1 February 2017 in Medical Image Analysis
20 May 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
This work presents a novel method of exploring human brain-visual representations, with a view towards replicating these processes in machines. The core idea is to learn plausible computational and biological representations by correlating human neural activity and natural images. Thus, we first propose a model, EEG-ChannelNet , to learn a brain manifold for EEG classification. After verifying that visual information can be extracted from EEG data, we introduce a multimodal approach that uses deep image and EEG encoders, trained in a siamese configuration, for learning a joint manifold that maximizes a compatibility measure between visual features and brain representations. We then carry out image classification and saliency detection on the learned manifold. Performance analyses show that our approach satisfactorily decodes visual information from neural signals. This, in turn, can be used to effectively supervise the training of deep learning models, as demonstrated by the high performance of image classification and saliency detection on out-of-training classes. The obtained results show that the learned brain-visual features lead to improved performance and simultaneously bring deep models more in line with cognitive neuroscience work related to visual perception and attention.
1 January 2008 in The Angle Orthodontist
Objective: To describe the techniques used for automatic landmarking of cephalograms, highlighting the strengths and weaknesses of each one and reviewing the percentage of success in locating each cephalometric point. Materials and Methods: The literature survey was performed by searching the Medline, the Institute of Electrical and Electronics Engineers, and the ISI Web of Science Citation Index databases. The survey covered the period from January 1966 to August 2006. Abstracts that appeared to fulfill the initial selection criteria were selected by consensus. The original articles were then retrieved. Their references were also hand-searched for possible missing articles. The search strategy resulted in 118 articles of which eight met the inclusion criteria. Many articles were rejected for different reasons; among these, the most frequent was that results of accuracy for automatic landmark recognition were presented as a percentage of success. Results: A marked difference in results was found between the included studies consisting of heterogeneity in the performance of techniques to detect the same landmark. All in all, hybrid approaches detected cephalometric points with a higher accuracy in contrast to the results for the same points obtained by the model-based, image filtering plus knowledge-based landmark search and “soft-computing” approaches. Conclusions: The systems described in the literature are not accurate enough to allow their use for clinical purposes. Errors in landmark detection were greater than those expected with manual tracing and, therefore, the scientific evidence supporting the use of automatic landmarking is low.
30 August 2010 in IEEE Transactions on Instrumentation and Measurement
This paper presents an automatic system for bone age evaluation according to the clinical method of Tanner and Whitehouse (TW2), based on the integration between two systems: The first processes the finger's bones [epiphysis/metaphysis region of interest (EMROI)], whereas the second one processes the wrist bones [carpal region of interest (CROI)]. The system ensures an accurate bone age assessment for age ranges of 0-10 years for males and 0-7 years for females. For both approaches, novel segmentation techniques are proposed. In detail, for CROI analysis, bone extraction is carried out by integrating anatomical knowledge of the hand and trigonometric concepts, whereas a TW2-stage assignment is achieved by combining the gradient vector flow Snakes and the derivative difference of Gaussian filter. One of the main difficulties for bone age assessment based on carpal bones is that trapezium and trapezoid, which are among the biggest bones in the wrist, are often fused even in very young patients. This problem is overtaken by a very effective algorithm that checks the compactness of the identified bones and separates them by using a curvature function. For EMROI analysis, image-processing techniques and geometrical feature analysis, based on the difference of Gaussian, are proposed. The system is evaluated on a set of 106 X-rays, reaching performances of about 90% success rate in bone stage assignment. The system is very reliable and outperforms other effective methods. Moreover, the mean error rate is about 0.46±0.37 years, which is comparable with clinicians' reliability, for whom the error has been estimated to be 0.33±0.6 years.