Segmentation and recognition of breast ultrasound images based on an expanded U-Net.
Ontology highlight
ABSTRACT:
SUBMITTER: Guo Y
PROVIDER: S-EPMC8205136 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundEndometrial thickness is an essential factor affecting female fertility. Clinically, ultrasound imaging is the first choice for the examination of uterine and endometrial-related diseases. However, the boundary of some endometrial is challenging to distinguish due to the effects of image resolution and noise. In addition, the irregular shape of the endometrium makes it more difficult for doctors to measure its thickness. Through the automatic segmentation and extraction of the endometrium, the maximum thickness of the endometrium can be measured automatically and accurately. This provides a quantitative index for doctors to use diagnostically.MethodsIn this study, 85 cases of three-dimensional transvaginal ultrasound (3D TVUS) images were collected retrospectively, including 75 cases of endometrial adhesion and 10 cases of non-adhesion. Firstly, the ultrasound images were filtered by block-matching and 3D filtering and speckle reducing anisotropic diffusion (SRAD). These two kinds of filtered images were combined with the original image to construct a three-channel image. Then, the augmented images were sent to 3D U-Net to realize endometrium segmentation. The performance of the segmentation models was evaluated using the Dice similarity coefficient (DSC), Jaccard, sensitivity, and 95th percentile Hausdorff distance (HD95). Finally, the medial axis transform was used to extract the endometrial centerline, based on which the endometrial thickness could be automatically measured.ResultsThe endometrium segmentation method proposed in this paper achieved 90.83% in Dice, 83.35% in Jaccard, 90.85% in sensitivity, and 12.75 mm in HD95 in the testing set. Taking the doctor's manual measurement as the gold standard, 94.20% of the automatic endometrial thickness measurements based on the segmentation results were within the allowable error range of clinical diagnosis.ConclusionsThis paper presents an automatic endometrium segmentation and thickness measurement method for 3D TVUS images. The experimental results show that this method has high segmentation accuracy to recognize endometrial adhesion images. Furthermore, the thickness measurement based on the segmentation results has high reliability and repeatability, and the accuracy can meet clinical diagnosis needs.
| S-EPMC9338380 | biostudies-literature
Project description:PURPOSE:Transrectal ultrasound (TRUS) is a versatile and real-time imaging modality that is commonly used in image-guided prostate cancer interventions (e.g., biopsy and brachytherapy). Accurate segmentation of the prostate is key to biopsy needle placement, brachytherapy treatment planning, and motion management. Manual segmentation during these interventions is time-consuming and subject to inter- and intraobserver variation. To address these drawbacks, we aimed to develop a deep learning-based method which integrates deep supervision into a three-dimensional (3D) patch-based V-Net for prostate segmentation. METHODS AND MATERIALS:We developed a multidirectional deep-learning-based method to automatically segment the prostate for ultrasound-guided radiation therapy. A 3D supervision mechanism is integrated into the V-Net stages to deal with the optimization difficulties when training a deep network with limited training data. We combine a binary cross-entropy (BCE) loss and a batch-based Dice loss into the stage-wise hybrid loss function for a deep supervision training. During the segmentation stage, the patches are extracted from the newly acquired ultrasound image as the input of the well-trained network and the well-trained network adaptively labels the prostate tissue. The final segmented prostate volume is reconstructed using patch fusion and further refined through a contour refinement processing. RESULTS:Forty-four patients' TRUS images were used to test our segmentation method. Our segmentation results were compared with the manually segmented contours (ground truth). The mean prostate volume Dice similarity coefficient (DSC), Hausdorff distance (HD), mean surface distance (MSD), and residual mean surface distance (RMSD) were 0.92 ± 0.03, 3.94 ± 1.55, 0.60 ± 0.23, and 0.90 ± 0.38 mm, respectively. CONCLUSION:We developed a novel deeply supervised deep learning-based approach with reliable contour refinement to automatically segment the TRUS prostate, demonstrated its clinical feasibility, and validated its accuracy compared to manual segmentation. The proposed technique could be a useful tool for diagnostic and therapeutic applications in prostate cancer.
| S-EPMC6625925 | biostudies-literature
Project description:BackgroundUltrasonic for detecting and evaluating pleural effusion is an essential part of the Extended Focused Assessment with Sonography in Trauma (E-FAST) in emergencies. Our study aimed to develop an Artificial Intelligence (AI) diagnostic model that automatically identifies and segments pleural effusion areas on ultrasonography.MethodsAn Attention U-net and a U-net model were used to detect and segment pleural effusion on ultrasound images of 848 subjects through fully supervised learning. Sensitivity, specificity, precision, accuracy, F1 score, the receiver operating characteristic (ROC) curve, and the area under the curve (AUC) were used to assess the model's effectiveness in classifying the data. The dice coefficient was used to evaluate the segmentation performance of the model.ResultsIn 10 random tests, the Attention U-net and U-net 's average sensitivity of 97% demonstrated that the pleural effusion was well detectable. The Attention U-net performed better at identifying negative images than the U-net, which had an average specificity of 91% compared to 86% for the U-net. Additionally, the Attention U-net was more accurate in predicting the pleural effusion region because its average dice coefficient was 0.86 as opposed to the U-net's average dice coefficient of 0.82.ConclusionsThe Attention U-net showed excellent performance in detecting and segmenting pleural effusion on ultrasonic images, which is expected to enhance the operation and application of E-FAST in clinical work.
| S-EPMC10795456 | biostudies-literature
Project description:BackgroundUltrasound image segmentation is challenging due to the low signal-to-noise ratio and poor quality of ultrasound images. With deep learning advancements, convolutional neural networks (CNNs) have been widely used for ultrasound image segmentation. However, due to the intrinsic locality of convolutional operations and the varying shapes of segmentation objects, segmentation methods based on CNNs still face challenges with accuracy and generalization. In addition, Transformer is a network architecture with self-attention mechanisms that performs well in the field of computer vision. Based on the characteristics of Transformer and CNNs, we propose a hybrid architecture based on Transformer and U-Net with joint loss for ultrasound image segmentation, referred to as TU-Net.MethodsTU-Net is based on the encoder-decoder architecture and includes encoder, parallel attention mechanism and decoder modules. The encoder module is responsible for reducing dimensions and capturing different levels of feature information from ultrasound images; the parallel attention mechanism is responsible for capturing global and multiscale local feature information; and the decoder module is responsible for gradually recovering dimensions and delineating the boundaries of the segmentation target. Additionally, we adopt joint loss to optimize learning and improve segmentation accuracy. We use experiments on datasets of two types of ultrasound images to verify the proposed architecture. We use the Dice scores, precision, recall, Hausdorff distance (HD) and average symmetric surface distance (ASD) as evaluation metrics for segmentation performance.ResultsFor the brachia plexus and fetal head ultrasound image datasets, TU-Net achieves mean Dice scores of 79.59% and 97.94%; precisions of 81.25% and 98.18%; recalls of 80.19% and 97.72%; HDs (mm) of 12.44 and 6.93; and ASDs (mm) of 4.29 and 2.97, respectively. Compared with those of the other six segmentation algorithms, the mean values of TU-Net increased by approximately 3.41%, 2.62%, 3.74%, 36.40% and 31.96% for the Dice score, precision, recall, HD and ASD, respectively.
| S-EPMC10703067 | biostudies-literature
Project description:Displacement of the myotendinous junction (MTJ) obtained by ultrasound imaging is crucial to quantify the interactive length changes of muscles and tendons for understanding the mechanics and pathological conditions of the muscle-tendon unit during motion. However, the lack of a reliable automatic measurement method restricts its application in human motion analysis. This paper presents an automated measurement of MTJ displacement using prior knowledge on tendinous tissues and MTJ, precluding the influence of nontendinous components on the estimation of MTJ displacement. It is based on the perception of tendinous features from musculoskeletal ultrasound images using Radon transform and thresholding methods, with information about the symmetric measures obtained from phase congruency. The displacement of MTJ is achieved by tracking manually marked points on tendinous tissues with the Lucas-Kanade optical flow algorithm applied over the segmented MTJ region. The performance of this method was evaluated on ultrasound images of the gastrocnemius obtained from 10 healthy subjects (26.0 ± 2.9 years of age). Waveform similarity between the manual and automatic measurements was assessed by calculating the overall similarity with the coefficient of multiple correlation (CMC). In vivo experiments demonstrated that MTJ tracking with the proposed method (CMC = 0.97 ± 0.02) was more consistent with the manual measurements than existing optical flow tracking methods (CMC = 0.79 ± 0.11). This study demonstrated that the proposed method was robust to the interference of nontendinous components, resulting in a more reliable measurement of MTJ displacement, which may facilitate further research and applications related to the architectural change of muscles and tendons.
| S-EPMC5884232 | biostudies-literature
Project description:Environmental monitoring of microplastics (MP) contamination has become an area of great research interest, given potential hazards associated with human ingestion of MP. In this context, determination of MP concentration is essential. However, cheap, rapid, and accurate quantification of MP remains a challenge to this date. This study proposes a deep learning-based image segmentation method that properly distinguishes fluorescent MP from other elements in a given microscopy image. A total of nine different deep learning models, six of which are based on U-Net, were investigated. These models were trained using at least 20,000 patches sampled from 99 fluorescence microscopy images of MP and their corresponding binary masks. MP-Net, which is derived from U-Net, was found to be the best performing model, exhibiting the highest mean F1-score (0.736) and mean IoU value (0.617). Test-time augmentation (using brightness, contrast, and HSV) was applied to MP-Net for robust learning. However, compared to the results obtained without augmentation, no clear improvement in predictive performance could be observed. Recovery assessment for both spiked and real images showed that, compared to already existing tools for MP quantification, the MP quantities predicted by MP-Net are those closest to the ground truth. This observation suggests that MP-Net allows creating masks that more accurately reflect the quantitative presence of fluorescent MP in microscopy images. Finally, MAP (Microplastics Annotation Package) is introduced, an integrated software environment for automated MP quantification, offering support for MP-Net, already existing MP analysis tools like MP-VAT, manual annotation, and model fine-tuning.
| S-EPMC9200300 | biostudies-literature
Project description:Over the past decades, histopathological cancer diagnostics has become more complex, and the increasing number of biopsies is a challenge for most pathology laboratories. Thus, development of automatic methods for evaluation of histopathological cancer sections would be of value. In this study, we used 624 whole slide images (WSIs) of breast cancer from a Norwegian cohort. We propose a cascaded convolutional neural network design, called H2G-Net, for segmentation of breast cancer region from gigapixel histopathological images. The design involves a detection stage using a patch-wise method, and a refinement stage using a convolutional autoencoder. To validate the design, we conducted an ablation study to assess the impact of selected components in the pipeline on tumor segmentation. Guiding segmentation, using hierarchical sampling and deep heatmap refinement, proved to be beneficial when segmenting the histopathological images. We found a significant improvement when using a refinement network for post-processing the generated tumor segmentation heatmaps. The overall best design achieved a Dice similarity coefficient of 0.933±0.069 on an independent test set of 90 WSIs. The design outperformed single-resolution approaches, such as cluster-guided, patch-wise high-resolution classification using MobileNetV2 (0.872±0.092) and a low-resolution U-Net (0.874±0.128). In addition, the design performed consistently on WSIs across all histological grades and segmentation on a representative × 400 WSI took ~ 58 s, using only the central processing unit. The findings demonstrate the potential of utilizing a refinement network to improve patch-wise predictions. The solution is efficient and does not require overlapping patch inference or ensembling. Furthermore, we showed that deep neural networks can be trained using a random sampling scheme that balances on multiple different labels simultaneously, without the need of storing patches on disk. Future work should involve more efficient patch generation and sampling, as well as improved clustering.
| S-EPMC9515451 | biostudies-literature
Project description:To develop a U-net deep learning method for breast tissue segmentation on fat-sat T1-weighted (T1W) MRI using transfer learning (TL) from a model developed for non-fat-sat images. The training dataset (N = 126) was imaged on a 1.5 T MR scanner, and the independent testing dataset (N = 40) was imaged on a 3 T scanner, both using fat-sat T1W pulse sequence. Pre-contrast images acquired in the dynamic-contrast-enhanced (DCE) MRI sequence were used for analysis. All patients had unilateral cancer, and the segmentation was performed using the contralateral normal breast. The ground truth of breast and fibroglandular tissue (FGT) segmentation was generated using a template-based segmentation method with a clustering algorithm. The deep learning segmentation was performed using U-net models trained with and without TL, by using initial values of trainable parameters taken from the previous model for non-fat-sat images. The ground truth of each case was used to evaluate the segmentation performance of the U-net models by calculating the dice similarity coefficient (DSC) and the overall accuracy based on all pixels. Pearson's correlation was used to evaluate the correlation of breast volume and FGT volume between the U-net prediction output and the ground truth. In the training dataset, the evaluation was performed using tenfold cross-validation, and the mean DSC with and without TL was 0.97 vs. 0.95 for breast and 0.86 vs. 0.80 for FGT. When the final model developed with and without TL from the training dataset was applied to the testing dataset, the mean DSC was 0.89 vs. 0.83 for breast and 0.81 vs. 0.81 for FGT, respectively. Application of TL not only improved the DSC, but also decreased the required training case number. Lastly, there was a high correlation (R2 > 0.90) for both the training and testing datasets between the U-net prediction output and ground truth for breast volume and FGT volume. U-net can be applied to perform breast tissue segmentation on fat-sat images, and TL is an efficient strategy to develop a specific model for each different dataset.
| S-EPMC8455741 | biostudies-literature
Project description:Computer aided diagnosis (CAD) of biomedical images assists physicians for a fast facilitated tissue characterization. A scheme based on combining fuzzy logic (FL) and deep learning (DL) for automatic semantic segmentation (SS) of tumors in breast ultrasound (BUS) images is proposed. The proposed scheme consists of two steps: the first is a FL based preprocessing, and the second is a Convolutional neural network (CNN) based SS. Eight well-known CNN based SS models have been utilized in the study. Studying the scheme was by a dataset of 400 cancerous BUS images and their corresponding 400 ground truth images. SS process has been applied in two modes: batch and one by one image processing. Three quantitative performance evaluation metrics have been utilized: global accuracy (GA), mean Jaccard Index (mean intersection over union (IoU)), and mean BF (Boundary F1) Score. In the batch processing mode: quantitative metrics' average results over the eight utilized CNNs based SS models over the 400 cancerous BUS images were: 95.45% GA instead of 86.08% without applying fuzzy preprocessing step, 78.70% mean IoU instead of 49.61%, and 68.08% mean BF score instead of 42.63%. Moreover, the resulted segmented images could show tumors' regions more accurate than with only CNN based SS. While, in one by one image processing mode: there has been no enhancement neither qualitatively nor quantitatively. So, only when a batch processing is needed, utilizing the proposed scheme may be helpful in enhancing automatic ss of tumors in BUS images. Otherwise applying the proposed approach on a one-by-one image mode will disrupt segmentation's efficiency. The proposed batch processing scheme may be generalized for an enhanced CNN based SS of a targeted region of interest (ROI) in any batch of digital images. A modified small dataset is available: https://www.kaggle.com/mohammedtgadallah/mt-small-dataset (S1 Data).
| S-EPMC8136850 | biostudies-literature
Project description:Ultrasound segmentation is a challenging problem due to the inherent speckle and some artifacts like shadows, attenuation and signal dropout. Existing methods need to include strong priors like shape priors or analytical intensity models to succeed in the segmentation. However, such priors tend to limit these methods to a specific target or imaging settings, and they are not always applicable to pathological cases. This work introduces a semi-supervised segmentation framework for ultrasound imaging that alleviates the limitation of fully automatic segmentation, that is, it is applicable to any kind of target and imaging settings. Our methodology uses a graph of image patches to represent the ultrasound image and user-assisted initialization with labels, which acts as soft priors. The segmentation problem is formulated as a continuous minimum cut problem and solved with an efficient optimization algorithm. We validate our segmentation framework on clinical ultrasound imaging (prostate, fetus, and tumors of the liver and eye). We obtain high similarity agreement with the ground truth provided by medical expert delineations in all applications (94% DICE values in average) and the proposed algorithm performs favorably with the literature.
| S-EPMC4091944 | biostudies-literature