Automatic pancreas segmentation in abdominal CT image with contrast enhancement block

Graph cut based automatic aorta segmentation with an adaptive smoothness constraint in 3D abdominal CT images

Background and objectiveThe size, shape, and position of the pancreas are affected by the patient characteristics such as age, sex, adiposity. Owing to more complex anatomical structures (size, shape, and position) of the pancreas, specialists have some difficulties in the analysis of pancreatic diseases (diabetes, pancreatic cancer, pancreatitis). Therefore, the treatment of the disease requires enormous time and depends on the experience of specialists. In order to decrease the rate of pancreatic disease deaths and to assist the specialist in the analysis of pancreatic diseases, automatic pancreas segmentation techniques have been actively developed in the research article for many years. MethodsAlthough the rapid growth of deep learning and proving satisfactory performance in many medical image processing and computer vision applications, the maximum Dice Similarity Coefficients (DSC) value of these techniques related to automatic pancreas segmentation is only around 85% due to complex structure of the pancreas and other factors. Contrary to previous techniques which are required significantly higher computational power and memory, this paper suggests a novel two-phase approach for high-accuracy automatic pancreas segmentation in computed tomography (CT) imaging. The proposed approach consists of two phases; (1) Pancreas Localization, where the rough pancreas position is detected on the 2D CT slice by adopting Mask R-CNN model, (2) Pancreas Segmentation, where the segmented pancreas region is produced by refining the candidate pancreas region with 3D U-Net on the 2D sub-CT slices generated in the first phase. Both qualitative and quantitative assessments of the proposed approach are performed on the NIH data set. ResultsIn order to evaluate the achievement of the recommended approach, a total of 16 different automatic pancreas segmentation techniques reported in the literature are compared by utilizing performance assessment procedures which are Dice Similarity Coefficient (DSC), Jaccard Index (JI), Precision (PRE), Recall (REC), Pixel Accuracy (ACC), Specificity (SPE), Receiver Operating Characteristics (ROC) and Area under ROC curve (AUC). The average values of DSC, JI, REC and ACC are computed as 86.15%, 75.93%, 86.27%, 86.27% and 99.95% respectively, which are the best values among well-established studies for automatic pancreas segmentation. ConclusionIt is demonstrated with qualitative and quantitative results that our suggested two-phase approach creates more favorable results than other existing approaches.

ObjectiveTo study the feasibility and the potential benefits of defining the internal gross tumor volume (IGTV) of hepatocellular carcinoma (HCC) using contrast-enhanced 4D CT images obtained by combining arterial-phase (AP) contrast-enhanced (CE) 3D CT and non-contrast-enhanced (NCE) 4D CT images using deformable registration (DR).MethodsTen HCC patients who had received radiotherapy beforehand were selected for this study. The following CT simulation images were acquired sequentially: NCE 4D CT in free breathing, NCE 3D CT and APCE 3D CT in end-expiration breath holding. All 4D CT images were sorted into ten phases according to breath cycle (CT00 ~ CT90). Gross tumor volumes (GTVs) were contoured on all CT images and the IGTV-1 was obtained by merging the GTVs in each phase of 4D CT images. The GTV on the APCE 3D CT image was deformably registered to each 4D CT phase image according to liver shape using RayStationTM 3.99.0.7 version treatment planning system. The IGTV-DR was obtained by merging the GTVs after DR on the 4D CT images. Volume differences among the GTVs and between the IGTV-1 and the IGTV-DR were compared.ResultsThe edge of most lesions could be definitively identified using APCE 3D CT images compared to NCE 4D and 3D CT images. The GTV volume on APCE 3D CT images increased by an average of 34.79% (P < 0.05). There was no significant difference among the GTV volumes obtained using NCE 4D and 3D CT images (P > 0.05). The GTV volumes after DR on 4D CT different phase images increased by an average of 36.29% (P < 0.05), as was observed using the APCE 3D CT image (P > 0.05). Lastly, the volume of IGTV-DR increased by an average of 19.91% compared to that of IGTV-1 (P < 0.05).ConclusionNCE 4D CT imaging alone has the potential risk of missing a partial volume of the HCC. The combination of APCE 3D CT and NCE 4D CT images using the DR technique improved the accuracy of the definition of the IGTV in HCC.

ObjectivesBody composition assessment using CT images at the L3-level is increasingly applied in cancer research and has been shown to be strongly associated with long-term survival. Robust high-throughput automated segmentation is key to assess large patient cohorts and to support implementation of body composition analysis into routine clinical practice. We trained and externally validated a deep learning neural network (DLNN) to automatically segment L3-CT images.MethodsExpert-drawn segmentations of visceral and subcutaneous adipose tissue (VAT/SAT) and skeletal muscle (SM) of L3-CT-images of 3187 patients undergoing abdominal surgery were used to train a DLNN. The external validation cohort was comprised of 2535 patients with abdominal cancer. DLNN performance was evaluated with (geometric) dice similarity (DS) and Lin’s concordance correlation coefficient.ResultsThere was a strong concordance between automatic and manual segmentations with median DS for SM, VAT, and SAT of 0.97 (IQR: 0.95-0.98), 0.98 (IQR: 0.95-0.98), and 0.95 (IQR: 0.92-0.97), respectively. Concordance correlations were excellent: SM 0.964 (0.959-0.968), VAT 0.998 (0.998-0.998), and SAT 0.992 (0.991-0.993). Bland-Altman metrics indicated only small and clinically insignificant systematic offsets; SM radiodensity: 0.23 Hounsfield units (0.5%), SM: 1.26 cm2.m−2 (2.8%), VAT: −1.02 cm2.m−2 (1.7%), and SAT: 3.24 cm2.m−2 (4.6%).ConclusionA robustly-performing and independently externally validated DLNN for automated body composition analysis was developed.Advances in knowledgeThis DLNN was successfully trained and externally validated on several large patient cohorts. The trained algorithm could facilitate large-scale population studies and implementation of body composition analysis into clinical practice.

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.

Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients

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.

The analysis of CT images of the abdomen has become increasingly important as lesions occurring in the liver are not easily detectable. The development of medical imaging technology has led to an explosive growth in the number of pathological sections of CT images. In the field of medical imaging, the use of computer-aided techniques for liver segmentation of abdominal CT images is particularly important. To further improve the accuracy of liver segmentation in abdominal CT images, this paper proposes the U2-OANet liver segmentation network on the basis of U2Net. This paper combines the new octave convolution module to design the OCRSU module, which produces better results for segmentation of liver boundaries while reducing the video memory usage. At the same time, this paper adds a dual attention module including the bottom attention module and the mixed attention module, to ensure the liver edge details while alleviating the noise problem and the false-positive problem, and further optimizes the liver segmentation network. Compared with the U2Net network, the U2-OANet network proposed in this paper has effectively improved the liver segmentation accuracy on CHAOS and 3DIRCADB datasets.

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.

The purpose of this study is to evaluate and compare the performance of modern deep learning techniques for automatically recognizing and segmenting multiple organ regions on 3D CT images. CT image segmentation is one of the important task in medical image analysis and is still very challenging. Deep learning approaches have demonstrated the capability of scene recognition and semantic segmentation on nature images and have been used to address segmentation problems of medical images. Although several works showed promising results of CT image segmentation by using deep learning approaches, there is no comprehensive evaluation of segmentation performance of the deep learning on segmenting multiple organs on different portions of CT scans. In this paper, we evaluated and compared the segmentation performance of two different deep learning approaches that used 2D- and 3D deep convolutional neural networks (CNN) without- and with a pre-processing step. A conventional approach that presents the state-of-the-art performance of CT image segmentation without deep learning was also used for comparison. A dataset that includes 240 CT images scanned on different portions of human bodies was used for performance evaluation. The maximum number of 17 types of organ regions in each CT scan were segmented automatically and compared to the human annotations by using ratio of intersection over union (IU) as the criterion. The experimental results demonstrated the IUs of the segmentation results had a mean value of 79% and 67% by averaging 17 types of organs that segmented by a 3D- and 2D deep CNN, respectively. All the results of the deep learning approaches showed a better accuracy and robustness than the conventional segmentation method that used probabilistic atlas and graph-cut methods. The effectiveness and the usefulness of deep learning approaches were demonstrated for solving multiple organs segmentation problem on 3D CT images.

To propose and evaluate a fully automated technique for quantification of fibroglandular tissue (FGT) and background parenchymal enhancement (BPE) in breast MRI. We propose a fully automated method, where after preprocessing, FGT is segmented in T1-weighted, nonfat-saturated MRI. Incorporating an anatomy-driven prior probability for FGT and robust texture descriptors against intensity variations, our method effectively addresses major image processing challenges, including wide variations in breast anatomy and FGT appearance among individuals. Our framework then propagates this segmentation to dynamic contrast-enhanced (DCE)-MRI to quantify BPE within the segmented FGT regions. Axial and sagittal image data from 40 cancer-unaffected women were used to evaluate our proposed method vs a manually annotated reference standard. High spatial correspondence was observed between the automatic and manual FGT segmentation (mean Dice similarity coefficient 81.14%). The FGT and BPE quantifications (denoted FGT% and BPE%) indicated high correlation (Pearson's r=0.99 for both) between automatic and manual segmentations. Furthermore, the differences between the FGT% and BPE% quantified using automatic and manual segmentations were low (mean differences: -0.66±2.91% for FGT% and -0.17±1.03% for BPE%). When correlated with qualitative clinical BI-RADS ratings, the correlation coefficient for FGT% was still high (Spearman's ρ=0.92), whereas that for BPE was lower (ρ=0.65). Our proposed approach also performed significantly better than a previously validated method for sagittal breast MRI. Our method demonstrated accurate fully automated quantification of FGT and BPE in both sagittal and axial breast MRI. Our results also suggested the complexity of BPE assessment, demonstrating relatively low correlation between segmentation and clinical rating.

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.

Quantification of diffusion restriction lesions in sporadic Creutzfeldt-Jakob disease (sCJD) may provide information of the disease burden. We aim to develop an automatic segmentation model for sCJD and to evaluate the volume of disease extent as a prognostic marker for overall survival. Fifty-six patients (mean age ± SD, 61.2 ± 9.9 years) were included from February 2000 to July 2020. A threshold-based segmentation was used to obtain abnormal signal intensity masks. Segmented volumes were compared with the visual grade. The Dice similarity coefficient was calculated to measure the similarity between the automatic vs. manual segmentation. Cox proportional hazards regression analysis was performed to evaluate the volume of disease extent as a prognostic marker. The automatic segmentation showed good correlation with the visual grading. The cortical lesion volumes significantly increased as the visual grade aggravated (extensive: 112.9 ± 73.2; moderate: 45.4 ± 30.4; minimal involvement: 29.6 ± 18.1 mm3) (P < 0.001). The deep gray matter lesion volumes were significantly higher for positive than for negative involvement of the deep gray matter (5.6 ± 4.6 mm3 vs. 1.0 ± 1.3 mm3, P < 0.001). The mean Dice similarity coefficients were 0.90 and 0.94 for cortical and deep gray matter lesions, respectively. However, the volume of disease extent was not associated with worse overall survival (cortical extent: P = 0.07; deep gray matter extent: P = 0.12).

PurposeTo evaluate the optimal period of replanning to spare the rectal dose by investigating daily rectal movements during computed tomography (CT) image‐guided proton therapy for prostate cancer.Materials and methodsTo evaluate the optimum reference period for replanning, we analyzed 1483 sets of daily CT (dCT) images acquired from 40 prostate cancer patients and measured the daily rectal movement along the anterior–posterior direction based on the simulator CT (sCT) images and dCT images. We calculated daily dose distributions based on initial plans on the sCT images and replans on the dCT images for 13 representative patients, and evaluated daily dose volume histograms (DVHs) for the prostate, seminal vesicles, and rectum.ResultsThe rectal anterior side on the dCT images around the seminal vesicles largely deviated toward the anterior side relative to the position on the reference sCT images, but the deviation decreased by referring to the dCT images and became nearly zero when we referred to the dCT images after 10‐day treatment. The daily DVH values for the prostate showed good dose coverage. For six patients showing rectal movement toward the anterior side, the daily rectal DVH (V77%) showed a 3.0 ± 1.7 cc excess from the initial plan and this excess was correlated with 9.9 ± 6.8 mm rectal movement. To identify the patients (37.5% in total) for whom the replanning on the 10th‐day and 20th‐day CT images reduced the V77% excess to 0.4 ± 1.5 cc and −0.2 ± 1.3 cc, respectively, we evaluated the accumulated mean doses with a 1.2 cc criterion.ConclusionOur data demonstrate that the daily movement of the rectal anterior side tends to move toward the anterior side, which results in a rectal overdose, and the mean of the movement gradually decreases with the passage of days. In such cases, replanning with the reference CT after 10 days is effective to spare the rectal dose.

Extension–contraction transformation network for pancreas segmentation in abdominal CT scans