scholarly journals One to Many: Adaptive Instrument Segmentation via Meta Learning and Dynamic Online Adaptation in Robotic Surgical Video

Author(s):  
Zixu Zhao ◽  
Yueming Jin ◽  
Bo Lu ◽  
Chi-Fai Ng ◽  
Qi Dou ◽  
...  
2019 ◽  
Vol 1 (2) ◽  
pp. V1
Author(s):  
Sima Sayyahmelli ◽  
Jian Ruan ◽  
Bryan Wheeler ◽  
Mustafa K. Başkaya

Primary glioblastoma multiforme tumors of the medulla oblongata are rare, especially in the adult population. Perhaps due to this rarity, we are not aware of any previous reports addressing the resection of these tumors or their clinical outcomes.In this surgical video, we present a 43-year-old man with a 1-month history of left-sided paresthesia. The paresthesia initiated in the left hand, along with weakness and reduced fine motor control, and then spread to the entire left side of the body. He had recent weight loss, imbalance, difficulty in swallowing, and hoarseness in his voice. He also had a diminished gag reflex, and significant atrophy of the right side of the tongue with an accompanying deviation of the uvula and fasciculations of the tongue. MRI showed an infiltrative expansile mass within the medulla with peripheral enhancement and central necrosis. In T2/FLAIR sequences, a hyperintense signal extended superiorly into the left inferior aspect of the pons and left inferior cerebellar peduncle and inferiorly into the upper cervical cord.The decision was made to proceed with surgical resection. The patient underwent a midline suboccipital craniotomy with C1 laminectomy for surgical resection of this infiltrative expansile intrinsic mass in the medulla oblongata, with concurrent monitoring of motor and somatosensory evoked potentials and monitoring of lower cranial nerves IX, X, XI, and XII. A gross-total resection of the enhancing portion of the tumor was performed, along with a subtotal resection of the nonenhancing portion. The surgery and postoperative course were uneventful. Histopathology revealed a grade IV astrocytoma. The patient received radiation therapy.In this surgical video, we demonstrate important steps for the microsurgical resection of this challenging glioblastoma multiforme of the medulla oblongata.The video can be found here: https://youtu.be/QHbOVxdxbeU.


IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 172859-172868
Author(s):  
Zhengwei Ma ◽  
Sensen Guo ◽  
Gang Xu ◽  
Saddam Aziz

Sensors ◽  
2020 ◽  
Vol 20 (20) ◽  
pp. 5966
Author(s):  
Ke Wang ◽  
Gong Zhang

The challenge of small data has emerged in synthetic aperture radar automatic target recognition (SAR-ATR) problems. Most SAR-ATR methods are data-driven and require a lot of training data that are expensive to collect. To address this challenge, we propose a recognition model that incorporates meta-learning and amortized variational inference (AVI). Specifically, the model consists of global parameters and task-specific parameters. The global parameters, trained by meta-learning, construct a common feature extractor shared between all recognition tasks. The task-specific parameters, modeled by probability distributions, can adapt to new tasks with a small amount of training data. To reduce the computation and storage cost, the task-specific parameters are inferred by AVI implemented with set-to-set functions. Extensive experiments were conducted on a real SAR dataset to evaluate the effectiveness of the model. The results of the proposed approach compared with those of the latest SAR-ATR methods show the superior performance of our model, especially on recognition tasks with limited data.


Sign in / Sign up

Export Citation Format

Share Document