Medical cross-modal retrieval aims to achieve semantic similarity search between different modalities of medical cases, such as quickly locating relevant ultrasound images through ultrasound reports, or using ultrasound images to retrieve matching reports. However, existing medical cross-modal hash retrieval methods face significant challenges, including semantic and visual differences between modalities and the scalability issues of hash algorithms in handling large-scale data. To address these challenges, this paper proposes a Medical image Semantic Alignment Cross-modal Hashing based on Transformer (MSACH). The algorithm employed a segmented training strategy, combining modality feature extraction and hash function learning, effectively extracting low-dimensional features containing important semantic information. A Transformer encoder was used for cross-modal semantic learning. By introducing manifold similarity constraints, balance constraints, and a linear classification network constraint, the algorithm enhanced the discriminability of the hash codes. Experimental results demonstrated that the MSACH algorithm improved the mean average precision (MAP) by 11.8% and 12.8% on two datasets compared to traditional methods. The algorithm exhibits outstanding performance in enhancing retrieval accuracy and handling large-scale medical data, showing promising potential for practical applications.
Algorithms ; Semantics ; Humans ; Ultrasonography ; Information Storage and Retrieval/methods* ; Image Processing, Computer-Assisted/methods*

Online hashing methods are receiving increasing attention in cross modal medical image retrieval research. However, existing online methods often lack the learning ability to maintain semantic correlation between new and existing data. To this end, we proposed online semantic similarity cross-modal hashing (OSCMH) learning framework to incrementally learn compact binary hash codes of medical stream data. Within it, a sparse representation of existing data based on online anchor datasets was designed to avoid semantic forgetting of the data and adaptively update hash codes, which effectively maintained semantic correlation between existing and arriving data and reduced information loss as well as improved training efficiency. Besides, an online discrete optimization method was proposed to solve the binary optimization problem of hash code by incrementally updating hash function and optimizing hash code on medical stream data. Compared with existing online or offline hashing methods, the proposed algorithm achieved average retrieval accuracy improvements of 12.5% and 14.3% on two datasets, respectively, effectively enhancing the retrieval efficiency in the field of medical images.
Semantics ; Humans ; Algorithms ; Information Storage and Retrieval/methods* ; Diagnostic Imaging ; Image Processing, Computer-Assisted/methods*

Objective:To investigate the effect of dexmedetomidine combined with parecoxib sodium on multimode analgesia during total knee arthroplasty (TKA) and its effect on cognitive function.Methods:One hundred and eighty-eight patients who underwent TKA from January 2017 to December 2019 in People′s Hospital of Xuyi County were divided into the multimode analgesia (MA) group and the postoperative patient-controlled intravenous analgesia (PCIA) group by the method of random number table, each group with 94 patients. Patients in the MA group were injected with parecoxib sodium and dexmedetomidine hydrochloride half an hour before anesthesia induction and PCIA after the operation, while PCIA was only given after the operation in the PCIA group. Visual analogue scale (VAS) and sedation Ramsay scores were performed at the time of entry into the operation room (T 0), 12 h (T 1), 24 h (T 2) and 48 h (T 3) postoperatively; simple mental state scale (MMSE) score, serum S-100β, and neuron-specific enolase (NSE) levels were measured at 24 h before the operation (T 01), T 2, and 72 h after the operation (T 4). The incidence of adverse reactions within 48 h after surgery and postoperatively cognitive dysfunction (POCD) in the two groups within 72 h after surgery were recorded and compared. Results:The VAS scores and sufentanil dosage at T 1, T 2 and T 3 in the MA group were significantly lower than those in the PCIA group ( P<0.05), and Ramsay scores were significantly higher than those in the PCIA group ( P<0.05). The total incidence of adverse reactions and POCD in the MA group were significantly lower than that in the PCIA group: 5.32% (5/94) vs. 20.21%(19/94), 8.51%(8/94) vs. 27.66%(26/94), there were significant differences ( P<0.05). At T 2 and T 4, the MMSE scores in the MA group were significantly higher than that in the PCIA group: (26.42 ± 1.68) scores vs. (25.30 ± 1.74) scores, (27.06 ± 1.93) scores vs. (26.49 ± 1.87) scores; the S-100β level in the MA group were significantly lower than that in the PCIA group: (1.35 ± 0.17) μg/L vs. (1.43 ± 0.19) μg/L, (1.26 ± 0.13) μg/L vs. (1.40 ± 0.16) μg/L; the NSE level in the MA group were significantly lower than that in the PCIA group: (0.88 ± 0.05) μg/L vs. (0.94 ± 0.06) μg/L, (0.83 ± 0.06) μg/L vs. (0.91 ± 0.04) μg/L, there were significant differences ( P<0.05). Conclusions:Dexmedetomidine combined with parecoxib sodium multimode analgesia has clear analgesia effect after TKA, can significantly reduce the occurrence of POCD and has high safety.

Protein tyrosine phosphatase 1B(PTP1B),a member of protein tyrosine phosphatases(PTPs),plays a key role in the negative regulation of insulin and leptin signalings.Recent studies showed that PTP1B had an important connection with endoplasmic reticulum(ER)stress, pancreatic beta cells proliferation and insulin secretion,and is closely related to the pathological process of type 2 diabetes mellitus(T2DM)and obesity. Therefore,PIP1B targeted inhibitors have become a research hotspot in the treatment of these metabolic disea-ses.Based on the structural features of PTP1B and its relationship with T2DM and obesity,PTP1B inhibitors were classified according to the sites of binding.Their latest research advances were reviewed in this paper,providing a reference for the development of anti-T2DM and anti-obesity drugs targeting PTP1B.