Abstract: Embodiments of this application disclose methods, systems, and devices for medical image analysis and medical video stream processing. In one aspect, a method comprises extracting video frames from a medical image video stream that includes at least two pathological-section-based video frames. The method also comprises identifying single-frame image features in the video frames, mapping the single-frame image features into single-frame diagnostic classification results, and performing a classification mapping based on a video stream feature sequence that comprises the single-frame image features. The classification mapping comprises performing a convolution operation on the video stream feature sequence through a preset convolutional layer, obtaining a convolution result in accordance with the convolution operation, and performing fully connected mapping on the convolution result through a preset fully connected layer.

Abstract: The present disclosure provides an audio system. The audio system includes: a target audio signal generator module including a plurality of target audio signal generators, configured to receive an audio signal and a tracking signal and generate a plurality of target audio signals based on the audio signal and tracking signal; a tracking power supply circuit module including a plurality of tracking power supply circuits, configured to receive the plurality of target audio signals and generate a plurality of power supply voltages based on the plurality of target audio signals; an audio power amplifying circuit module including a plurality of audio amplifying circuits, configured to receive the plurality of target audio signals and the plurality of power supply voltages, and amplify the plurality of target audio signals; wherein each of the plurality of tracking power supply circuits provides a corresponding power supply voltage for each of the plurality of audio amplifying circuits.

Abstract: The present disclosure provides a power filter. The power filter may include an overvoltage protection circuit and an LC filter circuit connected to the overvoltage protection circuit, wherein the overvoltage protection circuit includes a voltage regulator and a peak compensation circuit. The peak compensation circuit is configured to generate a gain peak at a resonance frequency of the LC filter circuit, so as to compensate for a gain dip at the voltage regulator stage occurring at the resonance frequency of the LC filter circuit.

Abstract: Embodiments of this application disclose methods, systems, and devices for medical image analysis and medical video stream processing. In one aspect, a method comprises extracting video frames from a medical image video stream that includes at least two pathological-section-based video frames. The method also comprises identifying single-frame image features in the video frames, mapping the single-frame image features into single-frame diagnostic classification results, and performing a classification mapping based on a video stream feature sequence that comprises the single-frame image features. The classification mapping comprises performing a convolution operation on the video stream feature sequence through a preset convolutional layer, obtaining a convolution result in accordance with the convolution operation, and performing fully connected mapping on the convolution result through a preset fully connected layer.

Abstract: A system for identifying arrhythmias based on cardiac waveforms includes a storage system storing a trained deep neural network system, wherein the trained deep neural system includes a trained representation neural network and a trained classifier neural network. A processing system is communicatively connected to the storage system and configured to receive cardiac waveform data for a patient, identify a time segment in the cardiac waveform data, and transform the time segment into a spectrum image. The processing system is further configured to generate, with the representation neural network, a latent representation from the spectrum image, and then to generate, with the classifier neural network, an arrhythmia classifier from the latent representation.

Abstract: A device for engagement with a bone includes a dynamically expandable tip (12), a dynamically expandable ring (40), or other dynamically expandable insert (60, 62, 401L) that reacts to forces pushing the implant into bone tissue. The tip (12), ring (40) or insert (60, 62, 401L) expands at least normal to the direction of motion, increasing contact area between the surrounding bone tissue and the material and thereby reducing the occurrence of high areas of contact stress in the adjacent bone tissue. The tip (12), ring (40) or insert (60, 62, 401L) translates forces along an axis of motion into lateral frictional forces that can resist penetration into the bone tissue without the need for additional operator or patient interaction. A method of reducing migration of the device for engagement includes the steps of providing the device and inserting the device within bone tissue.

Abstract: A system for identifying arrhythmias based on cardiac waveforms includes a storage system storing a trained deep neural network system, wherein the trained deep neural system includes a trained representation neural network and a trained classifier neural network. A processing system is communicatively connected to the storage system and configured to receive cardiac waveform data for a patient, identify a time segment in the cardiac waveform data, and transform the time segment into a spectrum image. The processing system is further configured to generate, with the representation neural network, a latent representation from the spectrum image, and then to generate, with the classifier neural network, an arrhythmia classifier from the latent representation.

Abstract: A sensing system for a resource recovery system is provided. The sensing system includes at least one sensing sub-assembly and a sensing computing device. The sensing computing device is configured to receive, from the at least one sensing sub-assembly, at least one signal that includes at least one pulse having at least one pulse peak. The sensing computing device is also configured to identify the at least one pulse peak which has a magnitude and a signal-to-noise ratio, and retrieve the at least one pulse peak from the at least one signal using the magnitude and the signal-to-noise ratio of the at least one pulse peak. The sensing computing device is further configured to store the at least one pulse peak within a database that includes one or more pulse peaks, and generate a component report that identifies one or more changes of at least one component.

Abstract: A sensing sub-assembly for use with a drilling assembly that includes a cylindrical body including an internal flow channel extending therethrough. The internal flow channel is configured to channel a first fluid therethrough. A recessed cavity is also defined therein. The recessed cavity is coupled in flow communication with an ambient environment exterior of the cylindrical body, and a second fluid flows within the ambient environment. The recessed cavity is configured to receive a continuous stream of the second fluid therethrough. At least one sensor is coupled to the cylindrical body, and the at least one sensor is configured to determine characteristics of the second fluid in the continuous stream that flows through the recessed cavity.

Abstract: An occlusion and/or reopening of an artery of a body caused by a changing pressure applied on the artery is detected. The systolic blood pressure of an artery of a body is also measured. A Doppler Ultrasound transducer attached to the exterior of the body outputs a blood flow signal indicative of a change of the blood flow in the artery caused by the changing pressure. At least one variable of a first variable indicative of the magnitude of the blood flow and a second variable indicative of the periodicity of the blood flow is derived from the blood flow signal. The occlusion and/or reopening of the artery is detected on the basis of the at least one variable. In this way, the occlusion/reopening of the artery can be detected automatically. Since the need to manually detect the occlusion and reopening of the artery by listening with a stethoscope or a Doppler probe is eliminated, the detecting result is more predictable and repeatable, and therefore also more accurate.

Abstract: A device for engagement with a bone includes a dynamically expandable tip (12), a dynamically expandable ring (40), or other dynamically expandable insert (60, 62, 401L) that reacts to forces pushing the implant into bone tissue. The tip (12), ring (40) or insert (60, 62, 401L) expands at least normal to the direction of motion, increasing contact area between the surrounding bone tissue and the material and thereby reducing the occurrence of high areas of contact stress in the adjacent bone tissue. The tip (12), ring (40) or insert (60, 62, 401L) translates forces along an axis of motion into lateral frictional forces that can resist penetration into the bone tissue without the need for additional operator or patient interaction. A method of reducing migration of the device for engagement includes the steps of providing the device and inserting the device within bone tissue.

Abstract: This invention provides a method and a device for detecting occlusion and/or reopening of an artery of a body caused by a changing pressure applied on the artery as well as a system for measuring the systolic blood pressure of an artery of a body. The method comprises the steps of: obtaining a blood flow signal indicative of a change of the blood flow in the artery caused by the changing pressure, using a Doppler Ultrasound transducer attached to the exterior of the body; deriving, from the blood flow signal, at least one variable of a first variable indicative of the magnitude of the blood flow and a second variable indicative of the periodicity of the blood flow; and detecting the occlusion and/or reopening of the artery on the basis of the at least one variable. In this way, the occlusion/reopening of the artery can be detected automatically.

Abstract: A mechanism to connect the supporting portions of orthopaedic implants such as in the head, spine, upper limb and lower limb and thereby prevent loosening and fretting at the implant interface of an orthopaedic implant construct has been developed based on shape memory effect and super-elasticity of shape memory materials such as nickel-titanium (nitinol or NiTi) shape-memory-alloy, without the use of typical threaded fastening technique. Advantages are conferred by making the entire device, not just connecting pieces, out of shape memory alloy and having shape memory effect and super-elasticity. Heating the memory head of the device will compress the connection portion without the use of an auxiliary device (e.g. coupling member) so that the connection portion can be completely clamped down by the memory head.

Abstract: The present invention provides bioactive bone cements that not only have sufficient radiopacity, low physiological toxicity, and requisite mechanism strength, but also promote local bone in-growth. The bone cement utilizes strontium salts as radiopacifiers, and comprises a powder component and a liquid component. In an embodiment, the powder component comprises a strontium salt, poly(methyl methacrylate) (PMMA), and a polymerization initiator; and the liquid component comprises methyl methacrylate (MMA) as reactive monomers and a polymerization accelerator.

Abstract: The present invention relates to a bone fixation device having a fixation member using a shape memory effect to secure bone fractures, including but not limited to, femur, tibia and humerus fractures. The fixation member can be malleable at a room temperature, but become rigid at a body temperature because of the shape memory effect, such as derived from a super-elastic property found in such as a nickel titanium alloy. The fixation member can be formed on one or more of the shaft portion and the two end portions of a nail member for securing bone fractures, such as by providing translational and rotational stabilities. The fixation member is also capable of providing a continuous and controllable compression force over the fractured bone, if needed.

Abstract: The present invention relates generally to a shape memory and/or super-elastic material, such as a nickel titanium alloy. Additionally or alternatively, the present invention relates to a super-elastic or pseudo-elastic material that has an initial transition temperature Af above a body temperature. The shape memory material can have a super-elasticity or pseudo-elasticity property at a temperature below the initial transition temperature Af of the material. For example, the shape memory material can have its workable temperature for producing super-elasticity or pseudo-elasticity of about 0° C. to 15° C. below the initial transition temperature Af. The shape memory material can be malleable at a room temperature, and become super-elastic or pseudo-elastic at a body temperature. In addition, the present invention relates to a method of making a shape memory or a super-elastic material.

Abstract: The present invention relates generally to a shape memory and/or super-elastic material, such as a nickel titanium alloy. Additionally or alternatively, the present invention relates to a super-elastic or pseudo-elastic material that has an initial transition temperature Af above a body temperature. The shape memory material can have a super-elasticity or pseudo-elasticity property at a temperature below the initial transition temperature Af of the material. For example, the shape memory material can have its workable temperature for producing super-elasticity or pseudo-elasticity of about 0° C. to 15° C. below the initial transition temperature Af. The shape memory material can be malleable at a room temperature, and become super-elastic or pseudo-elastic at a body temperature. In addition, the present invention relates to a method of making a shape memory or a super-elastic material.