IEEE Trans Image Process - The segmentation of the left ventricle of the heart from ultrasound data using deep learning architectures and derivative-based search methods.


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


We present a new supervised learning model designed for the automatic segmentation of the left ventricle (LV) of the heart in ultrasound images. We address the following problems inherent to supervised learning models: 1) the need of a large set of training images; 2) robustness to imaging conditions not present in the training data; and 3) complex search process. The innovations of our approach reside in a formulation that decouples the rigid and nonrigid detections, deep learning methods that model the appearance of the LV, and efficient derivative-based search algorithms. The functionality of our approach is evaluated using a data set of diseased cases containing 400 annotated images (from 12 sequences) and another data set of normal cases comprising 80 annotated images (from two sequences), where both sets present long axis views of the LV. Using several error measures to compute the degree of similarity between the manual and automatic segmentations, we show that our method not only has high sensitivity and specificity but also presents variations with respect to a gold standard (computed from the manual annotations of two experts) within interuser variability on a subset of the diseased cases. We also compare the segmentations produced by our approach and by two state-of-the-art LV segmentation models on the data set of normal cases, and the results show that our approach produces segmentations that are comparable to these two approaches using only 20 training images and increasing the training set to 400 images causes our approach to be generally more accurate. Finally, we show that efficient search methods reduce up to tenfold the complexity of the method while still producing competitive segmentations. In the future, we plan to include a dynamical model to improve the performance of the algorithm, to use semisupervised learning methods to reduce even more the dependence on rich and large training sets, and to design a shape model less dependent on the training set.

Resumo Limpo

present new supervis learn model design automat segment left ventricl lv heart ultrasound imag address follow problem inher supervis learn model need larg set train imag robust imag condit present train data complex search process innov approach resid formul decoupl rigid nonrigid detect deep learn method model appear lv effici derivativebas search algorithm function approach evalu use data set diseas case contain annot imag sequenc anoth data set normal case compris annot imag two sequenc set present long axi view lv use sever error measur comput degre similar manual automat segment show method high sensit specif also present variat respect gold standard comput manual annot two expert within interus variabl subset diseas case also compar segment produc approach two stateoftheart lv segment model data set normal case result show approach produc segment compar two approach use train imag increas train set imag caus approach general accur final show effici search method reduc tenfold complex method still produc competit segment futur plan includ dynam model improv perform algorithm use semisupervis learn method reduc even depend rich larg train set design shape model less depend train set

Resumos Similares

Int J Comput Assist Radiol Surg - Computer-aided diagnostics in digital pathology: automated evaluation of early-phase pancreatic cancer in mice. ( 0,682327347092219 )
J Am Med Inform Assoc - Supervised machine learning and active learning in classification of radiology reports. ( 0,661528049658677 )
Comput Math Methods Med - Three-dimensional reconstruction of coronary arteries and its application in localization of coronary artery segments corresponding to myocardial segments identified by transthoracic echocardiography. ( 0,64221626859176 )
Comput Methods Programs Biomed - Geometrical methods for level set based abdominal aortic aneurysm thrombus and outer wall 2D image segmentation. ( 0,638816360230699 )
Int J Comput Assist Radiol Surg - Investigating machine learning techniques for MRI-based classification of brain neoplasms. ( 0,635410720738866 )
Int J Comput Assist Radiol Surg - A geodesic deformable model for automatic segmentation of image sequences applied to radiation therapy. ( 0,627433297488199 )
Int J Comput Assist Radiol Surg - Toward a clinical lumbar CAD: herniation diagnosis. ( 0,617167108354706 )
Methods Inf Med - Fuzzy-based vascular structure enhancement in Time-of-Flight MRA images for improved segmentation. ( 0,611868820285975 )
IEEE Trans Image Process - Image registration under illumination variations using region-based confidence weighted M-estimators. ( 0,604740978206027 )
Int J Neural Syst - Self-supervised MRI tissue segmentation by discriminative clustering. ( 0,602952521312987 )
Comput Methods Programs Biomed - An attribute weight assignment and particle swarm optimization algorithm for medical database classifications. ( 0,601977300126971 )
J Chem Inf Model - Beyond the scope of Free-Wilson analysis: building interpretable QSAR models with machine learning algorithms. ( 0,599156527411173 )
Med Biol Eng Comput - Application of the RIMARC algorithm to a large data set of action potentials and clinical parameters for risk prediction of atrial fibrillation. ( 0,597479374681915 )
Int J Comput Assist Radiol Surg - Compression fracture diagnosis in lumbar: a clinical CAD system. ( 0,597100983653029 )
Comput Methods Programs Biomed - Automated segmentation of tissue images for computerized IHC analysis. ( 0,595970469937716 )
Int J Comput Assist Radiol Surg - Voxel classification and graph cuts for automated segmentation of pathological periprosthetic hip anatomy. ( 0,591337127113596 )
IEEE Trans Image Process - Saliency and gist features for target detection in satellite images. ( 0,590840751077357 )
Artif Intell Med - Fuzzy model identification of dengue epidemic in Colombia based on multiresolution analysis. ( 0,588289197993475 )
Artif Intell Med - Modern parameterization and explanation techniques in diagnostic decision support system: a case study in diagnostics of coronary artery disease. ( 0,585030168421639 )
J Med Syst - Discovering mammography-based machine learning classifiers for breast cancer diagnosis. ( 0,582433010326966 )
Med Biol Eng Comput - Automatic segmentation of brain MR images using an adaptive balloon snake model with fuzzy classification. ( 0,581895090494246 )
IEEE Trans Image Process - Enhancing training collections for image annotation: an instance-weighted mixture modeling approach. ( 0,576749807906691 )
Comput Math Methods Med - Abdominal tumor characterization and recognition using superior-order cooccurrence matrices, based on ultrasound images. ( 0,57307133002455 )
Med Biol Eng Comput - Interactive segmentation of plexiform neurofibroma tissue: method and preliminary performance evaluation. ( 0,570441828094304 )
Comput Math Methods Med - Unsupervised cardiac image segmentation via multiswarm active contours with a shape prior. ( 0,570144419653041 )
Int J Comput Assist Radiol Surg - Automatic subarachnoid space segmentation and hemorrhage detection in clinical head CT scans. ( 0,56951379413897 )
J Biomed Inform - Markov blanket-based approach for learning multi-dimensional Bayesian network classifiers: an application to predict the European Quality of Life-5 Dimensions (EQ-5D) from the 39-item Parkinson's Disease Questionnaire (PDQ-39). ( 0,568395999837555 )
J Biomed Inform - Incremental Gaussian Discriminant Analysis based on Graybill and Deal weighted combination of estimators for brain tumour diagnosis. ( 0,568232550922966 )
Comput Methods Programs Biomed - A novel method for pulmonary embolism detection in CTA images. ( 0,567121696218401 )
Comput Math Methods Med - Differential diagnosis tool for parkinsonian syndrome using multiple structural brain measures. ( 0,565514842826813 )
Artif Intell Med - Suppressed fuzzy-soft learning vector quantization for MRI segmentation. ( 0,563798291848087 )
J Chem Inf Model - Prediction of linear cationic antimicrobial peptides based on characteristics responsible for their interaction with the membranes. ( 0,561405426989964 )
IEEE Trans Image Process - In search of perceptually salient groupings. ( 0,561091320607886 )
Med Biol Eng Comput - Automatic segmentation of the fetal cerebellum on ultrasound volumes, using a 3D statistical shape model. ( 0,558225581391358 )
Int J Comput Assist Radiol Surg - Liver segmentation for contrast-enhanced MR images using partitioned probabilistic model. ( 0,557867443285377 )
J Chem Inf Model - Classification of compounds with distinct or overlapping multi-target activities and diverse molecular mechanisms using emerging chemical patterns. ( 0,555810426093136 )
Int J Comput Assist Radiol Surg - Brain tumor detection and segmentation in a CRF (conditional random fields) framework with pixel-pairwise affinity and superpixel-level features. ( 0,553222831324265 )
Neural Comput - Input statistics and Hebbian cross-talk effects. ( 0,552227315501053 )
IEEE Trans Image Process - Cross-Device Automated Prostate Cancer Localization With Multiparametric MRI. ( 0,551145643691949 )
IEEE Trans Image Process - Overlapping cell nuclei segmentation using a spatially adaptive active physical model. ( 0,550870001942429 )
J Chem Inf Model - Time-split cross-validation as a method for estimating the goodness of prospective prediction. ( 0,550012965033868 )
Comput. Biol. Med. - Automatic recognition of midline shift on brain CT images. ( 0,549505965673881 )
Int J Comput Assist Radiol Surg - Automatic left ventricle segmentation in volumetric SPECT data set by variational level set. ( 0,547705186458256 )
J Biomed Inform - An SVM-based high-quality article classifier for systematic reviews. ( 0,544242064074962 )
Int J Comput Assist Radiol Surg - Extreme leg motion analysis of professional ballet dancers via MRI segmentation of multiple leg postures. ( 0,544133972336064 )
Int J Comput Assist Radiol Surg - MIDG-Emerging grid technologies for multi-site preclinical molecular imaging research communities. ( 0,541822430826567 )
Comput Methods Programs Biomed - Carotid artery image segmentation using modified spatial fuzzy c-means and ensemble clustering. ( 0,541146790580321 )
J Chem Inf Model - Three useful dimensions for domain applicability in QSAR models using random forest. ( 0,539911943449757 )
Comput. Biol. Med. - Automatic brain extraction methods for T1 magnetic resonance images using region labeling and morphological operations. ( 0,539046179925521 )
Comput Methods Programs Biomed - Enhancing classification accuracy utilizing globules and dots features in digital dermoscopy. ( 0,538648185165064 )
Int J Neural Syst - Multichannel decoding for phase-coded SSVEP brain-computer interface. ( 0,538399813405168 )
Comput. Biol. Med. - Nearly automated motion artifacts correction between multi breath-hold short-axis and long-axis cine CMR images. ( 0,538036201684483 )
Int J Comput Assist Radiol Surg - Multi-compartment heart segmentation in CT angiography using a spatially varying gaussian classifier. ( 0,537831895612327 )
Methods Inf Med - ML segmentation strategies for object interference compensation in FDG-PET lesion quantification. ( 0,530596484481929 )
Artif Intell Med - Fuzzy logic-based diagnostic algorithm for implantable cardioverter defibrillators. ( 0,530420664936268 )
Comput Math Methods Med - Development of image segmentation methods for intracranial aneurysms. ( 0,529343825491968 )
IEEE Trans Image Process - An automatic graph-based approach for artery/vein classification in retinal images. ( 0,528612087401904 )
Comput Methods Programs Biomed - Automatic segmentation of human facial tissue by MRI-CT fusion: a feasibility study. ( 0,528458923169777 )
IEEE Trans Pattern Anal Mach Intell - Paired Regions for Shadow Detection and Removal. ( 0,527619897594372 )
Comput. Biol. Med. - A hierarchical model for automatic nuchal translucency detection from ultrasound images. ( 0,526749211329384 )
Comput Methods Programs Biomed - Automated PET-guided liver segmentation from low-contrast CT volumes using probabilistic atlas. ( 0,526263948111098 )
Methods Inf Med - A fast, automatic segmentation algorithm for locating and delineating touching cell boundaries in imaged histopathology. ( 0,525579841970586 )
Comput Math Methods Med - A new multistage medical segmentation method based on superpixel and fuzzy clustering. ( 0,525200890436609 )
Comput. Biol. Med. - Assessing common classification methods for the identification of abnormal repolarization using indicators of T-wave morphology and QT interval. ( 0,524917404460288 )
IEEE Trans Image Process - Towards online iris and periocular recognition under relaxed imaging constraints. ( 0,52454605243683 )
Comput. Biol. Med. - A review on segmentation of positron emission tomography images. ( 0,52247276230613 )
Comput Math Methods Med - Constructing benchmark databases and protocols for medical image analysis: diabetic retinopathy. ( 0,522388786541684 )
Comput. Biol. Med. - Gallbladder shape extraction from ultrasound images using active contour models. ( 0,522252470654351 )
Neural Comput - Divergence-based vector quantization. ( 0,522059871901089 )
J Chem Inf Model - Applicability Domain ANalysis (ADAN): a robust method for assessing the reliability of drug property predictions. ( 0,522018929008607 )
Artif Intell Med - Training artificial neural networks directly on the concordance index for censored data using genetic algorithms. ( 0,52199204584509 )
IEEE J Biomed Health Inform - Segmentation of tumor and edema along with healthy tissues of brain using wavelets and neural networks. ( 0,521595941727298 )
J Med Syst - Computer assisted diagnostic system in tumor radiography. ( 0,521073098018075 )
Comput Methods Programs Biomed - pSnakes: a new radial active contour model and its application in the segmentation of the left ventricle from echocardiographic images. ( 0,520761797178098 )
IEEE Trans Image Process - Subpixel registration with gradient correlation. ( 0,520588189895375 )
IEEE Trans Image Process - Incremental N-mode SVD for large-scale multilinear generative models. ( 0,520002685244961 )
Artif Intell Med - Exploring the knowledge contained in neuroimages: statistical discriminant analysis and automatic segmentation of the most significant changes. ( 0,519099599007997 )
J Chem Inf Model - Three-dimensional structure database of natural metabolites (3DMET): a novel database of curated 3D structures. ( 0,518445244028353 )
Comput Math Methods Med - A region growing vessel segmentation algorithm based on spectrum information. ( 0,518313038175374 )
Int J Comput Assist Radiol Surg - 2D/3D image fusion of X-ray mammograms with breast MRI: visualizing dynamic contrast enhancement in mammograms. ( 0,517852061890075 )
J Am Med Inform Assoc - Three-dimensional morphological and signal intensity features for detection of intervertebral disc degeneration from magnetic resonance images. ( 0,516964159578422 )
Int J Comput Assist Radiol Surg - Automatic lung segmentation method for MRI-based lung perfusion studies of patients with chronic obstructive pulmonary disease. ( 0,516686473467177 )
Comput. Biol. Med. - Lung nodule segmentation and recognition using SVM classifier and active contour modeling: a complete intelligent system. ( 0,516684432342641 )
Comput Methods Programs Biomed - Segmentation and detection of breast cancer in mammograms combining wavelet analysis and genetic algorithm. ( 0,516486269669406 )
Comput. Biol. Med. - Automatic differential diagnosis of pancreatic serous and mucinous cystadenomas based on morphological features. ( 0,514966339625155 )
J Chem Inf Model - Kernel-based partial least squares: application to fingerprint-based QSAR with model visualization. ( 0,513853737939945 )
J Chem Inf Model - In silico prediction of total human plasma clearance. ( 0,5136904136112 )
Comput. Biol. Med. - Automatic detection of lung nodules in CT datasets based on stable 3D mass-spring models. ( 0,513077042779915 )
IEEE Trans Image Process - A Bayesian network model for automatic and interactive image segmentation. ( 0,51218113135031 )
IEEE Trans Image Process - Integrated segmentation and interpolation of sparse data. ( 0,512144699666904 )
Comput Math Methods Med - Ant colony optimization approaches to clustering of lung nodules from CT images. ( 0,511268465944638 )
IEEE Trans Image Process - Active learning for solving the incomplete data problem in facial age classification by the furthest nearest-neighbor criterion. ( 0,511243407430106 )
J Med Syst - A new data preparation method based on clustering algorithms for diagnosis systems of heart and diabetes diseases. ( 0,51120257798122 )
Comput Methods Programs Biomed - A model for diagnosis of pulmonary infections in solid-organ transplant recipients. ( 0,511119803783407 )
J Chem Inf Model - Study of chromatographic retention of natural terpenoids by chemoinformatic tools. ( 0,510957077687782 )
Med Biol Eng Comput - Accelerometry-based prediction of movement dynamics for balance monitoring. ( 0,510241401287722 )
IEEE J Biomed Health Inform - A comparison of US- versus MR-based 3-D Prostate Shapes Using Radial Basis Function Interpolation and Statistical Shape Models. ( 0,510101997414271 )
Comput. Biol. Med. - Myocardial border detection from ventriculograms using support vector machines and real-coded genetic algorithms. ( 0,509344233489662 )
Int J Comput Assist Radiol Surg - Disc herniation diagnosis in MRI using a CAD framework and a two-level classifier. ( 0,508218846102689 )
IEEE Trans Pattern Anal Mach Intell - Online Learning and Sequential Anomaly Detection in Trajectories. ( 0,508040955716879 )