Abstract: A medical image classification method such as CT (or CAT) scans includes receiving the CT scan or medical image, inputting the medical image into an image classification model, which provides a cross entropy (CE) loss function and an aggregated cross entropy (ACE) loss function. According to the ACE loss function, image samples with generic label are used as input data during model training. The medical image can be classified by using the image classification model, and a classification of the medical image is thereby obtained. The present disclosure can classify indeterminate or general medical images and even unlabeled images and thus realize supervision of medical data. A device for applying the method is also provided.

Abstract: An engine enclosure for containing a gas turbine engine is provided. An exemplary engine enclosure includes features that improve noise and thermal attenuation, reduce the weight of the enclosure, and provide for more accessible access points to the interior volume of the engine enclosure.

Abstract: A fracture detection method executed by an electronic device is provided. The fracture detection method includes obtaining a to-be-detected image; using a Fully Convolutional Networks (FCN) model to process the to-be-detected image to obtain a fracture probability map of the to-be-detected image; performing a maximum pooling process on the fracture probability map to obtain a first fracture probability; extracting Regions of Interests (ROIs) of the to-be-detected image based on the FCN model; inputting the ROIs into a classification model to obtain a second fracture probability; calculating a product of the first fracture probability and the second fracture probability as a probability of a fracture phenomenon in the to-be-detected image. The present disclosure combines the FCN model and the ROIs to realize an automatic fracture detection, and the accuracy is higher. A device employing the method is also disclosed.

Abstract: A medical image classification method such as CT (or CAT) scans includes receiving the CT scan or medical image, inputting the medical image into an image classification model, which provides a cross entropy (CE) loss function and an aggregated cross entropy (ACE) loss function. According to the ACE loss function, image samples with generic label are used as input data during model training. The medical image can be classified by using the image classification model, and a classification of the medical image is thereby obtained. The present disclosure can classify indeterminate or general medical images and even unlabeled images and thus realize supervision of medical data. A device for applying the method is also provided.

Abstract: A fracture detection method executed by an electronic device is provided. The fracture detection method includes obtaining a to-be-detected image; using a Fully Convolutional Networks (FCN) model to process the to-be-detected image to obtain a fracture probability map of the to-be-detected image; performing a maximum pooling process on the fracture probability map to obtain a first fracture probability; extracting Regions of Interests (ROIs) of the to-be-detected image based on the FCN model; inputting the ROIs into a classification model to obtain a second fracture probability; calculating a product of the first fracture probability and the second fracture probability as a probability of a fracture phenomenon in the to-be-detected image. The present disclosure combines the FCN model and the ROIs to realize an automatic fracture detection, and the accuracy is higher. A device employing the method is also disclosed.

Abstract: The present disclosure provides a clinical target volume delineation method and an electronic device. The method includes: receiving a radiotherapy computed tomography (RTCT) image; and obtaining a plurality of binary images by delineating a gross tumor volume (GTV), lymph nodes (LNs), and organs at risk (OARs) in the RTCT image. A SDMs for each of the binary images is calculated. The RTCT image and all the SDM are finally input into a clinical target volume (CTV) delineation model; and a CTV in the RTCT image is delineated by the CTV delineation model. An automatic delineation of the CTV of esophageal cancer are realized, a delineation efficiency is high and a delineation effect is good.

Abstract: In a GTV segmentation method, a PET-CT image pair and an RTCT image of a human body are obtained. A PET image in the PET-CT image pair is aligned to the RTCT image to obtain an aligned PET image. A first PSNN performs a first GTV segmentation on the RTCT image to obtain a first segmentation image. The RTCT image and the aligned PET image are concatenated into a first concatenated image. A second PSNN performs a second GTV segmentation on the first concatenated image to obtain a second segmentation image. The RTCT image, the first segmentation image, and the second segmentation image are concatenated into a second concatenated image. A third PSNN performs a third GTV segmentation on the second concatenated image to obtain an object segmentation image.

Abstract: In a GTV segmentation method, a PET-CT image pair and an RTCT image of a human body are obtained. A PET image in the PET-CT image pair is aligned to the RTCT image to obtain an aligned PET image. A first PSNN performs a first GTV segmentation on the RTCT image to obtain a first segmentation image. The RTCT image and the aligned PET image are concatenated into a first concatenated image. A second PSNN performs a second GTV segmentation on the first concatenated image to obtain a second segmentation image. The RTCT image, the first segmentation image, and the second segmentation image are concatenated into a second concatenated image. A third PSNN performs a third GTV segmentation on the second concatenated image to obtain an object segmentation image.

Abstract: Foreign object damage (FOD) screen assemblies and gas turbine engine compartments having FOD screen assemblies are provided. FOD screen assemblies provided herein are formed of materials that reduce the overall weight of the assembly such that easier handling and repair of the FOD screen assembly may be achieved. Further, the FOD screen assemblies provided herein include features that provide for a secure attachment of one or more mesh members to frame members of the assembly. The one or more mesh members are secured to the frame members in such a way that minimal stress is placed on the mesh member at the attachment points.

Abstract: An apparatus may include a transmitter capable of sending a signal to a device that is configured with an action module that interprets the signal and a programming module, a dial that is adjustable to a plurality of positions, where position is matched by the programming module with a programmable action, and a button that is communicatively coupled to the transmitter and that, when pressed, triggers the transmitter to send to the device the signal indicating the current position of the dial, such that the action module activates a programmable action associated with the current position of the dial in response to the button being pressed. Various other apparatuses, systems, and methods are also disclosed.

Abstract: A defibrillator assesses cardio pulmonary resuscitation carried out on a subject and provides feedback. The defibrillator measures bio signals of the subject, determines when CPR is required and produces a start signal and determines and when CPR is no longer required and produces a stop signal. A measurement system measures compression signals during CPR chest compressions, a CPR assessment system receives the CPR start signal and the CPR stop signal and receives compression signals. The defibrillator uses the compression signals to establish a first CPR performance measurement, set a performance baseline of the person equal to the first CPR performance measurement of the person, compare the further CPR performance measurement of the person with the CPR performance baseline of the person, produce a feedback signal and set the CPR performance baseline of the person equal to the further CPR performance measurement of the person and return to earlier operations.

Abstract: Methods include processing image data through a plurality of network stages of a progressively holistically nested convolutional neural network, wherein the processing the image data includes producing a side output from a network stage m, of the network stages, where m>1, based on a progressive combination of an activation output from the network stage m and an activation output from a preceding stage m?1. Image segmentations are produced. Systems include a 3D imaging system operable to obtain 3D imaging data for a patient including a target anatomical body, and a computing system comprising a processor, memory, and software, the computing system operable to process the 3D imaging data through a plurality of progressively holistically nested convolutional neural network stages of a convolutional neural network.

Abstract: An engine enclosure for containing a gas turbine engine is provided. An exemplary engine enclosure includes features that improve noise and thermal attenuation, reduce the weight of the enclosure, and provide for more accessible access points to the interior volume of the engine enclosure.

Abstract: Foreign object damage (FOD) screen assemblies and gas turbine engine compartments having FOD screen assemblies are provided. FOD screen assemblies provided herein are formed of materials that reduce the overall weight of the assembly such that easier handling and repair of the FOD screen assembly may be achieved. Further, the FOD screen assemblies provided herein include features that provide for a secure attachment of one or more mesh members to frame members of the assembly. The one or more mesh members are secured to the frame members in such a way that minimal stress is placed on the mesh member at the attachment points.

Abstract: Compositions for providing hair care benefits, such as smoothing, anti-static control, color protection, frizz control and moisturization are disclosed. The compositions maintain clarity, show no separation upon standing, and remain flowable liquids at room temperature. The compositions comprise a premix consisting essentially of (a) siloxane polymers containing one or more functional groups selected from amino, phenyl, methoxy, hydroxyl, fatty alcohol, fatty acid, alkyl and combinations thereof; and (b) materials selected from dimethicones having a viscosity of from about 20 to about 10,000 centipoise, mono-esters containing 20 or fewer carbon atoms, ethers containing 20 or fewer carbon atoms, linear or branched hydrocarbons containing 12 to 20 carbon atoms, and combinations thereof. The compositions can be applied directly to hair (i.e., “neat”) or via conventional hair treatment compositions, such as shampoos or conditioners.

Abstract: A pull-activated applicator includes a barrel, a pledget, a finger grip, and a deployment element. The pledget includes a withdrawal string and is located within the barrel. The barrel, the pledget, and the deployment element are configured such that application of a force to the deployment element in a first direction deploys the pledget and withdrawal string from the barrel in a second direction generally opposite the first direction.

Abstract: An electric bicycle and electric bicycle frame including batteries or a battery pack stored in one or more tubes of the frame. In some cases, a pair of top tubes extend rearward of the bicycle seat tube, and an electronics housing may be disposed between the rearward extending top tube portions. Alternatively or in addition, a removable bottom bracket shell portion and a removable bottom bracket insert may be provided, to allow convenient access to the interior portions of the down tube and/or seat tube of the frame. A battery pack and/or a battery electronics management unit may be conveniently within one or both of the down tube and the seat tube.

Abstract: A pull-activated applicator includes a barrel, a pledget, a finger grip, and a deployment element. The pledget includes a withdrawal string and is located within the barrel. The barrel, the pledget, and the deployment element are configured such that application of a force to the deployment element in a first direction deploys the pledget and withdrawal string from the barrel in a second direction generally opposite the first direction.

Abstract: A pull-activated applicator includes a barrel, a pledget, a finger grip, and a deployment element. The pledget includes a withdrawal string and is located within the barrel. The barrel, the pledget, and the deployment element are configured such that application of a force to the deployment element in a first direction deploys the pledget and withdrawal string from the barrel in a second direction generally opposite the first direction.

Abstract: A debris protector for use with a vehicle lamp assembly installed to an opening in a vehicle body panel or garnish to prevent the migration of accumulated road debris through a gap between the lamp assembly and the body panel opening. Such a debris protector is generally in the form of a cover element that is installable along an upper, hidden portion of a vehicle lamp assembly and an inner surface of a corresponding vehicle body panel or garnish to prevent road debris from accumulating on the lamp assembly near the body panel opening. Such a debris protector may also include a seal that is located between the cover element and the rear surface of a body panel or garnish to assist with the debris blocking function of the cover element.