Artif Intell Med - Image partitioning and illumination in image-based pose detection for teleoperated flexible endoscopes.

Tópicos

{ model(2656) set(1616) predict(1553) }
{ featur(1941) imag(1645) propos(1176) }
{ imag(1057) registr(996) error(939) }
{ network(2748) neural(1063) input(814) }
{ studi(1119) effect(1106) posit(819) }
{ perform(999) metric(946) measur(919) }
{ extract(1171) text(1153) clinic(932) }
{ method(1969) cluster(1462) data(1082) }
{ chang(1828) time(1643) increas(1301) }
{ first(2504) two(1366) second(1323) }
{ data(1714) softwar(1251) tool(1186) }
{ motion(1329) object(1292) video(1091) }
{ activ(1138) subject(705) human(624) }
{ patient(2315) diseas(1263) diabet(1191) }
{ problem(2511) optim(1539) algorithm(950) }
{ visual(1396) interact(850) tool(830) }
{ monitor(1329) mobil(1314) devic(1160) }
{ measur(2081) correl(1212) valu(896) }
{ surgeri(1148) surgic(1085) robot(1054) }
{ error(1145) method(1030) estim(1020) }
{ control(1307) perform(991) simul(935) }
{ data(3963) clinic(1234) research(1004) }
{ patient(1821) servic(1111) care(1106) }
{ estim(2440) model(1874) function(577) }
{ can(774) often(719) complex(702) }
{ data(1737) use(1416) pattern(1282) }
{ learn(2355) train(1041) set(1003) }
{ howev(809) still(633) remain(590) }
{ research(1218) medic(880) student(794) }
{ group(2977) signific(1463) compar(1072) }
{ intervent(3218) particip(2042) group(1664) }
{ activ(1452) weight(1219) physic(1104) }
{ method(2212) result(1239) propos(1039) }
{ imag(1947) propos(1133) code(1026) }
{ imag(2830) propos(1344) filter(1198) }
{ take(945) account(800) differ(722) }
{ clinic(1479) use(1117) guidelin(835) }
{ model(2220) cell(1177) simul(1124) }
{ risk(3053) factor(974) diseas(938) }
{ compound(1573) activ(1297) structur(1058) }
{ blood(1257) pressur(1144) flow(957) }
{ spatial(1525) area(1432) region(1030) }
{ state(1844) use(1261) util(961) }
{ data(2317) use(1299) case(1017) }
{ signal(2180) analysi(812) frequenc(800) }
{ cost(1906) reduc(1198) effect(832) }
{ can(981) present(881) function(850) }
{ cancer(2502) breast(956) screen(824) }
{ detect(2391) sensit(1101) algorithm(908) }
{ model(3404) distribut(989) bayesian(671) }
{ inform(2794) health(2639) internet(1427) }
{ system(1976) rule(880) can(841) }
{ bind(1733) structur(1185) ligand(1036) }
{ sequenc(1873) structur(1644) protein(1328) }
{ method(1219) similar(1157) match(930) }
{ featur(3375) classif(2383) classifi(1994) }
{ imag(2675) segment(2577) method(1081) }
{ studi(2440) review(1878) systemat(933) }
{ assess(1506) score(1403) qualiti(1306) }
{ treatment(1704) effect(941) patient(846) }
{ framework(1458) process(801) describ(734) }
{ concept(1167) ontolog(924) domain(897) }
{ algorithm(1844) comput(1787) effici(935) }
{ method(1557) propos(1049) approach(1037) }
{ design(1359) user(1324) use(1319) }
{ care(1570) inform(1187) nurs(1089) }
{ general(901) number(790) one(736) }
{ method(984) reconstruct(947) comput(926) }
{ search(2224) databas(1162) retriev(909) }
{ case(1353) use(1143) diagnosi(1136) }
{ studi(1410) differ(1259) use(1210) }
{ research(1085) discuss(1038) issu(1018) }
{ system(1050) medic(1026) inform(1018) }
{ import(1318) role(1303) understand(862) }
{ model(2341) predict(2261) use(1141) }
{ perform(1367) use(1326) method(1137) }
{ record(1888) medic(1808) patient(1693) }
{ health(3367) inform(1360) care(1135) }
{ model(3480) simul(1196) paramet(876) }
{ ehr(2073) health(1662) electron(1139) }
{ patient(2837) hospit(1953) medic(668) }
{ age(1611) year(1155) adult(843) }
{ medic(1828) order(1363) alert(1069) }
{ sampl(1606) size(1419) use(1276) }
{ gene(2352) biolog(1181) express(1162) }
{ data(3008) multipl(1320) sourc(1022) }
{ time(1939) patient(1703) rate(768) }
{ use(2086) technolog(871) perceiv(783) }
{ analysi(2126) use(1163) compon(1037) }
{ health(1844) social(1437) communiti(874) }
{ structur(1116) can(940) graph(676) }
{ high(1669) rate(1365) level(1280) }
{ use(976) code(926) identifi(902) }
{ use(1733) differ(960) four(931) }
{ drug(1928) target(777) effect(648) }
{ result(1111) use(1088) new(759) }
{ implement(1333) system(1263) develop(1122) }
{ survey(1388) particip(1329) question(1065) }
{ decis(3086) make(1611) patient(1517) }
{ process(1125) use(805) approach(778) }

Resumo

JECTIVE: Colorectal cancer is one of the leading causes of cancer-related deaths in the world, although it can be effectively treated if detected early. Teleoperated flexible endoscopes are an emerging technology to ease patient apprehension about the procedure, and subsequently increase compliance. Essential to teleoperation is robust feedback reflecting the change in pose (i.e., position and orientation) of the tip of the endoscope. The goal of this study is to first describe a novel image-based tracking system for teleoperated flexible endoscopes, and subsequently determine its viability in a clinical setting. The proposed approach leverages artificial neural networks (ANNs) to learn the mapping that links the optical flow between two sequential images to the change in the pose of the camera. Secondly, the study investigates for the first time how narrow band illumination (NBI) - today available in commercial gastrointestinal endoscopes - can be applied to enhance feature extraction, and quantify the effect of NBI and white light illumination (WLI), as well as their color information, on the strength of features extracted from the endoscopic camera stream.METHODS AND MATERIALS: In order to provide the best features for the neural networks to learn the change in pose based on the image stream, we investigated two different imaging modalities - WLI and NBI - and we applied two different spatial partitions - lumen-centered and grid-based - to create descriptors used as input to the ANNs. An experiment was performed to compare the error of these four variations, measured in root mean square error (RMSE) from ground truth given by a robotic arm, to that of a commercial state-of-the-art magnetic tracker. The viability of this technique for a clinical setting was then tested using the four ANN variations, a magnetic tracker, and a commercial colonoscope. The trial was performed by an expert endoscopist (>2000 lifetime procedures) on a colonoscopy training model with porcine blood, and the RMSE of the ANN output was calculated with respect to the magnetic tracker readings. Using the image stream obtained from the commercial endoscope, the strength of features extracted was evaluated.RESULTS: In the first experiment, the best ANNs resulted from grid-based partitioning under WLI (2.42mm RMSE) for position, and from lumen-centered partitioning under NBI (1.69? RMSE) for rotation. By comparison, the performance of the tracker was 2.49mm RMSE in position and 0.89? RMSE in rotation. The trial with the commercial endoscope indicated that lumen-centered partitioning was the best overall, while NBI outperformed WLI in terms of illumination modality. The performance of lumen-centered partitioning with NBI was 1.03?0.8mm RMSE in positional degrees of freedom (DOF), and 1.26?0.98? RMSE in rotational DOF, while with WLI, the performance was 1.56?1.15mm RMSE in positional DOF and 2.45?1.90? RMSE in rotational DOF. Finally, the features extracted under NBI were found to be twice as strong as those extracted under WLI, but no significance in feature strengths was observed between a grayscale version of the image, and the red, blue, and green color channels.CONCLUSIONS: This work demonstrates that both WLI and NBI, combined with feature partitioning based on the anatomy of the colon, provide valid mechanisms for endoscopic camera pose estimation via image stream. Illumination provided by WLI and NBI produce ANNs with similar performance which are comparable to that of a state-of-the-art magnetic tracker. However, NBI produces features that are stronger than WLI, which enables more robust feature tracking, and better performance of the ANN in terms of accuracy. Thus, NBI with lumen-centered partitioning resulted the best approach among the different variations tested for vision-based pose estimation. The proposed approach takes advantage of components already available in commercial gastrointestinal endoscopes to provide accurate feedback about the motion of the tip of the endoscope. This solution may serve as an enabling technology for closed-loop control of teleoperated flexible endoscopes.

Resumo Limpo

jectiv colorect cancer one lead caus cancerrel death world although can effect treat detect earli teleoper flexibl endoscop emerg technolog eas patient apprehens procedur subsequ increas complianc essenti teleoper robust feedback reflect chang pose ie posit orient tip endoscop goal studi first describ novel imagebas track system teleoper flexibl endoscop subsequ determin viabil clinic set propos approach leverag artifici neural network ann learn map link optic flow two sequenti imag chang pose camera second studi investig first time narrow band illumin nbi today avail commerci gastrointestin endoscop can appli enhanc featur extract quantifi effect nbi white light illumin wli well color inform strength featur extract endoscop camera streammethod materi order provid best featur neural network learn chang pose base imag stream investig two differ imag modal wli nbi appli two differ spatial partit lumencent gridbas creat descriptor use input ann experi perform compar error four variat measur root mean squar error rmse ground truth given robot arm commerci stateoftheart magnet tracker viabil techniqu clinic set test use four ann variat magnet tracker commerci colonoscop trial perform expert endoscopist lifetim procedur colonoscopi train model porcin blood rmse ann output calcul respect magnet tracker read use imag stream obtain commerci endoscop strength featur extract evaluatedresult first experi best ann result gridbas partit wli mm rmse posit lumencent partit nbi rmse rotat comparison perform tracker mm rmse posit rmse rotat trial commerci endoscop indic lumencent partit best overal nbi outperform wli term illumin modal perform lumencent partit nbi mm rmse posit degre freedom dof rmse rotat dof wli perform mm rmse posit dof rmse rotat dof final featur extract nbi found twice strong extract wli signific featur strength observ grayscal version imag red blue green color channelsconclus work demonstr wli nbi combin featur partit base anatomi colon provid valid mechan endoscop camera pose estim via imag stream illumin provid wli nbi produc ann similar perform compar stateoftheart magnet tracker howev nbi produc featur stronger wli enabl robust featur track better perform ann term accuraci thus nbi lumencent partit result best approach among differ variat test visionbas pose estim propos approach take advantag compon alreadi avail commerci gastrointestin endoscop provid accur feedback motion tip endoscop solut may serv enabl technolog closedloop control teleoper flexibl endoscop

Resumos Similares

IEEE Trans Image Process - Image clustering using local discriminant models and global integration. ( 0,675558816029766 )
Neural Comput - Invariant object recognition and pose estimation with slow feature analysis. ( 0,667098838980471 )
IEEE Trans Image Process - Integrated segmentation and interpolation of sparse data. ( 0,630096479743258 )
Comput. Biol. Med. - Automatic colposcopy video tissue classification using higher order entropy-based image registration. ( 0,608185935263465 )
IEEE Trans Image Process - Fine-tuning regression forests votes for object alignment in the wild. ( 0,604794229842249 )
IEEE Trans Image Process - Geodesic invariant feature: a local descriptor in depth. ( 0,599676524930278 )
IEEE Trans Image Process - Boosting color feature selection for color face recognition. ( 0,591637505241018 )
J Chem Inf Model - Study of chromatographic retention of natural terpenoids by chemoinformatic tools. ( 0,590716493920282 )
Neural Comput - Geometry-invariant texture retrieval using a dual-output pulse-coupled neural network. ( 0,588379529481264 )
IEEE Trans Image Process - Manifold-manifold distance and its application to face recognition with image sets. ( 0,584188468721771 )
IEEE Trans Pattern Anal Mach Intell - Statistical 3D Shape Analysis by Local Generative Descriptors. ( 0,577993364954987 )
IEEE Trans Image Process - Multilinear supervised neighborhood embedding of a local descriptor tensor for scene/object recognition. ( 0,574936017826462 )
IEEE Trans Image Process - Coupled binary embedding for large-scale image retrieval. ( 0,574846013050073 )
J. Comput. Biol. - Boolean models can explain bistability in the lac operon. ( 0,573390690145736 )
IEEE Trans Pattern Anal Mach Intell - A Two-Stage Framework for 3D Face Reconstruction From RGBD Images. ( 0,560964441710857 )
IEEE Trans Image Process - Semisupervised multiview distance metric learning for cartoon synthesis. ( 0,560719351659279 )
IEEE Trans Image Process - Multiscale distance matrix for fast plant leaf recognition. ( 0,556118881296461 )
IEEE Trans Image Process - Robust 3D face landmark localization based on local coordinate coding. ( 0,553052859277702 )
Artif Intell Med - Training artificial neural networks directly on the concordance index for censored data using genetic algorithms. ( 0,551782192667053 )
Comput Methods Programs Biomed - Calculation of melatonin and resveratrol effects on steatosis hepatis using soft computing methods. ( 0,551535157639435 )
IEEE Trans Image Process - Common feature discriminant analysis for matching infrared face images to optical face images. ( 0,547034124870059 )
IEEE Trans Image Process - Gait-based person recognition using arbitrary view transformation model. ( 0,546866627986127 )
IEEE Trans Image Process - Combining LBP difference and feature correlation for texture description. ( 0,545817139769994 )
Methods Inf Med - Regularization in deformable registration of biomedical images based on divergence and curl operators. ( 0,545511549886665 )
IEEE Trans Image Process - Enhanced local texture feature sets for face recognition under difficult lighting conditions. ( 0,544987946521433 )
J. Med. Internet Res. - A case study of the New York City 2012-2013 influenza season with daily geocoded Twitter data from temporal and spatiotemporal perspectives. ( 0,544596937740622 )
Neural Comput - Learning intermediate-level representations of form and motion from natural movies. ( 0,544407944568806 )
Int J Health Geogr - Incorporating geographical factors with artificial neural networks to predict reference values of erythrocyte sedimentation rate. ( 0,543865848170224 )
IEEE Trans Image Process - Face illumination manipulation using a single reference image by adaptive layer decomposition. ( 0,542550129381443 )
AMIA Annu Symp Proc - Motivating the additional use of external validity: examining transportability in a model of glioblastoma multiforme. ( 0,542213708725866 )
J Chem Inf Model - Does rational selection of training and test sets improve the outcome of QSAR modeling? ( 0,542122499462623 )
IEEE Trans Image Process - Accurate Iris Recognition at a Distance Using Stabilized Iris Encoding and Zernike Moments Phase Features. ( 0,54156578119748 )
J Chem Inf Model - GRID-based three-dimensional pharmacophores II: PharmBench, a benchmark data set for evaluating pharmacophore elucidation methods. ( 0,541104886075172 )
J Chem Inf Model - Rank order entropy: why one metric is not enough. ( 0,540073068649283 )
IEEE Trans Image Process - The segmentation of 3D images using the random walking technique on a randomly created image adjacency graph. ( 0,537686598027854 )
IEEE Trans Image Process - Tensor discriminant color space for face recognition. ( 0,537005248741048 )
Med Biol Eng Comput - Effects of framing coil shape, orientation, and thickness on intra-aneurysmal flow. ( 0,536507787820641 )
IEEE Trans Image Process - Pose-invariant face recognition using Markov random fields. ( 0,535764406651527 )
IEEE Trans Image Process - Vehicle detection in aerial surveillance using dynamic Bayesian networks. ( 0,534806905576656 )
J Chem Inf Model - Best of both worlds: combining pharma data and state of the art modeling technology to improve in Silico pKa prediction. ( 0,534324782861036 )
IEEE Trans Pattern Anal Mach Intell - A Markov Random Field Groupwise Registration Framework for Face Recognition. ( 0,534239020451889 )
IEEE Trans Image Process - Nonnegative Tensor Co-Factorization and Its Unified Solution. ( 0,532016654207926 )
IEEE Trans Image Process - A feature-based learning framework for accurate prostate localization in CT images. ( 0,53197832113792 )
IEEE Trans Image Process - A completed modeling of local binary pattern operator for texture classification. ( 0,531920190600943 )
IEEE Trans Image Process - Rigid-motion-invariant classification of 3-D textures. ( 0,531091118744828 )
J Med Syst - Directional binary wavelet patterns for biomedical image indexing and retrieval. ( 0,530726985318201 )
IEEE Trans Image Process - Large-margin Learning of Compact Binary Image Encodings. ( 0,530236370406564 )
Comput Math Methods Med - Crossing fibers detection with an analytical high order tensor decomposition. ( 0,529743898397936 )
IEEE Trans Image Process - Face recognition using ensemble string matching. ( 0,529237291146737 )
IEEE Trans Pattern Anal Mach Intell - Monotonicity and Error Type Differentiability in Performance Measures for Target Detection and Tracking in Video. ( 0,52748260075992 )
IEEE Trans Image Process - Learning the spherical harmonic features for 3-D face recognition. ( 0,52591597699236 )
IEEE Trans Pattern Anal Mach Intell - Hidden Part Models for Human Action Recognition: Probabilistic versus Max Margin. ( 0,525050165689359 )
IEEE Trans Image Process - Human gait recognition using patch distribution feature and locality-constrained group sparse representation. ( 0,524146722425854 )
Comput Math Methods Med - Multiscale autoregressive identification of neuroelectrophysiological systems. ( 0,52252754629723 )
J Biomed Inform - Transfer learning based clinical concept extraction on data from multiple sources. ( 0,522254472044821 )
IEEE Trans Pattern Anal Mach Intell - Spatially-Constrained Similarity Measure for Large-Scale Object Retrieval. ( 0,522057625817754 )
IEEE Trans Image Process - Geodesics-based image registration: applications to biological and medical images depicting concentric ring patterns. ( 0,52177052267454 )
J Chem Inf Model - Doing a good turn: the use of quaternions for rotation in molecular docking. ( 0,521545176867749 )
Int J Comput Assist Radiol Surg - Feasibility of respiratory motion-compensated stereoscopic X-ray tracking for bronchoscopy. ( 0,521353852680021 )
Neural Comput - Population coding and the labeling problem: extrinsic versus intrinsic representations. ( 0,519941595525173 )
IEEE Trans Image Process - Estimation of sunlight direction using 3D object models. ( 0,519772558220557 )
IEEE Trans Image Process - Robust face representation using hybrid spatial feature interdependence matrix. ( 0,51893479952476 )
IEEE Trans Image Process - Scale-invariant features for 3-D mesh models. ( 0,518502568263332 )
J Chem Inf Model - Global quantitative structure-activity relationship models vs selected local models as predictors of off-target activities for project compounds. ( 0,518129880920814 )
IEEE Trans Image Process - Extracting multiple features in the CID color space for face recognition. ( 0,517744971507359 )
IEEE Trans Pattern Anal Mach Intell - Pose-Robust Recognition of Low-Resolution Face Images. ( 0,517343239382849 )
IEEE Trans Pattern Anal Mach Intell - What Makes a Photograph Memorable? ( 0,516101275930374 )
Med Biol Eng Comput - Quantitative color analysis for capillaroscopy image segmentation. ( 0,515447095592326 )
IEEE Trans Pattern Anal Mach Intell - LDAHash: Improved Matching with Smaller Descriptors. ( 0,515280142571594 )
IEEE Trans Image Process - Exploring duplicated regions in natural images. ( 0,514719368836168 )
Int J Comput Assist Radiol Surg - Assessing performance in brain tumor resection using a novel virtual reality simulator. ( 0,514330287295492 )
Med Biol Eng Comput - Development of a comprehensive musculoskeletal model of the shoulder and elbow. ( 0,513942268112829 )
IEEE Trans Image Process - Nonnegative local coordinate factorization for image representation. ( 0,513920154061709 )
IEEE Trans Image Process - Subspace-based discrete transform encoded local binary patterns representations for robust periocular matching on NIST's face recognition grand challenge. ( 0,512939638460329 )
IEEE Trans Image Process - Fast and robust 2D-shape extraction using discrete-point sampling and centerline grouping in complex images. ( 0,51211668574916 )
IEEE Trans Image Process - Properties of BV - G structures + textures decomposition models. Application to road detection in satellite images. ( 0,511889440060101 )
IEEE Trans Image Process - Semantic pyramids for gender and action recognition. ( 0,511384732601211 )
IEEE Trans Pattern Anal Mach Intell - Scalable Face Image Retrieval with Identity-Based Quantization and Multireference Reranking. ( 0,510741466491753 )
IEEE Trans Pattern Anal Mach Intell - CENTRIST: A Visual Descriptor for Scene Categorization. ( 0,50946843446942 )
IEEE Trans Image Process - Sparse color interest points for image retrieval and object categorization. ( 0,508659483003787 )
IEEE Trans Image Process - Sparse tensor discriminant analysis. ( 0,508430806626306 )
IEEE Trans Image Process - Representing and retrieving video shots in human-centric brain imaging space. ( 0,508372134400898 )
IEEE Trans Pattern Anal Mach Intell - Intensity-Based Image Registration by Nonparametric Local Smoothing. ( 0,508307846024444 )
IEEE Trans Pattern Anal Mach Intell - Retrieval-based Face Annotation by Weak Label Regularized Local Coordinate Coding. ( 0,5076592021427 )
J Chem Inf Model - Time-split cross-validation as a method for estimating the goodness of prospective prediction. ( 0,507558236398424 )
IEEE Trans Image Process - Automatic virus particle selection--the entropy approach. ( 0,507145101635906 )
Int J Med Robot - A robust automated markerless registration framework for neurosurgery navigation. ( 0,506796939383057 )
IEEE Trans Image Process - Low-resolution face tracker robust to illumination variations. ( 0,506685466613271 )
Int J Comput Assist Radiol Surg - Analysis of electrode deformations in deep brain stimulation surgery. ( 0,505815082048307 )
IEEE Trans Image Process - Fusing local patterns of Gabor magnitude and phase for face recognition. ( 0,505643521522546 )
IEEE Trans Image Process - Adaptive color feature extraction based on image color distributions. ( 0,50540399210577 )
IEEE Trans Image Process - DSIM: a DisSIMilarity-based image clutter metric for targeting performance. ( 0,50495977563384 )
J Biomed Inform - MysiRNA: improving siRNA efficacy prediction using a machine-learning model combining multi-tools and whole stacking energy (G). ( 0,503938092728852 )
IEEE Trans Image Process - Local energy pattern for texture classification using self-adaptive quantization thresholds. ( 0,50323201504228 )
Neural Comput - High-dimensional feature selection by feature-wise kernelized Lasso. ( 0,503217533507871 )
IEEE Trans Image Process - Wavelet domain multifractal analysis for static and dynamic texture classification. ( 0,501943052910631 )
IEEE Trans Image Process - Principal visual word discovery for automatic license plate detection. ( 0,501497577431011 )
IEEE Trans Image Process - BIK-BUS: biologically motivated 3D keypoint based on bottom-up saliency. ( 0,501447156945411 )
IEEE Trans Image Process - Efficient texture image retrieval using copulas in a Bayesian framework. ( 0,501346674568368 )
IEEE Trans Image Process - Local color vector binary patterns from multichannel face images for face recognition. ( 0,500586853337898 )