Similarity Coefficient Research Articles

A comparative study of pre-processing methods to improve glioma segmentation performance in brain MRI using deep learning

Background: Glioma is the most common brain tumor in adult patients and requires accurate treatment. The delineation of tumor boundaries must be accurate and precise, which is crucial for treatment planning. Currently, delineating boundaries for tumors is a tedious, time-consuming task and may be prone to human error among oncologists. Therefore, artificial intelligence plays a vital role in reducing these problems. Objective: This study aims to find a relationship between improving image enhancement and evaluating the performance of deep learning models for segmenting glioma image data on brain MRI images. Materials and methods: The BraTs2023 dataset was used in this study. The image dataset was converted from three dimensions to two dimensions and then subjected to pre-processing via four image enhancement techniques, including contrast-limited adaptive histogram equalization (CLAHE), gamma correction (GC), non-local mean filter (NLMF), and median and Wiener filter (MWF). Subsequently, it was evaluated for structural similarity index (SSIM) and mean squared error. The deep learning segmentation model was created using the U-Net architecture and assessed for dice similarity coefficient (DSC), accuracy, precision, recall, F1-score, and Jaccard index for tumor segmentation. Results: The performance of enhanced image results for CLAHE, GC, NLMF, and MWF techniques shows SSIM values of 0.912, 0.905, 0.999, and 0.911, respectively. The dice similarity coefficient (DSC) for segmentation without image enhancement was 0.817. The DSC of segmentation for CLAHE, GC, NLMF, and MWF techniques were 0.818, 0.812, 0.820, and 0.797, respectively. Conclusion: The enhanced image technique could affect the performance of tumor segmentation. by the enhanced image for use in a trained model may increase or decrease performance depending on the chosen image enhancement technique and the parameters determined by each method.

PSMA-positive prostatic volume prediction with deep learning based on T2-weighted MRI.

High PSMA expression might be correlated with structural characteristics such as growth patterns on histopathology, not recognized by the human eye on MRI images. Deep structural image analysis might be able to detect such differences and therefore predict if a lesion would be PSMA positive. Therefore, we aimed to train a neural network based on PSMA PET/MRI scans to predict increased prostatic PSMA uptake based onthe axial T2-weighted sequence alone. All patients undergoing simultaneous PSMA PET/MRI for PCa staging or biopsy guidance between April 2016 and December 2020 at our institution were selected. To increase the specificity of our model, the prostatic beds on PSMA PET scans were dichotomized in positive and negative regions using an SUV threshold greater than 4 to generate a PSMA PET map. Then, a C-ENet was trained on the T2 images of the training cohort to generate a predictive prostatic PSMA PET map. One hundred and fifty-four PSMA PET/MRI scans were available (133 [68Ga]Ga-PSMA-11 and 21 [18F]PSMA-1007). Significant cancer was present in 127 of them. The whole dataset was divided into a training cohort (n = 124) and a test cohort (n = 30). The C-ENet was able to predict the PSMA PET map with a dice similarity coefficient of 69.5 ± 15.6%. Increased prostatic PSMA uptake on PET might be estimated based on T2 MRI alone. Further investigation with larger cohorts and external validation is needed to assess whether PSMA uptake can be predicted accurately enough to help in the interpretation of mpMRI.

Improving image quality of sparse-view lung tumor CT images with U-Net

BackgroundWe aimed to improve the image quality (IQ) of sparse-view computed tomography (CT) images using a U-Net for lung metastasis detection and determine the best tradeoff between number of views, IQ, and diagnostic confidence.MethodsCT images from 41 subjects aged 62.8 ± 10.6 years (mean ± standard deviation, 23 men), 34 with lung metastasis, 7 healthy, were retrospectively selected (2016–2018) and forward projected onto 2,048-view sinograms. Six corresponding sparse-view CT data subsets at varying levels of undersampling were reconstructed from sinograms using filtered backprojection with 16, 32, 64, 128, 256, and 512 views. A dual-frame U-Net was trained and evaluated for each subsampling level on 8,658 images from 22 diseased subjects. A representative image per scan was selected from 19 subjects (12 diseased, 7 healthy) for a single-blinded multireader study. These slices, for all levels of subsampling, with and without U-Net postprocessing, were presented to three readers. IQ and diagnostic confidence were ranked using predefined scales. Subjective nodule segmentation was evaluated using sensitivity and Dice similarity coefficient (DSC); clustered Wilcoxon signed-rank test was used.ResultsThe 64-projection sparse-view images resulted in 0.89 sensitivity and 0.81 DSC, while their counterparts, postprocessed with the U-Net, had improved metrics (0.94 sensitivity and 0.85 DSC) (p = 0.400). Fewer views led to insufficient IQ for diagnosis. For increased views, no substantial discrepancies were noted between sparse-view and postprocessed images.ConclusionsProjection views can be reduced from 2,048 to 64 while maintaining IQ and the confidence of the radiologists on a satisfactory level.Relevance statementOur reader study demonstrates the benefit of U-Net postprocessing for regular CT screenings of patients with lung metastasis to increase the IQ and diagnostic confidence while reducing the dose.Key points• Sparse-projection-view streak artifacts reduce the quality and usability of sparse-view CT images.• U-Net-based postprocessing removes sparse-view artifacts while maintaining diagnostically accurate IQ.• Postprocessed sparse-view CTs drastically increase radiologists’ confidence in diagnosing lung metastasis.Graphical

Artificial intelligence for volumetric measurement of cerebral white matter hyperintensities on thick-slice fluid-attenuated inversion recovery (FLAIR) magnetic resonance images from multiple centers

We aimed to develop a new artificial intelligence software that can automatically extract and measure the volume of white matter hyperintensities (WMHs) in head magnetic resonance imaging (MRI) using only thick-slice fluid-attenuated inversion recovery (FLAIR) sequences from multiple centers. We enrolled 1092 participants in Japan, comprising the thick-slice Private Dataset. Based on 207 randomly selected participants, neuroradiologists annotated WMHs using predefined guidelines. The annotated images of participants were divided into training (n = 138) and test (n = 69) datasets. The WMH segmentation model comprised a U-Net ensemble and was trained using the Private Dataset. Two other models were trained for validation using either both thin- and thick-slice MRI datasets or the thin-slice dataset alone. The voxel-wise Dice similarity coefficient (DSC) was used as the evaluation metric. The model trained using only thick-slice MRI showed a DSC of 0.820 for the test dataset, which is comparable to the accuracy of human readers. The model trained with the additional thin-slice dataset showed only a slightly improved DSC of 0.822. This automatic WMH segmentation model comprising a U-Net ensemble trained on a thick-slice FLAIR MRI dataset is a promising new method. Despite some limitations, this model may be applicable in clinical practice.

Deep-Learning Models for Abdominal CT Organ Segmentation in Children: Development and Validation in Internal and Heterogeneous Public Datasets.

Background: Deep-learning abdominal organ segmentation algorithms have shown excellent results in adults; validation in children is sparse. Objective: To develop and validate deep-learning models for liver, spleen, and pancreas segmentation on pediatric CT examinations. Methods: This retrospective study developed and validated deep-learning models for liver, spleen, and pancreas segmentation using 1731 CT examinations (1504 training, 221 testing), derived from three internal institutional pediatric (age ≤18) datasets (n=483) and three public datasets comprising pediatric and adult examinations with various pathologies (n=1248). Three deep-learning model architectures (SegResNet, DynUNet, and SwinUNETR) from the Medical Open Network for AI (MONAI) framework underwent training using native training (NT), relying solely on institutional datasets, and transfer learning (TL), incorporating pre-training on public datasets. For comparison, TotalSegmentator (TS), a publicly available segmentation model, was applied to test data without further training. Segmentation performance was evaluated using mean Dice similarity coefficient (DSC), with manual segmentations as reference. Results: For internal pediatric data, DSC for normal liver was 0.953 (TS), 0.964-0.965 (NT models), and 0.965-0.966 (TL models); normal spleen, 0.914 (TS), 0.942-0.945 (NT models), and 0.937-0.945 (TL models); normal pancreas, 0.733 (TS), 0.774-0.785 (NT models), and 0.775-0.786 (TL models); pancreas with pancreatitis, 0.703 (TS), 0.590-0.640 (NT models), and 0.667-0.711 (TL models). For public pediatric data, DSC for liver was 0.952 (TS), 0.876-0.908 (NT models), and 0.941-0.946 (TL models); spleen, 0.905 (TS), 0.771-0.827 (NT models), and 0.897-0.926 (TL models); pancreas, 0.700 (TS), 0.577-0.648 (NT models), and 0.693-0.736 (TL models). For public primarily adult data, DSC for liver was 0.991 (TS), 0.633-0.750 (NT models), and 0.926-0.952 (TL models); spleen, 0.983 (TS), 0.569-0.604 (NT models), and 0.923-0.947 (TL models); pancreas, 0.909 (TS), 0.148-0.241 (NT models), and 0.699-0.775 (TL models). DynUNet-TL was selected as the best-performing NT or TL model and was made available as an opensource MONAI bundle (https://github.com/cchmc-dll/pediatric_abdominal_segmentation_bundle.git). Conclusion: TL models trained on heterogeneous public datasets and fine-tuned using institutional pediatric data outperformed internal NT models and TotalSegmentator across internal and external pediatric test data. Segmentation performance was better in liver and spleen than in pancreas. Clinical Impact: The selected model may be used for various volumetry applications in pediatric imaging.

Evaluation of a Cascaded Deep Learning-based Algorithm for Prostate Lesion Detection at Biparametric MRI.

Background Multiparametric MRI (mpMRI) improves prostate cancer (PCa) detection compared with systematic biopsy, but its interpretation is prone to interreader variation, which results in performance inconsistency. Artificial intelligence (AI) models can assist in mpMRI interpretation, but large training data sets and extensive model testing are required. Purpose To evaluate a biparametric MRI AI algorithm for intraprostatic lesion detection and segmentation and to compare its performance with radiologist readings and biopsy results. Materials and Methods This secondary analysis of a prospective registry included consecutive patients with suspected or known PCa who underwent mpMRI, US-guided systematic biopsy, or combined systematic and MRI/US fusion-guided biopsy between April 2019 and September 2022. All lesions were prospectively evaluated using Prostate Imaging Reporting and Data System version 2.1. The lesion- and participant-level performance of a previously developed cascaded deep learning algorithm was compared with histopathologic outcomes and radiologist readings using sensitivity, positive predictive value (PPV), and Dice similarity coefficient (DSC). Results A total of 658 male participants (median age, 67 years [IQR, 61-71 years]) with 1029 MRI-visible lesions were included. At histopathologic analysis, 45% (294 of 658) of participants had lesions of International Society of Urological Pathology (ISUP) grade group (GG) 2 or higher. The algorithm identified 96% (282 of 294; 95% CI: 94%, 98%) of all participants with clinically significant PCa, whereas the radiologist identified 98% (287 of 294; 95% CI: 96%, 99%; P = .23). The algorithm identified 84% (103 of 122), 96% (152 of 159), 96% (47 of 49), 95% (38 of 40), and 98% (45 of 46) of participants with ISUP GG 1, 2, 3, 4, and 5 lesions, respectively. In the lesion-level analysis using radiologist ground truth, the detection sensitivity was 55% (569 of 1029; 95% CI: 52%, 58%), and the PPV was 57% (535 of 934; 95% CI: 54%, 61%). The mean number of false-positive lesions per participant was 0.61 (range, 0-3). The lesion segmentation DSC was 0.29. Conclusion The AI algorithm detected cancer-suspicious lesions on biparametric MRI scans with a performance comparable to that of an experienced radiologist. Moreover, the algorithm reliably predicted clinically significant lesions at histopathologic examination. ClinicalTrials.gov Identifier: NCT03354416 © RSNA, 2024 Supplemental material is available for this article.

MOS-GAN: A U-Net++ based GAN for multi-organ segmentation

Radiotherapy, a standard and common form of cancer treatment, is used in about half of all cancer cases. It is critical to segment organs at risk (OARs) accurately and promptly for radiation treatment planning to be efficient and high-quality. In this paper, an adversarial training strategy is used in our deep learning network. This model is called the Multiple Organ Segmentation Generative Adversarial Network (MOS-GAN). The U-Net++ is our generator to create a multi-organ segmentation image by learning the end-to-end mapping from CT images to OARs segmentation. A convolutional neural network (CNN) acts as the discriminator to identify the difference between the manual contour and the segmented images created by the generator. A 2.5D method is employed by us to extract the spatial information among slices. We applied the proposed method to segment the five organs from the 2017 AAPM segmentation challenge dataset. Segmentation of the bilateral lungs, heart, and spinal cord were successfully achieved, as well as the outline of the esophagus. In terms of dice similarity coefficients, the aforementioned five OARs have average values of 0.97, 0.97, 0.92, 0.91 and 0.77, respectively.

Affine registration of thermal images of plantar feet using convolutional neural networks

The use of a thermal camera to detect abnormal plantar foot temperature changes can be an effective way to identify the early signs of diabetic foot ulceration. In this work, we performed the affine registration of the plantar foot thermal images using four models based on convolutional neural networks. The process include two parts: an affine registration model for estimating transformation parameters and a spatial transformer for getting the registered image. The performances of the four models were evaluated using the Dice similarity coefficient (DSC), Mean Square Error (MSE), and peak signal-to-noise ratio (PSNR). In the first step, Methods were applied to register the left and right feet of the same subject, called “contralateral registration” and in the second step, the methods were evaluated on a pair of images of the same subject taken in two different times (T0 and T10) using a cold stress test protocol. Results showed that the used convolutional neural networks are robust in both types of registration (contralateral and multitemporal), and they are suitable for the targeted application, with the DSC of 95% for contralateral registration and a DSC of 92% for multitemporal registration. Furthermore, a transversal clinical study was perform on diabetic patients, that classified individuals into ischemic and non-ischemic groups. The objective was to analyze the coherence between the thermal results and medical data. The mean absolute point-to-point temperature difference |ΔT| between left and right foot is lower in non-ischemic patients than in those with ischemia, with p<0.05.

First Report of 'Candidatus Phytoplasma asteris'-related Strain (16SrI group) Associated with Small Leaves, Leaf Yellowing, and Shoot Proliferation of Morning Glory (Ipomoea biflora) in Taiwan.

Ipomoea biflora L., commonly known as morning glory, is an herbaceous vine plant in the Convolvulaceae family and is widespread at low elevations in Taiwan and other East Asian countries. In September 2023, six I. biflora plants exhibiting small leaves, leaf yellowing, and shoot proliferation were observed in a vacant lot in Taiwan Agricultural Research Institute (TARI), Wufeng District, Taichung, Taiwan, representing 100% disease incidence in the area. All the symptomatic morning glory climbed onto Murraya paniculata L. (common jasmine orange) which however showed no similar symptoms. The total DNA (two samples for each plant) from leaf tissues of three symptomatic morning glory plants, two asymptomatic morning glory plants, and one asymptomatic common jasmine orange was isolated by the CTAB method (Fulton et al. 1995) and used for PCR with the universal primers, P1 (Deng and Hiruki 1991)/P7 (Schneider et al. 1995), to amplify a fragment containing partial 16S rDNA. Expected 1.8-kb bands were amplified from DNA extracted from all symptomatic plants, whereas no PCR product was detected from that of the asymptomatic I.biflora and M. paniculata plants. Six PCR products were cloned and sequenced in the Biotechnology Center DNA-sequencing facility at National Chung Hsing University, and one representative sequence was selected and deposited in GenBank. BLAST analysis revealed that the obtained 16S rDNA sequence (PP230905) shared 99.92% identity with the following phytoplasma strains: rapeseed phyllody phytoplasma (CP055264), plumbago auriculata leaf yellowing phytoplasma (MN239503), and aster yellows phytoplasma (MK992774), which all belong to the 16SrI subgroup. The query 16S rDNA sequence shares 99.84% identity with that of the 'Candidatus Phytoplasma asteris' reference strain (M30790), suggesting that the phytoplasma is a 'Ca. Phytoplasma asteris'-related strain. A virtual restriction fragment length polymorphism (RFLP) analysis was conducted using iPhyClassifier tool (Zhao et al. 2009), and the pattern derived from the 16S rDNA fragment of the I. biflora phytoplasma was identical (similarity coefficient 1.00) to the reference pattern of 16SrI, subgroup B (onion yellows phytoplasma OY-M; AP006628). Six total DNA samples from symptomatic plants were used as templates to amplify 842 bp secA sequences with SecAfor1 and SecArev3 primers (Hodgetts et al. 2008), and one representative sequence was deposited in GenBank. The partial secA sequence (PP263636) showed 98.22% identity with that of Trema levigatum witches'-broom phytoplasma (MW032212) that also belongs to the 16SrI group (Wan et al. 2021). Phylogenetic analysis of both 16S rDNA and secA confirmed I. biflora phytoplasma as 16SrI, subgroup B. Taken together, we concluded that the morning glory phytoplasma in this study was a 'Ca. Phytoplasma asteris'-related strain belonging to the 16SrI group. To the best of our knowledge, this is the first report of a phytoplasma-infected I. biflora in Taiwan, suggesting morning glory as a new natural host of 16SrI phytoplasmas, alongside other plants like roselle and citrus (Tseng et al. 2014; Feng et al. 2015).

Do Deep Learning Algorithms Accurately Segment Intracerebral Hemorrhages on Noncontrast Computed Tomography? A Systematic Review and Meta‐Analysis

BACKGROUND Stroke, a major global health issue, is broadly categorized into ischemic and hemorrhagic types. The volume of hemorrhage on noncontrast computed tomography guides the treatment options and hints at prognosis. Conventional approaches to calculate intracerebral hemorrhage (ICH) volume, like the ABC/2 method, typically rely on an assumed standard shape and might be inaccurate. Advances in deep learning have significantly improved noncontrast computed tomography's capabilities in ICH volume estimation. This study conducts a comprehensive systematic review and meta‐analysis to evaluate the precision of deep learning algorithms in delineating ICH on noncontrast computed tomography. METHODS A systematic review and meta‐analysis, adhering to Preferred Reporting Items for Systematic Reviews and Meta‐Analyses guidelines, was conducted on literature from 2000 to October 2023. Studies were selected on the basis of strict inclusion and exclusion criteria. Performance evaluation was done using the Dice Similarity Coefficient, and the Prediction Model Risk of Bias Assessment Tool was used for quality assessment. Statistical analysis was carried out using Stata 17.0. RESULTS The review included 28 studies, mainly retrospective cohorts, with a focus on convolutional neural network architectures, particularly U‐Net variants. A meta‐analysis of 14 studies revealed a combined Dice Similarity Coefficient of 0.85 (95% CI, 0.82–0.88). Performance was consistent across various methodologies but varied on the basis of ICH pathogenesis, with spontaneous ICH having higher accuracy. CONCLUSION Deep learning models are highly effective in segmenting ICH on noncontrast computed tomography, demonstrating potential improvements in clinical neuroimaging. Despite their efficacy, challenges in segmenting smaller hemorrhages remain. The findings suggest that deep learning could reduce health care professional workloads and enhance patient care, although further research is needed to address limitations and extend clinical utility.

A novel evaluation model of image registration for cone-beam computed tomography guided lung cancer radiotherapy.

The aim of the study was to establish a weighted comprehensive evaluation model (WCEM) of image registration for cone-beam computed tomography (CBCT) guided lung cancer radiotherapy that considers the geometric accuracy of gross target volume (GTV) and organs at risk (OARs), and assess the registration accuracy of different image registration methods to provide clinical references. The planning CT and CBCT images of 20 lung cancer patients were registered using diverse algorithms (bony and grayscale) and regions of interest (target, ipsilateral, and body). We compared the coverage ratio (CR) of the planning target volume (PTVCT) to GTVCBCT, as well as the dice similarity coefficient (DSC) of the GTV and OARs, considering the treatment position across various registration methods. Furthermore, we developed a mathematical model to assess registration results comprehensively. This model was evaluated and validated using CRFs across four automatic registration methods. The grayscale registration method, coupled with the registration of the ipsilateral structure, exhibited the highest level of automatic registration accuracy, the DSC were 0.87 ± 0.09 (GTV), 0.71 ± 0.09 (esophagus), 0.74 ± 0.09 (spinal cord), and 0.91 ± 0.05 (heart), respectively. Our proposed WCEM proved to be both practical and effective. The results clearly indicated that the grayscale registration method, when applied to the ipsilateral structure, achieved the highest CRF score. The average CRF scores, excellent rates, good rate and qualification rates were 58 ± 26, 40%, 75%, and 85%, respectively. This study successfully developed a clinically relevant weighted evaluation model for CBCT-guided lung cancer radiotherapy. Validation confirmed the grayscale method's optimal performance in ipsilateral structure registration.

A Deep Learning Framework for Analysis of the Eustachian Tube and the Internal Carotid Artery.

Obtaining automated, objective 3-dimensional (3D) models of the Eustachian tube (ET) and the internal carotid artery (ICA) from computed tomography (CT) scans could provide useful navigational and diagnostic information for ET pathologies and interventions. We aim to develop a deep learning (DL) pipeline to automatically segment the ET and ICA and use these segmentations to compute distances between these structures. Retrospective cohort. Tertiary referral center. From a database of 30 CT scans, 60 ET and ICA pairs were manually segmented and used to train an nnU-Net model, a DL segmentation framework. These segmentations were also used to develop a quantitative tool to capture the magnitude and location of the minimum distance point (MDP) between ET and ICA. Performance metrics for the nnU-Net automated segmentations were calculated via the average Hausdorff distance (AHD) and dice similarity coefficient (DSC). The AHD for the ET and ICA were 0.922 and 0.246 mm, respectively. Similarly, the DSC values for the ET and ICA were 0.578 and 0.884. The mean MDP from ET to ICA in the cartilaginous region was 2.6 mm (0.7-5.3 mm) and was located on average 1.9 mm caudal from the bony cartilaginous junction. This study describes the first end-to-end DL pipeline for automated ET and ICA segmentation and analyzes distances between these structures. In addition to helping to ensure the safe selection of patients for ET dilation, this method can facilitate large-scale studies exploring the relationship between ET pathologies and the 3D shape of the ET.

A Prostate Boundary Localization and Edge Denoising Algorithm

This research aimed at presenting a two-step method for prostate segmentation in TRUS images. The research used a prostate boundary localization and prostate edge denoising approach. The proposed method contribution is the use of the optimized Hodge’s method as the boundary operator and the use of the Bidirectional Exponential moving average to perform edge denoising. The results showed that the proposed method is effective in completing the prostate segmentation task. (1) The prostate region is effectively initialized and localized. (2) The recovery of noise points is accomplished and the segmentation result being consistent with the general shape of the prostate. The experimental results showed that this method can improve the overall segmentation accuracy. The process uses a combination of traditional and unsupervised methods, eliminating the need to rely on large data sets compared to current deep learning methods. The proposed method achieved excellent segmentation accuracy, with the Dice similarity coefficient (DICE) value of 0.9679, an average Intersection over Union (IoU) value of 0.9377, and an average False Positive Rate (FPR) of 0.0399. The results obtained from this study have significant implications for clinical practice. Accurate prostate segmentation is crucial for various applications, including radiation therapy planning, image-guided interventions, and computer-aided diagnosis. The proposed method has the potential to improve these applications by providing more precise and reliable prostate segmentations. However, it is important to acknowledge some limitations of this study. First, the proposed method was evaluated on a limited dataset, which may not fully represent the diversity of prostate images encountered in clinical practice. Further validation on larger datasets is necessary to assess its generalizability. Additionally, the proposed method relied on manual annotations for training, which can introduce inter-observer variability. Incorporating automated or semi-automated annotation techniques could enhance the robustness of the method

Analysis of the effectiveness of clustering algorithms for multimodal samples using computer simulation of an educational experiment

Introduction. The article is devoted to the problem of primary data processing of pedagogical experiments having a multimodal character. The purpose of the study is to identify the most effective and universal clustering algorithms for pedagogical experiments. Materials and Methods. The study used the method of modeling a pedagogical experiment. The analysis of 5 clustering algorithms is conducted. The effectiveness of clustering algorithms was evaluated based on the proportion of observations with clustering errors at various tolerance levels and the Jacquard similarity coefficient. Regression analysis was used to assess the influence of modeling parameters of a pedagogical experiment and indicators of descriptive statistics on the effectiveness of clustering algorithms. Results. The assessment of the effectiveness of various data clustering algorithms is provided, as well as a correlation and regression analysis of factors affecting clustering efficiency indicators was carried out. Conclusions. The most effective clustering algorithms for multimodal samples include the K-means algorithm and the agglomerative hierarchical algorithm. The results obtained in this research can be used for statistical analysis of pedagogical, psychological, sociological, biological and medical research data.

A temporal enhanced semi-supervised training framework for needle segmentation in 3D ultrasound images.

Automated biopsy needle segmentation in 3D ultrasound images can be used for biopsy navigation, but it is quite challenging due to the low ultrasound image resolution and interference similar to the needle appearance. For 3D medical image segmentation, such deep learning (DL) networks as convolutional neural network (CNN) and transformer have been investigated. However, these segmentation methods require numerous labeled data for training, have difficulty in meeting the real-time segmentation requirement and involve high memory consumption.&#xD;Approach. In this paper, we have proposed the temporal information-based semi-supervised training framework for fast and accurate needle segmentation. Firstly, a novel circle transformer module based on the static and dynamic features has been designed after the encoders for extracting and fusing the temporal information. Then, the consistency constraints of the outputs before and after combining temporal information are proposed to provide the semi-supervision for the unlabeled volume. Finally, the model is trained using the loss function which combines the cross-entropy and Dice similarity coefficient (DSC) based segmentation loss with mean square error based consistency loss. The trained model with the single ultrasound volume input is applied to realize the needle segmentation in ultrasound volume.&#xD;Main results. Experimental results on three needle ultrasound datasets acquired during the beagle biopsy show that our approach is superior to the most competitive mainstream temporal segmentation model and semi-supervised method by providing higher DSC (77.1% vs 76.5%), smaller needle tip position (1.28mm vs 1.87mm) and length (1.78mm vs 2.19mm) errors on the kidney dataset as well as DSC (78.5% vs 76.9%), needle tip position (0.86mm vs 1.12mm) and length (1.01mm vs 1.26mm) errors on the prostate dataset.&#xD;Significance. The proposed method can significantly enhance needle segmentation accuracy by training with sequential images at no additional cost. This enhancement may further improve the effectiveness of biopsy navigation systems.&#xD.

A deep learning-based 3D Prompt-nnUnet model for automatic segmentation in brachytherapy of postoperative endometrial carcinoma.

To create and evaluate a three-dimensional (3D) Prompt-nnUnet module that utilizes the prompts-based model combined with 3D nnUnet for producing the rapid and consistent autosegmentation of high-risk clinical target volume (HR CTV) and organ at risk (OAR) in high-dose-rate brachytherapy (HDR BT) for patients with postoperative endometrial carcinoma (EC). On two experimental batches, a total of 321 computed tomography (CT) scans were obtained for HR CTV segmentation from 321 patients with EC, and 125 CT scans for OARs segmentation from 125 patients. The numbers of training/validation/test were 257/32/32 and 87/13/25 for HR CTV and OARs respectively. A novel comparison of the deep learning neural network 3D Prompt-nnUnet and 3D nnUnet was applied for HR CTV and OARs segmentation. Three-fold cross validation and several quantitative metrics were employed, including Dice similarity coefficient (DSC), Hausdorff distance (HD), 95th percentile of Hausdorff distance (HD95%), and intersection over union (IoU). The Prompt-nnUnet included two forms of parameters Predict-Prompt (PP) and Label-Prompt (LP), with the LP performing most similarly to the experienced radiation oncologist and outperforming the less experienced ones. During the testing phase, the mean DSC values for the LP were 0.96±0.02, 0.91±0.02, and 0.83±0.07 for HR CTV, rectum and urethra, respectively. The mean HD values (mm) were 2.73±0.95, 8.18±4.84, and 2.11±0.50, respectively. The mean HD95% values (mm) were 1.66±1.11, 3.07±0.94, and 1.35±0.55, respectively. The mean IoUs were 0.92±0.04, 0.84±0.03, and 0.71±0.09, respectively. A delineation time<2.35s per structure in the new model was observed, which was available to save clinician time. The Prompt-nnUnet architecture, particularly the LP, was highly consistent with ground truth (GT) in HR CTV or OAR autosegmentation, reducing interobserver variability and shortening treatment time.

A hybrid estimation of distribution algorithm for solving assembly flexible job shop scheduling in a distributed environment

This paper proposes a novel distributed assembly flexible job shop scheduling problem (DAFJSP), which involves three stages: production stage, assembly stage, and delivery stage. The production stage is accomplished in a few flexible job shops, the assembly stage is accomplished in a few single-machine factories, and the delivery stage is to deliver the obtained products to the corresponding customers. To address the problem, a hybrid estimation of distribution algorithm based on differential evolution operator and variable neighborhood search (HEDA-DEV) is proposed with the goal of minimizing the total cost and tardiness. Firstly, a new multidimensional coding method is designed based on the features of the DAFJSP. Secondly, two mutation operators and the similarity coefficient based on the probability matrix are put forward to implement the dynamic mutation. Thirdly, five types of neighborhood structures satisfying cooperative search strategies are employed to adequately improve the local exploitation ability. Finally, the comparison experiment results suggest that the proposed HEDA-DEV has competitive performance compared to the selected efficient algorithms. Moreover, a real case study is used to demonstrate that HEDA-DEV is an effective method for solving DAFJSP.

Deep learning-aided 3D proxy-bridged region-growing framework for multi-organ segmentation

Accurate multi-organ segmentation in 3D CT images is imperative for enhancing computer-aided diagnosis and radiotherapy planning. However, current deep learning-based methods for 3D multi-organ segmentation face challenges such as the need for labor-intensive manual pixel-level annotations and high hardware resource demands, especially regarding GPU resources. To address these issues, we propose a 3D proxy-bridged region-growing framework specifically designed for the segmentation of the liver and spleen. Specifically, a key slice is selected from each 3D volume according to the corresponding intensity histogram. Subsequently, a deep learning model is employed to pinpoint the semantic central patch on this key slice, to calculate the growing seed. To counteract the impact of noise, segmentation of the liver and spleen is conducted on superpixel images created through proxy-bridging strategy. The segmentation process is then extended to adjacent slices by applying the same methodology iteratively, culminating in the comprehensive segmentation results. Experimental results demonstrate that the proposed framework accomplishes segmentation of the liver and spleen with an average Dice Similarity Coefficient of approximately 0.93 and a Jaccard Similarity Coefficient of around 0.88. These outcomes substantiate the framework's capability to achieve performance on par with that of deep learning methods, albeit requiring less guidance information and lower GPU resources.

Unveiling Genetic Variation in Garlic Genotypes in Response to Rust Disease Using RAPD Markers

Garlic (&lt;em&gt;Allium sativum&lt;/em&gt;), cultivated worldwide for its medicinal and nutritional value, faces challenges due to diseases caused by various pathogens. In this study, eleven garlic genotypes from Iran and one from China were selected and sown under natural infection rendered by the rust fungus (&lt;em&gt;Puccinia alli&lt;/em&gt;) over two consecutive years. Subsequently, disease distribution and severity, percentage of infection and susceptibility of different garlic genotypes to rust disease were investigated. The results showed that genotype Solan was the most susceptible, with disease severity of 30.81%. In comparison, genotypes Aliabad and Bahar were resistant against rust disease with the lowest infection percentages of 13% and 16.37%, respectively. Further, genetic diversity was assessed using random-amplified polymorphic DNA (RAPD) markers. Out of 10 primers used, 95 scorable bands were generated, of which 66 (69.48%) were found to be polymorphic. A dendrogram was constructed based on RAPD polymorphism using the UPGMA method, and the genotypes were separated into six distinct clusters based on Jaccard's coefficient of similarity. Additionally, it was observed that there is no genetic differentiation among the genotypes based on their geographical origin. This study highlights the significant diversity in resistance and susceptibility among garlic genotypes, which can be harnessed in plant breeding programs.

Phenotypic Characteristics, Pathogenicity, and Molecular Identification of Hypomyces perniciosus Causing Wet Bubble Disease of Edible Mushrooms

Abstract The research aimed to determine the phenotypic characteristic, pathogenicity and molecular characterization of Hypomyces perniciosus isolates responsible for wet bubble disease of the white button mushroom Agaricus bisporus. Phenotypic characteristics such as colony appearance, mycelium texture, and pigmentation were studied on four different agar media, i.e., potato dextrose agar (PDA), malt extract agar (MEA), Czapek-Dox yeast agar (CYA), and Sabouraud dextrose agar (SDA), after eight days of incubation. Additionally, the growth rate of the tested isolates was studied depending on the pH of the medium. Fungal isolates showed the highest mycelial growth on MEA and SDA at pH 6.0. However, on CYA at pH 7.0, the mycelium exhibited the worst growth. Isolate identification and genetic relationship analysis were carried out using internal transcribed spacer region sequencing and the random amplified polymorphic DNA method. The research confirmed that all Polish isolates belong to the species H. perniciosus, and the genetic diversity is relatively low. Phylogenetic analyses revealed three subgroups of H. perniciosus isolates. The first group included three genetically distinct isolates with a similarity coefficient in the range of 0.76–0.85 to isolates CBS 815.73 and CBS 322.52. The second group was divided into two subgroups and included 16 isolates with a genetic similarity range of 0.91 to 1.0 to CBS 815.73 and CBS 322.52 isolates. Furthermore, the eight genetically similar isolates exhibited the greatest pathogenicity towards A. bisporus.