ObjectiveTo address the challenges of unstructured classical Chinese expressions， nested entity relationships， and limited annotated data in famous traditional Chinese medicine（TCM） case records， this study proposes a joint relation extraction framework that integrates data augmentation and entity mapping， aiming to support the construction of TCM diagnostic knowledge graphs and clinical pattern mining. MethodsWe developed an annotation structure for entities and their relationships in TCM case texts and applied a data augmentation strategy by incorporating multiple ancient texts to expand the relation extraction dataset. A cascade binary tagging framework for relation triple extraction（CasRel） model for TCM semantics was designed， integrating a pre-trained bidirectional encoder representations from transformers（BERT） layer for classical TCM texts to enhance semantic representation， and using a head entity-relation-tail entity mapping mechanism to address entity nesting and relation overlapping issues. ResultsExperimental results showed that the CasRel model， combining data augmentation and entity mapping， outperformed the pipeline-based Bert-Radical-Lexicon（BRL）-bidirectional long short-term memory（BiLSTM）-Attention model. The overall precision， recall， and F₁-score across 12 relation types reached 65.73%， 64.03%， and 64.87%， which represent improvements of 14.26%， 7.98%， and 11.21% compared to the BRL-BiLSTM-Attention model， respectively. Notably， the F₁-score for tongue syndrome relations increased by 22.68%（69.32%）， and the prescription-syndrome relations performed the best with the F₁-score of 70.10%. ConclusionThe proposed framework significantly improves the semantic representation and complex dependencies in TCM texts， offering a reusable technical framework for structured mining of TCM case records. The constructed knowledge graph can support clinical syndrome differentiation， prescription optimization， and drug compatibility， providing a methodological reference for TCM artificial intelligence research.

ObjectiveIn traditional Chinese medicine (TCM), the foundational doctrine that the eyes reflect the essence of the internal viscera establishes ocular observation as a cornerstone of diagnostic practice. Specifically, the morphological characteristics and coloration variations of the scleral microvasculature serve as critical clinical indicators for assessing the dynamic balance of Qi and Blood, as well as the pathological status of internal organs. Historically, however, TCM eye diagnosis has relied predominantly on the subjective clinical experience and visual acuity of individual practitioners, leading to inherent challenges in standardization and reproducibility. While automated computer-aided diagnostic systems offer a promising solution, existing vessel segmentation algorithms encounter significant domain-specific bottlenecks when applied to scleral imagery. These challenges primarily stem from the highly reflective and moist nature of the ocular surface, which generates severe reflective interference. Furthermore, the inherent low contrast of fine capillary networks against complex background textures, compounded by non-uniform illumination, frequently results in high false-positive rates, misdetections, and severe vessel fragmentation. To address these critical limitations and advance the objective quantification of TCM diagnostics, this paper proposes a novel, highly robust sclera vessel segmentation framework that innovatively integrates Frangi-Sato dual-filter adaptive enhancement with pixel-level reflection detection. MethodsThe proposed methodology systematically addresses the segmentation pipeline through three synergistic stages. First, to overcome the structural limitations of single-filter approaches, a multi-scale weighted fusion strategy is meticulously designed to harness the complementary extraction capabilities of both Frangi and Sato filters. This adaptive enhancement optimally balances the preservation of main vessel trunk continuity with the heightened sensitivity required for delineating delicate, low-contrast peripheral capillaries. Second, to tackle the persistent issue of reflective highlights, a sophisticated multi-feature synergistic reflection detection module is introduced. By jointly analyzing local information entropy, gradient field variations, and intensity statistical distributions, this module achieves precise, pixel-level identification and elimination of reflective artifacts without compromising the underlying vascular structures. Finally, a dual-level adaptive thresholding strategy, featuring an innovative “core protection” mechanism, is implemented. This critical step effectively suppresses complex background noise while rigorously preserving the structural and topological integrity of the intricate vessel network, preventing the structural breaks often seen in conventional binarization methods. ResultsThe efficacy of the proposed framework was rigorously evaluated using both self-constructed clinical datasets specifically acquired for TCM research and standardized public datasets. Extensive experimental results demonstrate that the proposed method consistently outperforms state-of-the-art traditional approaches and contemporary deep learning models. Specifically, the proposed method achieves a Dice similarity coefficient of approximately 0.71 on the private clinical dataset, and secures the best performance across the majority of quantitative metrics on both datasets. Notably, the framework exhibits exceptional robustness and generalization capabilities in highly challenging scenarios characterized by intense reflective interference, low signal-to-noise ratios, and cross-domain image variations. ConclusionThis study successfully realizes the high-integrity, automated segmentation of scleral vessel networks under complex clinical imaging conditions. By overcoming the fundamental algorithmic challenges of reflection interference and micro-vessel loss, the proposed methodology provides potential support for the digitization, objective standardization, and intelligent advancement of modern TCM eye diagnosis systems.

ObjectiveIn traditional Chinese medicine (TCM), the foundational doctrine that the eyes reflect the essence of the internal viscera establishes ocular observation as a cornerstone of diagnostic practice. Specifically, the morphological characteristics and coloration variations of the scleral microvasculature serve as critical clinical indicators for assessing the dynamic balance of Qi and Blood, as well as the pathological status of internal organs. Historically, however, TCM eye diagnosis has relied predominantly on the subjective clinical experience and visual acuity of individual practitioners, leading to inherent challenges in standardization and reproducibility. While automated computer-aided diagnostic systems offer a promising solution, existing vessel segmentation algorithms encounter significant domain-specific bottlenecks when applied to scleral imagery. These challenges primarily stem from the highly reflective and moist nature of the ocular surface, which generates severe reflective interference. Furthermore, the inherent low contrast of fine capillary networks against complex background textures, compounded by non-uniform illumination, frequently results in high false-positive rates, misdetections, and severe vessel fragmentation. To address these critical limitations and advance the objective quantification of TCM diagnostics, this paper proposes a novel, highly robust sclera vessel segmentation framework that innovatively integrates Frangi-Sato dual-filter adaptive enhancement with pixel-level reflection detection. MethodsThe proposed methodology systematically addresses the segmentation pipeline through three synergistic stages. First, to overcome the structural limitations of single-filter approaches, a multi-scale weighted fusion strategy is meticulously designed to harness the complementary extraction capabilities of both Frangi and Sato filters. This adaptive enhancement optimally balances the preservation of main vessel trunk continuity with the heightened sensitivity required for delineating delicate, low-contrast peripheral capillaries. Second, to tackle the persistent issue of reflective highlights, a sophisticated multi-feature synergistic reflection detection module is introduced. By jointly analyzing local information entropy, gradient field variations, and intensity statistical distributions, this module achieves precise, pixel-level identification and elimination of reflective artifacts without compromising the underlying vascular structures. Finally, a dual-level adaptive thresholding strategy, featuring an innovative “core protection” mechanism, is implemented. This critical step effectively suppresses complex background noise while rigorously preserving the structural and topological integrity of the intricate vessel network, preventing the structural breaks often seen in conventional binarization methods. ResultsThe efficacy of the proposed framework was rigorously evaluated using both self-constructed clinical datasets specifically acquired for TCM research and standardized public datasets. Extensive experimental results demonstrate that the proposed method consistently outperforms state-of-the-art traditional approaches and contemporary deep learning models. Specifically, the proposed method achieves a Dice similarity coefficient of approximately 0.71 on the private clinical dataset, and secures the best performance across the majority of quantitative metrics on both datasets. Notably, the framework exhibits exceptional robustness and generalization capabilities in highly challenging scenarios characterized by intense reflective interference, low signal-to-noise ratios, and cross-domain image variations. ConclusionThis study successfully realizes the high-integrity, automated segmentation of scleral vessel networks under complex clinical imaging conditions. By overcoming the fundamental algorithmic challenges of reflection interference and micro-vessel loss, the proposed methodology provides potential support for the digitization, objective standardization, and intelligent advancement of modern TCM eye diagnosis systems.

Objective:To investigate the efficacy and safety of fluoroscopically-guided percutaneous gastrostomy (FGPG) for establishing enteral nutrition access in the treatment of esophageal fistula after radiotherapy for cervical esophageal cancer (CEC).Methods:A retrospective analysis was conducted on the clinical data of 54 patients who underwent FGPG due to esophageal fistula after radiotherapy for CEC at our department from November 2009 to August 2019. All patients received endoscopy before radiotherapy, and CEC was pathologically confirmed. Enteral nutrition support was offered through a gastrostomy tube postoperatively. The success rate of FGPG, complications, and healing of perforation were recorded and analyzed.Results:FGPG was successfully performed in all 54 patients (100%). During the 12-month follow-up, 50 patients (92.6) survived while four (7.4%) died. Among 36 patients with esophagomediastinal fistula, 32 (88.9%) healed in a median of 12 weeks; of 18 patients with esophagotracheal fistula, 8 (44.4%) healed in a median of 18 weeks. Thus, patients with esophagomediastinal fistula had a significantly higher healing rate ( P<0.01) and shorter healing time ( P=0.017). Gastrostomy tube-related complications were minimal, and no serious complication was noted. Conclusions:FGPG is effective for the treatment of esophageal fistula after CEC radiotherapy and may be an alternative treatment for esophageal fistula.

Objective To propose an EBT3 film technology-based quality control measurement method for the INTRABEAM PRS500 intraoperative radiotherapy equipment to solve the problems of the traditional methods in cumbersome operation and setup error.Methods According to HJ 1198-2021 Requirements of radiation safety and protection for radiotherapy and GBZ 121-2020 Requirements for radiological protection in radiotherapy,the environmental radiation testing of the INTRABEAM PRS500 intraoperative radiotherapy equipment was carried out point by point by means of the radiation inspection instrument.The INTRABEAM PRS500 intraoperative radiotherapy equipment was characterized by a point X-ray source(XRS),and the XRS was detected in terms of the probe linearity,radiation dose,dynamic deviation,isotropy and dose rate.The EBT3 film technology was used to verify the symmetry and isotropy of the XRS planar dose of INTRABEAM PRS500 intraoperative radiotherapy equipment.Results The X-γ dose equivalent rate of each monitoring site of the INTRABEAM PRS500 intraoperative radiotherapy device was lower than the method detection limit(MDL).The results of SQA quality control showed that the INTRABEAM PRS500 intraoperative radiotherapy equipment XRS met the quality control requirements in terms of the probe linearity,radiation dose,dynamic deviation and etc,and the isotropy differences in the+X,-X,+Y,and-Y axis directions ranged from-1.40％to 1.79％,which were all within the allowable range of measurement tolerance(5.60％to 5.65％).The results of measuring the isotropy of the INTRABEAM PRS500 intraoperative radiotherapy equipment based on the EBT3 film technology showed that the dose distribution of the XRS in the directions of the+X,-X,+Y,and-Y axes at the same plane was well isotropic,and that the doses in the directions of the X and Y axes were symmetrically distributed,and that the maximum skewness value for the isotropy of the XRS in the XY plane was-1.581％,which met the requirements of AAPM TG61 report on the reference dosimetry of low-energy and medium-energy X-rays for radiotherapy and radiobiology of≤±5.3％.Conclusion The EBT3 film technology-based measurement method gains high simplicity and feasibility for the isotropy of the INTRABEAM PRS500 intraoperative radiotherapy equipment in the directions of the+X,-X,+Y,and-Y axes at the same planet,which realizes the dynamic monitoring of the dosimetric changes and facilitates the whole-process quality control management of the intraoperative radiotherapy equipment.[Chinese Medical Equipment Journal,2025,46(6):47-53]

Objective:To investigate the clinical efficacy of posterior midline incision combined with anteromedial approach in the treatment of complex olecranon fracture-dislocation.Methods:A retrospective analysis was performed on 26 patients (15 males and 11 females) with olecranon fracture-dislocation who were admitted from January 2020 to January 2024, including 5 cases of anterior transolecranon fracture-dislocation (2 cases of upper ulnar-radial joint dislocation), 21 cases of posterior transolecranon fracture-dislocation (5 cases of them were accompanied by upper ulnar-radial joint dislocation). Among them, there were 13 cases of traffic accidents, 7 cases of falling from heights, and 6 cases of walking falls. The average age is 45.1±15.3 years old (21-84 years old).Results:The operation time was 151.2±41.9 minutes, average tourniquet time was 93.7±22.6 minutes, and the intraoperative blood loss was 76.2±20.2 ml. The average follow-up was 16(12, 23) months, and the VAS score decreased significantly and the MEPS score increased significantly over time. At the last follow-up, the VAS score was 2(1, 2), and the MEPS score was 86.5±10.3, with 16 cases excellent, 7 cases good, and 3 cases medium, with an excellent rate of 89%. The range of motion of flexion-extension and pronation-supination were 119.3°±13.5°and 138.6°±15.2° respectively. Complications included 16 cases of ectopic ossification, of which 4 patients with significant effects on elbow function underwent surgical release 3-6 months after surgery. 1 case of ulnar nerve injury symptoms improved after emergency ulnar nerve release, and 1 case of elbow subluxation due to inaccurate coronoid process reduction and fixation. There were no serious complications such as vascular injury, internal fixation failure, fracture nonunion, and incision infection.Conclusion:The posterior midline incision combined with anteromedial approach can effectively treat complex olecranon fracture-dislocation and meet the requirements of early postoperative elbow rehabilitation.

Objective:To investigate the clinical efficacy of posterior midline incision combined with anteromedial approach in the treatment of complex olecranon fracture-dislocation.Methods:A retrospective analysis was performed on 26 patients (15 males and 11 females) with olecranon fracture-dislocation who were admitted from January 2020 to January 2024, including 5 cases of anterior transolecranon fracture-dislocation (2 cases of upper ulnar-radial joint dislocation), 21 cases of posterior transolecranon fracture-dislocation (5 cases of them were accompanied by upper ulnar-radial joint dislocation). Among them, there were 13 cases of traffic accidents, 7 cases of falling from heights, and 6 cases of walking falls. The average age is 45.1±15.3 years old (21-84 years old).Results:The operation time was 151.2±41.9 minutes, average tourniquet time was 93.7±22.6 minutes, and the intraoperative blood loss was 76.2±20.2 ml. The average follow-up was 16(12, 23) months, and the VAS score decreased significantly and the MEPS score increased significantly over time. At the last follow-up, the VAS score was 2(1, 2), and the MEPS score was 86.5±10.3, with 16 cases excellent, 7 cases good, and 3 cases medium, with an excellent rate of 89%. The range of motion of flexion-extension and pronation-supination were 119.3°±13.5°and 138.6°±15.2° respectively. Complications included 16 cases of ectopic ossification, of which 4 patients with significant effects on elbow function underwent surgical release 3-6 months after surgery. 1 case of ulnar nerve injury symptoms improved after emergency ulnar nerve release, and 1 case of elbow subluxation due to inaccurate coronoid process reduction and fixation. There were no serious complications such as vascular injury, internal fixation failure, fracture nonunion, and incision infection.Conclusion:The posterior midline incision combined with anteromedial approach can effectively treat complex olecranon fracture-dislocation and meet the requirements of early postoperative elbow rehabilitation.

Objective To investigate the influence of helical tomographic radiotherapy plans with different combinations of lead gate width,pitch and algorithms on threading effects.Methods A target model was established with a Cheese Phantom used as the simulated human body,then three lead gate widths(1.0,2.5,and 5.0 cm),six screw pitches(0.143,0.172,0.215,0.287,0.430,and 0.500)and two computational grids(Fine algorithm and Normal algorithm)were respectively combined for designing the helical tomography radiotherapy plans.The radiotherapy plans with a pitch of 0.143,0.172,0.215,0.287 or 0.430 were enrolled into an experimental group,and the plans with a pitch of 0.500 were divided into a control group.The dosimetric parameters including maximum dose(Dmax),minimum dose(Dmin)and mean dose(Dmean)of the target area PTV1 and PTV2 were evaluated by the dose volume histogram(DVH).The dose homogeneity index(HI)of the target area was calculated,and the single rotation time and total treatment time of each plan were recorded and counted.SPSS 27.0 software was used for statistical analysis.Results No significant threading effect appeared regardless of the pitch value when the lead gate width was 1.0 cm.The threading effects in the experimental group were weaker than those in the control group when the lead gate width was 2.5 or 5.0 cm.The threading effect gradually rose with the pitch increased when the lead gate width was 5.0 cm.The most significant difference was found between the threading effect in case of the screw pitch being 0.500 and that with the screw pitch being 0.143,with the differenes being statistically obvious(P<0.05).The lead gate width had significant effects on the Dmax,Dmin,Dmean and HI of PTV1 and PTV2.When the lead gate width was 5.0 cm,high HI value and uneven dose distribution were detected and lowered screw pitch weakened the threading effect.The single rotation time first remained constant and then increased with the screw pitch was enlarged,with the changing points occurring in case of the screw pitches of 0.287 and 0.430.With a certain lead gate width,the treatment time for plans was shortened with the decrease of the pitches in case of the pritches lower than 0.287,and tended to be constant after the screw pitches reached 0.287.The changes of the computational grid had no significant effects on the results of radiotherapy plans when the lead gate width and screw pitch were kept constant.Conclusion When designing a spiral tomotherapy plan with conventional doses,a lead gate width of 1.0 or 2.5 cm and a screw pitch of 0.287 or 0.430 should be selected in order to minimize the threading effect while ensuring the efficiency of plan implementation.[Chinese Medical Equipment Journal,2025,46(8):58-66]

Objective:To investigate the efficacy and safety of fluoroscopically-guided percutaneous gastrostomy (FGPG) for establishing enteral nutrition access in the treatment of esophageal fistula after radiotherapy for cervical esophageal cancer (CEC).Methods:A retrospective analysis was conducted on the clinical data of 54 patients who underwent FGPG due to esophageal fistula after radiotherapy for CEC at our department from November 2009 to August 2019. All patients received endoscopy before radiotherapy, and CEC was pathologically confirmed. Enteral nutrition support was offered through a gastrostomy tube postoperatively. The success rate of FGPG, complications, and healing of perforation were recorded and analyzed.Results:FGPG was successfully performed in all 54 patients (100%). During the 12-month follow-up, 50 patients (92.6) survived while four (7.4%) died. Among 36 patients with esophagomediastinal fistula, 32 (88.9%) healed in a median of 12 weeks; of 18 patients with esophagotracheal fistula, 8 (44.4%) healed in a median of 18 weeks. Thus, patients with esophagomediastinal fistula had a significantly higher healing rate ( P<0.01) and shorter healing time ( P=0.017). Gastrostomy tube-related complications were minimal, and no serious complication was noted. Conclusions:FGPG is effective for the treatment of esophageal fistula after CEC radiotherapy and may be an alternative treatment for esophageal fistula.

Objective To investigate the influence of helical tomographic radiotherapy plans with different combinations of lead gate width,pitch and algorithms on threading effects.Methods A target model was established with a Cheese Phantom used as the simulated human body,then three lead gate widths(1.0,2.5,and 5.0 cm),six screw pitches(0.143,0.172,0.215,0.287,0.430,and 0.500)and two computational grids(Fine algorithm and Normal algorithm)were respectively combined for designing the helical tomography radiotherapy plans.The radiotherapy plans with a pitch of 0.143,0.172,0.215,0.287 or 0.430 were enrolled into an experimental group,and the plans with a pitch of 0.500 were divided into a control group.The dosimetric parameters including maximum dose(Dmax),minimum dose(Dmin)and mean dose(Dmean)of the target area PTV1 and PTV2 were evaluated by the dose volume histogram(DVH).The dose homogeneity index(HI)of the target area was calculated,and the single rotation time and total treatment time of each plan were recorded and counted.SPSS 27.0 software was used for statistical analysis.Results No significant threading effect appeared regardless of the pitch value when the lead gate width was 1.0 cm.The threading effects in the experimental group were weaker than those in the control group when the lead gate width was 2.5 or 5.0 cm.The threading effect gradually rose with the pitch increased when the lead gate width was 5.0 cm.The most significant difference was found between the threading effect in case of the screw pitch being 0.500 and that with the screw pitch being 0.143,with the differenes being statistically obvious(P<0.05).The lead gate width had significant effects on the Dmax,Dmin,Dmean and HI of PTV1 and PTV2.When the lead gate width was 5.0 cm,high HI value and uneven dose distribution were detected and lowered screw pitch weakened the threading effect.The single rotation time first remained constant and then increased with the screw pitch was enlarged,with the changing points occurring in case of the screw pitches of 0.287 and 0.430.With a certain lead gate width,the treatment time for plans was shortened with the decrease of the pitches in case of the pritches lower than 0.287,and tended to be constant after the screw pitches reached 0.287.The changes of the computational grid had no significant effects on the results of radiotherapy plans when the lead gate width and screw pitch were kept constant.Conclusion When designing a spiral tomotherapy plan with conventional doses,a lead gate width of 1.0 or 2.5 cm and a screw pitch of 0.287 or 0.430 should be selected in order to minimize the threading effect while ensuring the efficiency of plan implementation.[Chinese Medical Equipment Journal,2025,46(8):58-66]