RESUMO
OBJECTIVES: The relationship between radiographic evidence of osteoarthritis and knee pain has been weak. This may be because features that best discriminate knees with pain have not been included in analyses. We tested the correlation between knee pain and radiographic features taking into account both image analysis features and manual scores. METHODS: Using data of the Multicentre Osteoarthritis Study, we tested in a cross-sectional design how well X-ray features discriminated those with frequent knee pain (one question at one time) or consistent frequent knee pain (three questions at three times during the 2 weeks prior to imaging) from those without it. We trained random forest models on features from two radiographic views for classification. RESULTS: X-rays were better at classifying those with pain using three questions compared with one. When we used all manual radiographic features, the area under the curve (AUC) was 73.9%. Using the best model from automated image analyses or a combination of these and manual grades, no improvement over manual grading was found. CONCLUSIONS: X-ray changes of OA are more strongly associated with repeated reports of knee pain than pain reported once. In addition, a fully automated system that assessed features not scored on X-ray performed no better than manual grading of features.
Assuntos
Articulação do Joelho/diagnóstico por imagem , Osteoartrite do Joelho/diagnóstico por imagem , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Idoso , Estudos Transversais , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Dor/diagnóstico por imagem , Medição da Dor/métodos , Radiografia , Reprodutibilidade dos Testes , Índice de Gravidade de DoençaRESUMO
Designing activity detection systems that can be successfully deployed in daily-living environments requires datasets that pose the challenges typical of real-world scenarios. In this paper, we introduce a new untrimmed daily-living dataset that features several real-world challenges: Toyota Smarthome Untrimmed (TSU). TSU contains a wide variety of activities performed in a spontaneous manner. The dataset contains dense annotations including elementary, composite activities and activities involving interactions with objects. We provide an analysis of the real-world challenges featured by our dataset, highlighting the open issues for detection algorithms. We show that current state-of-the-art methods fail to achieve satisfactory performance on the TSU dataset. Therefore, we propose a new baseline method for activity detection to tackle the novel challenges provided by our dataset. This method leverages one modality (i.e. optic flow) to generate the attention weights to guide another modality (i.e RGB) to better detect the activity boundaries. This is particularly beneficial to detect activities characterized by high temporal variance. We show that the method we propose outperforms state-of-the-art methods on TSU and on another popular challenging dataset, Charades.
RESUMO
Action segmentation is the task of predicting the actions for each frame of a video. As obtaining the full annotation of videos for action segmentation is expensive, weakly supervised approaches that can learn only from transcripts are appealing. In this paper, we propose a novel end-to-end approach for weakly supervised action segmentation based on a two-branch neural network. The two branches of our network predict two redundant but different representations for action segmentation and we propose a novel mutual consistency (MuCon) loss that enforces the consistency of the two redundant representations. Using the MuCon loss together with a loss for transcript prediction, our proposed approach achieves the accuracy of state-of-the-art approaches while being 14 times faster to train and 20 times faster during inference. The MuCon loss proves beneficial even in the fully supervised setting.
Assuntos
Algoritmos , Aprendizado de Máquina Supervisionado , Redes Neurais de ComputaçãoRESUMO
Here, we tested the feasibility of predicting CAP with multi-spectral EIT. Conductivity and CAP were acquired from nonalcoholic fatty liver disease patients using a portable EIT system and vibration-controlled transient elastography (VCTE). We then used frequency-difference conductivity and waist-over-height as prediction features to estimate CAP and found an adj. R2 of 0.92. We further developed a novel prediction method by incorporating EIT spectral unmixing reconstruction and demonstrated an improvement in CAP estimation. Last, we optimized the EIT acquisition process by minimizing the total variance of the CAP estimator. Clinical Relevance: EIT can estimate clinical-standard liver disease classification. This portable EIT system is potentially cost-effective and self-administrable with short acquisition time (3 mins), while VCTE are costly and usually requires a trained personnel to operate with longer acquisition time (5-10 mins).