedious challenge to a gastroenterologist for abnormality detection. Major challenges to an expert are lengthy videos, need of constant concentration and subjectivity of the abnormality. To address these challenges along with high diagnostic accuracy, design and development of automated abnormality detection system is a must. Machine learning and computer vision techniques are devised to develop such automated systems. Study presents a review of quality research papers published in IEEE, Scopus, and Science Direct database with search criteria as capsule endoscopy, engineering, and journal papers. The initial search retrieved 144 publications. After evaluating all articles, 62 publications pertaining to image analysis are selected. This paper presents a rigorous review comprising all the aspects of medical image analysis concerning capsule endoscopy namely video summarization and redundant image elimination, Image enhancement and interpretation, segmentation and region identification, Computer-aided abnormality detection in capsule endoscopy, Image and video compression. The study provides a comparative analysis of various approaches, experimental setup, performance, strengths, and limitations of the aspects stated above. The analyzed image analysis techniques for capsule endoscopy have not yet overcome all current challenges mainly due to lack of dataset and complex nature of the gastrointestinal tract.