Letter to editor: Volumetric segmentation in the context of posterior fossa­related pathologies: a systematic review.

This letter provides feedback on the article titled "Volumetric Segmentation in the Context of Posterior Fossa-Related Pathologies: A Systematic Review." It highlights the positive impacts of the review, such as its comprehensive examination of existing literature and its potential to enhance diagnostic accuracy and treatment planning. However, it also addresses limitations and challenges associated with volumetric segmentation, including variability in image quality and accessibility issues.

A combined encoder-transformer-decoder network for volumetric segmentation of adrenal tumors.

BACKGROUND: The morphology of the adrenal tumor and the clinical statistics of the adrenal tumor area are two crucial diagnostic and differential diagnostic features, indicating precise tumor segmentation is essential. Therefore, we build a CT image segmentation method based on an encoder-decoder structure combined with a Transformer for volumetric segmentation of adrenal tumors. METHODS: This study included a total of 182 patients with adrenal metastases, and an adrenal tumor volumetric segmentation method combining encoder-decoder structure and Transformer was constructed. The Dice Score coefficient (DSC), Hausdorff distance, Intersection over union (IOU), Average surface distance (ASD) and Mean average error (MAE) were calculated to evaluate the performance of the segmentation method. RESULTS: Analyses were made among our proposed method and other CNN-based and transformer-based methods. The results showed excellent segmentation performance, with a mean DSC of 0.858, a mean Hausdorff distance of 10.996, a mean IOU of 0.814, a mean MAE of 0.0005, and a mean ASD of 0.509. The boxplot of all test samples' segmentation performance implies that the proposed method has the lowest skewness and the highest average prediction performance. CONCLUSIONS: Our proposed method can directly generate 3D lesion maps and showed excellent segmentation performance. The comparison of segmentation metrics and visualization results showed that our proposed method performed very well in the segmentation.

Generating novel pituitary datasets from open-source imaging data and deep volumetric segmentation.

PURPOSE: The estimated incidence of pituitary adenomas in the general population is 10-30%, yet radiographic diagnosis remains a challenge. Diagnosis is complicated by the heterogeneity of radiographic features in both normal (e.g. complex anatomy, pregnancy) and pathologic states (e.g. primary endocrinopathy, hypophysitis). Clinical symptoms and laboratory testing are often equivocal, which can result in misdiagnosis or unnecessary specialist referrals. Computer vision models can aid in pituitary adenoma diagnosis; however, a major challenge to model development is the lack of dedicated pituitary imaging datasets. We hypothesized that deep volumetric segmentation models trained to extract the sellar and parasellar region from existing whole-brain MRI scans could be used to generate a novel dataset of pituitary imaging. METHODS: Six open-source whole-brain MRI datasets, created for research purposes, were included for model development. Deep learning-based volumetric segmentation models were trained using 318 manually annotated MRI scans from a single open-source MRI dataset. Out-of-distribution volumetric segmentation performance was then tested on 418 MRIs from five held-out research datasets. RESULTS: On our annotated images, agreement between manual and model volumetric segmentations was high. Dice scores (a measure of overlap) ranged 0.76-0.82 for both in-distribution and out-of-distribution model testing. In total, 6,755 MRIs from six data sources were included in the final generated pituitary dataset. CONCLUSIONS: We present the first and largest dataset of pituitary imaging constructed using existing MRI data and deep volumetric segmentation models trained to identify sellar and parasellar anatomy. The model generalizes well across patient populations and MRI scanner types. We hope our pituitary dataset will be an integral part of future machine learning research on pituitary pathologies.

Retrograde CT urethrography using a power injector quantitatively reveals effects of bladder distension on urethral size in healthy male Beagle dogs.

Quantitative analysis of the normal retrograde urethrogram is well reported in radiography, but studies on CT urethrography are lacking. Recently, a method of retrograde CT urethrography using a power injector was described. The purpose of the current, prospective, analytical study was to quantify the urethral size of five, healthy, intact, male Beagle dogs using retrograde CT urethrography and a power injector. With the injection rate of the power injector set at 0.3 mL/s, 1 mL/kg of diluted contrast medium (15 mg I/mL) was injected, and a CT examination was performed. The state of the initial urethrogram taken was defined as "empty bladder." The same procedures were repeated with the injection of an additional 1 mL/kg of diluted contrast medium until the ureteral reflux was seen (distended bladder). There was a significant difference in volumes between the empty and distended bladder, but the membranous urethra showed the least difference (P = .0044) among the three regions (P < .0001 for the prostatic and penile urethra). Urethral diameters at six sites were measured from sagittal images, and the sites of measurements were adopted from the earlier radiographic studies. The most significant difference in the urethral diameters between the empty and distended bladder occurred at the cranial and middle prostatic urethra (P < .0001). The results of this study can be useful for interpreting the results of retrograde CT urethrography. Care must be taken when narrowing is suspected at the prostatic urethra, and if necessary, further distension of the urinary bladder should be tried.

Volumetric analysis of magnetic resonance-guided focused ultrasound thalamotomy lesions.

OBJECTIVE Magnetic resonance-guided focused ultrasound (MRgFUS) thalamotomy was recently approved for use in the treatment of medication-refractory essential tremor (ET). Previous work has described lesion appearance and volume on MRI up to 6 months after treatment. Here, the authors report on the volumetric segmentation of the thalamotomy lesion and associated edema in the immediate postoperative period and 1 year following treatment, and relate these radiographic characteristics with clinical outcome. METHODS Seven patients with medication-refractory ET underwent MRgFUS thalamotomy at Brigham and Women's Hospital and were monitored clinically for 1 year posttreatment. Treatment effect was measured using the Clinical Rating Scale for Tremor (CRST). MRI was performed immediately postoperatively, 24 hours posttreatment, and at 1 year. Lesion location and the volumes of the necrotic core (zone I) and surrounding edema (cytotoxic, zone II; vasogenic, zone III) were measured on thin-slice T2-weighted images using Slicer 3D software. RESULTS Patients had significant improvement in overall CRST scores (baseline 51.4 ± 10.8 to 24.9 ± 11.0 at 1 year, p = 0.001). The most common adverse events (AEs) in the 1-month posttreatment period were transient gait disturbance (6 patients) and paresthesia (3 patients). The center of zone I immediately posttreatment was 5.61 ± 0.9 mm anterior to the posterior commissure, 14.6 ± 0.8 mm lateral to midline, and 11.0 ± 0.5 mm lateral to the border of the third ventricle on the anterior commissure-posterior commissure plane. Zone I, II, and III volumes immediately posttreatment were 0.01 ± 0.01, 0.05 ± 0.02, and 0.33 ± 0.21 cm3, respectively. These volumes increased significantly over the first 24 hours following surgery. The edema did not spread evenly, with more notable expansion in the superoinferior and lateral directions. The spread of edema inferiorly was associated with the incidence of gait disturbance. At 1 year, the remaining lesion location and size were comparable to those of zone I immediately posttreatment. Zone volumes were not associated with clinical efficacy in a statistically significant way. CONCLUSIONS MRgFUS thalamotomy demonstrates sustained clinical efficacy at 1 year for the treatment of medication-refractory ET. This technology can create accurate, predictable, and small-volume lesions that are stable over time. Instances of AEs are transient and are associated with the pattern of perilesional edema expansion. Additional analysis of a larger MRgFUS thalamotomy cohort could provide more information to maximize clinical effect and reduce the rate of long-lasting AEs.

Impact of 5-Hz rTMS over the primary sensory cortex is related to white matter volume in individuals with chronic stroke.

Repetitive transcranial magnetic stimulation (rTMS) is a non-invasive brain stimulation technique that may facilitate mechanisms of motor learning. In a recent single-blind, pseudo-randomized study, we showed that 5-Hz rTMS over ipsilesional primary somatosensory cortex followed by practice of a skilled motor task enhanced motor learning compared with sham rTMS + practice in individuals with chronic stroke. However, the beneficial effect of stimulation was inconsistent. The current study examined how differences in sensorimotor cortex morphology might predict rTMS-related improvements in motor learning in these individuals. High-resolution T1-weighted magnetic resonance images were acquired and processed in FreeSurfer using a newly developed automated, whole brain parcellation technique. Gray matter and white matter volumes of the ipsilesional primary somatosensory and motor cortices were extracted. A significant positive association was observed between the volume of white matter in the primary somatosensory cortex and motor learning-related change, exclusively in the group that received active 5-Hz rTMS. A regression model with age, gray matter and white matter volumes as predictors was significant for predicting motor learning-related change in individuals who received active TMS. White matter volume predicted the greatest amount of variance (47.6%). The same model was non-significant when volumes of the primary motor cortex were considered. We conclude that white matter volume in the cortex underlying the TMS coil may be a novel predictor for behavioral response to 5-Hz rTMS over the ipsilesional primary somatosensory followed by motor practice.

Evaluation of a Fully Automated Method for Ventricular Volume Segmentation Before and After Shunt Surgery in Idiopathic Normal Pressure Hydrocephalus.

BACKGROUND: Determination of the ventricle size in idiopathic normal pressure hydrocephalus (iNPH) is essential for diagnosis and follow-up of shunt results. Fully automated segmentation methods are anticipated to optimize the accuracy and time efficiency of ventricular volume measurements. We evaluated the accuracy of preoperative and postoperative ventricular volume measurements in iNPH by a magnetic resonance imaging (MRI)-based licensed software for fully automated quantitative assessment. METHODS: Forty-eight patients diagnosed with iNPH were retrospectively analyzed. All patients received a ventriculoperitoneal shunt and had symptom grading and routine MRI preoperatively and 3-6 months postoperatively. Ventricular volumes, generated by fully automated T1-weighted imaging volume sequence segmentation, were compared with semiautomatic measurements and routine radiologic reports. The relation of postoperative ventricular size change to clinical response was evaluated. RESULTS: Fully automated segmentation was achieved in 95% of the MRIs, but showed various rates of 8 minor segmentation errors. The correlation between both segmentation methods was very strong (r >0.9) and the agreement very good using Bland-Altman analyses. The ventricular volumes differed significantly between semiautomated and fully automated segmentations and between preoperative and postoperative MRI. The fully automated method systematically overestimated the ventricles by a median 15 mL preoperatively and 14 mL postoperatively; hence, the magnitudes of volume changes were equivalent. Routine radiologic reports of ventricular size changes were inaccurate in 51% and lacked association with treatment response. Objectively measured ventricular volume changes correlated moderately with postoperative clinical improvement. CONCLUSIONS: A fully automated volumetric method permits reliable evaluation of preoperative ventriculomegaly and postoperative ventricular volume change in idiopathic normal pressure hydrocephalus.

Can Delta Radiomics Improve the Prediction of Best Overall Response, Progression-Free Survival, and Overall Survival of Melanoma Patients Treated with Immune Checkpoint Inhibitors?

BACKGROUND: The prevalence of metastatic melanoma is increasing, necessitating the identification of patients who do not benefit from immunotherapy. This study aimed to develop a radiomic biomarker based on the segmentation of all metastases at baseline and the first follow-up CT for the endpoints best overall response (BOR), progression-free survival (PFS), and overall survival (OS), encompassing various immunotherapies. Additionally, this study investigated whether reducing the number of segmented metastases per patient affects predictive capacity. METHODS: The total tumour load, excluding cerebral metastases, from 146 baseline and 146 first follow-up CTs of melanoma patients treated with first-line immunotherapy was volumetrically segmented. Twenty-one random forest models were trained and compared for the endpoints BOR; PFS at 6, 9, and 12 months; and OS at 6, 9, and 12 months, using as input either only clinical parameters, whole-tumour-load delta radiomics plus clinical parameters, or delta radiomics from the largest ten metastases plus clinical parameters. RESULTS: The whole-tumour-load delta radiomics model performed best for BOR (AUC 0.81); PFS at 6, 9, and 12 months (AUC 0.82, 0.80, and 0.77); and OS at 6 months (AUC 0.74). The model using delta radiomics from the largest ten metastases performed best for OS at 9 and 12 months (AUC 0.71 and 0.75). Although the radiomic models were numerically superior to the clinical model, statistical significance was not reached. CONCLUSIONS: The findings indicate that delta radiomics may offer additional value for predicting BOR, PFS, and OS in metastatic melanoma patients undergoing first-line immunotherapy. Despite its complexity, volumetric whole-tumour-load segmentation could be advantageous.

Assessing the Volume of the Head of the Mandibular Condyle Using 3T-MRI-A Preliminary Trial.

Due to potentially harmful exposure to X-rays, condylar growth in response to orthodontic treatment is poorly studied. To overcome this limitation, here, the authors have proposed high-resolution MRI as a viable alternative to CBCT for clinical 3D assessment of TMJ. A male subject underwent both MRI and CBCT scans. The obtained three-dimensional reconstructions of the TMJ were segmented and superimposed by a semiautomatic algorithm developed in MATLAB R2022a. The condylar geometries were reconstructed using dedicated software for image segmentation. Two geometrical parameters, i.e., the total volume and surface of the single condyle model, were selected to quantify the intraclass and interclass variability from the mean of each DICOM series (CBCT and MRI). The final comparison between the reference standard model of CBCT and 3T MRI showed that the former was more robust in terms of reproducibility, while the latter reached a higher standard deviation compared to CBCT, but these values were similar between the operators and clinically not significant. Within the inherent limitation of image reconstruction on MRI scans due to the current lower resolution of this technique, the method proposed here could be considered as a nucleus for developing future completely automatic AI algorithms, owing to its great potential and satisfactory consistency among different times and operators.

Volumetric Assessment of Traumatic Intracranial Hematomas: Is ABC/2 Reliable?

Accurate measurement of traumatic intracranial hematoma volume is important for assessing disease progression and prognosis, as well as for serving as an important end-point in clinical trials aimed at preventing hematoma expansion. While the ABC/2 formula has traditionally been used for volume estimation in spontaneous intracerebral hemorrhage, its adaptation to traumatic hematomas lacks validation. This study aimed to compare the accuracy of ABC/2 with computer-assisted volumetric analysis (CAVA) in estimating the volumes of traumatic intracranial hematomas. We performed a dual-center observational study that included adult patients with moderate-to-severe traumatic brain injury. Volumes of intracerebral, subdural (SDHs), and epidural hematomas from admission computed tomography scans were measured using ABC/2 and CAVA, and compared using the Wilcoxon signed-rank test, Spearman's rank correlation, Lin's concordance correlation coefficient (CCC), and Bland-Altman plots. Prognostic significance for outcomes was evaluated through logistic and linear regression models. In total, 1,179 patients with 1,543 hematomas were included. Despite a high correlation (Spearman coefficients between 0.95 and 0.98) and excellent concordance (Lin's CCC from 0.89 to 0.96) between ABC/2 and CAVA, ABC/2 overestimated hematoma volumes compared with CAVA, in some instances exceeding 50 ml. Bland-Altman analysis highlighted wide limits of agreement, especially in SDH. While both methods demonstrated comparable accuracy in predicting outcomes, CAVA was slightly better at predicting craniotomies and midline shift. We conclude that while ABC/2 provides a generally reliable volumetric assessment suitable for descriptive purposes and as baseline variables in studies, CAVA should be the gold standard in clinical situations and studies requiring more precise volume estimations, such as those using hematoma expansion as an outcome.

A Novel Nomogram Based on Quantitative MRI and Clinical Features for the Prediction of Neonatal Intracranial Hypertension.

Intracranial hypertension (ICH) is a serious threat to the health of neonates. However, early and accurate diagnosis of neonatal intracranial hypertension remains a major challenge in clinical practice. In this study, a predictive model based on quantitative magnetic resonance imaging (MRI) data and clinical parameters was developed to identify neonates with a high risk of ICH. Newborns who were suspected of having intracranial lesions were included in our study. We utilized quantitative MRI to obtain the volumetric data of gray matter, white matter, and cerebrospinal fluid. After the MRI examination, a lumbar puncture was performed. The nomogram was constructed by incorporating the volumetric data and clinical features by multivariable logistic regression. The performance of the nomogram was evaluated by discrimination, calibration curve, and decision curve. Clinical parameters and volumetric quantitative MRI data, including postmenstrual age (p = 0.06), weight (p = 0.02), mode of delivery (p = 0.01), and gray matter volume (p = 0.003), were included in and significantly associated with neonatal intracranial hypertension risk. The nomogram showed satisfactory discrimination, with an area under the curve of 0.761. Our results demonstrated that decision curve analysis had promising clinical utility of the nomogram. The nomogram, incorporating clinical and quantitative MRI features, provided an individualized prediction of neonatal intracranial hypertension risk and facilitated decision making guidance for the early diagnosis and treatment for neonatal ICH. External validation from studies using a larger sample size before implementation in the clinical decision-making process is needed.

A systematic review of the techniques for automatic segmentation of the human upper airway using volumetric images.

The human upper airway is comprised of many anatomical volumes. The obstructions in the upper airway volumes are needed to be diagnosed which requires volumetric segmentation. Manual segmentation is time-consuming and requires expertise in the field. Automatic segmentation provides reliable results and also saves time and effort for the expert. The objective of this study is to systematically review the literature to study various techniques used for the automatic segmentation of the human upper airway regions in volumetric images. PRISMA guidelines were followed to conduct the systematic review. Four online databases Scopus, Google Scholar, PubMed, and JURN were used for the searching of the relevant papers. The relevant papers were shortlisted using inclusion and exclusion eligibility criteria. Three review questions were made and explored to find their answers. The best technique among all the literature studies based on the Dice coefficient and precision was identified and justified through the analysis. This systematic review provides insight to the researchers so that they shall be able to overcome the prominent issues in the field identified from the literature. The outcome of the review is based on several parameters, e.g., accuracy, techniques, challenges, datasets, and segmentation of different sub-regions. Flowchart of the search process as per PRISMA guidelines along with inclusion and exclusion criteria.

PACS-Integrated Tools for Peritumoral Edema Volumetrics Provide Additional Information to RANO-BM-Based Assessment of Lung Cancer Brain Metastases after Stereotactic Radiotherapy: A Pilot Study.

Stereotactic radiotherapy (SRT) is the standard of care treatment for brain metastases (METS) today. Nevertheless, there is limited understanding of how posttreatment lesional volumetric changes may assist prediction of lesional outcome. This is partly due to the paucity of volumetric segmentation tools. Edema alone can cause significant clinical symptoms and, therefore, needs independent study along with standard measurements of contrast-enhancing tumors. In this study, we aimed to compare volumetric changes of edema to RANO-BM-based measurements of contrast-enhancing lesion size. Patients with NSCLC METS ≥10 mm on post-contrast T1-weighted image and treated with SRT had measurements for up to seven follow-up scans using a PACS-integrated tool segmenting the peritumoral FLAIR hyperintense volume. Two-dimensional contrast-enhancing and volumetric edema changes were compared by creating treatment response curves. Fifty NSCLC METS were included in the study. The initial median peritumoral edema volume post-SRT relative to pre-SRT baseline was 37% (IQR 8-114%). Most of the lesions with edema volume reduction post-SRT experienced no increase in edema during the study. In over 50% of METS, the pattern of edema volume change was different than the pattern of contrast-enhancing lesion change at different timepoints, which was defined as incongruent. Lesions demonstrating incongruence at the first follow-up were more likely to progress subsequently. Therefore, edema assessment of METS post-SRT provides critical additional information to RANO-BM.

Tumorous kidney segmentation in abdominal CT images using active contour and 3D-UNet.

BACKGROUND AND PURPOSE: The precise segmentation of the kidneys in computed tomography (CT) images is vital in urology for diagnosis, treatment, and surgical planning. Medical experts can get assistance through segmentation, as it provides information about kidney malformations in terms of shape and size. Manual segmentation is slow, tedious, and not reproducible. An automatic computer-aided system is a solution to this problem. This paper presents an automated kidney segmentation technique based on active contour and deep learning. MATERIALS AND METHODS: In this work, 210 CTs from the KiTS 19 repository were used. The used dataset was divided into a train set (168 CTs), test set (21 CTs), and validation set (21 CTs). The suggested technique has broadly four phases: (1) extraction of kidney regions using active contours, (2) preprocessing, (3) kidney segmentation using 3D U-Net, and (4) reconstruction of the segmented CT images. RESULTS: The proposed segmentation method has received the Dice score of 97.62%, Jaccard index of 95.74%, average sensitivity of 98.28%, specificity of 99.95%, and accuracy of 99.93% over the validation dataset. CONCLUSION: The proposed method can efficiently solve the problem of tumorous kidney segmentation in CT images by using active contour and deep learning. The active contour was used to select kidney regions and 3D-UNet was used for precisely segmenting the tumorous kidney.

White matter changes should not exclude patients with idiopathic normal pressure hydrocephalus from shunt surgery.

INTRODUCTION: White matter changes (WMC) on brain imaging can be classified as deep white matter hyperintensities (DWMH) or periventricular hyperintensities (PVH) and are frequently seen in patients with idiopathic normal pressure hydrocephalus (iNPH). Contradictory results have been reported on whether preoperative WMC are associated with outcome after shunt surgery in iNPH patients. The aim of this study was to investigate any association between DWMH and PVH and shunt outcome in patients with iNPH, using magnetic resonance volumetry. METHODS: A total of 253 iNPH patients operated with shunt surgery and clinically assessed before and 12 months after surgery were included. All patients were investigated preoperatively with magnetic resonance imaging of the brain. The volumes of DWMH and PVH were quantified on fluid-attenuated inversion recovery images using an in-house semi-automatic volumetric segmentation software (SmartPaint). Shunt outcome was defined as the difference in symptom score between post- and preoperative investigations, measured on the iNPH scale, and shunt response was defined as improvement with ≥ 5 points. RESULTS: One year after shunt surgery, 51% of the patients were improved on the iNPH scale. When defining improvement as ≥ 5 points on the iNPH scale, there was no significant difference in preoperative volume of WMC between shunt responders and non-responders. If outcome was determined by a continuous variable, a larger volume of PVH was negatively associated with postoperative change in the total iNPH scale (p < 0.05) and negatively associated with improvement in gait (p < 0.01) after adjusting for age, sex, waiting time for surgery, preoperative level of symptoms, Evans' index, and disproportionately enlarged subarachnoid space hydrocephalus. The volume of DWMH was not associated with shunt outcome. CONCLUSIONS: An association between outcome after shunt surgery and volume of PVH was seen, but there was no difference between shunt responders and non-responders in the volumes of DWMH and PVH. We conclude that preoperative assessment of WMC should not be used to exclude patients with iNPH from shunt surgery.

Volumetric segmentation of ground glass nodule based on 3D attentional cascaded residual U-Net and conditional random field.

BACKGROUND: Ground glass nodule (GGN) segmentation is one of the important and challenging tasks in diagnosing early-stage lung adenocarcinomas. Manually delineating of 3D GGN in a computed tomography (CT) image is a subjective, laborious, and tedious task, which presents poor repeatability. PURPOSE: To reduce the annotation burden and improve the segmentation performance, this study proposes a 3D deep learning-based volumetric segmentation model to segment the GGN in CT images. METHODS: A total of 379 GGNs were retrospectively collected from the public database, Shanghai Pulmonary Hospital (SHPH), and Fudan University Shanghai Cancer Center (FUSCC). First, a series of image preprocessing techniques involving image resampling, intensity normalization, 3D nodule patch cropping, and data augmentation, were adopted to generate the input images for the deep learning model by using CT scans. Then, a 3D attentional cascaded residual network (ACRU-Net) was proposed to develop the deep learning-based segmentation model by using the residual network and the atrous spatial pyramid pooling module. To improve the model performance, a voxel-based conditional random field (CRF) method was used to optimize the segmentation results. Finally, a balanced cross-entropy and Dice combined loss function was applied to train and build the segmentation model. RESULTS: Testing on SHPH and FUSCC datasets, the proposed method generates the Dice coefficients of 0.721 ± 0.167 and 0.733 ± 0.100, respectively, which are higher than those of 3D residual U-Net and ACRU-Net without CRF optimization. CONCLUSIONS: The results demonstrated that combining 3D ACRU-Net and CRF effectively improved the GGN segmentation performance. The proposed segmentation model may provide a potential tool to help the radiologist in the segmentation and diagnosis of 3D GGN.

Tumor Doubling Time Using CT Volumetric Segmentation in Metastatic Adrenocortical Carcinoma.

Adrenocortical carcinoma (ACC) is a rare malignancy with an overall unfavorable prognosis. Clinicians treating patients with ACC have noted accelerated growth in metastatic liver lesions that requires rapid intervention compared to other metastatic locations. This study measured and compared the growth rates of metastatic ACC lesions in the lungs, liver, and lymph nodes using volumetric segmentation. A total of 12 patients with metastatic ACC (six male; six female) were selected based on their medical history. Computer tomography (CT) exams were retrospectively reviewed and a sampling of ≤5 metastatic lesions per organ were selected for evaluation. Lesions in the liver, lung, and lymph nodes were measured and evaluated by volumetric segmentation. Statistical analyses were performed to compare the volumetric growth rates of the lesions in each organ system. In this cohort, 5/12 had liver lesions, 7/12 had lung lesions, and 5/12 had lymph node lesions. A total of 92 lesions were evaluated and segmented for lesion volumetry. The volume doubling time per organ system was 27 days in the liver, 90 days in the lungs, and 95 days in the lymph nodes. In this series of 12 patients with metastatic ACC, liver lesions showed a faster growth rate than lung or lymph node lesions.

Automatic multi-organ segmentation from abdominal CT volumes with LLE-based graph partitioning and 3D Chan-Vese model.

This paper presents a fully automatic method for multi-organ segmentation from 3D abdominal CT volumes. Firstly, spines and ribs are removed by exponential transformation and binarization to reduce the disturbance to subsequent segmentation. Then, a Local Linear Embedding (LLE)-based graph partitioning approach is employed to perform initial segmentation for liver, spleen, and bilateral kidneys simultaneously, and a novel segmentation refinement scheme is applied composed of hybrid intensity model, 3D Chan-Vese model, and histogram equalization-based organ separation algorithm. Finally, a pseudo-3D bottleneck detection algorithm is introduced for boundary correction. The proposed method does not require heavy training or registration process and is capable of dealing with shape and location variations as well as the weak boundaries of target organs. Experiments on XHCSU20 database show the proposed method is competitive with state-of-the-art methods with Dice similarity coefficients of 95.9%, 95.1%, 94.7%, and 94.5%, Jaccard indices of 92.2%, 90.8%, 90.0%, and 89.5%, and average symmetric surface distances of 1.1 mm, 1.0 mm, 0.9 mm and 1.1 mm, for liver, spleen, left and right kidneys, respectively, and the average running time is around 6 min for a CT volume. The accuracy, precision, recall, and specificity also maintain high values for each of the four organs. Moreover, experiments on SLIVER07 dataset prove its high efficiency and accuracy on liver-only segmentation.

MRI-based Alzheimer's disease-resemblance atrophy index in the detection of preclinical and prodromal Alzheimer's disease.

Alzheimer's Disease-resemblance atrophy index (AD-RAI) is an MRI-based machine learning derived biomarker that was developed to reflect the characteristic brain atrophy associated with AD. Recent study showed that AD-RAI (≥0.5) had the best performance in predicting conversion from mild cognitive impairment (MCI) to dementia and from cognitively unimpaired (CU) to MCI. We aimed to validate the performance of AD-RAI in detecting preclinical and prodromal AD. We recruited 128 subjects (MCI=50, CU=78) from two cohorts: CU-SEEDS and ADNI. Amyloid (A+) and tau (T+) status were confirmed by PET (11C-PIB, 18F-T807) or CSF analysis. We investigated the performance of AD-RAI in detecting preclinical and prodromal AD (i.e. A+T+) among MCI and CU subjects and compared its performance with that of hippocampal measures. AD-RAI achieved the best metrics among all subjects (sensitivity 0.74, specificity 0.91, accuracy 85.94%) and among MCI subjects (sensitivity 0.92, specificity 0.81, accuracy 86.00%) in detecting A+T+ subjects over other measures. Among CU subjects, AD-RAI yielded the best specificity (0.95) and accuracy (85.90%) over other measures, while hippocampal volume achieved a higher sensitivity (0.73) than AD-RAI (0.47) in detecting preclinical AD. These results showed the potential of AD-RAI in the detection of early AD, in particular at the prodromal stage.

Automatic segmentation of tumors and affected organs in the abdomen using a 3D hybrid model for computed tomography imaging.

Automatic segmentation on computed tomography images of kidney and liver tumors remains a challenging task due to heterogeneity and variation in shapes. Recently, two-dimensional (2D) and three-dimensional (3D) deep convolutional neural networks have become popular in medical image segmentation tasks because they can leverage large labeled datasets, thus enabling them to learn hierarchical features. However, 3D networks have some drawbacks due to their high cost of computational resources. In this paper, we propose a hybrid 3D residual network (RN) with a squeeze-and-excitation (SE) block for volumetric segmentation of kidney, liver, and their associated tumors. The proposed network uses SE blocks to capture spatial information based on the reweighting function in a 3D RN. This study is the first to use an SE residual mechanism to process medical volumetric images using the proposed 3D residual network composed of various combinations of residual blocks. Our framework was evaluated both on the Kidney Tumor Segmentation 2019 dataset and the public MICCAI 2017 Liver Tumor Segmentation dataset. The results show that our architecture outperforms other state-of-the-art methods. Moreover, the SE-RN achieves good performance in volumetric biomedical segmentation.