Dataset Information

Segmentation and recognition of breast ultrasound images based on an expanded U-Net.

ABSTRACT: This paper establishes a fully automatic real-time image segmentation and recognition system for breast ultrasound intervention robots. It adopts the basic architecture of a U-shaped convolutional network (U-Net), analyses the actual application scenarios of semantic segmentation of breast ultrasound images, and adds dropout layers to the U-Net architecture to reduce the redundancy in texture details and prevent overfitting. The main innovation of this paper is proposing an expanded training approach to obtain an expanded of U-Net. The output map of the expanded U-Net can retain texture details and edge features of breast tumours. Using the grey-level probability labels to train the U-Net is faster than using ordinary labels. The average Dice coefficient (standard deviation) and the average IOU coefficient (standard deviation) are 90.5% (±0.02) and 82.7% (±0.02), respectively, when using the expanded training approach. The Dice coefficient of the expanded U-Net is 7.6 larger than that of a general U-Net, and the IOU coefficient of the expanded U-Net is 11 larger than that of the general U-Net. The context of breast ultrasound images can be extracted, and texture details and edge features of tumours can be retained by the expanded U-Net. Using an expanded U-Net can quickly and automatically achieve precise segmentation and multi-class recognition of breast ultrasound images.

SUBMITTER: Guo Y

PROVIDER: S-EPMC8205136 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Segmentation and recognition of breast ultrasound images based on an expanded U-Net.

Guo Yanjun Y Duan Xingguang X Wang Chengyi C Guo Huiqin H

PloS one 20210615 6

This paper establishes a fully automatic real-time image segmentation and recognition system for breast ultrasound intervention robots. It adopts the basic architecture of a U-shaped convolutional network (U-Net), analyses the actual application scenarios of semantic segmentation of breast ultrasound images, and adds dropout layers to the U-Net architecture to reduce the redundancy in texture details and prevent overfitting. The main innovation of this paper is proposing an expanded training app ...[more]

PMID: 34129619

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.

Project description:Structural planes decrease the strength and stability of rock masses, severely affecting their mechanical properties and deformation and failure characteristics. Therefore, investigation and analysis of structural planes are crucial tasks in mining rock mechanics. The drilling camera obtains image information of deep structural planes of rock masses through high-definition camera methods, providing important data sources for the analysis of deep structural planes of rock masses. This paper addresses the problems of high workload, low efficiency, high subjectivity, and poor accuracy brought about by manual processing based on current borehole image analysis and conducts an intelligent segmentation study of borehole image structural planes based on the U2-Net network. By collecting data from 20 different borehole images in different lithological regions, a dataset consisting of 1,013 borehole images with structural plane type, lithology, and color was established. Data augmentation methods such as image flipping, color jittering, blurring, and mixup were applied to expand the dataset to 12,421 images, meeting the requirements for deep network training data. Based on the PyTorch deep learning framework, the initial U2-Net network weights were set, the learning rate was set to 0.001, the training batch was 4, and the Adam optimizer adaptively adjusted the learning rate during the training process. A dedicated network model for segmenting structural planes was obtained, and the model achieved a maximum F-measure value of 0.749 when the confidence threshold was set to 0.7, with an accuracy rate of up to 0.85 within the range of recall rate greater than 0.5. Overall, the model has high accuracy for segmenting structural planes and very low mean absolute error, indicating good segmentation accuracy and certain generalization of the network. The research method in this paper can serve as a reference for the study of intelligent identification of structural planes in borehole images.

Project description:PurposeTransrectal 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 materialsWe 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.ResultsForty-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.ConclusionWe 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.

Project description:BackgroundBreast ultrasound (BUS) imaging is one of the most prevalent approaches for the detection of breast cancers. Tumor segmentation of BUS images can facilitate doctors in localizing tumors and is a necessary step for computer-aided diagnosis systems. While the majority of clinical BUS scans are normal ones without tumors, segmentation approaches such as U-Net often predict mass regions for these images. Such false-positive problem becomes serious if a fully automatic artificial intelligence system is used for routine screening.MethodsIn this study, we proposed a novel model which is more suitable for routine BUS screening. The model contains a classification branch that determines whether the image is normal or with tumors, and a segmentation branch that outlines tumors. Two branches share the same encoder network. We also built a new dataset that contains 1600 BUS images from 625 patients for training and a testing dataset with 130 images from 120 patients for testing. The dataset is the largest one with pixel-wise masks manually segmented by experienced radiologists. Our code is available at https://github.com/szhangNJU/BUS_segmentation.ResultsThe area under the receiver operating characteristic curve (AUC) for classifying images into normal/abnormal categories was 0.991. The dice similarity coefficient (DSC) for segmentation of mass regions was 0.898, better than the state-of-the-art models. Testing on an external dataset gave a similar performance, demonstrating a good transferability of our model. Moreover, we simulated the use of the model in actual clinic practice by processing videos recorded during BUS scans; the model gave very low false-positive predictions on normal images without sacrificing sensitivities for images with tumors.ConclusionsOur model achieved better segmentation performance than the state-of-the-art models and showed a good transferability on an external test set. The proposed deep learning architecture holds potential for use in fully automatic BUS health screening.

Dataset Information

Segmentation and recognition of breast ultrasound images based on an expanded U-Net.

Publications

Segmentation and recognition of breast ultrasound images based on an expanded U-Net.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets