87 results about "PET-CT" patented technology

The invention discloses a nasopharyngeal-carcinoma (NPC) lesion automatic-segmentation method and nasopharyngeal-carcinoma lesion automatic-segmentation systems based on deep learning. The method comprises: carrying out registration on a PET (Positron Emission Tomography) image and a CT (Computed Tomography) image of nasopharyngeal carcinoma to obtain a PET image and a CT image after registration;and inputting the PET image and the CT image after registration into a convolutional neural network to carry out feature representation and scores map reconstruction to obtain a nasopharyngeal-carcinoma lesion segmentation result graph. The method carries out registration on the PET image and the CT image of the nasopharyngeal carcinoma, obtains a nasopharyngeal-carcinoma lesion by automatic segmentation through the convolutional neural network, and is more objective and accurate as compared with manual segmentation manners of doctors; and the convolutional neural network in deep learning isadopted, consistency is better, feature learning ability is higher, the problems of dimension disasters, easy falling into a local optimum and the like are solved, lesion segmentation can be carried out on multi-modal images of the PET-CT images, and an application range is wider. The method can be widely applied to the field of medical image processing.

The invention discloses a PET-CT scanning imaging method and a related imaging method. The PET-CT scanning imaging method comprises that an area to be imaged is positioned and scanned, the positioning image of the area to be imaged is obtained and displayed, and the displayed positioning image is used for a user to determine the scanning area; the scanning area information which is input by the user is received, the PET total scanning area is determined according to the scanning area information; the PET total scanning area generates a plurality of PET sub scanning areas, each PET sub scanning area corresponds to a PET scanning bed, and the PET sub scanning areas are superposed to cover the PET total scanning area completely,; multi-bed PET scanning is carried out; CT scanning is carried out; and scanning data are reconstructed to obtain PET-CT images. According to the invention, unrelated scanning areas in the PET-CT scanning imaging process are eliminated, the PET-CT scanning time is shortened, and the CT radiation dose received by a patient in the PET-CT scanning imaging process is reduced.

The invention discloses a CT or PET-CT system and a positioning method for conducting scanning through the CT or PET-CT system. The CT or PET-CT system comprises an imaging device and a picture processing device. A patient can not suffer X-ray radiation when positioning is conducted through the CT or PET-CT system, and potential health hazards of the patient are reduced. In addition, in a positioning method for conducting scanning through an existing CT or PET-CT system, an examining table is usually required to move for a quite long time, the examining table scans the patient in the moving process to obtain locating plates, and subsequent examining can be further scheduled only according to the locating plates, and the positioning method mainly includes the steps of obtaining scanning a starting position parameter of the examining table and a scanning stopping position parameter of the examining table. However, by means of the positioning method for conducting scanning through the existing CT or PET-CT system, positioning time is too long. The examining table is kept still when positioning is conducted through the CT or PET-CT system, the scanning starting position of the examining table and the scanning stopping position of the examining table can be known by taking pictures, measuring the electronic pictures and conducting calculation, and positioning time is shortened.

The invention belongs to the field of biomedical image processing and specifically relates to a PET-CT lung tumor segmentation method combining a three dimensional graph cut algorithm with a random walk algorithm. The method comprises the following steps of: performing linear up-sampling on an original PET image and performing affine registration on PET and CT images; calibrating tumor seed points and non-tumor seed point; performing random walk algorithm segmentation on the PET image in combination with the tumor seed points; acquiring a foreground target area Ro completely including a target lung tumor area, using the areas, except the Ro, as a background area Rb of a non-lung tumor area; establishing gauss mixture models for the foreground area Ro and the background area Rb separately; computing energy items according to the gauss mixture models of the foreground area Ro and the background area Rb and obtaining a final segmentation result by using an graph cut algorithm. The method fully utilizes the function information and the PET image and the structure information of the CT image, enables complements between the random walk algorithm and the graph cut algorithm, and achieves an accurate lung tumor segmentation result.

A radiation detector (16) having a first detector layer (24) and a second detector layer (26) encircles an examination region (14). Detectors of the first layer include scintillators (72) and light detectors (74), such as avalanche photodiodes. The detectors of the second detector layer (26) include scintillators (62) and optical detectors (64). The scintillators (72) of the first layer have a smaller cross-section than the scintillators (62) of the second layers. A group, e.g., nine, of the first layer scintillators (72) overlay each second group scintillator (62). In a CT mode, detectors of the first layer detect transmission radiation to generate a CT image with a relatively high resolution and the detectors of the second layer detect PET or SPECT radiation to generate nuclear data for reconstruction into a lower resolution emission image. Because the detectors of the first and second layers are aligned, the transmission and emission images are inherently aligned.

The invention provides an installation and alignment indicating device and an installation and alignment indicating method for PET-CT (positron emission tomography-computed tomography) frameworks. The installation and alignment indicating method includes respectively installing a CT (computed tomography) center indicating assembly and a PET(positron emission tomography) center indicating assembly on a CT framework rotary portion and a PET framework; enabling a laser device of the CT center indicating assembly to emit a laser beam to the PET framework, adjusting front and back supporting point positions of the PET frameworks, aligning the laser beam to a first center indicator and a second center indicator of the PET center indicating assembly and aligning a CT rotation center to the center of a PET detector at the moment. The laser beam is used for indicating the CT rotation center. The installation and alignment indicating device and the installation and alignment indicating method have the advantages that the installation and alignment indicating device is simple in structure and convenient to adjust, influence of CT center assembly machining and installation errors can be eliminated, the alignment precision is high, and the requirement on the installation coaxiality of the center of the PET detector and the CT rotation center can be assuredly met.

The invention discloses PET-CT equipment and a travel mechanism of a barrier, wherein the disclosed travel mechanism comprises a frame for supporting the barrier and a guide rail arranged on the frame and extending in the axial direction; the barrier is capable of moving along the guide rail; the travel mechanism further comprises a driving device for driving the barrier to move; and the driving device is directly arranged on the frame. The driving device of the travel mechanism is directly arranged on the frame; as a result, the driving device can be basically located in the space between the solid part of the frame and the guide rail without increasing the axial length of the whole travel mechanism; and the axial length of the whole travel mechanism can be basically controlled to be the sum of the axial lengths of the frame and the guide rail so that the axial space is thoroughly utilized. Compared with the scheme of arranging the driving device in the axial direction on the basis of the end portion of the guide rail in the background art, apparently, the scheme of directly arranging the driving device on the frame is capable of obviously reducing the integrated length of the travel mechanism; therefore, the distance between the PET machine and the CT machine is reduced.

The invention relates to a radioactive fluorine labeled Larotrectinib compound and a preparation method thereof, in particular, an in vivo imaging agent for Trk receptor subtype in refractory solid tumors, the present invention provides a radiofluorocompound 18F-Larotrectinib and 18F-Larotorectinib analogues based on a novel inhibitor Larotrectinib for tyrosine receptor kinase (TRK), and more particularly a preparation method of the Larotrectinib and its analogue radioactive fluorine-18 labeled compound 18F-Larotdirectinib and its 18F-Larotorectinib analogue. Compared with the prior art, the invention has the advantages of fast reaction speed, relatively mild condition, simple operation, short reaction time and simple post-treatment, and the prepared carrier-free radioactive label compounds have high radiochemical purity and positron emission characteristics, and PET-CT positron emission tomography can be used, so as to visually display the distribution of Larotrectinib compounds and their analogues in vivo and tumors, and a new imaging agent for early diagnosis of tumors is provided.

The invention discloses a PET-CT (positron emission tomography-computed tomography) scanning device and a control method of the PET-CT scanning device. The PET-CT scanning device comprises a CT machine and a PET machine, wherein a luminous screen is arranged at a connecting part of the CT machine and the PET machine, the PET machine comprises a rebuilding computer, a coincidence circuit board and a PET control circuit board, the PET control circuit board is connected with the coincidence circuit board, the coincidence circuit board is connected with the rebuilding computer, and the PET control circuit board is connected with a driving circuit board of the luminous screen. The PET-CT scanning device and the control method of the PET-CT scanning device provided by the invention have the advantages that the body position change information of patients can be obtained through collecting light environment signal changes, so the scanning mages can be more accurately rebuilt.

The invention relates to a PET-CT (Positron Emission Tomography-Computed Tomography) arrangement system capable of reducing the stroke of a scanning table and a disassembling and assembling method of the PET-CT arrangement system. The PET-CT arrangement system comprises a PET machine, a CT machine, a sickbed, two groups of main supporting units, two groups of guide rail units, two groups of sickbed supporting units and two groups of sickbed synchronous moving units, wherein the PET machine is provided with a PET rack; the PET machine is arranged at the front side of the CT machine; the sickbed is arranged in front of the PET machine; the main supporting units are respectively arranged at two sides of the bottom part of the PET machine and are used for supporting, aligning and adjusting the PET machine; the guide rail units are respectively and detachably arranged at the front sides of the main supporting units; the PET rack can slide from the main supporting units to the guide rail units; the sickbed supporting units are used for supporting and locating the sickbed; the sickbed synchronous moving units are arranged on the sickbed supporting units and can move on the sickbed supporting units; each sickbed synchronous moving unit comprises a flexible connecting device; the flexible connecting devices are detachably connected with the PET rack. According to the PET-CT arrangement system disclosed by the invention, the separation of the PET machine and the CT machine is simple and easy, and the time for adjusting a scanning axis after the separated PET machine is reset is greatly reduced.

The invention provides an MRI/PET/CT/PET-CT panoramic video auxiliary system which is applied in scanning detection of MRI, PET, CT, PET-CT and the like to acquire and monitor human pose states on a scanning bed in a scanning rack hole in real time. The system comprises a video synchronous acquisition module composed of multiple wide-angle cameras and a pose adjusting device thereof, a video preprocessing module for performing video distortion correction processing, a video splicing module for performing fusion splicing on video overlapping areas, a video storage module for storing spliced videos and a video display module for displaying the spliced videos. According to the system, GPU parallel computing multi-thread control is adopted, and video acquisition, preprocessing, splicing, display and storage are carried out by using a translation and variable diameter rotation composite motion model. The system can meet direct and complete observation of body position change when a doctor scans a patient.

The invention provides a PET-CT dynamic medical image intelligent quantitative analysis system and analysis method. The PET-CT dynamic medical image intelligent quantitative analysis system comprises a medical image information management sub-system connected with a medical service mechanism information system, a user information management sub-system, a medical image quantitative analysis sub-system connected with the user information management sub-system and the medical image information management sub-system separately, an information interaction module to which the medical image information management sub-system and the medical image quantitative analysis sub-system are connected, and a user terminal. The medical image quantitative analysis sub-system has a built-in PET-CT quantitative analysis system; the information interaction module is used for displaying quantitative analysis results. Dynamic model parameters can be optimized through a hybrid intelligent optimization algorithm. An accurate region of interest can be obtained by calculation through a time-radioactivity curve set based on dynamic feature distribution. The system can provide individualized quantitative analysis service through update and study of user experience.

A Photodynamic Therapy (PDT) system with an elongated interventional device (IDV) with a bundle of optical fibers (F1, F2, F3) forming respective light exit ports which can be individually accessed. The bundle has an optical shape sensing fiber (OSS), e.g. including Fiber Bragg Gratings, arranged for sensing position and orientation (P_O) of the light exit ports. A processor executes a control algorithm which generate a light dose signal (LDS) to allow generation of light outputs (LD1, LD2, LD3) to the plurality of optical fibers (F1, F2, F3) accordingly. The control algorithm generates the light dose signal (LDS) in response to the determined position and orientation of the light exit ports (P_O), and three-dimensional body anatomy image information obtained by a first image modality (I1), e.g. X-ray, MRI, CT, ultrasound, or PET-CT. This combination allows precise application of a light dose distribution for PDT treatment of a tumor with a minimal destruction of connective tissue. In embodiments, the control algorithm takes image information regarding distribution of a photo sensitizer in the body tissue (I2) as input. The control algorithm may further take into account image information regarding a concentration of oxygen in the body tissue (I3). Both of such inputs allow a more precise PDT light application.

A method and device for stereoscopically and directionally examining the PET-CT and MRI images of skull at same time by combining them together is disclosed. The same layer of skull for PET-CT and MRI images can be precisely repeated and combined for processing, so directly and really showing the lesion in skull.

The invention discloses a pulmonary nodule diagnosis method based on a double-mode extreme learning machine. The method comprises the steps that firstly, pulmonary nodule PET-CT images are subjected to autonomous characteristic learning by using a self-encoding network with the supervision depth respectively, then, the extracted CT characteristics and PET characteristics are subjected to characteristics layer fusion, and finally, the fusion characteristics are classified by using a classifier. The method is simple and easy to implement, the identification accuracy is high, and according to the PET-CT images of pulmonary nodules, the benign and malignancy of the pulmonary nodules in the PET-CT images can be automatically and accurately identified based on the deep learning technology and the characteristic fusion method respectively.

The invention relates to a method for detecting the position of a hub motor of a PET-CT (Positron Emission Tomography-Computed Tomography) machine on the basis of a magnetic ring and a Hall sensor, which comprises the following steps of: in the operating process of the hub motor of the PET-CT machine, detecting a position detection ring driven by a rotor of the hub motor of the PET-CT machine by the linear Hall sensor, wherein the electromagnetic induction is generated between the linear Hall sensor and the position detection ring to generate a Hall electric potential; comparing the measured Hall electric potential with a standard value in a comparator, outputting a comparison result and judging whether the hub motor of the PET-CT machine operates to the accurate position or not by the comparison result; and when the hub motor of the PET-CT machine is started, after carrying out positioning and control of a rotating speed on an initial position of the motor by an absolute position sensor, ensuring the absolute position sensor to enter a detection state and controlling current phase conversion of the motor by a relative position sensor. Due to the adoption of the method for detecting the position of the hub motor of the PET-CT machine on the basis of the magnetic ring and the Hall sensor, the influence of position error, which is caused by the problems of magnetic asymmetry and strength of a magnetic field in the manufacturing and working process of magnetic steel of the motor of the PET-CT machine, is greatly weakened and the position accuracy of the motor is improved.

The invention discloses a separate-rod-source telescoping mechanism for PET-CT and a control method thereof. The separate-rod-source telescoping mechanism for PET-CT comprises a sliding head, a shift plate, a shifting mechanism and a motor. The sliding head is disposed at the tail end of a rod source. The shifting mechanism disposed on the frame locates behind the rod source and is parallel to the same. The shift plate is disposed at the front end of the shifting mechanism which is connected with the motor. The sliding head is in a channel shape with two open sides. The shift plate locates in a channel of the sliding head and can separate from the side. The sliding head and the shift plate are separable; the shifting mechanism driving the rod source to telescope is fixed; when the rod source needs to telescope, the shift plate locating in the sliding head contacts with the rod source and pushes the rod source to telescope; when the rod source rotates, the shift plate does not contact with the sliding head, and the rod source is not affected in rotation. The mechanism is low in cost of converting telescoping and rotating of the rod source and is simple in structure.