Automatic Prostate Segmentation on 3D MRI Scans Using Convolutional Neural Networks with Residual Connections and Superpixels

Tumor computed tomography (CT) image segmentation can provide a basis for the determination of tumor location and type. Therefore, it is of great significance to study the automatic segmentation method of tumor CT images. To address the problem of poor segmentation effect of traditional automatic tumor CT images segmentation methods, we propose an automatic segmentation method for tumor CT images using deep convolutional neural networks (DCNNs). First, the CT tumor image is simplified. According to the features of the target region and the background region, the distribution features of the tumor region in the CT images are obtained by convolution calculation, and the feature extraction is completed by feature fusion. Second, based on the feature extraction results, a deep supervised network is constructed to determine the image depth, which lays a solid foundation for accurate segmentation of tumor regions. Finally, DCNN was used to construct automatic segmentation for tumor CT images, which achieves the automatic segmentation of tumor CT images by mode calculation. The results show that the segmented tumor region is close to the actual region and the maximum pixel loss coefficient is 0.07, the maximum segmentation sensitivity is 7865[Formula: see text]kbps/s, the pixel segmentation specific coefficient and the segmentation edge distance are kept at a low level, which has a certain application value in the field of tumor CT images.

Multiparametric ultrasound (mpUS) is being investigated as an alternative to magnetic resonance imaging (MRI) for detection of prostate cancer (PC). Automated prostate segmentation facilitates workflows, and zonal segmentation can aid in PC diagnosis, accounting for differences in imaging characteristics and tumor incidence. Our aim was to develop a deep learning algorithm that can automatically segment the prostate and its zones on three-dimensional (3D) contrast-enhanced ultrasound (CEUS) and conventional brightness-mode (B-mode) images (NCT04605276). A total of 259 3D mpUS images were collected from men with suspicion for PC in a prospective multicenter trial to develop a computer-aided diagnosis system for PC. Manual segmentation was performed using a custom tool, and an algorithm was developed using a convolutional neural network based on the U-Net architecture. Cross-validation of the automated segmentation algorithm revealed Dice similarity coefficients (DSCs) of 0.91 (95% confidence interval [CI] 0.90-0.91) for CEUS and 0.94 (95% CI 0.93-0.94) for B-mode ultrasound for 3D prostate segmentation. Zonal segmentation was less accurate, with DSCs of 0.83 (95% CI 0.82-0.84) for CEUS and 0.86 (95% CI 0.85-0.87) for B-mode ultrasound. There was high agreement for prostate volume between automatic segmentation on CEUS and physician-estimated volumes on MRI (R2=0.96). Qualitative assessment of prostate segmentation using a scale from 1 to 5 revealed a median grade of 5 (interquartile range [IQR] 4-5) for manual segmentation and 4 (IQR 4-5) for automated segmentation (p=0.10). Our deep learning algorithm demonstrated strong performance for automatic prostate and zonal segmentation from 3D CEUS and B-mode ultrasound images. We developed a computer tool to automatically identify the prostate in three-dimensional ultrasound images. The results show high accuracy and closely match manual assessments by urologists. This tool has potential for use in a computer-aided diagnostic system for prostate cancer.

Attention-guided multi-scale learning network for automatic prostate and tumor segmentation on MRI

Purpose: Medical image segmentation models are essential for efficiently diagnosing prostate cancer. Current models for segmentation of micro ultrasound images do not utilize foundation models, or geometric and spatial data from the ultrasound image. We aim to leverage the Segment Anything Model (SAM) as a pretrained backbone to create a fully automatic prostate segmentation model and investigate prompting with positonal information such as the slice frame number and previous segmentations. Methods: The Segment Anything Model (SAM) was fine-tuned on Micro-Ultrasound images1 and adapted for the context of clinical prostate segmentation. We explored different fine-tuning methods and prompting combinations fit for automatic segmentation. Dice coefficient (DSC) and Hausdorff 95% distance (HD95) were used as evaluation metrics to compare our model against past models. Results: In comparison to the state of the art models, SliceTrack-SAM improved the mean Dice coefficient from the MicroSegNet2 model (93.1) to 94.3, and reduced the Hausdorff distance from the nnU-Net model (1.09 mm) to 0.81 mm. Conclusion: In summary, using a fully-finetuned SAM, improves prostate segmentation accuracy. In addition, prompting with geometric and spatial data derived from ultrasound images shows potential to enhance segmentation accuracy, particularly on difficult datasets.

To apply deep convolution neural network to the segmentation task in myocardial arterial spin labeled perfusion imaging and to develop methods that measure uncertainty and that adapt the convolution neural network model to a specific false-positive versus false-negative tradeoff. The Monte Carlo dropout U-Net was trained on data from 22 subjects and tested on data from 6 heart transplant recipients. Manual segmentation and regional myocardial blood flow were available for comparison. We consider 2 global uncertainty measures, named "Dice uncertainty" and "Monte Carlo dropout uncertainty," which were calculated with and without the use of manual segmentation, respectively. Tversky loss function with a hyperparameter β was used to adapt the model to a specific false-positive versus false-negative tradeoff. The Monte Carlo dropout U-Net achieved a Dice coefficient of 0.91 ± 0.04 on the test set. Myocardial blood flow measured using automatic segmentations was highly correlated to that measured using the manual segmentation (R2 = 0.96). Dice uncertainty and Monte Carlo dropout uncertainty were in good agreement (R2 = 0.64). As β increased, the false-positive rate systematically decreased and false-negative rate systematically increased. We demonstrate the feasibility of deep convolution neural network for automatic segmentation of myocardial arterial spin labeling, with good accuracy. We also introduce 2 simple methods for assessing model uncertainty. Finally, we demonstrate the ability to adapt the convolution neural network model to a specific false-positive versus false-negative tradeoff. These findings are directly relevant to automatic segmentation in quantitative cardiac MRI and are broadly applicable to automatic segmentation problems in diagnostic imaging.

Automatic prostate segmentation from MR images is an important task in various clinical applications such as prostate cancer staging and MR-guided radiotherapy planning. However, the large appearance and shape variations of the prostate in MR images make the segmentation problem difficult to solve. Traditional Active Shape/Appearance Model (ASM/AAM) has limited accuracy on this problem, since its basic assumption, i.e., both shape and appearance of the targeted organ follow Gaussian distributions, is invalid in prostate MR images. To this end, the authors propose a sparse dictionary learning method to model the image appearance in a nonparametric fashion and further integrate the appearance model into a deformable segmentation framework for prostate MR segmentation. To drive the deformable model for prostate segmentation, the authors propose nonparametric appearance and shape models. The nonparametric appearance model is based on a novel dictionary learning method, namely distributed discriminative dictionary (DDD) learning, which is able to capture fine distinctions in image appearance. To increase the differential power of traditional dictionary-based classification methods, the authors' DDD learning approach takes three strategies. First, two dictionaries for prostate and nonprostate tissues are built, respectively, using the discriminative features obtained from minimum redundancy maximum relevance feature selection. Second, linear discriminant analysis is employed as a linear classifier to boost the optimal separation between prostate and nonprostate tissues, based on the representation residuals from sparse representation. Third, to enhance the robustness of the authors' classification method, multiple local dictionaries are learned for local regions along the prostate boundary (each with small appearance variations), instead of learning one global classifier for the entire prostate. These discriminative dictionaries are located on different patches of the prostate surface and trained to adaptively capture the appearance in different prostate zones, thus achieving better local tissue differentiation. For each local region, multiple classifiers are trained based on the randomly selected samples and finally assembled by a specific fusion method. In addition to this nonparametric appearance model, a prostate shape model is learned from the shape statistics using a novel approach, sparse shape composition, which can model nonGaussian distributions of shape variation and regularize the 3D mesh deformation by constraining it within the observed shape subspace. The proposed method has been evaluated on two datasets consisting of T2-weighted MR prostate images. For the first (internal) dataset, the classification effectiveness of the authors' improved dictionary learning has been validated by comparing it with three other variants of traditional dictionary learning methods. The experimental results show that the authors' method yields a Dice Ratio of 89.1% compared to the manual segmentation, which is more accurate than the three state-of-the-art MR prostate segmentation methods under comparison. For the second dataset, the MICCAI 2012 challenge dataset, the authors' proposed method yields a Dice Ratio of 87.4%, which also achieves better segmentation accuracy than other methods under comparison. A new magnetic resonance image prostate segmentation method is proposed based on the combination of deformable model and dictionary learning methods, which achieves more accurate segmentation performance on prostate T2 MR images.

Objective:Precise segmentation of human organs and anatomic structures (especially organs at risk, OARs) is the basis and prerequisite for the treatment planning of radiation therapy. In order to ensure rapid and accurate design of radiotherapy treatment planning, an automatic organ segmentation technique was investigated based on deep learning convolutional neural network.MethodA deep learning convolutional neural network (CNN) algorithm called BCDU-Net has been modified and developed further by us. Twenty two thousand CT images and the corresponding organ contours of 17 types delineated manually by experienced physicians from 329 patients were used to train and validate the algorithm. The CT images randomly selected were employed to test the modified BCDU-Net algorithm. The weight parameters of the algorithm model were acquired from the training of the convolutional neural network.ResultThe average Dice similarity coefficient (DSC) of the automatic segmentation and manual segmentation of the human organs of 17 types reached 0.8376, and the best coefficient reached up to 0.9676. It took 1.5–2 s and about 1 h to automatically segment the contours of an organ in an image of the CT dataset for a patient and the 17 organs for the CT dataset with the method developed by us, respectively.ConclusionThe modified deep neural network algorithm could be used to automatically segment human organs of 17 types quickly and accurately. The accuracy and speed of the method meet the requirements of its application in radiotherapy.

Develop and evaluate a deep learning-based automatic meningioma segmentation method for preoperative meningioma differentiation using radiomic features. A retrospective multicentre inclusion of MR examinations (T1/T2-weighted and contrast-enhanced T1-weighted imaging) was conducted. Data from centre 1 were allocated to training (n = 307, age = 50.94 ± 11.51) and internal testing (n = 238, age = 50.70 ± 12.72) cohorts, and data from centre 2 external testing cohort (n = 64, age = 48.45 ± 13.59). A modified attention U-Net was trained for meningioma segmentation. Segmentation accuracy was evaluated by five quantitative metrics. The agreement between radiomic features from manual and automatic segmentations was assessed using intra class correlation coefficient (ICC). After univariate and minimum-redundancy-maximum-relevance feature selection, L1-regularized logistic regression models for differentiating between low-grade (I) and high-grade (II and III) meningiomas were separately constructed using manual and automatic segmentations; their performances were evaluated using ROC analysis. Dice of meningioma segmentation for the internal testing cohort were 0.94 ± 0.04 and 0.91 ± 0.05 for tumour volumes in contrast-enhanced T1-weighted and T2-weighted images, respectively; those for the external testing cohort were 0.90 ± 0.07 and 0.88 ± 0.07. Features extracted using manual and automatic segmentations agreed well, for both the internal (ICC = 0.94, interquartile range: 0.88-0.97) and external (ICC = 0.90, interquartile range: 0.78-70.96) testing cohorts. AUC of radiomic model with automatic segmentation was comparable with that of the model with manual segmentation for both the internal (0.95 vs. 0.93, p = 0.176) and external (0.88 vs. 0.91, p = 0.419) testing cohorts. The developed deep learning-based segmentation method enables automatic and accurate extraction of meningioma from multiparametric MR images and can help deploy radiomics for preoperative meningioma differentiation in clinical practice. • A deep learning-based method was developed for automatic segmentation of meningioma from multiparametric MR images. • The automatic segmentation method enabled accurate extraction of meningiomas and yielded radiomic features that were highly consistent with those that were obtained using manual segmentation. • High-grade meningiomas were preoperatively differentiated from low-grade meningiomas using a radiomic model constructed on features from automatic segmentation.

The paper addresses a problem of feature selection for automatic prostate segmentation in Computed Tomography (CT) planning data for radiotherapy process. The following image descriptors have been tested in 2D and 3D scenarios: standard Hounsfield Unit (HU) profiles, histogram of oriented gradient (HoG), Haar wavelets, and Modality Independent Neighborhood Descriptor (MIND). The task was to distinguish a prostate interior and exterior. 22 CT volumes with different spatial resolution and different organ outlines have been used. The k-Nearest Neighbors (kNN) classifier was applied and the following recognition measures were evaluated, with 10-fold cross-validation: accuracy, precision, sensitivity and specificity.

We present a new method for the automatic segmentation and components classification of brain Optic Pathway Gliomas (OPGs) from multi-spectral MRI datasets. Our method accurately identifies the sharp OPG boundaries and consistently delineates the missing contours by effectively incorporating prior location, shape, and intensity information. It then classifies the segmented OPG volume into its three main components--solid, enhancing, and cyst--with a probabilistic tumor tissue model generated from training datasets that accounts for the datasets grey-level differences. Experimental results on 25 datasets yield a mean OPG boundary surface distance error of 0.73mm and mean volume overlap difference of 30.6% as compared to manual segmentation by an expert radiologist. A follow-up patient study shows high correlation between the clinical tumor progression evaluation and the component classification results. To the best of our knowledge, ours is the first method for automatic OPG segmentation and component classification that may support quantitative disease progression and treatment efficacy evaluation.

Prostate cancer is one of the most frequent cancers in men and is a major cause of mortality in the most of countries. In many diagnostic and treatment procedures for prostate disease accurate detection of prostate boundaries in transrectal ultrasound(TRUS) images is required. This is a challenging and difficult task due to weak prostate boundaries, speckle noise and the short range of gray levels. In this paper a method for automatic prostate segmentation in TRUS images using Gabor feature extraction and snake-like contour is presented. This method involves preprocessing, extracting Gabor feature, training, and prostate segmentation. The speckle reduction for preprocessing step has been achieved by using stick filter and top-hat transform has been implemented for smoothing the contour. A Gabor filter bank for extraction of rotation- invariant texture features has been implemented. A support vector machine(SVM) for training step has been used to get each feature of prostate and nonprostate. Finally, the boundary of prostate is extracted by the snake-like contour algorithm. A number of experiments are conducted to validate this method and results showed that this new algorithm extracted the prostate boundary with less than 10.2% of the accuracy which is relative to boundary provided manually by experts Keywords—Gabor Filter Bank, Support Vector Machines, Prostate Segmentation

—Segmenting tumor from MRI images is an essential but time consuming manual duty. Performing an automatic segmentation is a defying task since different forms of tumor tissue exist for diverse patients and in many cases the tumor is similar to the normal tissue. Various studies proposed earlier to handle the issue of precisely segmenting the tumor but they discard the degradations and their effect to the precision of the segmentation. This article provides a more precise segmentation process through the use of appropriate pre-processing algorithms. The authors studied many enhancement and restoration algorithms and selected the NL-means, Laplacian filter and histogram equalization to be used as preprocessing techniques. Experimental results showed that using a suitable preprocessing scheme would produce a better segmentation process. Index Terms — Medical image processing, Tumor segmentation, MRI images, Non-local Means, Histogram equalization, Laplacian filter. I. INTRODUCTION A tumor is a mass of tissue that grows out of control of the normal forces that regulates growth. Brain tumor has a higher mortality rate when compared to more common types of cancer. This underlines the need of accurate prognosis of brain tumor in health care industry [1]. MRI has become a widely-used method of high-quality medical imaging, especially in brain imaging [2]. Image segmentation refers to the process of partitioning a digital image into multiple segments, also known as super pixels. Image segmentation is an important process in computer vision and image processing, which divides an image into a number of disjoint regions such that the pixels have high similarity in order to use its different fields; science, medical, agriculture and industrial fields [3]. Besides, Magnetic Resonance Imaging (MRI) images are known to be corrupted by noise [4], blur [5] and low contrast artifact [6]. Therefore, this article discusses the issue of achieving a better segmentation through the use of proper image restoration and enhancement techniques. Moreover, the accurate and automatic segmentation of a brain tumor on MRI image is of great interest for assessing tumor growth and treatment responses, enhancing computer-assisted surgery, and constructing tumor growth models [7]. For those reasons, an automatic and reliable tumor segmentation method would be a useful tool since the medical image segmentation plays an instrumental role in clinical diagnosis [8]. The rest of the article sections are organized as the following: in section two, a brief elucidation about some related studies is presented as the used literature review. Moreover, detailed explanations about the employed algorithms are delivered in section three as a methodology. Also, the results of the proposed methodology are illustrated in section four as the experimental results. Likewise, a detailed discussion about the use of certain algorithms and its results is deliberated in section five. Finally, a brief closure about this article is provided in section six as a conclusion. II. LITERATURE REVIEW In this section, three recent studies are briefly described. The first study was presented by [9] which proposed a texture based analysis to identify irregularity in the brain and automatic segmentation using seeded region growing segmentation. The method of tumor detection based on the texture of the MRI is proposed to segment the abnormality from the regular adjacent, although small quantities misclassified, but the segmentation result is precise. Moreover, [10] suggested a strong technique for automatic detection of tumor for brain MRI images. He also proposed a new morphological technique which is used for the stripped skull region from the brain images. Detecting tumor precisely based on seeded region growing segmentation on an improved single seed point selection algorithm is

Accurate automatic segmentation of the prostate in magnetic resonance images (MRI) is a challenging task due to the high variability of prostate anatomic structure. Artifacts such as noise and similar signal intensity of tissues around the prostate boundary inhibit traditional segmentation methods from achieving high accuracy. We investigate both patch-based and holistic (image-to-image) deep-learning methods for segmentation of the prostate. First, we introduce a patch-based convolutional network that aims to refine the prostate contour which provides an initialization. Second, we propose a method for end-to-end prostate segmentation by integrating holistically nested edge detection with fully convolutional networks. Holistically nested networks (HNN) automatically learn a hierarchical representation that can improve prostate boundary detection. Quantitative evaluation is performed on the MRI scans of 250 patients in fivefold cross-validation. The proposed enhanced HNN model achieves a mean ± standard deviation. A Dice similarity coefficient (DSC) of [Formula: see text] and a mean Jaccard similarity coefficient (IoU) of [Formula: see text] are used to calculate without trimming any end slices. The proposed holistic model significantly ([Formula: see text]) outperforms a patch-based AlexNet model by 9% in DSC and 13% in IoU. Overall, the method achieves state-of-the-art performance as compared with other MRI prostate segmentation methods in the literature.

Manual segmentation in lumbar paraspinal muscle studies is time-consuming, subject to variability, and limits comprehensive evaluation. To solve the problems, we aim to develop a deep learning algorithm for the automatic segmentation and multi-parameter quantification of eight paraspinal muscles in lumbar CT. We collected CT images covering the range from the superior endplate of the L1 vertebra to the inferior endplate of the S1 vertebra. The dataset was partitioned into training, validation, and test sets in a ratio of 7:1:2. Six convolutional neural networks were employed to automatically segment the bilateral psoas major, quadratus lumborum, erector spinae, and multifidus across all slices. Model performance was evaluated using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and mean Intersection over Union (mIoU). Muscle parameters including cross-sectional area, muscle volume, fat infiltration, CT density, and paraspinal muscle index were calculated. The Intraclass Correlation Coefficient [ICC(3,1)] was used to assess agreement between model's segmentations and manual ground truth. 100 lumbar CT scans (age, 55.02 ± 16.2; 62 female) were used for model development. The mean DSC across all six models ranged from 0.754 to 0.903. TransUNet demonstrated the best overall (DSC, 0.903; 95% CI: 0.902, 0.913) (HD, 9.934mm; 95% CI: 9.815, 11.902) (mIoU, 0.841; 95% CI: 0.839, 0.850). For individual muscles segmented by TransUNet, the highest DSC was 0.936 (95% CI: 0.934-0.938) for the right multifidus. The mean ICC for all parameters was 0.931. The highest ICC value was 0.999 (p < 0.001). The deep learning tool enables automatic and accurate segmentation of eight lumbar paraspinal muscles. Muscle parameter measurements derived from model's segmentations and manual ground truth exhibit high agreement. Accurate segmentation and quantification of paraspinal muscle parameters facilitates large-scale epidemiological studies of paraspinal muscles and spine-related diseases, overcoming the limitations in manual methods.

Automated image segmentation for cardiac septal defects based on contour region with convolutional neural networks: A preliminary study