Segmentation of parotid glands from registered CT and MR images

PurposeTo develop an automatic multimodal method for segmentation of parotid glands (PGs) from pre-registered computed tomography (CT) and magnetic resonance (MR) images and compare its results to the results of an existing state-of-the-art algorithm that segments PGs from CT images only.MethodsMagnetic resonance images of head and neck were registered to the accompanying CT images using two different state-of-the-art registration procedures. The reference domains of registered image pairs were divided on the complementary PG regions and backgrounds according to the manual delineation of PGs on CT images, provided by a physician. Patches of intensity values from both image modalities, centered around randomly sampled voxels from the reference domain, served as positive or negative samples in the training of the convolutional neural network (CNN) classifier. The trained CNN accepted a previously unseen (registered) image pair and classified its voxels according to the resemblance of its patches to the patches used for training. The final segmentation was refined using a graph-cut algorithm, followed by the dilate-erode operations.ResultsUsing the same image dataset, segmentation of PGs was performed using the proposed multimodal algorithm and an existing monomodal algorithm, which segments PGs from CT images only. The mean value of the achieved Dice overlapping coefficient for the proposed algorithm was 78.8%, while the corresponding mean value for the monomodal algorithm was 76.5%.ConclusionsAutomatic PG segmentation on the planning CT image can be augmented with the MR image modality, leading to an improved RT planning of head and neck cancer.     

Application of CT images in the diagnosis of lung cancer based on finite mixed model

ObjectiveInvestigating the application of CT images when diagnosing lung cancer based on finite mixture model is the objective. Method: 120 clean healthy rats were taken as the research objects to establish lung cancer rat model and carry out lung CT image examination. After the successful CT image data preprocessing, the image is segmented by different methods, which include lung nodule segmentation on the basis of Adaptive Particle Swarm Optimization – Gaussian mixture model (APSO-GMM), lung nodule segmentation on the basis of Adaptive Particle Swarm Optimization – gamma mixture model (APSO-GaMM), lung nodule segmentation based on statistical information and self-selected mixed distribution model, and lung nodule segmentation based on neighborhood information and self-selected mixed distribution model. The segmentation effect is evaluated. Results: Compared with the results of lung nodule segmentation based on statistical information and self-selected mixed distribution model, the Dice coefficient of lung nodule segmentation based on neighborhood information and self-selected mixed distribution model is higher, the relative final measurement accuracy is smaller, the segmentation is more accurate, but the running time is longer. Compared with APSO-GMM and APSO-GaMM, the dice value of self-selected mixed distribution model segmentation method is larger, and the final measurement accuracy is smaller. Conclusion: Among the five methods, the dice value of the self-selected mixed distribution model based on neighborhood information is the largest, and the relative accuracy of the final measurement is the smallest, indicating that the segmentation effect of the self-selected mixed distribution model based on neighborhood information is the best.     

Convolutional neural network-based automatic liver delineation on contrast-enhanced and non-contrast-enhanced CT images for radiotherapy planning

AimThis study evaluated a convolutional neural network (CNN) for automatically delineating the liver on contrast-enhanced or non-contrast-enhanced CT, making comparisons with a commercial automated technique (MIM Maestro®).BackgroundIntensity-modulated radiation therapy requires careful labor-intensive planning involving delineation of the target and organs on CT or MR images to ensure delivery of the effective dose to the target while avoiding organs at risk.Materials and MethodsContrast-enhanced planning CT images from 101 pancreatic cancer cases and accompanying mask images showing manually-delineated liver contours were used to train the CNN to segment the liver. The trained CNN then performed liver segmentation on a further 20 contrast-enhanced and 15 non-contrastenhanced CT image sets, producing three-dimensional mask images of the liver.ResultsFor both contrast-enhanced and non-contrast-enhanced images, the mean Dice similarity coefficients between CNN segmentations and ground-truth manual segmentations were significantly higher than those between ground-truth and MIM Maestro software (p < 0.001). Although mean CT values of the liver were higher on contrast-enhanced than on non-contrast-enhanced CT, there were no significant differences in the Hausdorff distances of the CNN segmentations, indicating that the CNN could successfully segment the liver on both image types, despite being trained only on contrast-enhanced images.ConclusionsOur results suggest that a CNN can perform highly accurate automated delineation of the liver on CT images, irrespective of whether the CT images are contrast-enhanced or not.     

Fully Automatic Localization and Segmentation of 3D Vertebral Bodies from CT/MR Images via a Learning-Based Method

In this paper, we address the problems of fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images. We propose a learning-based, unified random forest regression and classification framework to tackle these two problems. More specifically, in the first stage, the localization of 3D vertebral bodies is solved with random forest regression where we aggregate the votes from a set of randomly sampled image patches to get a probability map of the center of a target vertebral body in a given image. The resultant probability map is then further regularized by Hidden Markov Model (HMM) to eliminate potential ambiguity caused by the neighboring vertebral bodies. The output from the first stage allows us to define a region of interest (ROI) for the segmentation step, where we use random forest classification to estimate the likelihood of a voxel in the ROI being foreground or background. The estimated likelihood is combined with the prior probability, which is learned from a set of training data, to get the posterior probability of the voxel. The segmentation of the target vertebral body is then done by a binary thresholding of the estimated probability. We evaluated the present approach on two openly available datasets: 1) 3D T2-weighted spine MR images from 23 patients and 2) 3D spine CT images from 10 patients. Taking manual segmentation as the ground truth (each MR image contains at least 7 vertebral bodies from T11 to L5 and each CT image contains 5 vertebral bodies from L1 to L5), we evaluated the present approach with leave-one-out experiments. Specifically, for the T2-weighted MR images, we achieved for localization a mean error of 1.6 mm, and for segmentation a mean Dice metric of 88.7% and a mean surface distance of 1.5 mm, respectively. For the CT images we achieved for localization a mean error of 1.9 mm, and for segmentation a mean Dice metric of 91.0% and a mean surface distance of 0.9 mm, respectively.     

Automatic lung segmentation in COVID-19 patients: Impact on quantitative computed tomography analysis

PurposeTo assess the impact of lung segmentation accuracy in an automatic pipeline for quantitative analysis of CT images.MethodsFour different platforms for automatic lung segmentation based on convolutional neural network (CNN), region-growing technique and atlas-based algorithm were considered. The platforms were tested using CT images of 55 COVID-19 patients with severe lung impairment. Four radiologists assessed the segmentations using a 5-point qualitative score (QS). For each CT series, a manually revised reference segmentation (RS) was obtained. Histogram-based quantitative metrics (QM) were calculated from CT histogram using lung segmentationsfrom all platforms and RS. Dice index (DI) and differences of QMs (ΔQMs) were calculated between RS and other segmentations.ResultsHighest QS and lower ΔQMs values were associated to the CNN algorithm. However, only 45% CNN segmentations were judged to need no or only minimal corrections, and in only 17 cases (31%), automatic segmentations provided RS without manual corrections. Median values of the DI for the four algorithms ranged from 0.993 to 0.904. Significant differences for all QMs calculated between automatic segmentations and RS were found both when data were pooled together and stratified according to QS, indicating a relationship between qualitative and quantitative measurements. The most unstable QM was the histogram 90th percentile, with median ΔQMs values ranging from 10HU and 158HU between different algorithms.ConclusionsNone of tested algorithms provided fully reliable segmentation. Segmentation accuracy impacts differently on different quantitative metrics, and each of them should be individually evaluated according to the purpose of subsequent analyses.     

Conditional generative adversarial networks to generate pseudo low monoenergetic CT image from a single-tube voltage CT scanner

PurposeTo generate pseudo low monoenergetic CT images of the abdomen from 120-kVp CT images with cGAN.Materials and MethodsWe retrospectively included 48 patients who underwent contrast-enhanced abdominal CT using dual-energy CT. We reconstructed paired data sets of 120 kVp CT images and virtual low monoenergetic (55-keV) CT images. cGAN was prepared to generate pseudo 55-keV CT images from 120-kVp CT images. The pseudo 55 keV CT images in epoch 10, 50, 100, and 500 were compared to the 55 keV images generated using peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM).ResultsThe PSNRs were 28.0, 28.5, 28.6, and 28.8 at epochs 10, 50, 100, and 500, respectively. The SSIM was approximately constant from epochs 50 to 500.ConclusionPseudo low monoenergetic abdominal CT images were generated from 120-kVp CT images using cGAN, and the images had good quality similar to that of monochromatic images obtained with DECT software.     

Automated CT bone segmentation using statistical shape modelling and local template matching

Abstract

Accurate CT bone segmentation is essential to develop chair-side manufacturing of implants based on additive manufacturing. We herewith present an automated method able to accurately segment challenging bone regions, while simultaneously providing anatomical correspondences. The method was evaluated on demanding regions: normal and osteoarthritic scapulae, healthy and atrophied mandibles, and orbital bones. On average, results were accurate with surface distances of approximately 0.5?mm and average Dice coefficients >90%. Since anatomical correspondences are propagated during the segmentation process, this approach can directly yield anatomical measurements, provide design parameters for personalized surgical instruments, or determine the bone geometry to manufacture patient-specific implants.     

MRI-Only Based Radiotherapy Treatment Planning for the Rat Brain on a Small Animal Radiation Research Platform (SARRP)

Computed tomography (CT) is the standard imaging modality in radiation therapy treatment planning (RTP). However, magnetic resonance (MR) imaging provides superior soft tissue contrast, increasing the precision of target volume selection. We present MR-only based RTP for a rat brain on a small animal radiation research platform (SARRP) using probabilistic voxel classification with multiple MR sequences. Six rat heads were imaged, each with one CT and five MR sequences. The MR sequences were: T1-weighted, T2-weighted, zero-echo time (ZTE), and two ultra-short echo time sequences with 20 μs (UTE1) and 2 ms (UTE2) echo times. CT data were manually segmented into air, soft tissue, and bone to obtain the RTP reference. Bias field corrected MR images were automatically segmented into the same tissue classes using a fuzzy c-means segmentation algorithm with multiple images as input. Similarities between segmented CT and automatic segmented MR (ASMR) images were evaluated using Dice coefficient. Three ASMR images with high similarity index were used for further RTP. Three beam arrangements were investigated. Dose distributions were compared by analysing dose volume histograms. The highest Dice coefficients were obtained for the ZTE-UTE2 combination and for the T1-UTE1-T2 combination when ZTE was unavailable. Both combinations, along with UTE1-UTE2, often used to generate ASMR images, were used for further RTP. Using 1 beam, MR based RTP underestimated the dose to be delivered to the target (range: 1.4%-7.6%). When more complex beam configurations were used, the calculated dose using the ZTE-UTE2 combination was the most accurate, with 0.7% deviation from CT, compared to 0.8% for T1-UTE1-T2 and 1.7% for UTE1-UTE2. The presented MR-only based workflow for RTP on a SARRP enables both accurate organ delineation and dose calculations using multiple MR sequences. This method can be useful in longitudinal studies where CT’s cumulative radiation dose might contribute to the total dose.     

Rotationally resliced 3D prostate segmentation of MR images using Bhattacharyya similarity and active band theory

PurposeIn this article, we propose a novel, semi-automatic segmentation method to process 3D MR images of the prostate using the Bhattacharyya coefficient and active band theory with the goal of providing technical support for computer-aided diagnosis and surgery of the prostate.MethodsOur method consecutively segments a stack of rotationally resectioned 2D slices of a prostate MR image by assessing the similarity of the shape and intensity distribution in neighboring slices. 2D segmentation is first performed on an initial slice by manually selecting several points on the prostate boundary, after which the segmentation results are propagated consecutively to neighboring slices. A framework of iterative graph cuts is used to optimize the energy function, which contains a global term for the Bhattacharyya coefficient with the help of an auxiliary function. Our method does not require previously segmented data for training or for building statistical models, and manual intervention can be applied flexibly and intuitively, indicating the potential utility of this method in the clinic.ResultsWe tested our method on 3D T2-weighted MR images from the ISBI dataset and PROMISE12 dataset of 129 patients, and the Dice similarity coefficients were 90.34 ± 2.21% and 89.32 ± 3.08%, respectively. The comparison was performed with several state-of-the-art methods, and the results demonstrate that the proposed method is robust and accurate, achieving similar or higher accuracy than other methods without requiring training.ConclusionThe proposed algorithm for segmenting 3D MR images of the prostate is accurate, robust, and readily applicable to a clinical environment for computer-aided surgery or diagnosis.     

Automatic Nuclei Segmentation in H&E Stained Breast Cancer Histopathology Images

The introduction of fast digital slide scanners that provide whole slide images has led to a revival of interest in image analysis applications in pathology. Segmentation of cells and nuclei is an important first step towards automatic analysis of digitized microscopy images. We therefore developed an automated nuclei segmentation method that works with hematoxylin and eosin (H&E) stained breast cancer histopathology images, which represent regions of whole digital slides. The procedure can be divided into four main steps: 1) pre-processing with color unmixing and morphological operators, 2) marker-controlled watershed segmentation at multiple scales and with different markers, 3) post-processing for rejection of false regions and 4) merging of the results from multiple scales. The procedure was developed on a set of 21 breast cancer cases (subset A) and tested on a separate validation set of 18 cases (subset B). The evaluation was done in terms of both detection accuracy (sensitivity and positive predictive value) and segmentation accuracy (Dice coefficient). The mean estimated sensitivity for subset A was 0.875 (±0.092) and for subset B 0.853 (±0.077). The mean estimated positive predictive value was 0.904 (±0.075) and 0.886 (±0.069) for subsets A and B, respectively. For both subsets, the distribution of the Dice coefficients had a high peak around 0.9, with the vast majority of segmentations having values larger than 0.8.     

3D-printed patient-specific pelvis phantom for dosimetry measurements for prostate stereotactic radiotherapy with dominant intraprostatic lesion boost

AimDeveloping and assessing the feasibility of using a three-dimensional (3D) printed patient-specific anthropomorphic pelvis phantom for dose calculation and verification for stereotactic ablative radiation therapy (SABR) with dose escalation to the dominant intraprostatic lesions.Material and methodsA 3D-printed pelvis phantom, including bone-mimicking material, was fabricated based on the computed tomography (CT) images of a prostate cancer patient. To compare the extent to which patient and phantom body and bones overlapped, the similarity Dice coefficient was calculated. Modular cylindrical inserts were created to encapsulate radiochromic films and ionization chamber for absolute dosimetry measurements at the location of prostate and at the boost region. Gamma analysis evaluation with 2%/2mm criteria was performed to compare treatment planning system calculations and measured dose when delivering a 10 flattening filter free (FFF) SABR plan and a 10FFF boost SABR plan.ResultsDice coefficients of 0.98 and 0.91 were measured for body and bones, respectively, demonstrating agreement between patient and phantom outlines. For the boost plans the gamma analysis yielded 97.0% of pixels passing 2%/2mm criteria and these results were supported by the chamber average dose difference of 0.47 ± 0.03%. These results were further improved when overriding the bone relative electron density: 97.3% for the 2%/2mm gamma analysis, and 0.05 ± 0.03% for the ionization chamber average dose difference.ConclusionsThe modular patient-specific 3D-printed pelvis phantom has proven to be a highly attractive and versatile tool to validate prostate SABR boost plans using multiple detectors.     

Automated voxel-by-voxel tissue classification for hippocampal segmentation: Methods and validation

The hippocampus is an important structural biomarker for Alzheimer's disease (AD) and has a primary role in the pathogenesis of other neurological and psychiatric diseases. This study presents a fully automated pattern recognition system for an accurate and reproducible segmentation of the hippocampus in structural Magnetic Resonance Imaging (MRI). The method was validated on a mixed cohort of 56 T1-weighted structural brain images, and consists of three processing levels: (a) Linear registration: all brain images were registered to a standard template and an automated method was applied to capture the global shape of the hippocampus. (b) Feature extraction: all voxels included in the previously selected volume were characterized by 315 features computed from local information. (c) Voxel classification: a Random Forest algorithm was used to classify voxels as belonging or not belonging to the hippocampus. In order to improve the classification performance, an adaptive learning method based on the use of the Pearson's correlation coefficient was developed. The segmentation results (Dice similarity index = 0.81 ± 0.03) compare well with other state-of-the art approaches. A validation study was conducted on an independent dataset of 100 T1-weighted brain images, achieving significantly better results than those obtained with FreeSurfer.     

Spinal Cord Segmentation by One Dimensional Normalized Template Matching: A Novel,Quantitative Technique to Analyze Advanced Magnetic Resonance Imaging Data

Spinal cord segmentation is a developing area of research intended to aid the processing and interpretation of advanced magnetic resonance imaging (MRI). For example, high resolution three-dimensional volumes can be segmented to provide a measurement of spinal cord atrophy. Spinal cord segmentation is difficult due to the variety of MRI contrasts and the variation in human anatomy. In this study we propose a new method of spinal cord segmentation based on one-dimensional template matching and provide several metrics that can be used to compare with other segmentation methods. A set of ground-truth data from 10 subjects was manually-segmented by two different raters. These ground truth data formed the basis of the segmentation algorithm. A user was required to manually initialize the spinal cord center-line on new images, taking less than one minute. Template matching was used to segment the new cord and a refined center line was calculated based on multiple centroids within the segmentation. Arc distances down the spinal cord and cross-sectional areas were calculated. Inter-rater validation was performed by comparing two manual raters (n = 10). Semi-automatic validation was performed by comparing the two manual raters to the semi-automatic method (n = 10). Comparing the semi-automatic method to one of the raters yielded a Dice coefficient of 0.91 +/- 0.02 for ten subjects, a mean distance between spinal cord center lines of 0.32 +/- 0.08 mm, and a Hausdorff distance of 1.82 +/- 0.33 mm. The absolute variation in cross-sectional area was comparable for the semi-automatic method versus manual segmentation when compared to inter-rater manual segmentation. The results demonstrate that this novel segmentation method performs as well as a manual rater for most segmentation metrics. It offers a new approach to study spinal cord disease and to quantitatively track changes within the spinal cord in an individual case and across cohorts of subjects.     

CTANet: Confidence-Based Threshold Adaption Network for Semi-Supervised Segmentation of Uterine Regions from MR Images for HIFU Treatment

ObjectivesThe accurate preoperative segmentation of the uterus and uterine fibroids from magnetic resonance images (MRI) is an essential step for diagnosis and real-time ultrasound guidance during high-intensity focused ultrasound (HIFU) surgery. Conventional supervised methods are effective techniques for image segmentation. Recently, semi-supervised segmentation approaches have been reported in the literature. One popular technique for semi-supervised methods is to use pseudo-labels to artificially annotate unlabeled data. However, many existing pseudo-label generations rely on a fixed threshold used to generate a confidence map, regardless of the proportion of unlabeled and labeled data.Materials and MethodsTo address this issue, we propose a novel semi-supervised framework called Confidence-based Threshold Adaptation Network (CTANet) to improve the quality of pseudo-labels. Specifically, we propose an online pseudo-labels method to automatically adjust the threshold, producing high-confident unlabeled annotations and boosting segmentation accuracy. To further improve the network's generalization to fit the diversity of different patients, we design a novel mixup strategy by regularizing the network on each layer in the decoder part and introducing a consistency regularization loss between the outputs of two sub-networks in CTANet.ResultsWe compare our method with several state-of-the-art semi-supervised segmentation methods on the same uterine fibroids dataset containing 297 patients. The performance is evaluated by the Dice similarity coefficient, the precision, and the recall. The results show that our method outperforms other semi-supervised learning methods. Moreover, for the same training set, our method approaches the segmentation performance of a fully supervised U-Net (100% annotated data) but using 4 times less annotated data (25% annotated data, 75% unannotated data).ConclusionExperimental results are provided to illustrate the effectiveness of the proposed semi-supervised approach. The proposed method can contribute to multi-class segmentation of uterine regions from MRI for HIFU treatment.     

Automatic Segmentation of Eight Tissue Classes in Neonatal Brain MRI

Purpose

Volumetric measurements of neonatal brain tissues may be used as a biomarker for later neurodevelopmental outcome. We propose an automatic method for probabilistic brain segmentation in neonatal MRIs.

Materials and Methods

In an IRB-approved study axial T1- and T2-weighted MR images were acquired at term-equivalent age for a preterm cohort of 108 neonates. A method for automatic probabilistic segmentation of the images into eight cerebral tissue classes was developed: cortical and central grey matter, unmyelinated and myelinated white matter, cerebrospinal fluid in the ventricles and in the extra cerebral space, brainstem and cerebellum. Segmentation is based on supervised pixel classification using intensity values and spatial positions of the image voxels. The method was trained and evaluated using leave-one-out experiments on seven images, for which an expert had set a reference standard manually. Subsequently, the method was applied to the remaining 101 scans, and the resulting segmentations were evaluated visually by three experts. Finally, volumes of the eight segmented tissue classes were determined for each patient.

Results

The Dice similarity coefficients of the segmented tissue classes, except myelinated white matter, ranged from 0.75 to 0.92. Myelinated white matter was difficult to segment and the achieved Dice coefficient was 0.47. Visual analysis of the results demonstrated accurate segmentations of the eight tissue classes. The probabilistic segmentation method produced volumes that compared favorably with the reference standard.

Conclusion

The proposed method provides accurate segmentation of neonatal brain MR images into all given tissue classes, except myelinated white matter. This is the one of the first methods that distinguishes cerebrospinal fluid in the ventricles from cerebrospinal fluid in the extracerebral space. This method might be helpful in predicting neurodevelopmental outcome and useful for evaluating neuroprotective clinical trials in neonates.     

Fully Automated Enhanced Tumor Compartmentalization: Man vs. Machine Reloaded

ObjectiveComparison of a fully-automated segmentation method that uses compartmental volume information to a semi-automatic user-guided and FDA-approved segmentation technique.MethodsNineteen patients with a recently diagnosed and histologically confirmed glioblastoma (GBM) were included and MR images were acquired with a 1.5 T MR scanner. Manual segmentation for volumetric analyses was performed using the open source software 3D Slicer version 4.2.2.3 (www.slicer.org). Semi-automatic segmentation was done by four independent neurosurgeons and neuroradiologists using the computer-assisted segmentation tool SmartBrush® (referred to as SB), a semi-automatic user-guided and FDA-approved tumor-outlining program that uses contour expansion. Fully automatic segmentations were performed with the Brain Tumor Image Analysis (BraTumIA, referred to as BT) software. We compared manual (ground truth, referred to as GT), computer-assisted (SB) and fully-automated (BT) segmentations with regard to: (1) products of two maximum diameters for 2D measurements, (2) the Dice coefficient, (3) the positive predictive value, (4) the sensitivity and (5) the volume error.ResultsSegmentations by the four expert raters resulted in a mean Dice coefficient between 0.72 and 0.77 using SB. BT achieved a mean Dice coefficient of 0.68. Significant differences were found for intermodal (BT vs. SB) and for intramodal (four SB expert raters) performances. The BT and SB segmentations of the contrast-enhancing volumes achieved a high correlation with the GT. Pearson correlation was 0.8 for BT; however, there were a few discrepancies between raters (BT and SB 1 only). Additional non-enhancing tumor tissue extending the SB volumes was found with BT in 16/19 cases. The clinically motivated sum of products of diameters measure (SPD) revealed neither significant intermodal nor intramodal variations. The analysis time for the four expert raters was faster (1 minute and 47 seconds to 3 minutes and 39 seconds) than with BT (5 minutes).ConclusionBT and SB provide comparable segmentation results in a clinical setting. SB provided similar SPD measures to BT and GT, but differed in the volume analysis in one of the four clinical raters. A major strength of BT may its independence from human interactions, it can thus be employed to handle large datasets and to associate tumor volumes with clinical and/or molecular datasets ("-omics") as well as for clinical analyses of brain tumor compartment volumes as baseline outcome parameters. Due to its multi-compartment segmentation it may provide information about GBM subcompartment compositions that may be subjected to clinical studies to investigate the delineation of the target volumes for adjuvant therapies in the future.     

Automatic fetal biometry prediction using a novel deep convolutional network architecture

PurposeFetal biometric measurements face a number of challenges, including the presence of speckle, limited soft-tissue contrast and difficulties in the presence of low amniotic fluid. This work proposes a convolutional neural network for automatic segmentation and measurement of fetal biometric parameters, including biparietal diameter (BPD), head circumference (HC), abdominal circumference (AC), and femur length (FL) from ultrasound images that relies on the attention gates incorporated into the multi-feature pyramid Unet (MFP-Unet) network.MethodsThe proposed approach, referred to as Attention MFP-Unet, learns to extract/detect salient regions automatically to be treated as the object of interest via the attention gates. After determining the type of anatomical structure in the image using a convolutional neural network, Niblack's thresholding technique was applied as pre-processing algorithm for head and abdomen identification, whereas a novel algorithm was used for femur extraction. A publicly-available dataset (HC18 grand-challenge) and clinical data of 1334 subjects were utilized for training and evaluation of the Attention MFP-Unet algorithm.ResultsDice similarity coefficient (DSC), hausdorff distance (HD), percentage of good contours, the conformity coefficient, and average perpendicular distance (APD) were employed for quantitative evaluation of fetal anatomy segmentation. In addition, correlation analysis, good contours, and conformity were employed to evaluate the accuracy of the biometry predictions. Attention MFP-Unet achieved 0.98, 1.14 mm, 100%, 0.95, and 0.2 mm for DSC, HD, good contours, conformity, and APD, respectively.ConclusionsQuantitative evaluation demonstrated the superior performance of the Attention MFP-Unet compared to state-of-the-art approaches commonly employed for automatic measurement of fetal biometric parameters.     

Square-cut: a segmentation algorithm on the basis of a rectangle shape

We present a rectangle-based segmentation algorithm that sets up a graph and performs a graph cut to separate an object from the background. However, graph-based algorithms distribute the graph's nodes uniformly and equidistantly on the image. Then, a smoothness term is added to force the cut to prefer a particular shape. This strategy does not allow the cut to prefer a certain structure, especially when areas of the object are indistinguishable from the background. We solve this problem by referring to a rectangle shape of the object when sampling the graph nodes, i.e., the nodes are distributed non-uniformly and non-equidistantly on the image. This strategy can be useful, when areas of the object are indistinguishable from the background. For evaluation, we focus on vertebrae images from Magnetic Resonance Imaging (MRI) datasets to support the time consuming manual slice-by-slice segmentation performed by physicians. The ground truth of the vertebrae boundaries were manually extracted by two clinical experts (neurological surgeons) with several years of experience in spine surgery and afterwards compared with the automatic segmentation results of the proposed scheme yielding an average Dice Similarity Coefficient (DSC) of 90.97±2.2%.     

Magnetic Resonance Imaging of the Newborn Brain: Automatic Segmentation of Brain Images into 50 Anatomical Regions

We studied methods for the automatic segmentation of neonatal and developing brain images into 50 anatomical regions, utilizing a new set of manually segmented magnetic resonance (MR) images from 5 term-born and 15 preterm infants imaged at term corrected age called ALBERTs. Two methods were compared: individual registrations with label propagation and fusion; and template based registration with propagation of a maximum probability neonatal ALBERT (MPNA). In both cases we evaluated the performance of different neonatal atlases and MPNA, and the approaches were compared with the manual segmentations by means of the Dice overlap coefficient. Dice values, averaged across regions, were 0.81±0.02 using label propagation and fusion for the preterm population, and 0.81±0.02 using the single registration of a MPNA for the term population. Segmentations of 36 further unsegmented target images of developing brains yielded visibly high-quality results. This registration approach allows the rapid construction of automatically labeled age-specific brain atlases for neonates and the developing brain.     

GVC-Net: Global Vascular Context Network for Cerebrovascular Segmentation Using Sparse Labels

ObjectivesCerebrovascular disease is a serious threat to human health. Because of its high mortality and disability rate, early diagnosis and prevention are very important. The performance of existing cerebrovascular segmentation methods based on deep learning depends on the integrity of labels. However, manual labels are usually of low quality and poor connectivity at small blood vessels, which directly affects the cerebrovascular segmentation results.Material and methodIn this paper, we propose a new segmentation network to segment cerebral vessels from MRA images by using sparse labels. The long-distance dependence between vascular structures is captured by the global vascular context module, and the topology is constrained by the hybrid loss function to segment the cerebral vessels with good connectivity.ResultExperiments show that our method performed with a sensitivity, precision, dice similarity coefficient, intersection over union and centerline dice similarity coefficient of 61.24%, 75.58%, 67.66%, 51.13% and 83.79% respectively.ConclusionThe obtained results reveal that the proposed cerebrovascular segmentation network has better segmentation performance for cerebrovascular segmentation under sparse labels, and can suppress the noise of background to a certain extent.