4,349 Hits in 10.2 sec

Evaluating Reinforcement Learning Agents for Anatomical Landmark Detection

Amir Alansary, Ozan Oktay, Yuanwei Li, Loic Le Folgoc, Benjamin Hou, Ghislain Vaillant, Konstantinos Kamnitsas, Athanasios Vlontzos, Ben Glocker, Bernhard Kainz, Daniel Rueckert
2019 Medical Image Analysis  
Automatic detection of anatomical landmarks is an important step for a wide range of applications in medical image analysis.  ...  In this paper, we evaluate novel deep reinforcement learning (RL) strategies to train agents that can precisely and robustly localize target landmarks in medical scans.  ...  Acknowledgments We thank the volunteers, radiographers and experts for providing manually annotated datasets, Wellcome Trust IEH Award [102431], NVIDIA for their GPU donations, and Intel.  ... 
doi:10.1016/ pmid:30784956 pmcid:PMC7610752 fatcat:snhtae3iebc2nlld7g5ardsrza

2-step deep learning model for landmarks localization in spine radiographs

Andrea Cina, Tito Bassani, Matteo Panico, Andrea Luca, Youssef Masharawi, Marco Brayda-Bruno, Fabio Galbusera
2021 Scientific Reports  
AbstractIn this work we propose to use Deep Learning to automatically calculate the coordinates of the vertebral corners in sagittal x-rays images of the thoracolumbar spine and, from those landmarks,  ...  For the localization tasks, we used a differentiable spatial to numerical transform (DSNT) as the top layer. We evaluated the model both qualitatively and quantitatively on a set of 195 test images.  ...  We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.  ... 
doi:10.1038/s41598-021-89102-w pmid:33947917 fatcat:uhqwr3odozcfnktylffyyllfx4

A Registration and Deep Learning Approach to Automated Landmark Detection for Geometric Morphometrics [article]

Jay Devine, Jose D. Aponte, David C. Katz, Wei Liu, Lucas D. Lo Vercio, Nils D. Forkert, Christopher J. Percival, Benedikt Hallgrímsson
2019 bioRxiv   pre-print
Image registration, or the spatial alignment of images, is a fundamental technique in automatic image analysis that is well-poised for such purposes.  ...  Using micro-computed tomography images of genetically and morphologically variable mouse skulls, we test our landmarking approach under a variety of registration conditions, including different non-linear  ...  In this paper, we combine techniques from machine learning and image registration, or the spatial alignment of images, to automatically and accurately detect landmarks for GM.  ... 
doi:10.1101/2019.12.11.873182 fatcat:vk4z4yhpxbednjirgfisltdquy

Detecting Anatomical Landmarks From Limited Medical Imaging Data Using Two-Stage Task-Oriented Deep Neural Networks

Jun Zhang, Mingxia Liu, Dinggang Shen
2017 IEEE Transactions on Image Processing  
One of the major challenges in anatomical landmark detection, based on deep neural networks, is the limited availability of medical imaging data for network learning.  ...  between local image patches and target anatomical landmarks.  ...  Accordingly, we propose an end-to-end deep learning approach to detect large-scale landmarks in real time, by using limited medical images. Figure 1 briefly illustrates our proposed method.  ... 
doi:10.1109/tip.2017.2721106 pmid:28678706 pmcid:PMC5729285 fatcat:cb5osyrw2ffepb3hgyd67srggi

Regression forests for efficient anatomy detection and localization in computed tomography scans

A. Criminisi, D. Robertson, E. Konukoglu, J. Shotton, S. Pathak, S. White, K. Siddiqui
2013 Medical Image Analysis  
This paper proposes a new algorithm for the efficient, automatic detection and localization of multiple anatomical structures within three-dimensional computed tomography (CT) scans.  ...  The main contribution of this work is a new, continuous parametrization of the anatomy localization problem, which allows it to be addressed effectively by multi-class random regression forests.  ...  The database comprises patients with a wide variety of medical conditions and body shapes and the scans exhibit large differences in image cropping, resolution, scanner type, and use of contrast agents  ... 
doi:10.1016/ pmid:23410511 fatcat:4wqymw5vqjgifmddqemiudvz4u

Automatic Analysis of Facial Actions: A Survey

Brais Martinez, Michel F. Valstar, Bihan Jiang, Maja Pantic
2017 IEEE Transactions on Affective Computing  
Image/Video Appearance-based approaches, Geometry-based approaches, Motion-based approaches, Hybrid approaches Face detection and tracking, Facial point detection and tracking, Face normalisation AU classification  ...  of machine recognition of facial actions: what are the challenges and opportunities that researchers in the field face.  ...  For example, the kernel Conditional Ordinal Random Fields was applied to the AU temporal segment detection problem in [141] , and makes use of the temporal ordering constraints of the labels.  ... 
doi:10.1109/taffc.2017.2731763 fatcat:6qp6zg5rrrgwrladsnwmyeqbq4

Deep Learning in Medical Imaging

Mingyu Kim, Jihye Yun, Yongwon Cho, Keewon Shin, Ryoungwoo Jang, Hyun-jin Bae, Namkug Kim
2019 Neurospine  
In this review article, we will explain the history, development, and applications in medical imaging.  ...  The advancement of computing power with graphics processing units and the availability of large data acquisition, deep neural network outperforms human or other ML capabilities in computer vision and speech  ...  They compared the performance of the Markov random field method to that of CNN and showed the CNN network can be used in denoising. Not only CNN but also autoencoder (AE) can be used in denoising.  ... 
doi:10.14245/ns.1938396.198 pmid:31905454 pmcid:PMC6945006 fatcat:miszi3fiojh35ldsgggxgpaowa

Facial Landmark Detection: A Literature Survey

Yue Wu, Qiang Ji
2018 International Journal of Computer Vision  
Many facial landmark detection algorithms have been developed to automatically detect those key points over the years, and in this paper, we perform an extensive review of them.  ...  The locations of the fiducial facial landmark points around facial components and facial contour capture the rigid and non-rigid facial deformations due to head movements and facial expressions.  ...  For example, Markov Random Field (MRF) model is used in [21] , and Dynamic Bayesian Network is used in [56] .  ... 
doi:10.1007/s11263-018-1097-z fatcat:ykqg6lr3j5bbrmrmli2dlrxupi

On the Methods for Detecting Brain Tumor from MRI images

Due to its high mortality rate, detection of tumor automatically is a new emerging technique in bio medical imaging.  ...  The segmentation of tumor methods is classified to image segmentation using gray level processing, machine learning and deep learning.  ...  So automatic detection became important and this study explores many methods used for detection and segmentation of tumor from MRI images.  ... 
doi:10.35940/ijitee.i1007.0799s20 fatcat:mpo2gpnwwvhv3fj74idihf4uom

Shaping the Future through Innovations: From Medical Imaging to Precision Medicine [article]

Dorin Comaniciu, Klaus Engel, Bogdan Georgescu, Tommaso Mansi
2016 arXiv   pre-print
Medical images constitute a source of information essential for disease diagnosis, treatment and follow-up.  ...  This manuscript describes recently developed technologies for better handling of image information: photorealistic visualization of medical images with Cinematic Rendering, artificial agents for in-depth  ...  We would also like to thank our clinical and non-clinical collaborators for the strong support over many years. Disclaimer This feature is based on research, and is not commercially available.  ... 
arXiv:1605.02029v2 fatcat:kwsyfx5jqrfuhlblnvnd4pf2n4

Facial Landmark Detection via Attention-Adaptive Deep Network

Muhammad Sadiq, Daming Shi, Meiqin Guo, Xiaochun Cheng
2019 IEEE Access  
Facial landmark detection is a key component of the face recognition pipeline as well as facial attribute analysis and face verification.  ...  It can be learnt automatically in the process of estimating the relationship between facial appearance and facial shape.  ...  These points also can be centred at common facial components. Facial analysis tasks can differ in numbers and types, in terms of number of needed facial points, and use of these facial points.  ... 
doi:10.1109/access.2019.2955156 fatcat:rkyphd4rmvfulcjajiipyuogbe

3D cephalometric landmark detection by multiple stage deep reinforcement learning

Sung Ho Kang, Kiwan Jeon, Sang-Hoon Kang, Sang-Hwy Lee
2021 Scientific Reports  
We here propose an automatic 3D cephalometric annotation system based on multi-stage deep reinforcement learning (DRL) and volume-rendered imaging.  ...  Our system, moreover, requires no additional steps of segmentation and 3D mesh-object construction for landmark detection.  ...  ., and K.J. S.H.K. and K.J. were partially supported by the National Institute for Mathematical Sciences (NIMS) grant funded by the Korean government (No. NIMS-B21910000).  ... 
doi:10.1038/s41598-021-97116-7 pmid:34471202 fatcat:rjrvbhtaozekdokyq3q7mif7me

Tracked Ultrasound in Navigated Spine Interventions [chapter]

Tamas Ungi, Andras Lasso, Gabor Fichtinger
2014 Lecture Notes in Computational Vision and Biomechanics  
Ultrasound is an increasingly popular imaging modality in image-guided interventions, due to its safety, accessibility, and low cost.  ...  But ultrasound imaging has a steep learning curve, and requires significant coordination skills from the operator.  ...  Position of the water tank bottom is automatically detected in the ultrasound image and used as position signal for the image data.  ... 
doi:10.1007/978-3-319-12508-4_15 fatcat:uzgt4n7fmzcpxjdthieneqgrlq

Object learning and detection using evolutionary deformable models for mobile robot navigation

M. Mata, J. M. Armingol, J. Fernández, A. de la Escalera
2007 Robotica (Cambridge. Print)  
Deformable models have been studied in image analysis over the last decade and used for recognition of flexible or rigid templates under diverse viewing conditions.  ...  Instead of receiving the detailed model definition from the user, the algorithm extracts and learns the information from each object automatically.  ...  This allows an exact "topological localization," and also confirms the detection of the right landmark.  ... 
doi:10.1017/s0263574707003633 fatcat:sr74z35pcjdcbpzatakiteifgy

Automated Motion Analysis of Bony Joint Structures from Dynamic Computer Tomography Images: A Multi-Atlas Approach

Benyameen Keelson, Luca Buzzatti, Jakub Ceranka, Adrián Gutiérrez, Simone Battista, Thierry Scheerlinck, Gert Van Gompel, Johan De Mey, Erik Cattrysse, Nico Buls, Jef Vandemeulebroucke
2021 Diagnostics  
In terms of motion estimation, mean differences in cardan angles between the automated algorithm and manual segmentation, and landmark identification performed by an expert were below 1°.  ...  The objective of this study is to present an automated workflow for the assessment of three-dimensional in vivo joint kinematics from dynamic musculoskeletal CT images.  ...  Acknowledgments: Special thanks to Mattias Nicolas Bossa, Kjell Van Royen and Tjeerd Jager for proofreading this manuscript. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/diagnostics11112062 pmid:34829409 pmcid:PMC8621122 fatcat:liqbotbkvffnxblilfjedi7lku
« Previous Showing results 1 — 15 out of 4,349 results