Background: Hematological malignancies of the heart (CHMs) are extremely rare, and include leukemia, lymphoma infiltration, and multiple myeloma with extramedullary manifestations. Cardiac lymphoma can be divided into primary cardiac lymphoma (PCL) and secondary cardiac lymphoma (SCL). Compared to PCL, SCL is relatively more common. Histologically, the most frequent SCL is diffuse large B-cell lymphoma (DLBCL). The prognosis of lymphoma in patients with cardiac involvement is extremely poor. CAR T-cell immunotherapy has been recently become a highly effective treatment for relapsed or refractory diffuse large B-cell lymphoma. To date, there are no guidelines that provide a clear consensus on the management of patients with secondary heart or pericardial involvement. We report a case of relapsed/refractory DLBCL that secondarily affected the heart.Case presentation: A male patient was diagnosed with double-expressor DLBCL based on biopsies of mediastinal and peripancreatic masses and fluorescence in situ hybridization. The patient received first-line chemotherapy and anti-CD19 CAR T cell immunotherapy, but developed heart metastases after 12 months. Considering his physical condition and economic situation of the patient, two cycles of multiline chemotherapies were administered, followed by CAR-NK cell immunotherapy and allogeneic hematopoietic stem cell transplantation (allo-HSCT) at another hospital. After achieving a six-month survival, the patient died of severe pneumonia.Conclusion: The response of our patient emphasizes the importance of early diagnosis and timely treatment to improve the prognosis of SCL and serves as an important reference for SCL treatment strategies.
In order to solve the challenges brought by multi-source and cross-domain scenarios to online music education, this paper designs an online music education system based on advanced artificial intelligence technology, which can provide personalized learning course resource recommendations for music online learners. The system includes four layers, consisting of user interface layer, application module layer, function module layer and data storage layer. At the application module level, this paper proposes a music recommendation algorithm based on a personalized multimodal network model. The recommendation algorithm performs music information retrieval (MIR) based on the similarity judgment of the contour of music pitch and the overall change, and constructs a multimodal network model based on the user’s preference for resources to achieve personalized music recommendation. This paper crawls more than one million music score data from a well-known music platform database in China to establish a dataset to evaluate the performance of this method. The comparison results with three existing works show that the method proposed in this paper has good performance and can provide users with suitable music recommendations. The artificial intelligence technology-driven online music education mechanism proposed in this paper has good prospects.
Guzheng tune progression involves intricately harmonizing melodic motif transitions. Effectively navigating this vast creative possibility space to expose musically consistent elaborations presents challenges. We develop a specialized large long short-term memory (LSTM) model for generating musically consistent Guzheng tune transitions. First, we propose novel firefly algorithm (FA) enhancements, e.g., adaptive diversity preservation and adaptive swim parameters, to boost exploration effectiveness for navigating the vast creative combinatorics when generating Guzheng tune transitions. Then, we develop a specialized stacked LSTM architecture incorporating residual connections and conditioned embedding vectors that can leverage long-range temporal dependencies in Guzheng music patterns, including unsupervised learning of concise Guzheng-specific melody embedding vectors via a variational autoencoder, encapsulating unique harmonic signatures from performance descriptors to provide style guidance. Finally, we use LSTM networks to develop adversarial generative large models that enable realistic synthesis and evaluation of Guzheng tunes switching. We gather an extensive 10+ hour corpus of solo Guzheng recordings spanning 230 musical pieces, 130 distinguished performing artists, and 600+ audio tracks. Simultaneously, we conduct thorough Guzheng data analysis. Comparative assessments against strong baselines over systematic musical metrics and professional listeners validate significant generation fidelity improvements. Our model achieves a 63 % reduction in reconstruction error compared to the standard FA optimization after 1000 iterations. It also outperforms baselines in capturing characteristic motifs, maintaining modality coherence with under 2 % dissonant pitch errors, and retaining desired rhythmic cadences. User studies further confirm the superior naturalness, novelty, and stylistic faithfulness of the generated tune transitions, with ratings close to real data.
Chinese contemporary music has made tremendous progress in the twentieth century. After entering the twentieth century, with the rise of pop music, Chinese contemporary music has gradually been forgotten by people. Apparently, Chinese contemporary music has a long history and covers huge varieties. Nevertheless, the diffusion of Chinese contemporary music is restricted by many factors. The fundamental reason is that people’s cognition of Chinese contemporary music has changed. However, the rise of social networks provides a new opportunity for the diffusion of Chinese contemporary music. By searching nodes with high influence in social networks, where the node is enabled by the sensor, we transform the problem for maximizing public opinion into a process of searching nodes set of maximum influence, thus providing power for the diffusion of Chinese contemporary music. In this paper, from the perspective of percolation, the network connectivity changes caused by node failure are considered, and the set selection problems of high-influence individuals are mapped to the optimal percolation problem when the network has a percolation transition. Then an influence maximization algorithm is proposed based on the network percolation process, and the efficiency of the proposed algorithm is optimized. Through experiments, we can infer the reasonable range of maximum searching times for the influence maximization algorithm. Meanwhile, compared with other baselines, the searching time of the algorithm proposed in this paper is also the least. The experimental results reveal that the proposed algorithm is feasible to diffuse Chinese contemporary music and maximize its public opinion and has a strong impetus for the revival of Chinese contemporary music.