Search

Introduction: Despite complete recanalization by mechanical thrombectomy, abnormal perfusion can be detected on MRI obtained post-endovascular therapy (EVT). The presence of residual perfusion abnormalities post-EVT may be associated with blood-brain barrier breakdown in response to mechanical disruption of the endothelium from multiple-pass thrombectomy. We hypothesize that multiple-pass versus single-pass thrombectomy is associated with a higher rate of residual hypoperfusion and increased lesion growth at 24 h. Materials and Methods: For this analysis, we included patients presenting to one of two stroke centers between January 2015 and February 2018 with an acute ischemic stroke within 12 h from symptom onset if they had a large vessel occlusion of the anterior circulation documented on magnetic resonance angiography or CTA, baseline MRI pre-EVT with imaging evidence of hypoperfusion, underwent EVT, and had a post-EVT MRI with qualitatively interpretable perfusion-weighted imaging data at 24 h. MRI Tmax maps using a time delay threshold of >6 s were used to quantitate hypoperfusion volumes. Residual hypoperfusion at 24 h was solely defined as Tmax volume >10 mL with >6 s delay. Complete recanalization was defined as modified treatment in cerebral infarction visualized on angiography at EVT completion. Hyperintense acute reperfusion injury marker was assessed on post-EVT pre-contrast fluid-attenuated inversion recovery at 24 h. Major early neurological improvement was defined as a reduction of the admission National Institutes of Health Stroke Scale by ≥8 points or a score of 0–1 at 24 h. Good functional outcome was defined as 0–2 on the modified Rankin Scale on day 30 or 90. Results: Fifty-five patients were included with median age 67 years, 58% female, 45% Black/African American, 36% White/Caucasian, median admission National Institutes of Health Stroke Scale 19, large vessel occlusion locations: 71% M1, 14.5% iICA, 14.5% M2, 69% treated with intravenous recombinant tissue plasminogen activator. Of these, 58% had multiple-pass thrombectomy, 39% had residual perfusion abnormalities at 24 h, and 64% had severe hyperintense acute reperfusion injury marker at 24 h. After adjusting for complete recanalization, only multiple-pass thrombectomy (odds ratio, 4.3 95% CI, 1.07–17.2; p = 0.04) was an independent predictor of residual hypoperfusion at 24 h. Patients with residual hypoperfusion had larger lesion growth on diffusion-weighted imaging (59 mL vs. 8 mL, p < 0.001), lower rate of major early neurological improvement (24% vs. 70%, p = 0.002) at 24 h, and worse long-term outcome based on the modified Rankin Scale at 30 or 90 days, 5 versus 2 (p < 0.001). Conclusions: Our findings suggest that incomplete reperfusion on post-EVT MRI is present even in some patients with successful recanalization at the time of EVT and is associated with multiple-pass thrombectomy, lesion growth, and worse outcome. Future studies are needed to investigate whether patients with residual hypoperfusion may benefit from immediate adjunctive therapy to limit lesion growth and improve clinical outcome. [ABSTRACT FROM AUTHOR]

Purpose: Automatic muscle segmentation is critical for advancing our understanding of human physiology, biomechanics, and musculoskeletal pathologies, as it allows for timely exploration of large multi‐dimensional image sets. Segmentation models are rarely developed/validated for the pediatric model. As such, autosegmentation is not available to explore how muscle architectural changes during development and how disease/pathology affects the developing musculoskeletal system. Thus, we aimed to develop and validate an end‐to‐end, fully automated, deep learning model for accurate segmentation of the rectus femoris and vastus lateral, medialis, and intermedialis using a pediatric database. Methods: We developed a two‐stage cascaded deep learning model in a coarse‐to‐fine manner. In the first stage, the U2‐Net roughly detects the muscle subcompartment region. Then, in the second stage, the shape‐aware 3D semantic segmentation method SASSNet refines the cropped target regions to generate the more finer and accurate segmentation masks. We utilized multifeature image maps in both stages to stabilize performance and validated their use with an ablation study. The second‐stage SASSNet was independently run and evaluated with three different cropped region resolutions: the original image resolution, and images downsampled 2× and 4× (high, mid, and low). The relationship between image resolution and segmentation accuracy was explored. In addition, the patella was included as a comparator to past work. We evaluated segmentation accuracy using leave‐one‐out testing on a database of 3D MR images (0.43 × 0.43 × 2 mm) from 40 pediatric participants (age 15.3 ± 1.9 years, 55.8 ± 11.8 kg, 164.2 ± 7.9 cm, 38F/2 M). Results: The mid‐resolution second stage produced the best results for the vastus medialis, rectus femoris, and patella (Dice similarity coefficient = 95.0%, 95.1%, 93.7%), whereas the low‐resolution second stage produced the best results for the vastus lateralis and vastus intermedialis (DSC = 94.5% and 93.7%). In comparing the low‐ to mid‐resolution cases, the vasti intermedialis, vastus medialis, rectus femoris, and patella produced significant differences (p = 0.0015, p = 0.0101, p < 0.0001, p = 0.0003) and the vasti lateralis did not (p = 0.2177). The high‐resolution stage 2 had significantly lower accuracy (1.0 to 4.4 dice percentage points) compared to both the mid‐ and low‐resolution routines (p value ranged from < 0.001 to 0.04). The one exception was the rectus femoris, where there was no difference between the low‐ and high‐resolution cases. The ablation study demonstrated that the multifeature is more reliable than the single feature. Conclusions: Our successful implementation of this two‐stage segmentation pipeline provides a critical tool for expanding pediatric muscle physiology and clinical research. With a relatively small and variable dataset, our fully automatic segmentation technique produces accuracies that matched or exceeded the current state of the art. The two‐stage segmentation avoids memory issues and excessive run times by using a first stage focused on cropping out unnecessary data. The excellent Dice similarity coefficients improve upon previous template‐based automatic and semiautomatic methodologies targeting the leg musculature. More importantly, with a naturally variable dataset (size, shape, etc.), the proposed model demonstrates slightly improved accuracies, compared to previous neural networks methods. [ABSTRACT FROM AUTHOR]

Purpose: Our clinical understanding of the relationship between 3D bone morphology and knee osteoarthritis, as well as our ability to investigate potential causative factors of osteoarthritis, has been hampered by the time‐intensive nature of manually segmenting bone from MR images. Thus, we aim to develop and validate a fully automated deep learning framework for segmenting the patella and distal femur cortex, in both adults and actively growing adolescents. Methods: Data from 93 subjects, obtained from on institutional review board–approved protocol, formed the study database. 3D sagittal gradient recalled echo and gradient recalled echo with fat saturation images and manual models of the outer cortex were available for 86 femurs and 90 patellae. A deep‐learning–based 2D holistically nested network (HNN) architecture was developed to automatically segment the patella and distal femur using both single (sagittal, uniplanar) and 3 cardinal plane (triplanar) methodologies. Errors in the surface‐to‐surface distances and the Dice coefficient were the primary measures used to quantitatively evaluate segmentation accuracy using a 9‐fold cross‐validation. Results: Average absolute errors for segmenting both the patella and femur were 0.33 mm. The Dice coefficients were 97% and 94% for the femur and patella. The uniplanar, relative to the triplanar, methodology produced slightly superior segmentation. Neither the presence of active growth plates nor pathology influenced segmentation accuracy. Conclusion: The proposed HNN with multi‐feature architecture provides a fully automatic technique capable of delineating the often indistinct interfaces between the bone and other joint structures with an accuracy better than nearly all other techniques presented previously, even when active growth plates are present. [ABSTRACT FROM AUTHOR]

The radio frequency ablation segmentation tool (RFAST) is a software application developed using the National Institutes of Health's medical image processing analysis and visualization (MIPAV) API for the specific purpose of assisting physicians in the planning of radio frequency ablation (RFA) procedures. The RFAST application sequentially leads the physician through the steps necessary to register, fuse, segment, visualize, and plan the RFA treatment. Three-dimensional volume visualization of the CT dataset with segmented three dimensional (3-D) surface models enables the physician to interactively position the ablation probe to simulate burns and to semimanually simulate sphere packing in an attempt to optimize probe placement. This paper describes software systems contained in RFAST to address the needs of clinicians in planning, evaluating, and simulating RFA treatments of malignant hepatic tissue. [ABSTRACT FROM AUTHOR]

Purpose: Automatic muscle segmentation is critical for advancing our understanding of human physiology, biomechanics, and musculoskeletal pathologies, as it allows for timely exploration of large multi-dimensional image sets. Segmentation models are rarely developed/validated for the pediatric model. As such, autosegmentation is not available to explore how muscle architectural changes during development and how disease/pathology affects the developing musculoskeletal system. Thus, we aimed to develop and validate an end-to-end, fully automated, deep learning model for accurate segmentation of the rectus femoris and vastus lateral, medialis, and intermedialis using a pediatric database., Methods: We developed a two-stage cascaded deep learning model in a coarse-to-fine manner. In the first stage, the U 2 -Net roughly detects the muscle subcompartment region. Then, in the second stage, the shape-aware 3D semantic segmentation method SASSNet refines the cropped target regions to generate the more finer and accurate segmentation masks. We utilized multifeature image maps in both stages to stabilize performance and validated their use with an ablation study. The second-stage SASSNet was independently run and evaluated with three different cropped region resolutions: the original image resolution, and images downsampled 2× and 4× (high, mid, and low). The relationship between image resolution and segmentation accuracy was explored. In addition, the patella was included as a comparator to past work. We evaluated segmentation accuracy using leave-one-out testing on a database of 3D MR images (0.43 × 0.43 × 2 mm) from 40 pediatric participants (age 15.3 ± 1.9 years, 55.8 ± 11.8 kg, 164.2 ± 7.9 cm, 38F/2 M)., Results: The mid-resolution second stage produced the best results for the vastus medialis, rectus femoris, and patella (Dice similarity coefficient = 95.0%, 95.1%, 93.7%), whereas the low-resolution second stage produced the best results for the vastus lateralis and vastus intermedialis (DSC = 94.5% and 93.7%). In comparing the low- to mid-resolution cases, the vasti intermedialis, vastus medialis, rectus femoris, and patella produced significant differences (p = 0.0015, p = 0.0101, p < 0.0001, p = 0.0003) and the vasti lateralis did not (p = 0.2177). The high-resolution stage 2 had significantly lower accuracy (1.0 to 4.4 dice percentage points) compared to both the mid- and low-resolution routines (p value ranged from < 0.001 to 0.04). The one exception was the rectus femoris, where there was no difference between the low- and high-resolution cases. The ablation study demonstrated that the multifeature is more reliable than the single feature., Conclusions: Our successful implementation of this two-stage segmentation pipeline provides a critical tool for expanding pediatric muscle physiology and clinical research. With a relatively small and variable dataset, our fully automatic segmentation technique produces accuracies that matched or exceeded the current state of the art. The two-stage segmentation avoids memory issues and excessive run times by using a first stage focused on cropping out unnecessary data. The excellent Dice similarity coefficients improve upon previous template-based automatic and semiautomatic methodologies targeting the leg musculature. More importantly, with a naturally variable dataset (size, shape, etc.), the proposed model demonstrates slightly improved accuracies, compared to previous neural networks methods., (© 2021 American Association of Physicists in Medicine. This article has been contributed to by US Government employees and their work is in the public domain in the USA.)

Automatic prostate segmentation in MR images is a challenging task due to inter-patient prostate shape and texture variability, and the lack of a clear prostate boundary. We propose a supervised learning framework that combines the atlas based AAM and SVM model to achieve a relatively high segmentation result of the prostate boundary. The performance of the segmentation is evaluated with cross validation on 40 MR image datasets, yielding an average segmentation accuracy near 90%.