Automated segmentation of abdominal organs plays an important role in supporting computer-assisted diagnosis, radiotherapy, biomarker extraction, surgery navigation, and treatment planning. Segmenting multiple abdominal organs using a single algorithm would improve model development efficiency and accelerate model deployment into clinical workflows. To achieve broadly generalized performance, we trained a residual UNet using 500 CT/MRI scans collected from multi-center, multi-vendor, multi-phase, multi-disease patients, each with voxel-level annotation of 15 abdominal organs. Using the model trained on multimodality (CT/MRI), we achieved an average dice of 0.8990 in the held-out test dataset with only CT scans (N=100). An average dice of 0.8948 was achieved in the held-out test dataset with both CT and MRI scans (N=120. Our results demonstrate broad generalization of the model.
In quiet standing, the central nervous system implements a pre-programmed ankle strategy of postural control to maintain upright balance and stability. This strategy comprises a synchronized common neural drive delivered to synergistically grouped muscles. This study evaluated connectivity between EMG signals of the unilateral and bilateral homologous muscle pairs of the lower legs during various standing balance conditions using magnitude-squared coherence (MSC). The leg muscles examined included the right and left tibialis anterior (TA), medial gastrocnemius (MG), and soleus (S). MSC is a frequency domain measure that quantifies the linear phase relation between two signals and was analyzed in the alpha (8–13 Hz), beta (13–30 Hz), and gamma (30–100 Hz) neural frequency bands for feet together and feet tandem, with eyes open and eyes closed conditions. Results showed that connectivity in the beta and lower and upper gamma bands (30–100 Hz) was influenced by standing balance conditions and was indicative of a neural drive originating from the motor cortex. Instability was evaluated by comparing less stable standing conditions with a baseline—eyes open feet together stance. Changes in connectivity in the beta and gamma bands were found to be most significant in the muscle pairs of the back leg during a tandem stance regardless of dominant foot placement. MSC identified the MG:S muscle pair as significant for the right and left leg. The results of this study provided insight into the neural mechanism of postural control.
Multimodal Positron Emission Tomography/Computed Tomography (PET/CT) plays a key role in the diagnosis, staging, restaging, treatment response assessment, and radiotherapy planning of malignant tumors. The complementary nature of high-resolution anatomic CT and high sensitivity/specificity molecular PET imaging provides accurate assessment of disease status [14] In oncology, 18-fluorodeoxyglucose (FDG) PET/CT is the most widely used method to identify and analyze metabolically active tumors. In particular, FDG uptake allows for more accurate detection of both nodal and distant forms of metastatic disease. Accurate quantification and staging of tumors is the most important prognostic factor for predicting the survival of patients and for designing personalized patient management plans. [8,3] Analyzing PET/CT quantitatively by experienced medical imaging experts/radiologists is timeconsuming and error-prone. Automated quantitative analysis by deep learning algorithms to segment tumor lesions will enable accurate feature extraction, tumor staging, radiotherapy planning, and treatment response assessment. The AutoPET Challenge 2022 provided an opensource platform to develop and benchmark deep learning models for automated PET lesion segmentation by providing large open-source wholebody FDG-PET/CT data. Using the multimodal PET/CT data from 900 subjects with 1014 studies provided by the AutoPET MICCAI 2022 Challenge, we applied fivefold cross-validation on residual UNETs to automatically segment lesions. We then utilized the output from adaptive ensemble highly contributive models as the final segmentation. Our method achieved a 10th ranking with a dice score of 0.5541 in the heldout test dataset (N=150 studies).
In bipedal stance the central nervous system implements a pre-programmed ankle strategy to maintain upright balance and respond to internal perturbations. This strategy comprises a synchronized common neural drive delivered to synergistically grouped muscles. This study evaluated the normalized mutual information (MI) between surface electromyographic (EMG) signals of unilateral and bilateral homologous muscle pairs of the lower legs during various quiet standing tasks in normal healthy adults. The leg muscles examined included the right and left tibialis anterior (TA), medial gastrocnemius (MG), and soleus (S). MI, an information-theoretic measure that quantifies the reduction in uncertainty in predicting a signal from another known signal,, was estimated using MATLAB toolbox Mutual Information Distance and Entropy Reduction (MIDER). This method for inferring network structures from shared information between two signals was applied to pairs of filtered EMG signals in the alpha (8 – 13 Hz), beta (13 – 30 Hz), and gamma (30 – 100 Hz) neural frequency bands for feet together and feet tandem stances, under eyes open and eyes closed conditions. Results showed that normalized MI was greater in the medial gastrocnemius and soleus muscle pairs across the beta, lower gamma, and upper gamma frequency bands in the tandem standing posture under both eyes open and eyes closed conditions, and generally increased in antagonistic muscle pairs in less stable standing positions. It appears that functional muscle synergies are more important than limb dominance in tandem standing. Significant inter-trial and inter-participant variability is consistent with biological differences and control of a complex system. Our results suggest that the use of MI analyses in the clinical testing of tandem standing tasks might be a useful adjunct for persons with standing balance impairments.
In quiet standing the central nervous system implements a pre-programmed ankle strategy of postural control to maintain upright balance and stability. This strategy comprises a synchronized common neural drive delivered to synergistically grouped muscles. This study evaluated connectivity between EMG signals of unilateral and bilateral homologous muscle pairs of the lower legs during various standing balance conditions using magnitude squared coherence (MSC). The leg muscles examined included the right and left tibialis anterior (TA), medial gastrocnemius (MG), and soleus (S). MSC is a frequency domain measure that quantifies the linear phase relation between two signals and was analyzed in the alpha (8 – 13 Hz), beta (13 – 30 Hz), and gamma (30 – 100 Hz) neural frequency bands for feet together and feet tandem, with eyes open and eyes closed conditions. Results showed that connectivity in the beta, and lower and upper gamma bands (30 – 100 Hz) was influenced by standing balance conditions and indicative of a neural drive originating from the motor cortex. Instability was evaluated by comparing less stable standing conditions with a baseline - eyes open feet together stance. Changes in connectivity in the beta and gamma bands were found to be most significant in the muscle pairs of the back leg during tandem stance regardless of dominant foot placement. MSC identified the MG:S muscle pair as significant for the right and left leg. The results of this study provided insight into the neural mechanism of postural control.