3D visualization diagnosis for pulmonary nodule detection and segmentation is becoming a promising topic in the field of surgical researches and applications. Aiming at assisting radiologists to diagnose pulmonary nodules more accurately, the methods of detection and segmentation for pulmonary nodule 3D visualization diagnosis were proposed based on Mask Region-Convolutional Neural Network (Mask R-CNN) and ray-casting volume rendering algorithm. The Mask R-CNN used resnet50 as the backbone and applied Feature Pyramid Network (FPN) to fully explore multiscale feature maps. And then, Region Proposal Network (RPN) was used to propose candidate bounding boxes. Furthermore, the mask matrices and the raw medical image sequences were multiplied to obtain sequences of predicted pulmonary nodules. Finally, ray-casting volume rendering algorithm was applied to generate the 3D models of pulmonary nodules. The proposed methods are tested and evaluated on publicly available LUNA16 dataset and the independent dataset from Ali TianChi challenge. Experimental results show that Mask R-CNN of weighted loss reaches sensitivities of 88.1% and 88.7% at 1 and 4 false positives per scan, respectively. Meanwhile, we can obtain AP@50 score of 0.882 using Mask R-CNN with weighted loss on labelme_LUNA16 dataset, which outperforms many existing state-of-the-art approaches of detection and segmentation of pulmonary nodules.

Medical Visual Question Answering (VQA-Med) is a challenging task that involves answering clinical questions related to medical images. However, most current VQA-Med methods ignore the causal correlation between specific lesion or abnormality features and answers, while also failing to provide accurate explanations for their decisions. To explore the interpretability of VQA-Med, this paper proposes a novel CCIS-MVQA model for VQA-Med based on a counterfactual causal-effect intervention strategy. This model consists of the modified ResNet for image feature extraction, a GloVe decoder for question feature extraction, a bilinear attention network for vision and language feature fusion, and an interpretability generator for producing the interpretability and prediction results. The proposed CCIS-MVQA introduces a layer-wise relevance propagation method to automatically generate counterfactual samples. Additionally, CCIS-MVQA applies counterfactual causal reasoning throughout the training phase to enhance interpretability and generalization. Extensive experiments on three benchmark datasets show that the proposed CCIS-MVQA model outperforms the state-of-the-art methods. Enough visualization results are produced to analyze the interpretability and performance of CCIS-MVQA.

With the rapid development in social media, single‐modal emotion recognition is hard to satisfy the demands of the current emotional recognition system. Aiming to optimize the performance of the emotional recognition system, a multimodal emotion recognition model from speech and text was proposed in this paper. Considering the complementarity between different modes, CNN (convolutional neural network) and LSTM (long short‐term memory) were combined in a form of binary channels to learn acoustic emotion features; meanwhile, an effective Bi‐LSTM (bidirectional long short‐term memory) network was resorted to capture the textual features. Furthermore, we applied a deep neural network to learn and classify the fusion features. The final emotional state was determined by the output of both speech and text emotion analysis. Finally, the multimodal fusion experiments were carried out to validate the proposed model on the IEMOCAP database. In comparison with the single modal, the overall recognition accuracy of text increased 6.70%, and that of speech emotion recognition soared 13.85%. Experimental results show that the recognition accuracy of our multimodal is higher than that of the single modal and outperforms other published multimodal models on the test datasets.

Deep learning is the crucial technology in intelligent question answering research tasks. Nowadays, extensive studies on question answering have been conducted by adopting the methods of deep learning. The challenge is that it not only requires an effective semantic understanding model to generate a textual representation but also needs the consideration of semantic interaction between questions and answers simultaneously. In this paper, we propose a stacked Bidirectional Long Short-Term Memory (BiLSTM) neural network based on the coattention mechanism to extract the interaction between questions and answers, combining cosine similarity and Euclidean distance to score the question and answer sentences. Experiments are tested and evaluated on publicly available Text REtrieval Conference (TREC) 8-13 dataset and Wiki-QA dataset. Experimental results confirm that the proposed model is efficient and particularly it achieves a higher mean average precision (MAR) of 0.7613 and mean reciprocal rank (MRR) of 0.8401 on the TREC dataset.

To naturally interact with virtual environment by hand gesture, this paper presents a robust RGB-D data based recognition method of static and dynamic hand gesture. Firstly, for static hand gesture recognition, starting from the hand gesture contour extraction, the palm center is identified by Distance Transform (DT) algorithm. The fingertips are localized by employing the K-Curvature-Convex Defects Detection algorithm (K-CCD). On the basis, the distances of the pixels on hand gesture contour to palm center and the angle between fingertips are considered as the auxiliary features to construct a multimodal feature vector, and then recognition algorithm is presented to robustly recognize the static hand gestures. Secondly, combining Euclidean distance between hand joints and shoulder center joint with the modulus ratios of skeleton features, this paper generates a unifying feature descriptor for each dynamic hand gesture and proposes an improved dynamic time warping (IDTW) algorithm to obtain recognition results of dynamic hand gestures. Finally, we conduct extensive experiments to test and verify the static and dynamic hand gesture recognition algorithm and realize a low-cost real-time application of natural interaction with virtual environment by hand gestures.