31results about How to "Increase the likelihood of survival" patented technology

The invention provides a device and method for achieving preoperative assessment of a congenital heart disease operation plan based on 3D printing. The method comprises the steps that normal person chest CT information is acquired, a normal person heart and lateral branch blood vessel stereo structure model is printed in a 3D mode, a normal person model is connected with an extracorporeal circulation machine to obtain normal person heart and lateral branch blood vessel physiological parameters, and then a standard contrast table is established; the normal person chest CT information is acquired, a doctor conducts simulated operation on a patient CT image, the normal person heart and lateral branch blood vessel stereo structure model after simulated operation is printed in a 3D mode, and the normal person model is connected with the extracorporeal circulation machine to obtain patient lateral branch blood vessel physiological parameters; the standard contrast table shows that the physiological parameter differences of a patient and a normal person are acceptable by the doctor. The risk brought by direct operative treatment performed by the doctor based on experiences is avoided, simulation of operative operation performed by the doctor is promoted, and the survival probability of the patient is improved.

The invention discloses a pulmonary nodule false positive sample inhibition method based on 3D CNN (convolutional neural networks). The pulmonary nodule false positive sample inhibition method comprises steps that 1) 3D reconstruction of a lung CT is carried out by adopting interpolations; 2) according to a to-be-inhibited sample coordinate, a cube of a fixed size is cut from reconstruction data, and is normalized, and then positive samples are expanded, and then negative samples and positive samples are used as the training data of the 3D CNN together; 3) a training sample is used to train a 3D CNN model; 4) during the model training, weighting correction of a standard loss function is carried out, and different weights are provided for the negative samples and the positive samples. A training network is cycled and iterated, and finally, the 3D CNN model is acquired. The method based on the 3D CNN training model is advantageous in that on one hand, the three-dimensional characteristics of the lung CT data are effectively used, and sample information is reflected to the greatest extent; and on the other hand, the weighting of the loss function is carried out during the model training, a problem of true and false sample imbalance is solved, and therefore the model having good pulmonary nodule identification effect is acquired after the training.

The invention discloses an emergency hammer, and relates to the technical field of escape tools. The emergency hammer comprises a U-shaped clamp, a hammer head and a positioning pin, wherein the U-shaped clamp and the hammer head are fixed together; the positioning pin is arranged in the U-shaped clamp; the U-shaped clamp is used for clamping the end, provided with a power line interface and / or adata line interface and / or an earphone wire interface, of a mobile terminal; and the positioning pin is used for being inserted into the power line interface and / or the data line interface and / or theearphone wire interface and positioning the hammer head when the U-shaped clamp clamps the end, provided with the power line interface and / or the data line interface and / or the earphone wire interface, of the mobile terminal. The emergency hammer is small in size and convenient to carry and use, and can help improve the survival possibility of the passengers in the dangerous situation.

The location capable mobile handset allows the user to provide a call recipient with the location of an unsuccessful attempted emergency call. In one specific example, the call may be an E911 call toa PSAP dispatcher. Additionally, the call may be to a towing service, or to a family member or friend to request assistance. The call may be any call that a mobile handset user wants to send locationinformation to the party that has been called. Returning to the E911 call example, the location information reported to dispatcher can include the location of initial E911 call, current location during a successful E911 call, or ground track information from the initial location to the current location. When an E911 call is unsuccessfully attempted, the mobile handset stores the location of the mobile handset at that time. This information can later be transmitted when the mobile handset is in a coverage area. Additionally, the mobile handset can auto-dial 911 upon entering a service area after an unsuccessful E911 attempt. Alternately the user can be prompted to initiate an E911 call when the mobile handset enters a service area.

The present invention relates to the technical field of automatic driving, and discloses an automatic driving system capable of monitoring the driver's safety state, including a state collection module, an information processing module and an action execution module. The state collection module obtains the driver's current sign state information, and The sign status information is sent to the information processing module, and the information processing module compares the acquired sign status information with the preset information and outputs a judgment instruction, and the action execution module controls the execution unit to execute the rescue strategy according to the judgment instruction. The present invention monitors the driver's physical sign information in real time, and when it is found that the driver is unable to operate the vehicle, it can call the automatic driving system to take over the vehicle in time, and execute the corresponding rescue strategy to rescue the driver, thus reducing driving time. When the driver is in a sudden state and loses the ability to control the vehicle, the probability of a vehicle driving accident occurs, and at the same time, the driver can be rescued in time through relevant rescue strategies.