Abstract: In this work we present the iterative multi-class multi-scale stacked sequential learning framework (IMMSSL), a novel learning scheme that is particularly suited for medical volume segmentation applications. This model exploits the inherent voxel contextual information of the structures of interest in order to improve its segmentation performance results. Without any feature set or learning algorithm prior assumption, the proposed scheme directly seeks to learn the contextual properties of a region from the predicted classifications of previous classifiers within an iterative scheme. Performance results regarding segmentation accuracy in three two-class and multi-class medical volume datasets show a significant improvement with respect to state of the art alternatives. Due to its easiness of implementation and its independence of feature space and learning algorithm, the presented machine learning framework could be taken into consideration as a first choice in complex volume segmentation scenarios.

Abstract: We present EgoACO, a deep neural architecture for video action recognition that learns to pool action-context-object descriptors from frame level features by leveraging the verb-noun structure of action labels in egocentric video datasets. The core component of EgoACO is class activation pooling (CAP), a differentiable pooling operation that combines ideas from bilinear pooling for fine-grained recognition and from feature learning for discriminative localization. CAP uses self-attention with a dictionary of learnable weights to pool from the most relevant feature regions. Through CAP, EgoACO learns to decode object and scene context descriptors from video frame features. For temporal modeling in EgoACO, we design a recurrent version of class activation pooling termed Long Short-Term Attention (LSTA). LSTA extends convolutional gated LSTM with built-in spatial attention and a re-designed output gate. Action, object and context descriptors are fused by a multi-head prediction that accounts for the inter-dependencies between noun-verb-action structured labels in egocentric video datasets. EgoACO features built-in visual explanations, helping learning and interpretation. Results on the two largest egocentric action recognition datasets currently available, EPIC-KITCHENS and EGTEA, show that by explicitly decoding action-context-object descriptors, EgoACO achieves state-of-the-art recognition performance.

Abstract: In this work we present a comprehensive computational framework to help in the clinical assessment of cancer response from a pair of time consecutive oncological PET-CT scans. In this scenario, the design and implementation of a supervised machine learning system to predict and quantify cancer progression or response conditions by introducing a novel feature set that models the underlying clinical context is described. Performance results in 100 clinical cases (corresponding to 200 whole body PET-CT scans) in comparing expert-based visual analysis and classifier decision making show up to 70% accuracy within a completely automatic pipeline and 90% accuracy when providing the system with expert-guided PET tumor segmentation masks.