RESUMO
OBJECTIVES: To examine the feasibility, reliability, granularity, and convergent validity of a video-based pairwise comparison technique that uses algorithmic support to enable automated rating of motor dysfunction in patients with multiple sclerosis (MS). DESIGN: Feasibility and larger cross-sectional cohort study. SETTING: The outpatient clinic of 2 specialist university medical centers. PARTICIPANTS: Selected sample from a cohort of patients with MS participating in the Assess MS study (N=42). Videos were randomly drawn from each strata of the ataxia severity-degrees as defined in the Expanded Disability Status Scale (EDSS). In Basel: 19 videos of 17 patients (mean age, 43.4±11.6y; 10 women). In Amsterdam: 50 videos of 25 patients (mean age, 50.0±10.0y; 15 women). INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: In each center, neurologists (n=13; n=10) viewed pairs of videos of patients performing standardized movements (eg, finger-to-nose test) to assess relative performance. A comparative assessment score was calculated for each video using the TrueSkill algorithm and analyzed for intrarater (test-retest; ratio of agreement) and interrater reliability (intraclass correlation coefficient [ICC] for absolute agreement) and convergent validity (Spearman ρ). Granularity was estimated from the average difference in comparative assessment scores at which 80% of neurologists considered performance to be different. RESULTS: Intrarater reliability was excellent (median ratio of agreement≥0.87). The comparative assessment scores calculated from individual neurologists demonstrated good-excellent ICCs for interrater reliability (0.89; 0.71). The comparative assessment scores correlated (very) highly with their Neurostatus-EDSS equivalent (ρ=0.78, P<.001; ρ=0.91, P<.05), suggesting a more fine-grained rating. CONCLUSIONS: Video-based pairwise comparison of motor dysfunction allows for reliable and fine-grained capturing of clinical judgment about neurologic performance, which can contribute to the development of a consistent quantified metric of motor ability in MS.
Assuntos
Avaliação da Deficiência , Esclerose Múltipla/fisiopatologia , Modalidades de Fisioterapia/normas , Centros Médicos Acadêmicos , Adulto , Algoritmos , Estudos Transversais , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Variações Dependentes do Observador , Reprodutibilidade dos Testes , Índice de Gravidade de Doença , Gravação de VideoteipeRESUMO
In this paper we introduce a method for multi-class, monocular 3D object detection from a single RGB image, which exploits a novel disentangling transformation and a novel, self-supervised confidence estimation method for predicted 3D bounding boxes. The proposed disentangling transformation isolates the contribution made by different groups of parameters to a given loss, without changing its nature. This brings two advantages: i) it simplifies the training dynamics in the presence of losses with complex interactions of parameters; and ii) it allows us to avoid the issue of balancing independent regression terms. We further apply this disentangling transformation to another novel, signed Intersection-over-Union criterion-driven loss for improving 2D detection results. We also critically review the AP metric used in KITTI3D and resolve a flaw which affected and biased all previously published results on monocular 3D detection. Our improved metric is now used as official KITTI3D metric. We provide extensive experimental evaluations and ablation studies on the KITTI3D and nuScenes datasets, setting new state-of-the-art results. We provide additional results on all the classes of KITTI3D as well as nuScenes datasets to further validate the robustness of our method, demonstrating its ability to generalize for different types of objects.
Assuntos
AlgoritmosRESUMO
Purpose: Clinical ordinal rating scales of movements, e.g., the Expanded Disability Status Scale, have poor intra- and interrater reliability, are insensitive to subtle differences and result in coarse-grained ratings compared to relative comparative rating methods. We therefore established video-based setwise comparison as a fine-grained, reliable and efficient rating method of motor dysfunction using algorithmic support.Materials and methods: Eight neurologists rated a set of 40 multiple sclerosis patient videos of the Finger-to-Nose-Test using both the newly developed setwise comparison and the established pairwise comparison techniques, which result in a continuous rating scale. Reliability was assessed by the intra-class correlation coefficient. Construct validity was estimated as Pearson's correlation between the continuous scale and severity ratings according to the Neurostatus scale for upper-extremity tremor/dysmetria and the Nine-hole-peg-test. Comparing the time needed for ratings assessed efficiency.Results: Intra-class correlation coefficient was 0.83 for setwise and 0.7 for pairwise comparison. Correlation to the tremor/dysmetria score of the Neurostatus was 0.86 for both rating procedures and correlation to the Nine-hole-peg-test was 0.64 (setwise) and 0.66 (pairwise). The time needed to rate 40 videos was 22.9 ± 6.9 minutes (setwise) and 77.8 ± 14.5 minutes (pairwise).Conclusions: Setwise comparison is an efficient, valid and reliable method for fine-grained rating of motor dysfunction that can be applied to larger datasets. It is substantially more efficient than pairwise comparison.Implications for rehabilitationDisability rating is crucial in clinical neurorehabilitation and in clinical trials.Humans are naturally inconsistent in rating items on ordinal scales leading to poor intra- and interrater reliability, insensitivity to subtle differences and coarse-grained ratings.Video-based setwise comparison is a new rating method enabling fine-grained, reliable and efficient ratings of motor dysfunction using algorithmic support.
Assuntos
Esclerose Múltipla , Humanos , Movimento , Estudo de Prova de Conceito , Reprodutibilidade dos TestesRESUMO
BACKGROUND: Sensor-based recordings of human movements are becoming increasingly important for the assessment of motor symptoms in neurological disorders beyond rehabilitative purposes. ASSESS MS is a movement recording and analysis system being developed to automate the classification of motor dysfunction in patients with multiple sclerosis (MS) using depth-sensing computer vision. It aims to provide a more consistent and finer-grained measurement of motor dysfunction than currently possible. OBJECTIVE: To test the usability and acceptability of ASSESS MS with health professionals and patients with MS. METHODS: A prospective, mixed-methods study was carried out at 3 centers. After a 1-hour training session, a convenience sample of 12 health professionals (6 neurologists and 6 nurses) used ASSESS MS to capture recordings of standardized movements performed by 51 volunteer patients. Metrics for effectiveness, efficiency, and acceptability were defined and used to analyze data captured by ASSESS MS, video recordings of each examination, feedback questionnaires, and follow-up interviews. RESULTS: All health professionals were able to complete recordings using ASSESS MS, achieving high levels of standardization on 3 of 4 metrics (movement performance, lateral positioning, and clear camera view but not distance positioning). Results were unaffected by patients' level of physical or cognitive disability. ASSESS MS was perceived as easy to use by both patients and health professionals with high scores on the Likert-scale questions and positive interview commentary. ASSESS MS was highly acceptable to patients on all dimensions considered, including attitudes to future use, interaction (with health professionals), and overall perceptions of ASSESS MS. Health professionals also accepted ASSESS MS, but with greater ambivalence arising from the need to alter patient interaction styles. There was little variation in results across participating centers, and no differences between neurologists and nurses. CONCLUSIONS: In typical clinical settings, ASSESS MS is usable and acceptable to both patients and health professionals, generating data of a quality suitable for clinical analysis. An iterative design process appears to have been successful in accounting for factors that permit ASSESS MS to be used by a range of health professionals in new settings with minimal training. The study shows the potential of shifting ubiquitous sensing technologies from research into the clinic through a design approach that gives appropriate attention to the clinic environment.
RESUMO
Ensembles of randomized decision trees, known as Random Forests, have become a valuable machine learning tool for addressing many computer vision problems. Despite their popularity, few works have tried to exploit contextual and structural information in random forests in order to improve their performance. In this paper, we propose a simple and effective way to integrate contextual information in random forests, which is typically reflected in the structured output space of complex problems like semantic image labelling. Our paper has several contributions: We show how random forests can be augmented with structured label information and be used to deliver structured low-level predictions. The learning task is carried out by employing a novel split function evaluation criterion that exploits the joint distribution observed in the structured label space. This allows the forest to learn typical label transitions between object classes and avoid locally implausible label configurations. We provide two approaches for integrating the structured output predictions obtained at a local level from the forest into a concise, global, semantic labelling. We integrate our new ideas also in the Hough-forest framework with the view of exploiting contextual information at the classification level to improve the performance on the task of object detection. Finally, we provide experimental evidence for the effectiveness of our approach on different tasks: Semantic image labelling on the challenging MSRCv2 and CamVid databases, reconstruction of occluded handwritten Chinese characters on the Kaist database and pedestrian detection on the TU Darmstadt databases.
RESUMO
This paper presents new learning-based techniques for measuring disease progression in Multiple Sclerosis (MS) patients. Our system aims to augment conventional neurological examinations by adding quantitative evidence of disease progression. An off-the-shelf depth camera is used to image the patient at the examination, during which he/she is asked to perform carefully selected movements. Our algorithms then automatically analyze the videos, assessing the quality of each movement and classifying them as healthy or non-healthy. Our contribution is three-fold: We i) introduce ensembles of randomized SVM classifiers and compare them with decision forests on the task of depth video classification; ii) demonstrate automatic selection of discriminative landmarks in the depth videos, showing their clinical relevance; iii) validate our classification algorithms quantitatively on a new dataset of 1041 videos of both MS patients and healthy volunteers. We achieve average Dice scores well in excess of the 80% mark, confirming the validity of our approach in practical applications. Our results suggest that this technique could be fruitful for depth-camera supported clinical assessments for a range of conditions.