A framework for automatic segmentation in three dimensions of microstructural tomography data

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.

Accurate segmentation and classification of different anatomical structures of teeth from medical images plays an essential role in many clinical applications. Usually, the anatomical structures of teeth are manually labelled by experienced clinical doctors, which is time consuming. However, automatic segmentation and classification is a challenging task because the anatomical structures and surroundings of the tooth in medical images are rather complex. Therefore, in this paper, we propose an effective framework which is designed to segment the tooth with a Selective Binary and Gaussian Filtering Regularized Level Set (GFRLS) method improved by fully utilizing three dimensional (3D) information, and classify the tooth by employing unsupervised learning Pulse Coupled Neural Networks (PCNN) model. In order to evaluate the proposed method, the experiments are conducted on the different datasets of mandibular molars and the experimental results show that our method can achieve better accuracy and robustness compared to other four state of the art clustering methods.

We present a robust, automated, model-based segmentation method for kidney MR Images. We used dynamic programming and a minimal path approach to detect the optimal path within a weighted graph between two end points. We used an energy function to combine distance and gradient information to guide the marching curve and thus evaluate the best path and span a broken edge. We developed an algorithm to automate the placement of initial end points. Dynamic programming was used to automatically optimize and update end points in the procedure for searching curves. A deformable 3D model was generated using principle component analysis (PCA) and it was used as the prior knowledge for the selection of initial end points and for the evaluation of the best path. We used our minimal path method with surface models to segment mouse kidneys slice-by-slice. The method has been tested for kidney MR images of 44 mice. To quantitatively assess the automatic segmentation method, we compared the automatic segmentation results with manual segmentation. The average and standard deviation of the overlap ratios is 0.93 + 0.05. The distance error between the automatic and manual segmentation is 0.85 plusmn 0.41 pixel. The 3D automatic minimal path segmentation method is fast, accurate, and robust. It provides a useful tool for quantification and characterization of kidney MR images.

Antinuclear antibodies (ANAs) testing is the main serological diagnosis screening test for autoimmune diseases. ANAs testing is conducted principally by the indirect immunofluorescence (IIF) on human epithelial cell-substrate (HEp-2) protocol. However, due to its high variability and human subjectivity, there is an insistent need to develop an efficient method for automatic image segmentation and classification. This article develops an automatic segmentation and classification framework based on artificial intelligence (AI) on the ANA images. The Otsu thresholding method and watershed segmentation algorithm are adopted to segment IIF images of cells. Moreover, multiple texture features such as scale-invariant feature transform (SIFT), local binary pattern (LBP), cooccurrence among adjacent LBPs (CoALBP), and rotation invariant cooccurrence among adjacent LBPs (RIC-LBP) are utilized. Firstly, this article adopts traditional machine learning methods such as support vector machine (SVM), k-nearest neighbor algorithm (KNN), and random forest (RF) and then uses ensemble classifier (ECLF) combined with soft voting rules to merge these machine learning methods for classification. The deep learning method InceptionResNetV2 is also utilized to train on the classification of cell images. Eventually, the best accuracy of 0.9269 on the Changsha dataset and 0.9635 on the ICPR 2016 dataset for the traditional methods is obtained by a combination of SIFT and RIC-LBP with the ECLF classifier, and the best accuracy obtained by the InceptionResNetV2 is 0.9465 and 0.9836 separately, which outperforms other schemes.

Automatic rib segmentation and labeling in computed tomography scans using a general framework for detection, recognition and segmentation of objects in volumetric data

Traditional Chinese Medicine (TCM) has a long history and has been recognized as a popular alternative medicine in western countries. Tongue diagnosis is a significant procedure in computer-aided TCM, where tongue image analysis plays a dominant role. In this paper, we proposed a fully automatic tongue detection and tongue segmentation framework, which is an essential step in computer-aided tongue image analysis. Comparing with other existing methods, our method is fully automatic without any need of adjusting parameters for different images and do not need any initialization.

To compare choroidal neovascularization (CNV) area and vessel density (VD) measurements between two different swept-source optical coherence tomography angiography (SS-OCTA) devices. En face optical coherence tomography angiography (OCTA) images of patients affected by neovascular age-related macular degeneration were collected prospectively from two devices: Zeiss PLEX Elite 9000 (Carl Zeiss Meditec, Dublin, CA) and Topcon DRI OCT Triton SS-OCTA (Topcon, Tokyo, Japan). Choroidal neovascularization area and VD of images were measured and analyzed with ImageJ software by two readers to evaluate the agreement between two devices, with respect to different image size (3 × 3 and 6 × 6 mm) and different image segmentation (automatic vs. manual), and a Topcon equivalent Zeiss segmentation as control (i.e., the equivalent anatomical slab given by Topcon device on the Zeiss device). A total of 30 eyes (30 patients) were analyzed. There was an excellent agreement between the two readers in CNV area measurements intraclass correlation coefficient >0.9 in all analyses. We found excellent agreement in CNV area measurements (manual and automatic segmentations) when comparing 3 × 3-mm or 6 × 6-mm images both for each single device and between the two devices (overall intraclass correlation coefficient > 0.9). Vessel density measurements between manual to automatic segmentation within the same device and same image size had a high intraclass correlation coefficient value, but there was a poor agreement in VD between different image sizes (3 × 3 mm vs. 6 × 6 mm) in the same device and also comparing the two devices (3 × 3 Topcon vs. 3 × 3 Zeiss; 6 × 6 Topcon vs. 6 × 6 Zeiss). There was a poor agreement between the Topcon equivalent Zeiss segmentation and all other segmentations. There was an excellent agreement in CNV area measurements for both swept-source optical coherence tomography angiography devices in automatic and manual segmentations. However, the Topcon equivalent Zeiss segmentation was not comparable with any of the preset segmentations of Topcon and Zeiss devices. There was a poor agreement in CNV VD between different image size and different devices. For these reasons, it seems that, for accurate longitudinal analysis of VD, it is better to use the same device for each individual, even if both devices can be used interchangeably for CNV area measurements using automatic or manual segmentations.

Accurate and efficient automated tumor segmentation in breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is highly desirable for computer-aided tumor diagnosis. We propose a novel automatic segmentation framework which incorporates mean-shift smoothing, superpixel-wise classification, pixel-wise graph-cuts partitioning, and morphological refinement. A set of 15 breast DCE-MR images, obtained from the American College of Radiology Imaging Network (ACRIN) 6657 I-SPY trial, were manually segmented to generate tumor masks (as ground truth) and breast masks (as regions of interest). Four state-of-the-art segmentation approaches based on diverse models were also utilized for comparison. Based on five standard evaluation metrics for segmentation, the proposed framework consistently outperformed all other approaches. The performance of the proposed framework was: 1) 0.83 for Dice similarity coefficient, 2) 0.96 for pixel-wise accuracy, 3) 0.72 for VOC score, 4) 0.79 mm for mean absolute difference, and 5) 11.71 mm for maximum Hausdorff distance, which surpassed the second best method (i.e., adaptive geodesic transformation), a semi-automatic algorithm depending on precise initialization. Our results suggest promising potential applications of our segmentation framework in assisting analysis of breast carcinomas.

Automatic detection and segmentation of sperm head, acrosome and nucleus in microscopic images of human semen smears

A fully automated and three-dimensional (3D) segmentation method for the identification of the pulmonary parenchyma in thorax X-ray computed tomography (CT) datasets is proposed. It is meant to be used as pre-processing step in the computer-assisted detection (CAD) system for malignant lung nodule detection that is being developed by the Medical Applications in a Grid Infrastructure Connection (MAGIC-5) Project. In this new approach the segmentation of the external airways (trachea and bronchi), is obtained by 3D region growing with wavefront simulation and suitable stop conditions, thus allowing an accurate handling of the hilar region, notoriously difficult to be segmented. Particular attention was also devoted to checking and solving the problem of the apparent 'fusion' between the lungs, caused by partial-volume effects, while 3D morphology operations ensure the accurate inclusion of all the nodules (internal, pleural, and vascular) in the segmented volume. The new algorithm was initially developed and tested on a dataset of 130 CT scans from the Italung-CT trial, and was then applied to the ANODE09-competition images (55 scans) and to the LIDC database (84 scans), giving very satisfactory results. In particular, the lung contour was adequately located in 96% of the CT scans, with incorrect segmentation of the external airways in the remaining cases. Segmentation metrics were calculated that quantitatively express the consistency between automatic and manual segmentations: the mean overlap degree of the segmentation masks is 0.96 ± 0.02, and the mean and the maximum distance between the mask borders (averaged on the whole dataset) are 0.74 ± 0.05 and 4.5 ± 1.5, respectively, which confirms that the automatic segmentations quite correctly reproduce the borders traced by the radiologist. Moreover, no tissue containing internal and pleural nodules was removed in the segmentation process, so that this method proved to be fit for the use in the framework of a CAD system. Finally, in the comparison with a two-dimensional segmentation procedure, inter-slice smoothness was calculated, showing that the masks created by the 3D algorithm are significantly smoother than those calculated by the 2D-only procedure.

Purpose: To evaluate the clinical application readiness of a statistically trainable deformable shape model, called an m‐rep, for automatic segmentation of the prostate from CTimages by comparison with manual contouring. Method and Materials: ConStruct, an in‐house automatic prostate segmentation tool featuring m‐rep (medial representations) models, was used in this study. This study is to test the robustness of the m‐rep models for prostate treatment planning segmentation in routine use. For each patient case, an m‐rep was initialized and automatically deformed to segment the prostate. Ground truth was taken to be the contour set used for treatment planning. Two radiation oncologists each manually created an additional contour set. The average distance between m‐rep segmentation (or manual segmentation) and the ground truth was calculated. Retrospective clinical validation was also carried out in all cases. Two radiation oncologists blindly scored all the contour sets including the ground truth. Score 1: perfect contour—no corrections needed; 2: minor correction—less than one third of the slices require correction; 3: major correction—more efficient than redrawing all the contours from scratch; 4: not acceptable. Results: Averaged over five patients, the average distances between m‐rep, set 1 and 2 manual contour sets and the ground truth are 0.51, 0.45, and 0.42 cm, respectively. The average scores for m‐rep, set 1, set 2 contour sets, and the ground truth are 2.4, 2.4, 2.0, and 2.1, respectively. Conclusion: The qualitative and clinical validations were performed on m‐rep‐based automatic segmentation by comparing it to manual contouring. M‐reps appeared to produce reasonable and acceptable prostate contour sets when compared to those generated by clinicians. We propose that m‐reps be used to improve clinical efficiency by automatically contouring the prostate as a starting shape and then manually editing when needed. Further validation on a larger patient cohort is indicated.

Cardiac MRI has experienced a crescent relevance in clinical investigations. The segmentation of myocardial walls is a prerequisite for assessment of cardiac viability. Manual or semi-automatic segmentation of all the images of a subject is tedious, as well as consuming much time from cardiologists. In this study, we selected 23 slices of simulated cardiac MR by MRXCAT and 30 real slices of CINE-MR from 15 patients with Chagas Disease. The proposed pipeline of the fully automatic segmentation consists of three steps: 1. Preprocessing; 2. Automatic Seeds Definition; and 3. Segmentation by Geodesic Active Contour. An experienced cardiologist provided the gold standard annotations of apical, mid-ventricular and basal LV myocardium. We use the following three metrics to validate the proposed pipeline with different signal to noise ratio: Dice similarity (DS), Precision (Pr) and Volumetric Similarity (VS). DS show good agreement between manual segmentation and the automatic segmentation in simulated images with SNR 200, 25, 15 and 5, i.e., 0.98, 0.93, 0.9 and 0.72, respectively. We found moderate agreements between manual segmentation and Snake segmentation in simulated images with SNR 200, 25, 15 and 5, i.e., 0.38, 0.42, 0.34 and 0.39, respectively. The DS, VS, and Pr obtained suggest substantial agreements between the manual and our proposed method segmentation in images of Chagas’s Disease, i.e., 0.8 [0.69–0.87], 0.89 [0.72–0.99] and 0.9 [0.76–0.98] (mean [min–max]), respectively. Our findings suggest that one can use the proposed method in the automatic myocardium segmentation with reliability similar to manual tracing, although completely free of human interaction.

Automatic segmentation of the choroid on optical coherence tomography (OCT) images helps ophthalmologists in diagnosing eye pathologies. Compared to manual segmentations, it is faster and is not affected by human errors. The presence of the large speckle noise in the OCT images limits the automatic segmentation and interpretation of them. To solve this problem, a new curvelet transform-based K-SVD method is proposed in this study. Furthermore, the dataset was manually segmented by a retinal ophthalmologist to draw a comparison with the proposed automatic segmentation technique. In this study, curvelet transform-based K-SVD dictionary learning and Lucy-Richardson algorithm were used to remove the speckle noise from OCT images. The Outer/Inner Choroidal Boundaries (O/ICB) were determined utilizing graph theory. The area between ICB and outer choroidal boundary was considered as the choroidal region. The proposed method was evaluated on our dataset and the average dice similarity coefficient (DSC) was calculated to be 92.14% ± 3.30% between automatic and manual segmented regions. Moreover, by applying the latest presented open-source algorithm by Mazzaferri et al. on our dataset, the mean DSC was calculated to be 55.75% ± 14.54%. A significant similarity was observed between automatic and manual segmentations. Automatic segmentation of the choroidal layer could be also utilized in large-scale quantitative studies of the choroid.

Separate renal function assessment is important in clinical decision making. The single-photon emission computed tomography is commonly used for the assessment although radioactive, tedious and of high cost. This study aimed to automatically assess the separate renal function using plain CT images and artificial intelligence methods, including deep learning-based automatic segmentation and radiomics modeling. We performed a retrospective study on 281 patients with nephrarctia or hydronephrosis from two centers (Training set: 159 patients from Center I; Test set: 122 patients from Center II). The renal parenchyma and hydronephrosis regions in plain CT images were automatically segmented using deep learning-based U-Net transformers (UNETR). Radiomic features were extracted from the two regions and used to build radiomic signature using the ElasticNet, then further combined with clinical characteristics using multivariable logistic regression to obtain an integrated model. The automatic segmentation was evaluated using the dice similarity coefficient (DSC). The mean DSC of automatic kidney segmentation based on UNETR was 0.894 and 0.881 in the training and test sets. The average time of automatic and manual segmentation was 3.4s/case and 1477.9s/case. The AUC of radiomic signature was 0.778 in the training set and 0.801 in the test set. The AUC of the integrated model was 0.792 and 0.825 in the training and test sets. It is feasible to assess the renal function of each kidney separately using plain CT and AI methods. Our method can minimize the radiation risk, improve the diagnostic efficiency and reduce the costs.

Hippocampal subfields play important and divergent roles in both memory formation and early diagnosis of many neurological diseases, but automatic subfield segmentation is less explored due to its small size and poor image contrast. In this paper, we propose an automatic learning-based hippocampal subfields segmentation framework using multi-modality 3TMR images, including T1 MRI and resting-state fMRI (rs-fMRI). To do this, we first acquire both 3T and 7T T1 MRIs for each training subject, and then the 7T T1 MRI are linearly registered onto the 3T T1 MRI. Six hippocampal subfields are manually labeled on the aligned 7T T1 MRI, which has the 7T image contrast but sits in the 3T T1 space. Next, corresponding appearance and relationship features from both 3T T1 MRI and rs-fMRI are extracted to train a structured random forest as a multi-label classifier to conduct the segmentation. Finally, the subfield segmentation is further refined iteratively by additional context features and updated relationship features. To our knowledge, this is the first work that addresses the challenging automatic hippocampal subfields segmentation using 3T routine T1 MRI and rs-fMRI. The quantitative comparison between our results and manual ground truth demonstrates the effectiveness of our method. Besides, we also find that (a) multi-modality features significantly improved subfield segmentation performance due to the complementary information among modalities; (b) automatic segmentation results using 3T multimodality images are partially comparable to those on 7T T1 MRI.