Recent studies have introduced attention models for medical visual question answering (MVQA). In medical research, not only is the modeling of “visual attention” crucial, but the modeling of “question attention” is equally significant. To facilitate bidirectional reasoning in the attention processes involving medical images and questions, a new MVQA architecture, named MCAN, has been proposed. This architecture incorporated a cross-modal co-attention network, FCAF, which identifies key words in questions and principal parts in images. Through a meta-learning channel attention module (MLCA), weights were adaptively assigned to each word and region, reflecting the model’s focus on specific words and regions during reasoning. Additionally, this study specially designed and developed a medical domain-specific word embedding model, Med-GloVe, to further enhance the model’s accuracy and practical value. Experimental results indicated that MCAN proposed in this study improved the accuracy by 7.7% on free-form questions in the Path-VQA dataset, and by 4.4% on closed-form questions in the VQA-RAD dataset, which effectively improves the accuracy of the medical vision question answer.
Objective To analyze the hotspots and development trends in the research field of tumor cell apoptosis and autophagy. Methods Relevant literature on tumor apoptosis and autophagy published between January 2012 and December 2021 were searched through the Web of Science core collection database, and CiteSpace 5.8.R3 software and VOSviewer version 1.6.10 software were used to analyze the country/region, institution, keywords and citation node information of the literature. Results A total of 6716 foreign-language articles were included in the study after searching and screening, and the number of papers showed a linear upward trend year by year. China published the largest number of articles and cooperated closely with other research institutions, but there were not many high-quality and influential articles. The two journals Autophagy and Cell were more authoritative in the field of tumor apoptosis and autophagy research. The signaling pathways and related proteins of apoptosis and autophagy, and the study of tumor suppressor mechanisms based on apoptosis/autophagy were current research hot topics. The migration, apoptosis and epithelial mesenchymal transformation of cancer cells would be the research focus and direction in the future. Conclusions In the past 10 years, the research on tumor apoptosis and autophagy has continued to develop. With the in-depth research on the molecular level, the study of its mechanism is expected to further reveal the mystery of tumor apoptosis and autophagy.
Objective To investigate the characteristics of multifocal visual evoked potential (mf-VEP) in healthy individuals, and provide normal reference values for its clinical application. Methods The mf-VEP of 37 healthy individuals (70 eyes) were examined by VERIS ScienceTM4.0. The visual stimulus was adart board with patterns consisted of 60 patches spanning a 25°visual field. The length of m-sequence was 214-1. The results were recorded by bipolar occipital straddle. The signal was amplified 100 K and was put through a band-pass filter between 3 and 100 Hz. The first slice of the second order kernel was analyzed by VERIS software. The summed responses of fields with different stimulus were a nalyzed and compared according to different ages, genders and eyes.Results The latencies and response densities of amplitude had statistically significant differences both in dimidiate and quartered field（Plt;0.05）. The latencies in ≥50 year group were much more delayed in some sectors of the visual field than those in lt; 50 year group（Plt;0.05）. The latencies of women were shorter than those of men（Plt;0.05）. There was no obvious difference of latencies and response densities of amplitude in each field sectors between both eyes（Pgt;0.05）. Conclusions The mf-VEP of healthy individuals can reflect the VEP at different field ocations objectively with its specific physiological characteristics, which may provide normal reference values for its clinical application.(Chin J Ocul Fundus Dis，2003，19：269-332)
ObjectiveTo explore the application value of multidisciplinary collaborative team (MDT) model in retroperitoneal tumors involving large vessels.MethodsThree cases of retroperitoneal tumors involving great vessels admitted to Xiang’an Hospital of Xiamen University in 2019 were retrospectively analyzed. With the support of 3D visual reconstruction and virtual reality (VR) technology, we performed MDT discussion and three cases received treatment of surgery, intervention, and targeted therapy.ResultsCase 1 was discussed by MDT and concluded that, based on CT examination, 3D reconstruction, and VR virtual image results, the tumor on the right side was determined to be completely resectable. The left tumor was judged to be unresectable, and the proposed treatment plan was right metastatic tumor resection + left metastatic tumor radiofrequency ablation. After surgery case 1 had been followed up for 6 months. The symptoms of diarrhea were significantly improved. CT reexamination showed that liver lesions and left retroperitoneal lesions were the same size and the condition was stable. After discussion by MDT, radiofrequency ablation around the tumor was proposed for case 2. This case was followed up for 3 months after surgery, and CT reexamination showed no new lesion in retroperitoneum. After MDT discussion, we concluded that arteriovenous fistula of case 3 had no indications for surgery, and proposed interventional combined with targeted therapy. After treatment, the tumor was found to be smaller after reexamination in 8 months than before treatment, and the efficacy was evaluated as partial remission. The follow-up was continued.ConclusionThe future development trend of retroperitoneal tumor therapy involving great vessels is to evaluate each patient’s condition under the MDT mode by using 3D visual reconstruction and VR technology, and to formulate the individualized treatment plan of operation combined with other treatments.
Attention can concentrate our mental resources on processing certain interesting objects, which is an important mental behavior and cognitive process. Recognizing attentional states have great significance in improving human’s performance and reducing errors. However, it still lacks a direct and standardized way to monitor a person’s attentional states. Based on the fact that visual attention can modulate the steady-state visual evoked potential (SSVEP), we designed a go/no-go experimental paradigm with 10 Hz steady state visual stimulation in background to investigate the separability of SSVEP features modulated by different visual attentional states. The experiment recorded the EEG signals of 15 postgraduate volunteers under high and low visual attentional states. High and low visual attentional states are determined by behavioral responses. We analyzed the differences of SSVEP signals between the high and low attentional levels, and applied classification algorithms to recognize such differences. Results showed that the discriminant canonical pattern matching (DCPM) algorithm performed better compared with the linear discrimination analysis (LDA) algorithm and the canonical correlation analysis (CCA) algorithm, which achieved up to 76% in accuracy. Our results show that the SSVEP features modulated by different visual attentional states are separable, which provides a new way to monitor visual attentional states.
ObjectiveTo compare the clinical efficacy between right visual double lumen tube (VDLT) intubation and right common double lumen tube (DLT) intubation in lung isolation technique. MethodsA total of 57 patients undergoing thoracoscopic surgery with right DLT lung isolation technique in the First People's Hospital of Chenzhou City and West China Hospital from June 2020 to June 2021 were randomly divided into two groups: a DLT group (n=29, 16 males and 13 females, with a mean age of 54.3±13.2 years) and a VDLT group (n=28, 18 males and 10 females, with a mean age of 55.1±13.7 years) at 1 : 1 with random number table generated by the computer. The clinical data of the two groups were compared. ResultsCompared with the DLT group, the catheter positioning time in the VDLT group was statistically shorter (74.9±47.5 s vs. 151.6±88.9 s, P<0.001), the right upper lung occlusion rate (21.4% vs. 51.7%) and the intraoperative re-adjustment catheterization rate (14.3% vs. 48.3%) were lower (P<0.05). The quality of lung collapses immediately after thoracotomy (67.9% vs. 24.1%) and 20 minutes after thoracotomy (100.0% vs. 75.9%) were improved (P<0.05). There was no significant difference in the rate of fiberoptic bronchoscope assistance for positioning, or the incidence of pharynx pain and hoarseness between the two groups (P>0.05). ConclusionCompared with common DLT, VDLT is more efficient, accurate and intuitive in the location of right bronchial intubation.
Objective To observe the functional state of the optic nerve and discover the injury of visual pathway function in time under general ane sthesia. The flash visual evoked potential (F-VEP) was used to monitor visual function during orbital surgery. Methods A total of 252 out of 282 patients undergoing orbital surgery under general anesthesia were successfully monitored by F-VEP during the surgery. All patients were monitored by this method under the following conditions:consious state before operation, under general anaesthesia, during and after dissection of orbital tumor and at the end of operation. Results ①There was no significant difference of wave amplitude and latency under general anesthesia and consciousness condition. ②The amplitude and latency of F-VEP were normal in the orbital surgery withou toptic nerve injury. ③Pulling and oppression of optic nerve could cause temporary wave loss, but the wave recovered after removal of the pull and oppression. ④ The wave loss of F-VEP would occur immedicately when optic nerve was severe injured and its blood supply was deficient. Since the application of the visual function monitoring, 24 cases were treated in time during disturbance of visual function and no patient has unexpected visual loss during orbital surgery. Conclusion The intraoperative monitoring of F-VEP during orbital surgery can decrease the proportion of permanent visual loss caused by orbit al surgery, and help the surgical procedures go to function-anatomy stage from experience-anatomy stage. (Chin J Ocul Fundus Dis, 2001,17:260-263)
Optometry involves knowledge from multiple fields such as biology, physics, chemistry, psychophysics, and medicine. Traditional undergraduate education in optometry mainly focuses on knowledge transmission and lacks interaction, resulting in low student interest and unsatisfactory teaching outcomes. In order to improve this situation, the teaching team of Department of Optometry and Visual Science, West China School of Medicine, Sichuan University proposed a method of integrating real visual experiences into teaching. By combining multimedia tools and existing methods, real visual phenomena and personal visual experiences are integrated into the curriculum. This new teaching method stimulates students’ interest in learning, increases classroom interaction, promotes knowledge understanding and application through vivid visual phenomena and students’ own visual experiences. This article will introduce the above teaching method.
Three-dimensional (3D) visualization technology can well characterize lung nodules, accurately locate lung nodules, accurately identify lung anatomical structures, shorten operation time, reduce intraoperative and postoperative complications, and make thoracoscopic precise lung resection safer and more efficient. However, the mastery of 3D reconstruction technology in some hospitals still needs to be improved. Due to the time and economic cost of 3D printing, the development of this technology is restricted. With the application and improvement of 3D visualization technology in more centers in the future, the development of precise lung resection will be more extensive. This article reviewed the progress on 3D visualization technology in thoracoscopic precise lung resection.
Coding with high-frequency stimuli could alleviate the visual fatigue of users generated by the brain-computer interface (BCI) based on steady-state visual evoked potential (SSVEP). It would improve the comfort and safety of the system and has promising applications. However, most of the current advanced SSVEP decoding algorithms were compared and verified on low-frequency SSVEP datasets, and their recognition performance on high-frequency SSVEPs was still unknown. To address the aforementioned issue, electroencephalogram (EEG) data from 20 subjects were collected utilizing a high-frequency SSVEP paradigm. Then, the state-of-the-art SSVEP algorithms were compared, including 2 canonical correlation analysis algorithms, 3 task-related component analysis algorithms, and 1 task discriminant component analysis algorithm. The results indicated that they all could effectively decode high-frequency SSVEPs. Besides, there were differences in the classification performance and algorithms' speed under different conditions. This paper provides a basis for the selection of algorithms for high-frequency SSVEP-BCI, demonstrating its potential utility in developing user-friendly BCI.