The value of multimodal ultrasonography in differential diagnosis of tuberculous and non-tuberculous superficial lymphadenitis

Background To investigate the value of multimodal ultrasonography in differentiating tuberculosis from other lymphadenopathy. Methods Sixty consecutive patients with superficial lymphadenopathy treated at our hospital from January 2017 to December 2018 were categorized into four types based on the color Doppler ultrasound, five types based on contrast-enhanced ultrasound, and five types based on elastography. Sensitivity and specificity were calculated of all the three imaging, including color Doppler examination, contrast-enhanced ultrasound and one individual multimodal method, for detecting lymph nodes. Results A total of 60 patients were included in the final analysis. Of those, Mycobacterium tuberculosis was positive in 38 patients and negative in 22 patients. Among the 38 patients who were positive for Mycobacterium tuberculosis, of which 23 had a history of pulmonary tuberculosis, accounting for 60.53% of the positive cases, and the remaining patients did not combine lesions of other organs. Among the 60 superficial lymph nodes, 63.3% presented with tuberculous lymphadenitis. The sensitivity, specificity, and accuracy of the color Doppler examination were 73.68%, 68.18%, and 71.67%, respectively. The sensitivity, specificity and accuracy of contrast-enhanced ultrasound were 89.47%, 63.64% and 80.00%, respectively. The sensitivity, specificity and accuracy of the elastography were 63.16%, 63.64% and 63.33%, respectively. The sensitivity, specificity and accuracy of one individual multimodal method were 42.11%, 95.45% and 61.67%, respectively. The sensitivity, specificity and accuracy of all modes combined were 100.00%, 27.27% and 73.33%, respectively. Conclusion Multimodal ultrasonography has high predictive value for the differential diagnosis of superficial tuberculous lymphadenitis.

Violence Recognition Based on Auditory-Visual Fusion of Autoencoder Mapping

In the process of violence recognition, accuracy is reduced due to problems related to time axis misalignment and the semantic deviation of multimedia visual auditory information. Therefore, this paper proposes a method for auditory–visual information fusion based on autoencoder mapping. First, a feature extraction model based on the CNN–LSTM framework is established, and multimedia segments are used as whole input to solve the problem of time axis misalignment of visual and auditory information. Then, a shared semantic subspace is constructed based on an autoencoder mapping model and is optimized by semantic correspondence, which solves the problem of audiovisual semantic deviation and realizes the fusion of visual and auditory information on segment level features. Finally, the whole network is used to identify violence. The experimental results show that the method can make good use of the complementarity between modes. Compared with single-mode information, the multimodal method can achieve better results.

Improving the Performance of Frequently Used Korean Handwritten Character Verification Based on Artificial Intelligence through Multimodal Fusion

Handwriting verification is a biometric recognition field that identifies individuals’ unique characteristics contained in their handwriting. A single written character shows subtle differences depending on habits accumulated over time or the manner of writing. Based on this, it is often adopted in forensic investigations and as evidence in court. Existing handwriting verification is conducted by an expert, and is affected by the expert’s ability or subjectivity, causing different results to arise depending on the expert. Therefore, we propose a handwriting verification method that excludes human subjectivity and has objectivity. Using computer vision and artificial intelligence (AI), we derived results that excluded human subjectivity, and the judgment strength was expressed through a likelihood ratio. To improve the existing method’s accuracy, we performed a more accurate verification through multimodal use from the biometric field. Multimodal handwriting verification is conducted using up to four characters (not just one) because individual handwriting in each character is different. For learning, n-fold tests were conducted to maintain test objectivity, and the average performance of single character-based verification was 80.14% and the multimodal method averaged 88.96%. Here, we proposed the objectivity of handwriting verification through learning using AI, and show that performance improved through multimodal fusion.

Stories of Hope and Resilience: A Multimodal Project

This multimodal project, influenced by an Appreciative Inquiry framework, aimed to elicit stories of hope and resilience amidst the Covid-19 pandemic. Thematic analysis was employed to analyse twenty collected stories. A multimodal method that combined linguistic and visual language (non-fiction comics) was adopted in order to present the research findings. In Elli’s case, as with other participants, engaging with customs and rituals turned out to be an important source of hope, joy and resilience.