Union Intersection Research Articles

Bridge Crack Segmentation Method Based on Parallel Attention Mechanism and Multi-Scale Features Fusion

Regular inspection of bridge cracks is crucial to bridge maintenance and repair. The traditional manual crack detection methods are time-consuming, dangerous and subjective. At the same time, for the existing mainstream vision-based automatic crack detection algorithms, it is challenging to detect fine cracks and balance the detection accuracy and speed. Therefore, this paper proposes a new bridge crack segmentation method based on parallel attention mechanism and multi-scale features fusion on top of the DeeplabV3+ network framework. First, the improved lightweight MobileNet-v2 network and dilated separable convolution are integrated into the original DeeplabV3+ network to improve the original backbone network Xception and atrous spatial pyramid pooling (ASPP) module, respectively, dramatically reducing the number of parameters in the network and accelerates the training and prediction speed of the model. Moreover, we introduce the parallel attention mechanism into the encoding and decoding stages. The attention to the crack regions can be enhanced from the aspects of both channel and spatial parts and significantly suppress the interference of various noises. Finally, we further improve the detection performance of the model for fine cracks by introducing a multi-scale features fusion module. Our research results are validated on the self-made dataset. The experiments show that our method is more accurate than other methods. Its intersection of union (IoU) and F1-score (F1) are increased to 77.96% and 87.57%, respectively. In addition, the number of parameters is only 4.10 M, which is much smaller than the original network; also, the frames per second (FPS) is increased to 15 frames/s. The results prove that the proposed method fits well the requirements of rapid and accurate detection of bridge cracks and is superior to other methods.

Mining Joint Intraimage and Interimage Context for Remote Sensing Change Detection

Recent deep learning methods for change detection focus on excavating more discriminative context within individual images. However, due to seasonal change, noise, and so on, the appearance of objects tends to be more heterogeneous among various scenes. Consequently, the above intra-image context is inadequate to represent specific-category objects and pseudo changes would be inevitable in detection results. To deal with this issue, we propose a context aggregation network (CANet) to mine inter-image context over all training images for further enhancing intra-image context. Specifically, a Siamese network attached with temporal attention modules is served as a feature encoder to extract multi-scale temporal features from bitemporal images. Then, a context extraction module is devised to capture long-range spatial-channel context within individual images. Meanwhile, context representations of underlying categories in the scene are inferred using all training images in an unsupervised manner. Finally, these two kinds of contextual information are aggregated to one which is subsequently fed into a multi-scale fusion module to produce the detection map. CANet is compared with several state-of-the-art methods on three benchmark datasets, including the season-varying change detection (SVCD) dataset, the Sun Yat-sen University change detection (SYSU-CD) dataset, and the Learning Vision and Remote Sensing Laboratory building change detection (LEVIR-CD) dataset. It is demonstrated that our method outperforms all comparison methods in terms of F1, overall accuracy (OA), and Intersection-of-Union (IoU). The results of CANet on three datasets are available at https://github.com/NuistZF/CANet-for-change-detection and codes will be public soon.

Generalization of U-Net Semantic Segmentation for Forest Change Detection in South Korea Using Airborne Imagery

Forest change detection is essential to prevent the secondary damage occurring by landslides causing profound results to the environment, ecosystem, and human society. The remote sensing technique is a solid candidate for identifying the spatial distribution of the forest. Even though the acquiring and processing of remote sensing images are costly and time- and labor-consuming, the development of open source data platforms relieved these burdens by providing free imagery. The open source images also accelerate the generation of algorithms with large datasets. Thus, this study evaluated the generalizability of forest change detection by using open source airborne images and the U-Net model. U-Net model is convolutional deep learning architecture to effectively extract the image features for semantic segmentation tasks. The airborne and tree annotation images of the capital area in South Korea were processed for building U-Net input, while the pre-trained U-Net structure was adopted and fine-tuned for model training. The U-Net model provided robust results of the segmentation that classified forest and non-forest regions, having pixel accuracies, F1 score, and intersection of union (IoU) of 0.99, 0.97, and 0.95, respectively. The optimal epoch and excluded ambiguous label contributed to maintaining virtuous segmentation of the forest region. In addition, this model could correct the false label images because of showing exact classification results when the training labels were incorrect. After that, by using the open map service, the well-trained U-Net model classified forest change regions of Chungcheong from 2009 to 2016, Gangwon from 2010 to 2019, Jeolla from 2008 to 2013, Gyeongsang from 2017 to 2019, and Jeju Island from 2008 to 2013. That is, the U-Net was capable of forest change detection in various regions of South Korea at different times, despite the training on the model with only the images of the capital area. Overall, this study demonstrated the generalizability of a deep learning model for accurate forest change detection.

OAB-YOLOv5: One-Anchor-Based YOLOv5 for Rotated Object Detection in Remote Sensing Images

Remote sensing images are widely distributed, small in object size, and complex in background, resulting in low accuracy and slow speed of remote sensing image detection. Existing remote sensing object detection is generally based on the detector with anchors. With the proposal of a feature pyramid network (FPN) and focal loss, an anchorless detector emerges, however, the accuracy of anchorless detection is often low. First, this study analyzes the differences and characteristics of the intersection of union (IoU) and shape matchings based on anchors in mainstream algorithms and indicates that in dense or complex scenes, some labels are not easily assigned to positive samples, which leads to detection failure. Subsequently, we proposean one-anchor-based (OAB) object detection algorithm based on the idea of central point sampling in the anchor-free detector. The positive samples and negative samples are defined according to the central point sampling and distance constraint, and an anchor box is preset for each positive sample to accelerate its convergence. It reduces the complexity of the anchor-based detector, improves the inference speed, and reduces the setting of hyperparameters in the traditional matching strategy, rendering the model more flexible. Finally, in order to suppress background noise in remote sensing images, the vision transformer (ViT) is adopted to connect the neck and head, making it easier for the network to pay attention to key information. Thus, it is not easy to lose in the training process. Experiments on challenging public dataset—DOTA dataset- verified the effectiveness of the proposed algorithm. The experimental results show that the mAP of the optimized OAB-YOLOv5 method is improved by 2.79%, the number of parameters is reduced by 13.2%, and the inference time is reduced by 11% compared with the YOLOv5 baseline.

Comparison of Deep Learning Network for Breast Tumor Segmentation from X-Ray

Over 8% of women will be diagnosed with breast tumors (BT) in their lifetime. Tumors are formed by the uncontrollable development of tissues in a specific area of the body. They can be benign or malignant. The best survival rate can be expected with earlier screening and diagnosis of the tumor. To distinguish between benign and malignant tumors in x-ray images of the breast, segmentation of the tumor is a crucial first step. Screening mammography is an efficient method of detecting BT. As a result, the research presented two distinct deep learning models, termed SegNet and UNet architectures, to segment BT from mammograms. Datasets accessible to the public were utilized in the proposed system, specifically INbreast. Histogram equalization is used on datasets during preprocessing to improve the compressed areas and normalize the pixel dispersion. To avoid overfitting and boost the quantity of training data, augmentation techniques are employed. The metrics like the dice coefficient (DC) and the Intersection of Union (IoU) score are considered to evaluate the model. The metrics of the SegNets model are greater than the U-Net, as demonstrated by the experimental results. For the INbreast dataset, the SegNets achieve a maximum DC of 92.75% and an IoU score of 86.49%.

Identification and Counting of Sugarcane Seedlings in the Field Using Improved Faster R-CNN

Sugarcane seedling emergence is important for sugar production. Manual counting is time-consuming and hardly practicable for large-scale field planting. Unmanned aerial vehicles (UAVs) with fast acquisition speed and wide coverage are becoming increasingly popular in precision agriculture. We provide a method based on improved Faster RCNN for automatically detecting and counting sugarcane seedlings using aerial photography. The Sugarcane-Detector (SGN-D) uses ResNet 50 for feature extraction to produce high-resolution feature expressions and provides an attention method (SN-block) to focus the network on learning seedling feature channels. FPN aggregates multi-level features to tackle multi-scale problems, while optimizing anchor boxes for sugarcane size and quantity. To evaluate the efficacy and viability of the proposed technology, 238 images of sugarcane seedlings were taken from the air with an unmanned aerial vehicle. Outcoming with an average accuracy of 93.67%, our proposed method outperforms other commonly used detection models, including the original Faster R-CNN, SSD, and YOLO. In order to eliminate the error caused by repeated counting, we further propose a seedlings de-duplication algorithm. The highest counting accuracy reached 96.83%, whilst the mean absolute error (MAE) reached 4.6 when intersection of union (IoU) was 0.15. In addition, a software system was developed for the automatic identification and counting of cane seedlings. This work can provide accurate seedling data, thus can support farmers making proper cultivation management decision.

MA-Xnet: Mobile-Attention X-Network for Crack Detection

Modern crack detection algorithms based on deep learning have unsolved issues, such as an abundance of parameters in the resulting models and lack of context information. Such issues may lower the efficiency of feature extraction and lead to unexpected task performance. Based on two semantic segmentation models, U-Net and the dual-attention network (DANet), an efficient mobile-attention X-network (MA-Xnet) is proposed for crack detection. For performance evaluation, segmentation experiments were performed on concrete crack images from an internationally recognized dataset, which were collected from various campus buildings of Middle East Technical University. The experimental results demonstrated that, compared with U-Net, the proposed method parameters were reduced by 82.33%, and improved by 11.32% and 12.37% in the key indices of the F1-Score and the mean intersection of union (mIoU), respectively, providing a reference for subsequent related lightweight crack-segmentation research.

Objective assessment of segmentation models for thyroid ultrasound images.

Ultrasound features related to thyroid lesions structure, shape, volume, and margins are considered to determine cancer risk. Automatic segmentation of the thyroid lesion would allow the sonographic features to be estimated. On the basis of clinical ultrasonography B-mode scans, a multi-output CNN-based semantic segmentation is used to separate thyroid nodules' cystic & solid components. Semantic segmentation is an automatic technique that labels the ultrasound (US) pixels with an appropriate class or pixel category, i.e., belongs to a lesion or background. In the present study, encoder-decoder-based semantic segmentation models i.e. SegNet using VGG16, UNet, and Hybrid-UNet implemented for segmentation of thyroid US images. For this work, 820 thyroid US images are collected from the DDTI and ultrasoundcases.info (USC) datasets. These segmentation models were trained using a transfer learning approach with original and despeckled thyroid US images. The performance of segmentation models is evaluated by analyzing the overlap region between the true contour lesion marked by the radiologist and the lesion retrieved by the segmentation model. The mean intersection of union (mIoU), mean dice coefficient (mDC) metrics, TPR, TNR, FPR, and FNR metrics are used to measure performance. Based on the exhaustive experiments and performance evaluation parameters it is observed that the proposed Hybrid-UNet segmentation model segments thyroid nodules and cystic components effectively.

Pre-perception and accurate recognition of coal–rock interface based on active excitation infrared characterization

Abstract Existing perception and identification methods for coal–rock interfaces are generally based on various cutting signals during shearer mining, but they cannot achieve pre-perception. Further, some pre-identification methods are significantly affected by the mining environment and cannot achieve accurate identification. In this study, a universal method is proposed to achieve pre-perception and accurate recognition of coal–rock interfaces. Using the coal–rock interface identification test-bed, active excitation infrared images of coal–rock were tested with different excitation time, distance, and intensities, and an image dataset was built for training the universal network model. This was done primarily to improve the universality of the model for infrared image identification of coal–rock under various parameter conditions. Second, the pyramid pooling module and MobileNetV2 were used to effectively extract the semantic features from the infrared images. Meanwhile, a convolutional block attention module was employed to improve the coal–rock interface identification ability of the proposed network. Finally, the efficiency of the proposed network model was tested on the infrared image dataset. The experimental results demonstrated that the memory occupied by the proposed network model is 9.12 MB, the test time is 38.46 ms/piece, and the intersection of union of coal and rock is 98.07 and 98.38%, respectively. Additionally, the pixel accuracy of coal and rock is 98.68 and 99.50%, respectively, which is significantly higher compared to other network models. Based on the constructed multi-parameter universality dataset, the proposed identification model of a coal–rock interface has good adaptability to active excitation infrared images acquired by different parameters and could provide the theoretical foundation and technical premise to achieve automated and intelligent mining.

Enhancing Channelized Feature Interpretability Using Deep Learning Predictive Modeling

Automating geobodies using insufficient labeled training data as input for structural prediction may result in missing important features and a possibility of overfitting, leading to low accuracy. We adopt a deep learning (DL) predictive modeling scheme to alleviate detection of channelized features based on classified seismic attributes (X) and different ground truth scenarios (y), to imitate actual human interpreters’ tasks. In this approach, diverse augmentation method was applied to increase the accuracy of the model after we were satisfied with the refined annotated ground truth dataset. We evaluated the effect of dropout as a training regularizer and facies’ spatial representation towards optimized prediction results, apart from conventional hyperparameter tuning. From our findings, increasing batch size helps speedup training speed and improve performance stability. Finally, we demonstrate that the designed Convolutional Neural Network (CNN) is capable of learning channelized variation from complex deepwater settings in a fluvial-dominated depositional environment while producing outstanding mean Intersection of Union (IoU) (95%) despite utilizing 6.4% from the overall dataset and avoiding overfitting possibilities.

Mask-Point: Automatic 3D Surface Defects Detection Network for Fiber-Reinforced Resin Matrix Composites.

Surface defects of fiber-reinforced resin matrix composites (FRRMCs) adversely affect their appearance and performance. To accurately and efficiently detect the three-dimensional (3D) surface defects of FRRMCs, a novel lightweight and two-stage semantic segmentation network, i.e., Mask-Point, is proposed. Stage 1 of Mask-Point is the multi-head 3D region proposal extractors (RPEs), generating several 3D regions of interest (ROIs). Stage 2 is the 3D aggregation stage composed of the shared classifier, shared filter, and non-maximum suppression (NMS). The two stages work together to detect the surface defects. To evaluate the performance of Mask-Point, a new 3D surface defects dataset of FRRMCs containing about 120 million points is produced. Training and test experiments show that the accuracy and the mean intersection of union (mIoU) increase as the number of different 3D RPEs increases in Stage 1, but the inference speed becomes slower when the number of different 3D RPEs increases. The best accuracy, mIoU, and inference speed of the Mask-Point model could reach 0.9997, 0.9402, and 320,000 points/s, respectively. Moreover, comparison experiments also show that Mask-Point offers relatively the best segmentation performance compared with several other typical 3D semantic segmentation networks. The mIoU of Mask-Point is about 30% ahead of the sub-optimal 3D semantic segmentation network PointNet. In addition, a distributed surface defects detection system based on Mask-Point is developed. The system is applied to scan real FRRMC products and detect their surface defects, and it achieves the relatively best detection performance in competition with skilled human workers. The above experiments demonstrate that the proposed Mask-Point could accurately and efficiently detect 3D surface defects of FRRMCs, and the Mask-Point also provides a new potential solution for the 3D surface defects detection of other similar materials

A Dead Broiler Inspection System for Large-Scale Breeding Farms Based on Deep Learning

Stacked cage is the main breeding method of the large-scale farm in China. In broiler farms, dead broiler inspection is a routine task in the breeding process. It refers to the manual inspection of all cages and removal of dead broilers in the broiler house by the breeders every day. However, as the total amount of broilers is huge, the inspection work is not only time-consuming but also laborious. Therefore, a dead broiler inspection system is constructed in this study to replace the manual inspection work. It mainly consists of an autonomous inspection platform and a dead broiler detection model. The automatic inspection platform performs inspections at the speed of 0.2 m/s in the broiler house aisle, and simultaneously collects images of the four-layer broilers. The images are sent to a server and processed by a dead broiler detection model, which was developed based on the YOLOv3 network. A mosaic augment, the Swish function, an spatial pyramid pooling (SPP) module, and complete intersection over union (CIoU) loss are used to improve the YOLOv3 performance. It achieves a 98.6% mean average precision (intersection of union (IoU) = 0.5) and can process images at 0.007 s per frame. The dead broiler detection model is robust to broilers of different ages and can adapt to different lighting conditions. It is deployed on the server with a human–machine interface. By observing the processing results using the human–machine interface, the breeders could directly find the cage position of dead broilers and remove them, which could reduce the workload of breeders and promote the intelligent development of poultry breeding.

Comparison between convolutional neural network and K-nearest neighbours object detection for autonomous drone

In autonomous drones, the drone’s ability to move depends on the drone’s capacity to know its position, either in relative or absolute position. The Pinhole model is one of the methods to calculate a drone’s relative position based on the triangle similarity concept using a single camera. This method utilizes bounding box information generated from an object detection algorithm. Thus, accuracy of the generated bounding box is crucial, and selection of object detection algorithm is necessary. This paper compares and evaluates machine learning and deep learning object detection methods to determine which method is suitable for distance measurement using a single camera for autonomous drone’s controller based on pinhole model. A novel K-nearest neighbours-based (KNN-based) object detection is constructed to represent the machine learning method while you only look once version 5 (YOLOv5) convolutional neural network (CNN) architecture is selected to represent the deep learning method. A dataset consists of two different classes, with a total of 1520 images, collected from the unmanned aerial vehicle (UAV) camera for training and evaluation purposes. Confusion matrix and intersection over union (IoU)/generalized intersection of union (GIoU) matrix are used to evaluate the performance of both methods. The result of this paper shows the performance of each system and concludes the suitable type of object detection algorithm for the autonomous UAV purpose.

Leather Defect Segmentation Using Semantic Segmentation Algorithms

Leather is one of the essential materials in our life. It can be used widely to make different industrial products. Products made from leather are strong, expensive and durable which lasts for decades. So, It is very important for the industry to make a defect free product for their maximum profit and good customer feedback. Quality inspection is one of the important processes in the textile industry. It is done manually in most of the industry which is time taking, expensive, less accurate and requires lots of people. The main aim of our research work is to replace the manual process with automatic leather defect detection techniques which can save both time and money and increase the rate of production in the company. In this article, we proposed a deep learning-based semantic segmentation model that detects defects in leather images and highlights the defect with proper defect type. The experiments were carried out using the MVTEC leather dataset. The input images are changed into 256*256 pixels and then converted to gray-scale image and finally a semantic segmentation algorithm is applied to detect the leather defects. The experimental results are evaluated and compared using various semantic segmentation algorithms. We obtained the satisfactory result with evaluation metrics of 72.1% Intersection of Union (IOU) with 82.59% F1 Score on one of the semantic segmentation architectures Mobilenet_unet.

Graph deep network for optic disc and optic cup segmentation for glaucoma disease using retinal imaging.

The fundus imaging method of eye screening detects eye diseases by segmenting the optic disc (OD) and optic cup (OC). OD and OC are still challenging to segment accurately. This work proposes three-layer graph-based deep architecture with an enhanced fusion method for OD and OC segmentation. CNN encoder-decoder architecture, extended graph network, and approximation via fusion-based rule are explored for connecting local and global information. A graph-based model is developed for combining local and overall knowledge. By extending feature masking, regularization of repetitive features with fusion for combining channels has been done. The performance of the proposed network is evaluated through the analysis of different metric parameters such as dice similarity coefficient (DSC), intersection of union (IOU), accuracy, specificity, sensitivity. Experimental verification of this methodology has been done using the four benchmarks publicly available datasets DRISHTI-GS, RIM-ONE for OD, and OC segmentation. In addition, DRIONS-DB and HRF fundus imaging datasets were analyzed for optimizing the model's performance based on OD segmentation. DSC metric of methodology achieved 0.97 and 0.96 for DRISHTI-GS and RIM-ONE, respectively. Similarly, IOU measures for DRISHTI-GS and RIM-ONE datasets were 0.96 and 0.93, respectively, for OD measurement. For OC segmentation, DSC and IOU were measured as 0.93 and 0.90 respectively for DRISHTI-GS and 0.83 and 0.82 for RIM-ONE data. The proposed technique improved value of metrics with most of the existing methods in terms of DSC and IOU of the results metric of the experiments for OD and OC segmentation.

DSLA: Dynamic smooth label assignment for efficient anchor-free object detection

Anchor-free detectors basically formulate object detection as dense classification and regression. For popular anchor-free detectors, it is common to introduce an individual prediction branch to estimate the quality of localization. The following inconsistencies are observed when we delve into the practices of classification and quality estimation. Firstly, for some adjacent samples which are assigned completely different labels, the trained model would produce similar classification scores. This violates the training objective and leads to performance degradation. Secondly, it is found that detected bounding boxes with higher confidences contrarily have smaller overlaps with the corresponding ground-truth. Accurately localized bounding boxes would be suppressed by less accurate ones in the Non-Maximum Suppression (NMS) procedure. To address the inconsistency problems, the Dynamic Smooth Label Assignment (DSLA) method is proposed. Based on the concept of centerness originally developed in FCOS, a smooth assignment strategy is proposed. The label is smoothed to a continuous value in [0,1] to make a steady transition between positive and negative samples. Intersection-of-Union (IoU) is predicted dynamically during training and is coupled with the smoothed label. The dynamic smooth label is assigned to supervise the classification branch. Under such supervision, quality estimation branch is naturally merged into the classification branch, which simplifies the architecture of anchor-free detector. Comprehensive experiments are conducted on the MS COCO benchmark. It is demonstrated that, DSLA can significantly boost the detection accuracy by alleviating the above inconsistencies for anchor-free detectors. Our codes are released at https://github.com/YonghaoHe/DSLA.

MTS-CNN: Multi-task semantic segmentation-convolutional neural network for detecting crops and weeds

Research is being extensively conducted on using deep learning in the field of crop and weed segmentation based on images captured with a camera. However, the segmentation performance for various crops and weeds varies significantly, implying that certain classes of crops or weeds are not being detected properly. This problem may also occur in the loss calculations used in crop and weed segmentation. In previous studies, the cross-entropy loss (corresponding to a distribution loss) and dice loss (using spatial information) have been widely used. However, such losses lead to large discrepancies in crop and weed segmentation performance, as the correlations between crop and weed classes are not considered. In order to solve these problems, this study proposes multi-task semantic segmentation-convolutional neural network for detecting crops and weeds (MTS-CNN) using one-stage training. This approach adds the crop, weed, and both (crop and weed) losses to heighten the correlations between the crop and weed classes, and designs the model so that the object (crop and weed) region is trained intensively. In experiments conducted using three types of open databases - the BoniRob dataset, a crop/weed field image dataset (CWFID), and rice seedling and weed dataset - the mean intersection of union (MIOU) values of the segmentation for the crops and weeds in the MTS-CNN are 0.9164, 0.8372, and 0.8260, respectively. Thus, the results indicate higher accuracy from the proposed approach than from the state-of-the-art methods.

Efficient Detection of Earthquake−Triggered Landslides Based on U−Net++: An Example of the 2018 Hokkaido Eastern Iburi (Japan) Mw = 6.6 Earthquake

Efficient detection of earthquake−triggered landslides is crucial for emergency response and risk assessment. With the development of multi−source remote sensing images, artificial intelligence has gradually become a powerful landslide detection method for similar tasks, aiming to mitigate time−consuming problems and meet emergency requirements. In this study, a relatively new deep learning (DL) network, called U−Net++, was designed to detect landslides for regions affected by the Iburi, Japan Mw = 6.6 earthquake, with only small training samples. For feature extraction, ResNet50 was selected as the feature extraction layer, and transfer learning was adopted to introduce the pre−trained weights for accelerating the model convergence. To prove the feasibility and validity of the proposed model, the random forest algorithm (RF) was selected as the benchmark, and the F1−score, Kappa coefficient, and IoU (Intersection of Union) were chosen to quantitatively evaluate the model’s performance. In addition, the proposed model was trained with different sample sizes (256,512) and network depths (3,4,5), respectively, to analyze their impacts on performance. The results showed that both models detected the majority of landslides, while the proposed model obtained the highest metric value (F1−score = 0.7580, Kappa = 0.7441, and IoU = 0.6104) and was capable of resisting the noise. In addition, the proposed model trained with sample size 256 possessed optimal performance, proving that the size is a non−negligible parameter in U−Net++, and it was found that the U−Net++ trained with shallower layer 3 yielded better results than that with the standard layer 5. Finally, the outstanding performance of the proposed model on a public landslide dataset demonstrated the generalization of U−Net++.

A pixel-level coarse-to-fine image segmentation labelling algorithm

Fine segmentation labelling tasks are time consuming and typically require a great deal of manual labor. This paper presents a novel method for efficiently creating pixel-level fine segmentation labelling that significantly reduces the amount of necessary human labor. The proposed method utilizes easily produced multiple and complementary coarse labels to build a complete fine label via supervised learning. The primary label among the coarse labels is the manual label, which is produced with simple contours or bounding boxes that roughly encompass an object. All others coarse labels are complementary and are generated automatically using existing algorithms. Fine labels can be rapidly created during the supervised learning of such coarse labels. In the experimental study, the proposed technique achieved a fine label IOU (intersection of union) of 92% in segmenting our newly constructed bean field dataset. The proposed method also achieved 95% and 92% mean IOU when tested on publicly available agricultural CVPPP and CWFID datasets, respectively. Our proposed method of segmentation also achieved a mean IOU of 81% when it was tested on our newly constructed paprika disease dataset, which includes multiple categories.

Automatic scan range for dose-reduced multiphase CT imaging of the liver utilizing CNNs and Gaussian models.

Multiphase CT scanning of the liver is performed for several clinical applications; however, radiation exposure from CT scanning poses a nontrivial cancer risk to the patients. The radiation dose may be reduced by determining the scan range of the subsequent scans by the location of the target of interest in the first scan phase. The purpose of this study is to present and assess an automatic method for determining the scan range for multiphase CT scans. Our strategy is to first apply a CNN-based method for detecting the liver in 2D slices, and to use a liver range search algorithm for detecting the liver range in the scout volume. The target liver scan range for subsequent scans can be obtained by adding safety margins achieved from Gaussian liver motion models to the scan range determined from the scout. Experiments were performed on 657 multiphase CT volumes obtained from multiple hospitals. The experiment shows that the proposed liver detection method can detect the liver in 223 out of a total of 224 3D volumes on average within one second, with mean intersection of union, wall distance and centroid distance of 85.5%, 5.7mm and 9.7mm, respectively. In addition, the performance of the proposed liver detection method is comparable to the best of the state-of-the-art 3D liver detectors in the liver detection accuracy while it requires less processing time. Furthermore, we apply the liver scan range generation method on the liver CT images acquired from radiofrequency ablation and Y-90 transarterial radioembolization (selective internal radiation therapy) interventions of 46 patients from two hospitals. The result shows that the automatic scan range generation can significantly reduce the effective radiation dose by an average of 14.5% (2.56 mSv) compared to manual performance by the radiographer from Y-90 transarterial radioembolization, while no statistically significant difference in performance was found with the CT images from intra RFA intervention (p = 0.81). Finally, three radiologists assess both the original and the range-reduced images for evaluating the effect of the range reduction method on their clinical decisions. We conclude that the automatic liver scan range generation method is able to reduce excess radiation compared to the manual performance with a high accuracy and without penalizing the clinical decision.