{"id":2047,"date":"2018-06-16T22:07:18","date_gmt":"2018-06-16T13:07:18","guid":{"rendered":"http:\/\/cinetjp-static3.nict.go.jp\/japanese\/?post_type=event&p=2047"},"modified":"2022-10-12T10:38:58","modified_gmt":"2022-10-12T01:38:58","slug":"20180719_3370","status":"publish","type":"event","link":"http:\/\/cinetjp-static3.nict.go.jp\/japanese\/event\/20180719_3370\/","title":{"rendered":"CiNet Monthly Seminar (extra) : Bo Zhu \u201cExploration of Machine Learning Approaches for Automating Medical Image Reconstruction and Acquisition\u201d"},"content":{"rendered":"\n

CiNet Monthly Seminar<\/strong><\/p>\n\n\n\n

2018\u5e748\u67086\u65e5\uff08\u6708\uff09
16:00 ~ 17:00
\u4f1a\u5834 \uff1a CiNet\u30001F\u3000\u5927\u4f1a\u8b70\u5ba4<\/p>\n\n\n\n

\u201cExploration of Machine Learning Approaches for Automating Medical Image Reconstruction and Acquisition\u201d<\/p>\n\n\n\n

Bo Zhu
Research Fellow
Harvard Medical School<\/p>\n\n\n\n

Host :\u00a0\u5929\u91ce \u85ab\u3000\uff08PI\uff09<\/p>\n\n\n\n

Abstract:
Image reconstruction plays a critical role in the implementation of all contemporary imaging modalities across the physical and life sciences including optical, radar, magnetic resonance imaging (MRI), X-ray computed tomography (CT), positron emission tomography (PET), ultrasound, and radio astronomy. Image reconstruction is challenging because analytic knowledge of the exact inverse transform may not exist a priori, especially in the presence of sensor non-idealities and noise.
Thus, the standard reconstruction approach involves approximating the inverse function with multiple ad hoc stages in a signal processing chain whose composition depends on the details of each acquisition strategy, and often requires expert parameter tuning to optimize reconstruction performance. We present a unified framework for image reconstruction, AUtomated TransfOrm by Manifold APproximation (AUTOMAP), which recasts image reconstruction as a data-driven, supervised learning task that allows a mapping between sensor and image domain to emerge from an appropriate corpus of training data. We implement AUTOMAP with a deep neural network and exhibit its flexibility in learning reconstruction transforms for a variety of MRI acquisition strategies, using the same network architecture and hyperparameters. We further demonstrate its efficiency in sparsely representing transforms along low-dimensional manifolds, resulting in superior immunity to noise and a reduction in reconstruction artifacts compared with conventional handcrafted reconstruction methods. In this talk I also describe work in progress on automated pulse sequence generation (AUTOSEQ), wherein we recast the general problem of MR pulse sequence development as a model-free problem optimized with a Bayesian derivative of reinforcement learning within a MRI physics simulation environment. We show preliminary proof-of-principle experiments and demonstrate our agent learning a canonical pulse sequence (the gradient echo) and also generating non-intuitive pulse sequences that can produce signals approximating Fourier spatial encoding.<\/p>\n","protected":false},"featured_media":0,"template":"","acf":[],"_links":{"self":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/japanese\/wp-json\/wp\/v2\/event\/2047"}],"collection":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/japanese\/wp-json\/wp\/v2\/event"}],"about":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/japanese\/wp-json\/wp\/v2\/types\/event"}],"wp:attachment":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/japanese\/wp-json\/wp\/v2\/media?parent=2047"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}