Watershed Algorithm Research Articles

Improved Watershed Algorithm-Based Microscopic Images Combined with Meibomian Gland Microprobe in the Treatment of Demodectic Blepharitis.

The objective of the study was to explore microscopic images under a watershed segmentation algorithm combined with meibomian gland microprobe in the treatment of demodectic blepharitis. For segmenting the connected target objects in the image, the watershed algorithm was utilized first to obtain the target region in the image, and then, the fuzzy C-means (FCM) clustering algorithm was used to cluster the targets. The different grayscale regions in the microscopic images were segmented. 90 patients with demodectic blepharitis-related dry eyes were selected, and they were divided into experimental group 1 (group E1, n = 30), experimental group 2 (group E2, n = 30), and control group (group CG, n = 30). The breakup time (BUT) of the tear film, the subjective score of clinical symptoms, and the number of mites were compared among the three groups before and after treatment. The results showed that after treatment, the indicators of group E1 and group E2 were significantly lower than those before treatment, and the differences were statistically significant (P < 0.05). The treatment effect of group E1 was significantly better than that of the other two groups (P < 0.05). The subjective clinical symptom scores of groups E1, E2, and CG were 13.43 ± 1.41, 13.51 ± 1.41, and 13.64 ± 0.84, respectively, before treatment, and those after treatment were 3.1 ± 1.841, 5.4 ± 0.661, and 13.4 ± 0.841, respectively. The clinical sign scores of the groups E1 and E2 after treatment were remarkably different from those before treatment (P < 0.05). Compared with the scores of clinical signs and clinical symptoms after treatment, those of group E1 showed the largest differences, indicating the best treatment effect. In conclusion, the treatment effect of blepharitis could be promoted with the improved watershed algorithm, and the microscopic images combined with meibomian gland microprobe gave the better effect in the treatment of demodectic blepharitis than the conventional drug heat compress.

Graphical Image Region Extraction with K-Means Clustering and Watershed.

With a wide range of applications, image segmentation is a complex and difficult preprocessing step that plays an important role in automatic visual systems, which accuracy impacts, not only on segmentation results, but directly affects the effectiveness of the follow-up tasks. Despite the many advances achieved in the last decades, image segmentation remains a challenging problem, particularly, the segmenting of color images due to the diverse inhomogeneities of color, textures and shapes present in the descriptive features of the images. In trademark graphic images segmentation, beyond these difficulties, we must also take into account the high noise and low resolution, which are often present. Trademark graphic images can also be very heterogeneous with regard to the elements that make them up, which can be overlapping and with varying lighting conditions. Due to the immense variation encountered in corporate logos and trademark graphic images, it is often difficult to select a single method for extracting relevant image regions in a way that produces satisfactory results. Many of the hybrid approaches that integrate the Watershed and K-Means algorithms involve processing very high quality and visually similar images, such as medical images, meaning that either approach can be tweaked to work on images that follow a certain pattern. Trademark images are totally different from each other and are usually fully colored. Our system solves this difficulty given it is a generalized implementation designed to work in most scenarios, through the use of customizable parameters and completely unbiased for an image type. In this paper, we propose a hybrid approach to Image Region Extraction that focuses on automated region proposal and segmentation techniques. In particular, we analyze popular techniques such as K-Means Clustering and Watershedding and their effectiveness when deployed in a hybrid environment to be applied to a highly variable dataset. The proposed system consists of a multi-stage algorithm that takes as input an RGB image and produces multiple outputs, corresponding to the extracted regions. After preprocessing steps, a K-Means function with random initial centroids and a user-defined value for k is executed over the RGB image, generating a gray-scale segmented image, to which a threshold method is applied to generate a binary mask, containing the necessary information to generate a distance map. Then, the Watershed function is performed over the distance map, using the markers defined by the Connected Component Analysis function that labels regions on 8-way pixel connectivity, ensuring that all regions are correctly found. Finally, individual objects are labelled for extraction through a contour method, based on border following. The achieved results show adequate region extraction capabilities when processing graphical images from different datasets, where the system correctly distinguishes the most relevant visual elements of images with minimal tweaking.

Adhesive Abrasive Detection for Diamond Images based on Improved Watershed Algorithm

Diamond images have characteristics of adhesive abrasives besides much background noise, irregular abrasive shapes and different abrasive size, which brings big challenges to accurate diamond abrasive detection. Therefore, an improved watershed algorithm is put forward to detect adhesive abrasive in this work. Firstly, the diamond abrasive image is filtered by Gaussian to suppress the background noise, and then the pre-processed diamond abrasive image is reconstructed by morphology. Through the distance transform of the reconstructed image, marking features for subsequent abrasive detection can be obtained. Finally, the watershed algorithm and extended-minima transform are used to finely detect diamond abrasives and separate adhesive abrasives, respectively, so as to realize the accurate detection of adhesive diamond abrasive image. According to the results of detection experiments, the proposed method based on improved watershed algorithm and extended-minima transform can accurately detect adhesive diamond abrasive images, the recall rate of abrasive is 94.8%, which indicates good recognition accuracy and robustness of the proposed method. The accurate detection results can be further used for subsequent image analysis and abrasive feature parameter extraction.

Classification of Overlapping Eggs Based on Image Processing

This paper presents a method for classifying the overlapped eggs and counting the number of eggs on the conveyor belt using image processing techniques. The image was acquired by a webcam camera that connected to the computer and then rescaled. The image was then converted to grayscale and noise was reduced using a Gaussian blur filter. Otsu’s Binarization is used to convert the image to binary. The binary image is then subjected to morphological operations. Following that, using the Watershed Algorithm, separate the egg’s overlapped area. Finally, the prepared image is ready to be counted using the contour matrix method. This method independently classifies each egg segmentation and can count up to 18 eggs per frame with a processing time of less than 1 second.

CD45-positive tumor infiltrating lymphocytes in early-stage hormone-positive, HER2-negative (ER+/HER2-) breast cancer: Correlation with proliferation and prognostic signature scores.

e12555 Background: Tumour infiltrating lymphocytes (TILs), have been associated in higher responses to treatment and are thought to be a prognostic marker in a number of cancer types. The role of TILs in breast cancer varies depending on the molecular subtype of the disease. In hormone positive, HER2-negative breast cancer, the significance of TILs is less clear, partly due to the paucity of data in this area. We aim to assess overall TILs in early-stage, hormone-positive, HER2-negative (ER+/HER2-) breast cancer and its relationship with proliferation index, Ki67, and the 21-gene recurrence score. Methods: Archival patient tissue samples of early-stage, ER+/HER2- breast cancer from the Irish arm of the TAILORx clinical trial were used. Full-face sections of these tumours were stained with anti-CD45 antibody (DAKA clone M0701) via the automated Leica Bond III system. A watershed cell-detection algorithm from the open-source digital pathology software, QuPath, was fine-tuned to identify true cell objects and positive immune markers. Optimised detection parameters were used to calculate the percentage of overall CD45+ cells (CD45%) within the tumour area. Patient TIL categories were dichotomised into High v Low CD45%, with 10% chosen as the threshold. CD45% was further correlated with proliferation index, clinical data, and 21-gene recurrence score. Results: 409 samples were included in the analysis. The mean CD45% was 5.96, with samples ranging from 0.13 to 78.86. The majority of samples were in the range of 0-10% of CD45% positivity with 89% (n = 367) patients in this category. Stratification of the cohort by 21-gene-recurrence score (RS) into Low, Intermediate and High, showed a statistically significantly high CD45% in patients with a High RS compared to Low RS (p = 0.0015). When divided by recurrence score group, high CD45% trended toward a lower disease free survival (DFS) when compared to low CD45%, with statistical significance found in those in the Intermediate RS chemotherapy treatment arm (p = 0.009). Conclusions: The role of TILs in ER+/HER2- breast cancer is still undefined. While a High RS was associated with a higher percentage of CD45-positive lymphocytes, the impact on recurrence and response to treatment remains unclear. Further studies to assess the role of different tumour infiltrating lymphocyte phenotypes, and the spatial distribution of assessed markers, are needed.

Deep learning-based individual tree crown delineation in mangrove forests using very-high-resolution satellite imagery

Mangrove forests are vulnerable ecosystems that require broad-scale monitoring. Various solutions based on satellite imagery have emerged for this purpose but still suffer from the lack of methods to accurately delineate individual tree crowns (ITCs). Within-stand variability in crown size and shape, crown clumping and fragmentation, and understory vegetation hamper the delineation in these ecosystems. To cope with these factors, the proposed method combines a deep learning-based enhancement of ITCs with a marker-controlled watershed segmentation algorithm. The MT-EDv3 neural network is employed to compute the normalized Euclidean distance of crown pixels to treetops and a Laplacian of Gaussian filter is applied to the resulting image to enhance crown borders before segmentation. The method was applied to WorldView imagery over four mangrove sites worldwide and compared to previously published methods using standardized metrics. Accurate detection (Overall Accuracy ≥ 0.93 and Kappa ≥ 0.87) and area estimation (R2 ≥ 0.66, NRMSE ≤ 12%) of crowns was achieved for all sites using either the panchromatic band or a combination of the pan-sharpened visible-near-infrared bands. Based on Precision, Recall, and F1-score, the proposed method outperformed previous watershed segmentation and software-based algorithms of crown delineation, as well as the Mask R-CNN segmentation framework. The viewing geometry of images and the forest heterogeneity were identified as important contributors to the delineation accuracy. This study is the first to achieve accurate delineation of ITCs in mangrove forests across sites, opening perspectives of applications to satellite-based monitoring. The method shows promising transferability to other very-high-resolution satellite sensors as well as to aerial and unmanned aerial vehicle imagery and could be improved by including more spectral information and LiDAR-derived canopy height models.

Automatic microscopic diagnosis of diseases using an improved UNet++ architecture

Anthrax is a severe infectious disease caused by the Bacillus anthracis bacterium. This paper aims to design and implement a fast and reliable system based on microscopic image processing of patient tissue samples for the automatic diagnosis of anthrax and other tissues diseases, metastasis detection, patient prognosis, etc. An improved UNet++ architecture is proposed to segment microscopic images of patient tissue samples. The proposed model combines multi-scale features by adding skip connections in two paths; the forward path from the encoder to the decoder and the decoder path to the output. These new connections improve the performance of the UNet++. Integration of the squeeze and excitation-inception blocks in the new skip connections provides the network with features at different scales with different kernel sizes. Several convolutional networks are used as the backbone to extract powerful representations in the encoder section. The use of batch normalization, dropout technique, and LRelu activation function in this model accelerates convergence and increases the generalization power of the model. To overcome the problem of data imbalance of different classes, a weighted hybrid loss function is proposed, which further improved segmentation efficiency. The semantic segmentation results are converted to the instance segmentation using the marker-based watershed algorithm. Experimental results show that despite many challenges of microscopic image analysis, the proposed model is a reliable system for the automatic diagnosis of anthrax and other tissues diseases. It produces better results than state-of-the-art architectures.

A method of blasted rock image segmentation based on improved watershed algorithm

It is of great theoretical significance and practical value to establish a fast and accurate detection method for particle size of rock fragmentation. This study introduces the Phansalkar binarization method, proposes the watershed seed point marking method based on the solidity of rock block contour, and forms an adaptive watershed segmentation algorithm for blasted rock piles images based on rock block shape, which is to better solve the problem of incorrect segmentation caused by adhesion, stacking and blurred edges in blasted rock images. The algorithm first obtains the binary image after image pre-processing and performs distance transformation; then by selecting the appropriate gray threshold, the adherent part of the distance transformation image, i.e., the adherent rock blocks in the blasted rock image, is segmented and the seed points are marked based on the solidity of the contour calculated by contour detection; finally, the watershed algorithm is used to segment. The area cumulative distribution curve of the segmentation result is highly consistent with the manual segmentation, and the segmentation accuracy was above 95.65% for both limestone and granite for rock blocks with area over 100 cm2, indicating that the algorithm can accurately perform seed point marking and watershed segmentation for blasted rock image, and effectively reduce the possibility of incorrect segmentation. The method provides a new idea for particle segmentation in other fields, which has good application and promotion value.

Hematoma Segmentation of Spontaneous Intracerebral Hemorrhage Based on Watershed and Region-Growing Algorithm

To establish a brain hematoma CT image segmentation method based on watershed and region-growing algorithm so as to measure hematoma volume quickly and accurately, to explore the consistency between the results of this segmentation method and those of manual segmentation, the clinical gold standard, and to compare the results of this method with the calculation of the two Tada formulas commonly used in clinical practice. The preoperative CT images of 152 patients who were treated for spontaneous cerebral hemorrhage at the Department of Neurosurgery, West China Hospital, Sichuan University between January 2018 and June 2019 were retrospectively collected. The CT images were randomly assigned, by using a random number table, to the training set, the test set and the validation set, which contained 100 patients, 22 patients and 30 patients, respectively. The labeling results of the training set and the test set were used in algorithm training and testing. Four methods, namely, manual segmentation, algorithm segmentation, i.e., segmentation calculation based on watershed and regional growth algorithm, Tada formula, i.e., the traditional Tada formula calculation, and accurate Tada formula, i.e., accurate Tada formula calculation based on 3D-Slicer, were applied on the validation set to measure the hematoma volume. The Digital Imaging and Communications in Medicine (DICOM) data of subjects meeting the selection criteria of the study were manually segmented by two experienced neurosurgeons. The hematoma segmentation model was built based on watershed algorithm and regional growth algorithm. Seed point selected by neurosurgeons was taken as the starting point of growth. Regional grayscale difference criterion combined with manual segmentation validation were adopted to determine the regional growth threshold that met the segmentation precision requirements for intracranial hematoma. Using manual segmentation as the gold standard, Bland-Altman consistency analysis was used to verify the consistency of the three other methods for measuring hematoma volume. With manual segmentation as the gold standard, among the three methods of measuring hematoma volume, algorithm segmentation had the smallest percentage error, the narrowest range of difference, the highest intra-group correlation coefficient (0.987), good consistency, and the narrowest 95% limits of agreement ( LoA). The percentage error of its segmentation was not statistically significant for hematomas of different volumes. The segmentation method of spontaneous intracerebral hemorrhage based on watershed and regional growth algorithm shows stable measurement performance and good consistency with the clinical gold standard, which has considerable clinical significance, but it still needs further validation with more clinical samples.

Image-Based 3D Reconstruction of Granular Grains via Hybrid Algorithm and Level Set with Convolution Kernel

This study develops a novel method for reconstructing three dimensional (3D) granular grains from computed tomography (CT) images. Unlike previous studies requiring trial-and-error hyperparameters, the hybrid algorithm introduced here, integrating the random forest (RF) algorithm and enhanced by particle swarm optimization for automatic determination of hyperparameters, is the first to train the model for constituent classification and grain segmentation. In addition, and different from previous manual methods, a convolution kernel is applied to assign an initial level set function inside an individual grain and determine whether to activate the level function for automatically reconstructing 3D grains from a CT image. All results indicate the hybrid algorithm can rapidly search the optimum hyperparameters, providing a more effective way to identify the optimum RF-based model. This model segments grains with an accuracy of 90%, in comparison with a 52% accuracy achieved by the conventional watershed algorithm. The convolution kernel can accurately and automatically identify individual grains, avoiding manual assignment of an initial calculation area and ensuring grains are correctly reconstructed. Overall, the proposed method provides a more intelligent and effective way to reconstruct 3D grains from CT images.

A Novel Method for the Intelligent Recognition of Lattice Fringes in Coal HRTEM Images Based on Semantic Segmentation and Fuzzy Superpixels.

High-resolution transmission electron microscopy (HRTEM) can directly obtain the lattice fringes and structure parameters of coal. Aiming at present problems in extracting lattice fringes in HRTEM images, such as unlocated fringe regions, single-threshold segmentation, unclassified fuzzy superpixels, and tedious fringe pruning, an intelligent recognition method based on semantic segmentation, deep neural networks, fuzzy superpixels, and other algorithms is proposed. For unlocated fringe regions, the fringe regions are automatically localized with semantic segmentation. The whole semantic segmentation network adopts DeepLab V3+ based on ResNet to reduce unnecessary operations brought by non-fringe regions. For single-threshold segmentation of the image, the image is chunked before anything else. The genetic-optimized watershed algorithm is applied to divide the fringe base maps and non-fringe ones in order to avoid the distortion caused by different lights and shades of the image. For the fuzzy superpixels between the fringes and non-fringes, a similarity category judgment method based on neighboring pixels is proposed to solve the problem of unclassified fuzzy superpixels and to enrich and perfect the information of the lattice fringe base map. Eventually, as for lattice fringe overlap caused by coals piling together, a similarity judgment method based on the fringes’ characteristics is proposed to remove the bur portion of the lattice fringes and improve the pruning rate. Combining the above theories, a visualization tool based on MATLAB App Designer is designed, and the above four steps can be completed by this app to accurately display the results of coal aromatic lattice fringe identification in HRTEM images. Comparison with the lattice fringes drawn by leading experts shows that the fringes interpreted by this method are reliable. This method facilitates the extraction of lattice fringes in HRTEM, which lays the foundation for the labeling of HRTEM images in a variety of deep learning algorithms and facilitates the direct observation of coal structures by researchers.

Particle shape characterizations for energetic materials by computational geometry and stereology method

Particle shapes significantly affect viscosity and flow behavior of energetic materials, and therefore affect their packability and processability. This study presents a computational geometry framework for automatically quantifying two-dimensional (2D) and three-dimensional (3D) particle shapes of energetic materials. A specimen by mixing three typical energetic materials including HMX (octahydro-1,3,5,7-tetranitro-1,3,5,7-tetrazocine), RDX (1,3,5-Trinitroperhydro-1,3,5-triazine) and AP (Ammonium Perchlorate) particles is used in this study. This specimen is scanned by high-resolution X-ray computed tomography (X-ray CT), yielding a volumetric image. An improved watershed analysis algorithm is used to process the volumetric image to identify individual 3D particles. The stereology sampling method is used to obtain 2D projections of 3D particles. Computational geometry techniques are developed by this study to analyze 2D particle projections and 3D particle geometries to compute seven commonly used shape descriptors, including convexity, circularity, intercept sphericity, area sphericity, diameter sphericity, circle ratio sphericity, and surface area sphericity. Results show that those different shape descriptors of energetic materials can be divided into three groups based on their numerical ranges. This study also evaluates the effectiveness and accuracy of 2D shape descriptors for quantifying the true 3D shapes. The inconsistent characterization results between 2D and 3D shape descriptors suggest that researchers should be cautious when using 2D images to characterize 3D particle shapes of energetic materials. The computational geometry framework and particle shape analysis results presented in this study can be potentially useful in numerical modeling, experimental analysis, and theoretical investigation for energetic materials.

Principal component-based image segmentation: a new approach to outline in vitro cell colonies

ABSTRACT Identification, segmentation and counting of stained in vitro cell colonies play a vital part in biological assays. Automating these tasks by optical scanning of cell dishes and subsequent image processing is not trivial due to challenges with, e.g. background noise and contaminations. Here, we present a machine learning procedure to amend these issues by characterising, extracting and segmenting inquired cell colonies using principal component analysis, -means clustering and a modified watershed segmentation algorithm to automatically identify visible colonies. The proposed segmentation algorithm was tested on two data sets: a T-47D (proprietary) cell colony and a bacteria (open source) data set. High scores ( for T-47D and for bacterial images), along with low absolute percentage errors ( for T-47D and for bacterial images), underlined good agreement with ground truth data. Our approach outperformed a recent state-of-the-art method on both data sets, demonstrating the usefulness of the presented algorithm.

AN AUTOMATIC DETECTION OF BREAST CANCER USING EFFICIENT FEATURE EXTRACTION AND OPTIMIZED CLASSIFIER MODEL

Image Processing Techniques (IPTs) are widely used in healthcare. IPTs work on images to extract useful information from them. IPTs are effective in the early diagnosis of cancers which helps in their proper treatment. The number of human beings affected by cancer has drastically increased recently and more in women in the form of Breast Cancers (BCs). This work is on detecting BCs from image datasets using IPTs. This work proposes the use of Weiner Filters (WFs) in Preprocessing BC image data. WFs are applied to images as they can improve the quality of images. Image segmentations are executed using the Watershed Algorithm which detects Regions of Interest (ROIs) in images. Feature Extractions are done using the statistical method Gray Level Co-occurrence Matrix (GLCM). These extracted features are then selected using Black Widow Optimization (BWO) Algorithm. The selected features are then trained by Fuzzy Neural Networks (FNNs) which classify BC cases. The results of the classifier when evaluated were found to have a better performance on medical images in terms of Accuracy.

Build coconut counting system using image technology

In our country today, the counting of dried coconuts at the production facilities is done manually, takes a lot of time and is not accurate. The goal of this study is to build an automatic, fast and accurate coconut counting system. The study was conducted on the peeled dried coconut fruit with a diameter of 15 cm to 20 cm using image processing technology and open-source computer vision library - OpenCV library. The algorithm includes four main steps. First, determine the object and the background using the Otsu segmentation method. Next, estimate the distance between the background and the object to determine the closest area to the center of the object. Then, find the contour, determine the center and area of the object to reduce the noise. The watershed segmentation algorithm is used to separate overlapping and stacking objects. Finally, count the number of objects contained in the image. In the initial experimental results, the counting system has had an accuracy of over 95% with processing time per image about 75 ms and the counting capacity of the system is over 2000 fruits/hour has confirmed the efficiency of the proposed method.

Measuring Shape Parameters of Pearls in Batches Using Machine Vision: A Case Study.

To solve the problem of low precision of pearl shape parameters’ measurement caused by the mutual contact of batches of pearls and the error of shape sorting, a method of contacting pearls’ segmentation based on the pit detection was proposed. Multiple pearl images were obtained by backlit imaging, the quality of the pearl images was improved through appropriate preprocessing, and the contacted pearl area was extracted by calculating the area ratio of the connected domains. Then, the contour feature of the contact area was obtained by edge tracking to establish the mathematical model of the angles between the edge contour points. By judging the angle with a threshold of 60° as the candidate concave point, a concave point matching algorithm was introduced to get the true concave point, and the Euclidean distance was adopted as a metric function to achieve the segmentation of the tangent pearls. The pearl shape parameters’ model was established through the pearl contour image information, and the shape classification standard was constructed according to the national standard. Experimental results showed that the proposed method produced a better segmentation performance than the popular watershed algorithm and morphological algorithm. The segmentation accuracy was above 95%, the average loss rate was within 4%, and the sorting accuracy based on the shape information was 94%.

Bone Region Segmentation in Medical Images Based on Improved Watershed Algorithm.

Watershed algorithm is widely used in image segmentation, but it has oversegmentation in image segmentation. Therefore, an image segmentation algorithm based on K-means and improved watershed algorithm is proposed. Firstly, Gaussian filter is used to denoise human skeleton image. K-means clustering algorithm is used to segment the denoised image and the connected component with the largest area is extracted as the initial human skeleton region. The initial bone region was morphologically opened and then morphologically closed to eliminate the noise. Morphologically open operation is used to disconnect other human tissues that adhere to the human bone region and eliminate the background noise with small area, while closed operation smoothes the edge of the human bone region and fills the fracture in the contour line. Secondly, the watershed segmentation algorithm is implemented on the image after morphological operation. The similarity degree of two blocks is defined according to the mean difference of gray level of adjacent blocks and the mean value of standard deviation of gray level of pixels in the edge of the block 4-neighborhood. The adaptive threshold T is generated by Otsu method for histogram of gradient amplitude image. If the similarity degree is greater than T, the image blocks will be merged; otherwise, the image blocks will not be merged. The proposed image segmentation algorithm is used to extract and segment the human bone region from 100 medical images containing human bone. The number of blocks segmented by watershed algorithm is 2775 to 3357, but the number of blocks segmented by the proposed algorithm is 221 to 559. The experimental results show that the proposed algorithm effectively solves the oversegmentation problem of watershed algorithm and effectively segments the image target.

Online measurement and segmentation algorithm of coarse aggregate based on deep learning and experimental comparison

The quality of image processing affects the results of aggregate particle size detection. So far, the aggregate image segmentation is still limited to the traditional watershed algorithm (WA) and threshold segmentation algorithm, and their segmentation effect is limited. Therefore, a deep learning algorithm (DLA) to segment stacked coarse aggregate images was presented in this paper. Then it was used to segment the images of aggregates with different aggregate materials, particle sizes and mixing ratios, and the segmentation results were analyzed. The dataset required was made by the labelme, and trained to obtain the segmentation model of the DLA. The test results were compared with that of the traditional WA. For single-stage aggregates with particle sizes of 5–10 mm, 10–20 mm and 20–31.5 mm, the proportion of cumulative gradation calculated by DLA was increased by 5.93%, 28.62% and 23.62%, respectively, for different base materials of coarse aggregate, the proportion of cumulative gradation calculated by DLA was increased by 28.62%, 37.68% and 12.78%, respectively. For aggregate images with different mixing ratios, the segmentation results of DLA were closer to the actually configured gradation. The experimental results showed that the DLA could avoid the common phenomenon of over-segmentation and under-segmentation in the WA, and had general applicability in segmenting coarse aggregates with different particle sizes and aggregate materials.

Efficacy of Morphine Combined with Mechanical Ventilation in the Treatment of Heart Failure with Cardiac Magnetic Resonance Imaging under Artificial Intelligence Algorithms.

This study was aimed at exploring the efficacy of morphine combined with mechanical ventilation in the treatment of heart failure with artificial intelligence algorithms. The cardiac magnetic resonance imaging (MRI) under the watershed segmentation algorithm was proposed, and the local grayscale clustering watershed (LGCW) model was designed in this study. A total of 136 patients with acute left heart failure were taken as the research objects and randomly divided into the control group (conventional treatment) and the experimental group (morphine combined with mechanical ventilation), with 68 cases in each group. The left ventricular end-diastolic diameter (LVEDD), left ventricular end-systolic diameter (LVESD), left ventricular ejection fraction (LVEF), N-terminal pro-brain natriuretic peptide (NT-proBNP), arterial partial pressure of oxygen (PaO2), and arterial partial pressure of carbon dioxide (PaCO2) were observed. The results showed that the mean absolute deviation (MAD) and maximum mean absolute deviation (max-MAD) of the LGCW model were lower than those of the fuzzy k-nearest neighbor (FKNN) algorithm and local gray-scale clustering model (LGSCm). The Dice metric was also significantly higher than that of other algorithms with statistically significant differences (P < 0.05). After treatment, LVEDD, LVESD, and NT-proBNP of patients in the experimental group were significantly lower than those in the control group, and LVEF in the experimental group was higher than that in the control group (P < 0.05). PaO2 of patients in the experimental group was also significantly higher than that in the control group (P < 0.05). It suggested that the LGCW model had a better segmentation effect, and morphine combined with mechanical ventilation gave a better clinical efficacy in the treatment of acute left heart failure, improving the patients' cardiac function and arterial blood gas effectively.

Corn Seed Defect Detection Based on Watershed Algorithm and Two-Pathway Convolutional Neural Networks.

Corn seed materials of different quality were imaged, and a method for defect detection was developed based on a watershed algorithm combined with a two-pathway convolutional neural network (CNN) model. In this study, RGB and near-infrared (NIR) images were acquired with a multispectral camera to train the model, which was proved to be effective in identifying defective seeds and defect-free seeds, with an averaged accuracy of 95.63%, an averaged recall rate of 95.29%, and an F1 (harmonic average evaluation) of 95.46%. Our proposed method was superior to the traditional method that employs a one-pathway CNN with 3-channel RGB images. At the same time, the influence of different parameter settings on the model training was studied. Finally, the application of the object detection method in corn seed defect detection, which may provide an effective tool for high-throughput quality control of corn seeds, was discussed.