Alerta

GUIDE ASSEMBLY, DEVICE HAVING A GUIDE ASSEMBLY, AND METHOD FOR PRODUCING A GUIDE ASSEMBLY

Resumen de: WO2025068080A1

The invention relates to a guide assembly (10), in particular for a medical device, wherein the guide assembly (10) comprises a first guide portion (12), which has a first guide surface (14), and a second guide portion (16), which is captively arranged on the first guide portion (12) and has a second guide surface (18) which corresponds to the first guide surface (14). The first guide portion (12) and the second guide portion (16) can be additively manufactured in a manufacturing state in which the first guide surface (14) is spaced apart from the second guide surface (18). The first guide portion (12) and the second guide portion (16) can be brought, by a relative movement, from the manufacturing state into a functional state in which the first guide surface (14) and the second guide surface (18) correspond to one another such that the first guide portion (12) and the second guide portion (16) together form a guide-surface pair which has a guide function for a guided movement. The invention also relates to a device having a guide assembly (10) and to a method for producing a guide assembly (10).

BODY SUPPORTING DEVICE FOR SUPPORTING A BODY PART DURING A MEDICAL TREATMENT

Resumen de: WO2025068342A1

A body supporting device (101) for mounting on a treatment board (102) of a radiation treatment system (100), the treatment board configured for receiving a patient thereon and having a radiation access orifice (103) in which the body supporting device (101) is configured to be removably mounted. The body supporting device comprises a shell (2) and a support frame (4) coupled to the shell, the support frame including a board mounting base (20) configured to be mounted against a border of the radiation access orifice of the treatment board.

DEVICE, METHOD, AND USER INTERFACE FOR DETERMINING BIO-SIGNAL MEASUREMENT CYCLE

Resumen de: EP4785854A1

According to an embodiment of the present disclosure, a method for determining a bio signal measurement interval is disclosed. Specifically, according to the present disclosure, a computing device receives a bio signal of a user, and determines a personalized bio signal measurement interval of the user based on inputting the bio signal of the user into a bio signal analysis model, wherein the bio signal analysis model comprises at least one bio signal analysis sub-model that analyzes a health condition of the user.

IMPLANT COMPONENT

Resumen de: WO2025068687A1

An implant component (100) for an orthopaedic implant for arthroplasty. The implant component (100) comprises an articulation portion (104). The articulation portion (104 comprises: a substantially non-porous peripheral portion (116) comprising an articulation surface (108), the articulation surface (108) being configured to articulate relative to another component of the orthopaedic implant or to native anatomy, when in use, the substantially non-porous peripheral portion comprising a cavity located adjacent a bone-facing side or bone- interfacing side of the peripheral portion (116); and a porous structure (114) providing at least a part of a bone-interfacing side of the articulation portion (104), at least a part of the porous structure (114) being located in the cavity in the substantially non-porous peripheral portion (116). The implant component (100) comprises a fixing portion (102), the fixing portion (102) for fixing the implant component (100) to a bone of a patient. The fixing portion (102) and the articulation portion (104) are unitary and comprise fused particles.

An optical device

Resumen de: GB2703552A

A 3D scanner uses cylindrical marker posts to measure the positions and angles of dental implants. The marker posts each comprise a dot pattern which spans 360 degrees around the curved surface. The pattern consists of more than one type of marker dots, for example dots and doughnuts wherein the doughnut shapes may form a regular array with dots distributed in a random pattern. An implant scanner 1 comprises stereo cameras 2 and illumination source 8. Global shutters of the cameras are synchronized so that stereo images are captured simultaneously. Images are processed to deduce locations and angles of the marker posts in 3D space. Dots and doughnuts can both be detected in a frame using one pass of a Laplacian of Gaussian filter. This enables fast and accurate alignment between frames. Figure 1

EXTRUSION PRINTING FORMULATION

Resumen de: EP4785932A1

The invention is aimed at providing a bioactive formulation suitable for printing, preferably 3D printing, the formulation comprises: a first and a second excipient and a bioactive substance that is easily interchangeable with either the first or second excipient. While heating and mixing the formulation a slurry comprising a matrix and a particulate matter is formed such that the formulation may have the required flowability during printing and the dimensional stability to create a final product.

生成装置、生成方法および生成プログラム

Resumen de: JP2026126946A

0001 【課題】妊婦の陣痛発来日をより精度よく予測するモデルを生成すること。 【解決手段】本願に係る生成装置は、取得部と、生成部とを備え、取得部は、ユーザから心拍数または脈拍数を含む生体データを取得し、生成部は、少なくとも陣痛発来日から遡って当該生体データの特徴量が最低となった日以降を含む当該陣痛発来日までの各日に対応する当該生体データの特徴量であって、所定日数後が陣痛発来日であるか否かをラベル付けした当該生体データの特徴量を学習データとして、当該所定日数後の陣痛発来を予測する予測モデルを生成することを特徴とする。 【選択図】図１

METHOD AND SYSTEM OF CREATING A REPLICA OF AN ANATOMICAL STRUCTURE

Resumen de: EP4787324A1

Creating a replica of an anatomical structure. At least some of the example embodiments are methods including: accepting a plurality of pictures of the anatomical structure of a subject; creating an object file that contains an initial model of an outside surface of the anatomical structure; cutting the initial model to a predetermined exterior shape circumscribing the anatomical structure, the cutting creates a positive model of the anatomical structure within the predetermined exterior shape; creating a negative model of the anatomical structure from the positive model; placing a stem tool object on an outside surface of the negative model in relationship to an orifice of the anatomical structure, and thereby creating a final negative model; printing, by way of a three-dimensional printer, the final negative model to create a negative mold; and casting the replica of the anatomical structure using the negative mold.

脊髄状態を診断し、脊髄状態の治療を判定するためのシステムおよび方法

Resumen de: US2024428954A1

0000 The present technology includes systems and methods for generating and implementing patient-specific diagnostic plans. The diagnostic plans include one or more specific diagnostic tests that should be performed on a particular patient based on the patient's demographics and/or health complaints. The diagnostic tests can be selected to determine specific diagnostic information that is expected to be useful in determining patient-specific surgical plans for the particular patient.

INTRAOPERATIVE ANATOMICAL LANDMARK IN THYROID SURGERY - RECURRENT LARYNGEAL NERVE INTERSTITIAL FLUID SHEATH

Resumen de: WO2023187558A1

The present disclosure is directed to an artificial 3D scaffold of thyroid comprising artificial laryngeal and tracheal framework, wherein the scaffold comprises an artificial interstitial fluid sheath. Further, methods for obtaining a 3D scaffold according to the present disclosure and methods for identification of the recurrent laryngeal nerve in a subject, are disclosed.

用于通过单次磁共振图像采集对水、脂肪和场不均匀性进行磁共振成像的系统和方法

Resumen de: US20260227474A1

0000 A method for generating magnetic resonance images includes obtaining, via a processing system, a single complex magnetic resonance image per slice from magnetic resonance scan data acquired of a subject with a magnetic resonance scanner utilizing a chemical shifted sequence where signal contributions from different pre-defined components to acquired echo signals are separated, wherein the single complex magnetic resonance image comprises a non-zero phase angle between the different pre-defined components. The method also includes inputting, via the processing system, the single complex magnetic resonance image for each slice into a decomposition model trained to predict chemical shifted-like images from the single complex magnetic resonance image for each slice. The method further includes outputting, via the processing system, from the decomposition model the chemical shifted-like images of one or more pre-defined components of the different pre-defined components based on the single complex magnetic resonance image for each slice.

一种高硅316L/Y2O3医用复合材料的制备方法及其应用

Resumen de: CN122500216A

本发明涉及生物医用金属材料及增材制造技术领域，更具体的说一种高硅316L/Y2O3医用复合材料的制备方法及其应用。制备方法包括以下步骤：将高硅316L不锈钢粉末与Y2O3纳米颗粒混合，其中所述高硅316L不锈钢粉末的硅含量为1.5‑2.5wt%，所述Y2O3纳米颗粒的含量为0.3‑1.0wt%；利用XGBoost回归模型构建环境代理模型，输入特征向量包括激光功率P、扫描速度v、以及基于凝固传热物理模型推导的物理描述符；采用物理一致性数据增强策略对训练样本进行扩充；采用Q‑learning强化学习算法，以相对密度和显微硬度作为双目标奖励函数进行策略寻优，获得最优激光功率P和扫描速度v；采用步骤二获得的最优激光功率P和扫描速度v，通过激光粉末床熔融成形工艺制备高硅316L/Y2O3医用复合材料。

一种多模态生理信号检测用的液态金属基仿生一体化传感器制备方法

Resumen de: CN122500214A

本发明公开了一种多模态生理信号检测用的液态金属基仿生一体化传感器制备方法，包括以下步骤：（1）配置凝胶溶液和表面功能化材料溶液，混合均匀，置于低温下进行预交联；然后加入交联剂溶液浸泡进行初步交联，取出交联产物，得到适合打印传感器的凝胶支撑和封装层；（2）将液态金属装入注射器中，放到注射泵上，调节挤出速度；在电源输出电压采用0~15 V范围内，调节相应电压；最后根据设置好的打印图案，使注射器针头在凝胶支撑和封装层中按照路径将液态金属打印成型，然后置于交联剂溶液中作进一步交联封装，形成多模态传感层，最后制得液态金属基仿生一体化传感器。

一种血透机排液管悬空防倒灌装置及其制备方法

Resumen de: CN122500944A

本发明公开一种血透机排液管悬空防倒灌装置及其制备方法，属于血管滤器增材制造技术领域。该方法包括悬空梯度流道增材构型、光敏树脂梯度光固化一体成型两道核心步骤，通过构建带梯度限流段与悬空气隙段的连续流道模型，配合树脂脱泡预处理、分层变功率扫描、水溶性支撑布设、后固化应力消除、内腔疏水改性的递进工艺，实现无拼接一体化装置的高精度制备。流道梯度收缩比为1:0.62，悬空气隙有效高度为25mm。本方法制备的装置无活动阀芯与装配接缝，反向阻断耐压达0.15MPa，内壁粗糙度Ra≤0.6μm，经1000次消毒循环后性能保留率98%以上，可同步提升血透排液的防倒灌可靠性与生物安全性。

物体の三次元モデルを形成するための１つ又は複数の光度エッジの生成

Resumen de: WO2019071157A1

Disclosed herein are various embodiments relate generally to computer vision, graphics, image scanning, and image processing as well as associated mechanical, electrical and electronic hardware, computer software and systems, and wired and wireless network communications to form at least three-dimensional models or images of objects and environments.

基于多频生物阻抗频谱的个体身份识别与意图感知系统

Resumen de: CN122508563A

0001 本发明公开了一种基于多频生物阻抗频谱的个体身份识别与意图感知系统。所述系统通过激励信号发生模块向人体施加宽频扫频信号，经由核心传感模块采集响应信号，通过信号处理模块获得复数阻抗数据。计算处理模块采用多频差分算法从阻抗频谱中提取表征个体深层组织结构的唯一性物理指纹特征，并引入基于动态电导模型的心理状态感知算法，通过AI融合决策，同步实现高精度身份认证与异常生理状态、睡眠等非自愿状态的实时判别。最终由执行输出模块执行解锁、静默报警等操作。本发明解决了传统生物识别技术易伪造、无法感知用户意愿的缺陷，兼具更高级防伪性、主动安全防御与隐私保护能力。

一种基于EEG-语音多模态融合的抑郁状态检测方法及系统

Resumen de: CN122498842A

0001 本发明属于人工智能与生物信号处理技术领域，公开了一种基于EEG‑语音多模态融合的抑郁状态检测方法及系统。所述方法为：对输入的EEG（脑电信号）依次通过深度可分离卷积、自适应平均池化及维度映射提取时序特征，对输入的语音信号依次通过多层深度可分离卷积、全局平均池化提取全局特征；将语音全局特征进行时序扩展后与EEG时序特征通道拼接，通过1×1卷积完成降维融合得到融合时序特征；将融合时序特征输入GRU循环神经网络捕获时序依赖关系，再通过MLP注意力机制对GRU输出特征加权聚合得到时序上下文特征；将时序上下文特征与语音全局特征拼接后输入包含全连接层、激活层及Dropout层的分类器，输出抑郁状态分类结果。该方法通过深度可分离卷积降低模型参数量与计算复杂度，利用GRU+MLP注意力机制强化时序特征的有效表征，结合EEG与语音双模态特征的互补优势提升抑郁状态检测的准确性和可靠性，应用于抑郁状态筛查、辅助诊断等人机交互及医疗辅助场景具有良好的产业化前景。

基于多波长光电传感器的深静脉血栓早期预警方法

Resumen de: CN122498808A

0001 本发明涉及医学检测技术领域，具体为利用生物传感器进行生理状态测量的诊断分支。本发明公开基于多波长光电传感器的深静脉血栓早期预警方法。在目标肢体贴附阵列排布的多波长光电传感器组，同步采集不同空间位置的多波长光电容积脉搏波信号；对信号进行经验模态分解，筛选静脉血流频段的本征模态函数分量；计算相邻节点在相同波长下所述分量的时频特征互相关系数，构建空间血流灌注相关系数矩阵；提取矩阵特征值分布状态输入预置异质性判定模型，当偏离正常分布阈值时输出预警信号。本方案将局部信号分析转为时空矩阵分析，通过空间相关性改变表征微循环灌注不对称性，克服单点检测因侧支循环建立造成的空间敏感性缺失缺陷。

用于心内超声心动图操纵以维持连续治疗设备尖端可见性的基于AI的引导系统

Resumen de: US20260224192A1

Systems and methods for estimating an incident angle and trajectory of therapy devices within Intra-cardiac Echocardiography (ICE) images in real time in order to provide guidance for ICE manipulation to maintain continuous therapy device tip visibility. An ICE imaging sequence is acquired. A pre-trained ultrasound foundation model is used to extract spatial and temporal features in the sequence of ICE images. A transformer based temporal deep learning model is used that integrates the extracted spatial while incorporating historical passing points and angular information to in order to track the catheter tip within the ICE imaging plane. The tip tracking transformer based temporal deep learning model improves upon existing incident angle and trajectory model estimations in ICE procedures by improving prediction accuracy and consistency.

神経毒性検出のための人工知能技法

Resumen de: WO2025019456A1

Detecting neurotoxicity associated abnormalities due to certain medication therapies can be significant for identifying various neurological disorders. The present disclosure relates to detection of neurotoxicity related disorders by leveraging an interface including one or more sets of queries and a set of components to receive a set of responses corresponding to the sets of queries. The techniques, as disclosed herein, may use one or more attributes of the set of responses including consistency, complexity, grammar and spelling correctness, and time taken during the responses. The disclosed technique may preprocess the responses, extract features and generate one or more metrics corresponding to the one or more attributes of the one or more responses provided by the subject during a session with the interface. The generated metrics over a baseline session and subsequent sessions may be used to determine trends in the metrics which may be used to estimate the extent of neurotoxicity developed by a subject and may trigger an alert about a potential neurotoxicity or a preventative measure to reduce a likelihood of further neurotoxicity.

運動データを生成及び／又は処理する方法、運動順序を記録及び／又は分析する方法、動的不安定性を識別及び／又は分析する方法、アルゴリズム及び／又はモデルを生成及び／又は最適化する方法、この種の方法を実行するための装置、並びにコンピュータプログラム

Resumen de: WO2025027158A1

The invention relates to a method for generating and/or processing movement data of a freely movable body (130), in which at least two sensor units (104, 106, 108, 110) which each have an angular velocity sensor and an acceleration sensor are arranged on the body (130) so as to be fixedly mutually spaced, and, on the basis of measurement signals from the at least two sensor units (104, 106, 108, 110) and with application of the laws of general movement of rigid bodies, an angular velocity vector is directly determined. The invention also relates to a method for recording and/or analyzing movement sequences of a freely movable body (130), in which movement data of the body (130) that have been generated and/or processed according to a method of the kind mentioned above are used. The invention also relates to a method for identifying and/or analyzing dynamic instabilities of a freely movable body (130), in which movement data of the body (130) that have been generated and/or processed according to a method of the kind mentioned above are used. The invention also relates to a method for generating and/or optimizing algorithms and/or models for calculating the dynamics of freely movable bodies (130), in which movement data of the body (130) that have been generated and/or processed according to a method of the kind mentioned above are used. The invention also relates to a device (100) for carrying out a method of this kind, comprising at least two sensor units (104, 106, 108, 110

Subgingival medicament delivery tray

Resumen de: US2022401202A1

Oral appliance delivery trays for use in maintaining or improving oral health, particularly the sub-gingival region, are provided. Methods of manufacturing individualized oral appliance delivery trays are provided. Pre-fabricated oral appliance trays comprising a compound pre-disposed therein are provided. The compositions and methods may be used to maintain or improve oral, periodontal and systemic health or to prevent or slow oral, periodontal or systemic health issues related to the oral cavity.

認知評価のためのシステムおよびプロセス

Resumen de: WO2025015414A1

A medical process, an assessment tool and a system are provided. The medical process may comprise: administering a first series of user tasks to a user and measuring user data points for one or more task performance parameters. The first series of user tasks are administered by displaying a first group of elements on a display and prompting the user to perform a first user task of selecting a first sub-group of elements from the first group and arranging the first sub-group in a first sequence; displaying a second group of elements on the display and prompting the user to perform a second user task of arranging one or more elements of the second group based on a predefined sequence; and displaying a third group of elements on the display, the third group of elements including the first sub-group, and prompting the user to perform the third user task.

用于直接3D打印的光固化性形状恢复高分子组合物及利用其制造的牙齿矫正装置

Resumen de: KR102815488B1

The present disclosure relates to a photocurable shape-memory polymer composition for direct 3D printing and an orthodontic device manufactured therefrom, and more specifically, to a photocurable shape-memory polymer composition for direct 3D printing and an orthodontic device manufactured therefrom, wherein the composition has rigidity, stiffness, and elasticity suitable for orthodontic treatment in a first temperature range, and exhibits shape recovery characteristics in a second temperature range different from the first temperature range.

基于个体多模态健康数据分析的保健食品制备方法与系统

Nº publicación: CN122494131A 31/07/2026

Solicitante:

华臻生物科技（深圳）有限公司

Resumen de: CN122494131A

本发明涉及基于个体多模态健康数据分析的保健食品制备方法与系统，属于保健食品制备技术领域，本发明通过结合所述用户多模态数据识别用户的核心需求采用贝叶斯优化，在约束空间中搜索帕累托前沿解集，最终输出一组最优配方，基于所述最优配方对3D打印设备进行路径规划，并实时监测保健产品打印质量，同时根据保健产品打印质量动态调整打印参数。本发明融合可穿戴设备连续生理信号、即时检测生化指标及饮食视觉识别等多模态数据，显著提升了个体健康状态评估的客观性与时效性，为精准配方生成奠定坚实基础；采用递进式多目标优化算法，协同考虑功效、口感、安全与成本，突破了传统静态规则库的局限性。