CN112641428B - Diagnosis device, diagnosis equipment and diagnosis system for brain injury condition - Google Patents
Diagnosis device, diagnosis equipment and diagnosis system for brain injury condition Download PDFInfo
- Publication number
- CN112641428B CN112641428B CN202011506999.9A CN202011506999A CN112641428B CN 112641428 B CN112641428 B CN 112641428B CN 202011506999 A CN202011506999 A CN 202011506999A CN 112641428 B CN112641428 B CN 112641428B
- Authority
- CN
- China
- Prior art keywords
- node
- index
- brain
- brain function
- near infrared
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0075—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence by spectroscopy, i.e. measuring spectra, e.g. Raman spectroscopy, infrared absorption spectroscopy
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
- A61B5/004—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part
- A61B5/0042—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part for the brain
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The present disclosure relates to a diagnostic device, a diagnostic apparatus, and a diagnostic system for diagnosing a neonatal hypoxic ischemic brain injury. The diagnostic device includes: an acquisition module configured to acquire near infrared data of a target region of a brain cortex of a neonatal subject in a resting state acquired by a near infrared spectrum detection apparatus; a network construction module configured to construct a brain function network based on the near infrared data; the extraction module is used for extracting detection indexes based on a brain function network, wherein the detection indexes comprise a central node index and a local network efficiency index, and at least one of a small world attribute index and a modularized index, the central node index represents the brain development condition of a neonate subject, and the local network efficiency index is defined as that the neonate suffering from hypoxia-ischemia brain injury shows higher local network efficiency than a healthy neonate; and a prediction module for predicting the anoxic ischemic brain injury status of the neonatal subject based on the detection index.
Description
Technical Field
The present disclosure relates to the technical field of medical diagnosis, and more particularly, to a diagnosis device, a diagnosis apparatus, and a diagnosis system for diagnosing a neonatal hypoxic ischemic brain injury condition in an assisted manner.
Background
Neonatal Hypoxic ischemic brain injury (Hypoxic-Ischemic Brain Damage, HIBD) is generally caused by perinatal asphyxia, which is a major cause of neurological disability in infants, and neurological sequelae such as mental retardation, cerebral paralysis, convulsions, cognitive dysfunction, etc. may remain in survivors. Therefore, early diagnosis and intervention of the neonatal hypoxic ischemic brain injury are important to improve the neurological prognosis of the neonatal brain injury.
The current diagnosis of the neonatal hypoxia ischemic brain injury mainly depends on the clinical manifestation of the neonate and the detection of brain structural injury by medical imaging technologies such as functional magnetic resonance and CT. However, in actual clinical work, on one hand, early clinical manifestations of neonatal brain injury are atypical, whether the neonate has brain injury and brain injury degree are difficult to judge at the first time only by bedside observation of a clinician, an important treatment time window is easy to miss, and the existing medical imaging technology has the defects that bedside real-time monitoring, radiation, tranquilizer and the like are difficult to perform, so that brain injury data are difficult to obtain, and the neonate is injured; on the other hand, no specific detection index capable of rapidly and accurately diagnosing the condition of the neonatal hypoxia-ischemic brain injury is researched, and the detection index and the intervention of the neonatal brain injury in time are limited.
Therefore, aiming at the special group of the neonate, how to obtain reliable and effective brain injury detection indexes under the condition of avoiding injury to the neonate, and help doctors to carry out auxiliary diagnosis on the neonate anoxic and ischemic brain injury condition is a problem which needs to be solved urgently at present clinically.
Disclosure of Invention
The present disclosure is provided to address the above-mentioned deficiencies in the background art. The diagnosis device, the diagnosis equipment and the diagnosis system are used for carrying out auxiliary diagnosis on the hypoxia and ischemic brain injury condition of the neonate, near infrared spectrum brain function imaging technology is adopted to acquire the resting state near infrared data of the cerebral cortex of the neonate, the neonate is not injured, the operation is simple, and at least one of a central node index, a local network efficiency index, a small world attribute index and a modularized index is specially selected for the hypoxia and ischemic brain injury of the neonate to serve as a specific detection index, so that the accuracy and the reliability of diagnosis are improved, and the efficiency of clinical diagnosis is also improved.
A first aspect of the present disclosure provides a diagnostic device for a brain injury condition for aiding diagnosis of a neonatal hypoxic ischemic brain injury condition, the diagnostic device comprising: an acquisition module configured to acquire near infrared data of a target region of a brain cortex of a neonatal subject in a resting state acquired by a near infrared spectrum detection apparatus; a network construction module configured to construct a brain function network based on the near infrared data; an extraction module that extracts detection metrics based on the brain function network, the detection metrics including a central node metric that characterizes brain development of a neonatal subject and a local network efficiency metric defined as a neonate with hypoxic ischemic brain injury exhibiting higher local network efficiency than a healthy neonate, and at least one of a small world attribute metric and a modular metric; and a prediction module for predicting the anoxic ischemic brain injury status of the neonatal subject based on the detection index.
In some embodiments, the small world property index employs a characteristic path length.
In some embodiments, the central node index is determined by the mean and standard deviation of node degree values of all nodes in the brain function network, wherein the node degree value is the number of connecting edges of one node; and/or the local network efficiency is determined by a value obtained by adding the reciprocal of the connection distance between all node pairs in the brain function network and the maximum number of connection edges that can exist between all nodes.
In some embodiments, the network construction module is further configured to: the brain function network is constructed based on a sparseness threshold in the range of 0.3 to 0.34.
In some embodiments, the network construction module is further configured to: based on a plurality of sparseness thresholds in the range of 0.3 to 0.34, a corresponding plurality of brain function networks are constructed.
In some embodiments, the network construction module is further configured to: defining network nodes and quantifying the connection strength between any pair of nodes; and judging whether functional connection exists between any node pair or not by using a threshold judgment method based on the quantized value of the connection strength, thereby forming a brain functional network.
In some embodiments, the network construction module is further configured to:
regarding each detection channel formed by the near infrared spectrum detection device in the target area as one node of the brain function network, wherein the length of the time sequence of each node is equal, and calculating the Pearson correlation coefficient r of the time sequence of any node pair by the following formula (1):
wherein X is i And Y is equal to i The time series of detection channels X and Y are shown respectively,and->Respectively represent time series X i And Y i N represents the length of the time series;
and judging whether functional connection exists among all node pairs by using the Pearson correlation coefficient r of the time sequence of any node pair as a quantized value of the connection strength of the Pearson correlation coefficient, and forming the brain function network by using a preset threshold, wherein when the quantized value of the connection strength among the node pairs is larger than or equal to the preset threshold, the functional connection exists among the node pairs.
In some embodiments, the prediction module predicts the hypoxic ischemic brain injury condition of the neonatal subject using a classification model.
A second aspect of the present disclosure provides a diagnostic apparatus for assisting in diagnosing a neonatal hypoxic ischemic brain injury condition, the diagnostic apparatus comprising at least a processor and a memory, the memory having stored thereon computer executable instructions which, when executed, perform the following: acquiring near infrared data of a target area of a brain cortex of a neonate subject in a resting state acquired by a near infrared spectrum detection device; constructing a brain function network based on the near infrared data; extracting detection metrics based on the brain function network, the detection metrics including a central node metric and a local network efficiency metric, and at least one of a small world attribute metric and a modular metric, wherein the central node metric characterizes brain development of a neonatal subject, the local network efficiency metric is defined as a neonate with hypoxic ischemic brain injury exhibiting higher local network efficiency than a relatively healthy neonate; predicting the hypoxic ischemic brain injury condition of the neonatal subject based on the detection index.
A third aspect of the present disclosure provides a diagnostic system for assisted diagnosis of a neonatal hypoxic ischemic brain injury condition, the diagnostic system comprising a near infrared spectroscopy detection apparatus and a diagnostic device as described in any of the above.
The diagnosis device, the diagnosis equipment and the diagnosis system for the brain injury condition provided by the embodiment of the disclosure acquire near infrared data of the brain cortex of the neonate in a resting state by adopting a near infrared spectrum brain function imaging technology, construct a brain function network based on the near infrared data, extract at least one of a central node index, a local network efficiency index, a small world attribute index and a modularized index, and perform auxiliary diagnosis on the neonate hypoxia-ischemic brain injury condition. The device only needs near infrared data of the brain of a neonate subject in a resting state in a short time, is less limited by the environment, has no harm to the neonate, is simple to operate, can realize real-time continuous observation at the bedside, can be suitable for most neonate groups, provides a new means for early diagnosis and timely intervention of the disease, and improves the efficiency of clinical diagnosis. In addition, the method and the device select at least one of a central node index, a local network efficiency index, a small world attribute index and a modularized index as specific detection indexes aiming at the neonatal hypoxic ischemic brain injury, wherein the indexes have obvious differences between the hypoxic ischemic brain injury infant and the healthy neonate, so that the efficiency and the accuracy of clinical diagnosis are improved, and meanwhile, the indexes can be used for mutual reference and cooperative judgment, so that the effectiveness and the reliability of the clinical diagnosis are further improved.
Drawings
In the drawings, which are not necessarily drawn to scale, like numerals may describe similar components in different views. The same reference numerals with letter suffixes or different letter suffixes may represent different instances of similar components. The accompanying drawings illustrate various embodiments by way of example in general and not by way of limitation, and together with the description and claims serve to explain the disclosed embodiments. Such embodiments are illustrative and not intended to be exhaustive or exclusive of the present apparatus or method.
Fig. 1 is a schematic diagram illustrating a structure of a diagnostic device according to an embodiment of the present disclosure.
Fig. 2 is a diagram illustrating connections between nodes in a certain area of a brain function network according to an exemplary embodiment of the present disclosure.
Fig. 3 is a schematic diagram for calculating local network efficiency according to an exemplary embodiment of the present disclosure.
Fig. 4 is a schematic diagram of a module according to an exemplary embodiment of the present disclosure.
Fig. 5 is a schematic diagram illustrating a structure of a diagnostic apparatus according to an embodiment of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more apparent, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present disclosure. It will be apparent that the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments, which can be made by one of ordinary skill in the art without the need for inventive faculty, are within the scope of the present disclosure, based on the described embodiments of the present disclosure.
Unless defined otherwise, technical or scientific terms used in this disclosure should be given the ordinary meaning as understood by one of ordinary skill in the art to which this disclosure belongs. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items.
In order to keep the following description of the embodiments of the present disclosure clear and concise, the present disclosure omits detailed description of known functions and known components.
Fig. 1 is a schematic structural view illustrating a diagnosis apparatus for brain injury condition according to an embodiment of the present disclosure. The diagnosis device is used for performing auxiliary diagnosis on the neonatal hypoxic ischemic brain injury condition, and as shown in fig. 1, the diagnosis device 100 includes an acquisition module 110, a network construction module 120, an extraction module 130 and a prediction module 140.
The acquisition module 110 is configured to acquire near infrared data of a target region of the brain cortex of the neonatal subject in a resting state acquired by the near infrared spectrum detection device.
Specifically, the target area may include brain regions such as frontal, temporal and parietal regions on the left and right sides of the cerebral cortex, which are involved in the processing of some advanced cognitive functions, and whether or not the correlation cooperation thereof reflects the brain development level of the neonate.
In acquiring near infrared data, a transmitting probe of a near infrared spectrum detection apparatus may be placed on the head of a neonate subject, and a receiving probe may be placed at a distance (e.g., 3 cm) from the transmitting probe to receive an optical signal, which is computationally converted into blood oxygen data, and acquired by the acquisition module 110, that is, near infrared data of a target region of the brain cortex of the neonate subject in a resting state is obtained.
The network construction module 120 is configured to construct a brain function network based on the near infrared data acquired by the acquisition module 110, and the extraction module 130 extracts detection indicators for use in the assisted diagnosis of the hypoxic ischemic brain injury condition based on the brain function network constructed by the network construction module 120.
For the detection index, it may include a hub node index and a local network efficiency index, and at least one of a small world property index and a modularization index. The detection indexes can effectively reflect the phenomena of central node development retardation, low coordination capacity between brains, low information transmission and integration efficiency and the like of the infant caused by hypoxia and ischemia in the development process.
In particular, the pivot index may characterize the brain development of a neonate subject, particularly the development of important brain area hinges, where the number of pivot points is fewer for an infant than for a healthy neonate. The local network efficiency index represents information transfer and processing efficiency of a local brain region of the brain, which is defined as that a neonate suffering from hypoxic ischemic brain injury exhibits higher local network efficiency than a healthy neonate, that is, the local network efficiency of an affected neonate is higher than that of a healthy neonate. The small world attribute index can be used for measuring the information transmission capacity of the brain function network, can evaluate the intensity of the communication capacity between the brain regions of the neonate, and can comprise three characteristic measures of characteristic path length, clustering coefficient and small world. The modularization index reflects the degree to which the network is organized into a modularized or community structure, and is defined as a modularization index that a neonate suffering from hypoxia-ischemic brain injury exhibits a higher modularization index than a healthy neonate, that is, a modularization index of an infant is higher than a modularization index of a healthy neonate, similarly to the local network efficiency index.
The prediction module 140 predicts the anoxic and ischemic brain injury status of the neonatal subject based on the detection index, for example, comprehensively determines whether the neonatal subject has anoxic and ischemic brain injury and/or the degree of brain injury based on at least one of a central node index, a local network efficiency index, and a small world attribute index and a modularized index.
The acquisition module 110, the network construction module 120, the extraction module 130, and the prediction module 140 described above may be implemented in software, firmware, hardware, or any combination thereof, for example, by software or programmable code embedded in a computer readable medium and executable by a processor. Of course, those skilled in the art will be able to make many modifications to the above-described configuration without departing from the spirit of the invention.
The diagnosis device for brain injury condition provided by the embodiment of the disclosure adopts a near infrared spectrum brain function imaging technology to acquire near infrared data of the brain cortex of the neonate in a resting state, constructs a brain function network based on the near infrared data, and extracts at least one of a central node index, a local network efficiency index, a small world attribute index and a modularized index to carry out auxiliary diagnosis on the neonate hypoxia-ischemic brain injury condition. The device only needs near infrared data of the brain of a neonate subject in a resting state in a short time, is less limited by the environment, has no harm to the neonate, is simple to operate, can realize real-time continuous observation at the bedside, can be suitable for most neonate groups, provides a new means for early diagnosis and timely intervention of the disease, and improves the efficiency of clinical diagnosis.
In addition, through research of the applicant, some indexes in the brain function network, such as global network efficiency indexes, network cost indexes and the like, have no obvious difference between the hypoxia-ischemic brain injury infant and the healthy newborn infant, while the indexes of the four brain function networks, namely the central node indexes, the local network efficiency indexes, the small world attribute indexes and the modularized indexes, extracted in the present disclosure have obvious differences between the hypoxia-ischemic brain injury infant and the healthy newborn infant, and the hypoxia-ischemic brain injury condition of the newborn infant is subjected to auxiliary diagnosis by utilizing the indexes, so that the efficiency and the accuracy of clinical diagnosis are improved. For example, since the brain of an infant is not yet developed completely, the central node representing the central development of an important brain region is not completely formed, and the number of central nodes formed by the infant suffering from the hypoxic ischemic brain injury due to the lack of blood and oxygen supply is smaller than that of a healthy infant, the central node representing the development progress of the brain of the infant is selected as a detection index, and thus, the infant suffering from the hypoxic ischemic brain injury has remarkable specificity and recognition degree for distinguishing the infant from the healthy infant. As another example, the present disclosure selects as a detection indicator a local network efficiency indicator that is generally believed to be reduced due to suffering from brain injury, also has significant specificity and recognition for distinguishing hypoxic ischemic brain injury infants from healthy newborns. The method is characterized in that the anoxic ischemic brain injury to a certain extent causes the improvement of the local network efficiency, which breaks the knowledge of the traditional concept. The infant's brain-crossing region has weaker development, and the local development of the infant suffering from the hypoxia-ischemic brain injury to a certain extent is higher than that of the healthy infant due to the overcompensation effect, so that the local network efficiency of the infant is higher. The index is selected as the index for detecting the neonatal hypoxic ischemic brain injury condition, so that the technical prejudice is overcome, and the unexpected remarkable effect is obtained. Meanwhile, the method and the device also take at least one of the small world attribute index and the modularized index as a reference to carry out auxiliary judgment, and use the indexes to carry out mutual reference and cooperative judgment, so that the accuracy and the reliability of clinical diagnosis are further improved.
In some embodiments, the network construction module 120 may define network nodes and quantify the connection strength between any node pair, and determine whether a functional connection exists between any node pair using a threshold judgment method based on the quantified value of the connection strength, thereby forming a brain function network.
Specifically, each detection channel formed by the near infrared spectrum detection device in the target area can be regarded as one node of the brain function network, the time series of each node is equal in length, and the Pearson correlation coefficient r of the time series of any node pair is calculated by the following formula (1):
wherein X is i And Y is equal to i The time series of detection channels X and Y are shown respectively,and->Respectively represent time series X i And Y i N represents the length of the time series.
Assuming that m nodes (probe channels) are included in the network, it can be obtained by equation (1)And obtaining the correlation coefficient r, namely obtaining the quantized value of the connection strength between all the node pairs.
Next, the network construction module 120 uses the Pearson correlation coefficient r of the time series of any node pair as a quantized value of the connection strength thereof, and determines whether functional connections exist between all node pairs by using a preset threshold value to form a brain function network, wherein when the quantized value of the connection strength between the node pairs is greater than or equal to the preset threshold value, it is determined that functional connections exist between the node pairs.
For the threshold mode, a sparseness threshold may be adopted, or other threshold modes such as a similarity threshold may be adopted.
In some embodiments, the network construction module 120 constructs the brain function network based on a sparseness threshold in a range of 0.3 to 0.34. Taking the sparseness threshold p=0.3 as an example, i.e., the connection strength of the correlation coefficient r value accounting for the first 30% is set to 1, and the rest is set to 0, a brain function network with the sparseness threshold P of 0.3 can be obtained.
In general, the sparsity threshold P is selected to be between 0.05 and 0.4, and the sparsity threshold in the range of 0.3 to 0.34 of the present disclosure is specifically selected for the neonatal hypoxic ischemic brain injury, and the sparsity threshold in the range also very accords with the sparsity of the neonatal brain function network under the principle of following the integrity and the small world attribute of the brain function network, and in the threshold range, the above detection index can show obvious difference between the neonatal hypoxic ischemic brain injury infant and the healthy neonatal infant, so that good detection effect is ensured, and accuracy and effectiveness are improved.
In some embodiments, multiple thresholds may be selected to result in a network of brain functions under multiple threshold conditions, making predictions of neonatal hypoxic ischemic brain injury conditions more accurate and reliable. For example, the network construction module 120 may construct a corresponding plurality of brain function networks based on a plurality of sparseness thresholds in a range of 0.3 to 0.34. The threshold values of 5 sparsity, for example, 0.3, 0.31, 0.32, 0.33, and 0.34, may be set at equal intervals in the range of 0.3 to 0.34, for example, in steps of 0.01, respectively, so that respective brain function networks are formed under the condition of the 5 threshold values. However, those skilled in the art may make various settings according to specific needs or situations, and the specific values and amounts of setting the sparseness threshold are not specifically limited in this disclosure.
In some embodiments, the extraction module 130 may extract feature path lengths in the small world property index as the detection index. The applicant researches show that compared with the clustering coefficient and the small world degree in the small world attribute index, the characteristic path length shows more obvious difference between the hypoxia-ischemic brain injury infant and the healthy newborn, so that the efficiency and the accuracy of clinical diagnosis can be further improved by taking the characteristic path length as the detection index.
The characteristic path length may be obtained by calculating the average of the shortest path lengths between all node pairs. Specifically, as shown in fig. 2, for example, when the node a is directly connected to the node c, the shortest path length between the node pair is 1, and similarly, when the node c is directly connected to the node d, the shortest path length between the node pair is also 1, and when the node a is not directly connected to the node d, the shortest path length between the node pair is 1+1=2. And by analogy, the shortest path length between all node pairs can be calculated, and the characteristic path length can be obtained by mean value processing. The index represents the speed of parallel information transmission, the smaller the characteristic path length is, the faster the average information transmission speed between any two nodes is, and the characteristic path length of the infant suffering from hypoxia-ischemia brain injury is generally higher than that of the healthy infant.
The central node index can be obtained by a node degree method, specifically, the central node index in the method is determined by the average value and standard deviation of node degree values of all nodes in the brain function network, wherein the node degree value is the number of connecting edges of one node.
Still taking fig. 2 as an example, for example, as shown in fig. 2, the number of connection sides of the node c is 5, the node degree value is 5, the number of connection sides of the node d is 3, the node degree value is 3, the average value and standard deviation of the node degree values of all the nodes in the brain function network are obtained, and the node with the node degree value higher than the average value plus the standard deviation can be set as the central node. The central nodes are considered to play a central role in the functional integrity of the whole brain network, and the number of the central nodes can effectively reflect the development condition of important functional positions of the neonate, so that the central nodes can be used as specific detection indexes for diagnosing the neonate hypoxia-ischemic brain injury condition, and the effectiveness and the accuracy of clinical diagnosis can be ensured.
In addition, the hub node may be determined by other methods, such as the mesocenter method. The medium number centrality method sets a node with a medium number centrality value higher than the average value plus standard deviation as a central node, wherein the medium number centrality of a certain node refers to the proportion of the shortest path between any node pair in the brain function network, which is occupied by the path passing through the node. Reference is made to the relevant description of the prior art for this method and this is not repeated here.
For the local network efficiency, it may be determined by a value obtained by adding the reciprocal of the connection distance between all node pairs in the brain function network and the maximum number of connection edges that can exist between all nodes, for example, a result obtained by dividing the value obtained by adding the reciprocal of the connection distance between all node pairs and the maximum number of connection edges that can exist between all nodes may be used as the local network efficiency. Specifically, the reciprocal of the connection distance between all node pairs may be added, and assuming that the value is K, the maximum number of connections that can exist between all nodes is calculated, and assuming that N nodes are in total in the network, the maximum number of connections that can exist between all nodes is N (N-1)/2, 2*K/(N-1)) may be used as the local network efficiency.
For example, as shown in fig. 3, the nodes A, B, D are directly connected in pairs, each with a distance of 1; node B and C are also directly connected, and the distance is also 1; the node A is indirectly connected with the node C, and the distance is 2; c and D are unconnected, and the distance is infinite. Then here k=1+1+1+ (1/2) + (1/≡) =4.5; where N is 4 (including 4 nodes), and thus the maximum number of connections is 6, then 4.5/6=0.75 is the local network efficiency. The higher this ratio is ultimately obtained, the less costly the network can be considered to be in communicating information.
In the conventional concept, it is generally considered that brain injury may cause a decrease in local network efficiency of the brain of a patient, that is, lower than that of a healthy person, and in the present disclosure, considering the overcompensation effect of a specific population of infants on a cross brain region, the local network efficiency index is defined as that of a neonate suffering from a certain degree of hypoxic ischemic brain injury is higher than that of a healthy neonate, and is used as a specific detection index for diagnosing the condition of the hypoxic ischemic brain injury of the neonate, overcoming the technical bias, and obtaining a remarkable effect.
For the modularization index, it can be determined as follows: the area with a high number of connecting sides inside and few connections with other parts in the brain function network is determined to be modularized.
Specifically, the above-established brain function network may be segmented in blocks to extract the modularization index. Firstly, setting a random network, wherein the random network has the same connection number of all nodes as a real network, but randomly connects the nodes in the whole network range, and then comparing the random network with the real network, wherein a large number of connections in a small area exist in the real network, namely, the random network represents a module which is different from the random network and has a specific function. As shown in fig. 4, the area 11 has a higher connection number, and has few connections with other parts of the network, thus exhibiting the characteristic of modularization. The parameters can clearly reflect the abnormal differentiation of the brain function development of the infant suffering from the hypoxia-ischemia brain injury, and can detect whether the infant finishes a certain specific cognitive processing process or not. The modularization index is defined as that a neonate suffering from hypoxia-ischemic brain injury exhibits a higher modularization index than a healthy neonate, that is, the modularization index of an infant is higher than that of a healthy neonate.
In some embodiments, the prediction module 140 may predict the hypoxic ischemic brain injury condition of the neonatal subject using a classification model. As for the classification model, for example, a support vector machine classification model, a neural network model, a binary tree classification model, or the like may be selected, which is not particularly limited by the present disclosure.
For the establishment of the classification model, taking the support vector machine classification model as an example, a plane can be firstly assumed, two types of samples A and B are separated, wherein the type A sample is data of an anoxic ischemic brain injury infant, the type B sample is data of a healthy newborn, and then the distance between each characteristic point of the two types of samples and the plane is calculated, so that the normal vector of the plane is gradually adjusted. Specifically, a feature vector can be calculated for each one of the two types of samples by calculating the feature vector as a separation plane normal vector of the dimension index, the separation plane normal vector corresponding to each one of the dimension indexes is calculated in a similar way, the plane normal vectors are iterated in a linear combination mode to form a combined method vector suitable for separating all the dimension indexes, the maximum vertical distance between samples closest to the hyperplane in the two types of samples is finally realized, the error classification rate of the plane is evaluated through the marks (A and B) of the sample types until the minimum error classification rate and the maximum interval of the two types of data are realized, the finally determined plane is set as the optimal hyperplane, and the plane model can effectively distinguish the data in the training set.
The embodiment of the disclosure also provides a diagnosis device for brain injury conditions, which is used for carrying out auxiliary diagnosis on neonatal hypoxia-ischemic brain injury conditions. As shown in fig. 5, diagnostic device 500 includes at least a processor 510 and a memory 520. The memory 520 has stored thereon computer executable instructions that when executed by the processor 510 perform the following: acquiring near infrared data of a target area of a brain cortex of a neonate subject in a resting state acquired by a near infrared spectrum detection device; constructing a brain function network based on the near infrared data; extracting detection indexes based on a brain function network; predicting the anoxic ischemic brain injury condition of the neonatal subject based on the detection index. The detection indexes comprise a central node index and a local network efficiency index, and at least one of a small world attribute index and a modularization index. The central node index characterizes brain development of a neonatal subject, and the local network efficiency index is defined as that a neonate suffering from hypoxic ischemic brain injury exhibits a higher local network efficiency than a healthy neonate.
The processor 510 may be a processing device including one or more general purpose processing devices, such as a microprocessor, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), or the like. More specifically, processor 510 may be a Complex Instruction Set Computing (CISC) microprocessor, a Reduced Instruction Set Computing (RISC) microprocessor, a Very Long Instruction Word (VLIW) microprocessor, a processor running other instruction sets, or a processor running a combination of instruction sets. Processor 510 may also be one or more special purpose processing devices such as an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), a system on a chip (SoC), or the like. The processor 510 may be communicatively coupled to the memory 520 and configured to execute computer-executable instructions stored thereon to perform the method of controlling the headset of the above-described embodiments.
Memory 520 may be a non-transitory computer-readable medium such as read-only memory (ROM), random-access memory (RAM), phase-change random-access memory (PRAM), static random-access memory (SRAM), dynamic random-access memory (DRAM), electrically erasable programmable read-only memory (EEPROM), other types of random-access memory (RAM), flash memory disks or other forms of flash memory, buffers, registers, static memory, compact disc read-only memory (CD-ROM), digital Versatile Discs (DVD) or other optical memory, magnetic cassettes, or other magnetic storage devices, or any other possible non-transitory medium which is used to store information or instructions that can be accessed by a computer device, and the like.
The diagnostic device 500 provided by the embodiment of the disclosure adopts the near infrared spectrum brain function imaging technology to acquire near infrared data of the brain cortex of the neonate in a resting state to perform auxiliary diagnosis on the anoxic and ischemic brain injury condition of the neonate, has no harm to the neonate, is simple to operate, can realize real-time continuous observation at the bedside, provides a new means for early diagnosis and timely intervention of the disease, and improves the efficiency of clinical diagnosis. In addition, the present disclosure specifically selects at least one of a central node index, a local network efficiency index, and a small world attribute index and a modularized index as a specific detection index for the neonatal hypoxic ischemic brain injury, which have a significant difference between the hypoxic ischemic brain injury infant and the healthy neonate, thereby improving the effectiveness, accuracy and reliability of clinical diagnosis, and simultaneously, can use these indexes to make mutual reference and cooperative judgment, which further increases the effectiveness and reliability of clinical diagnosis.
The embodiment of the disclosure also provides a diagnosis system for brain injury conditions, which is used for carrying out auxiliary diagnosis on neonatal hypoxia-ischemic brain injury conditions. The diagnostic system may comprise a near infrared spectrum detection device and a diagnostic apparatus as described in any of the embodiments above.
The diagnosis system for the brain injury condition provided by the embodiment of the disclosure comprises a diagnosis device capable of carrying out auxiliary diagnosis on the hypoxia and ischemic brain injury condition of the neonate, wherein the diagnosis device adopts a near infrared spectrum brain function imaging technology to acquire near infrared data of the brain cortex of the neonate in a resting state for carrying out auxiliary diagnosis, has no harm to the neonate, is simple to operate, can realize real-time continuity observation at the bedside, provides a new means for early diagnosis and timely intervention of the disease, and improves the efficiency of clinical diagnosis. In addition, the present disclosure specifically selects at least one of a central node index, a local network efficiency index, and a small world attribute index and a modularized index as a specific detection index for the neonatal hypoxic ischemic brain injury, which have a significant difference between the hypoxic ischemic brain injury infant and the healthy neonate, thereby improving the effectiveness, accuracy and reliability of clinical diagnosis, and simultaneously, can use these indexes to make mutual reference and cooperative judgment, which further increases the effectiveness and reliability of clinical diagnosis.
Furthermore, although exemplary embodiments have been described herein, the scope thereof includes any and all embodiments having equivalent elements, modifications, omissions, combinations (e.g., of the various embodiments across schemes), adaptations or alterations based on the present disclosure. Elements in the claims are to be construed broadly based on language employed in the claims and not limited to examples described in the present specification or during the practice of the present disclosure, which examples are to be construed as non-exclusive. It is intended, therefore, that the specification and examples be considered as exemplary only, with a true scope and spirit being indicated by the following claims and their full scope of equivalents.
The above description is intended to be illustrative and not restrictive. For example, the above-described examples (or one or more aspects thereof) may be used in combination with each other. For example, other embodiments may be used by those of ordinary skill in the art upon reading the above description. In addition, in the above detailed description, various features may be grouped together to streamline the disclosure. This is not to be interpreted as an intention that the disclosed features not being claimed are essential to any claim. Rather, inventive subject matter may lie in less than all features of a particular disclosed embodiment. Thus, the following claims are hereby incorporated into the detailed description as examples or embodiments, with each claim standing on its own as a separate embodiment, and it is contemplated that these embodiments may be combined with one another in various combinations or permutations. The scope of the invention should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.
The above embodiments are only exemplary embodiments of the present invention and are not intended to limit the present invention, the scope of which is defined by the claims. Various modifications and equivalent arrangements of this invention will occur to those skilled in the art, and are intended to be within the spirit and scope of the invention.
Claims (8)
1. A diagnostic device for early-assisted diagnosis of a neonatal hypoxic ischemic brain injury condition, the diagnostic device comprising:
an acquisition module configured to acquire near infrared data of a target region of a brain cortex of a neonatal subject in a resting state acquired by a near infrared spectrum detection apparatus;
the network construction module is configured to construct a brain function network based on the near infrared data, and the construction of the brain function network specifically comprises: regarding each detection channel formed by near infrared spectrum detection equipment in the target area as one node of the brain function network, and quantifying the connection strength between any node pair; judging whether functional connection exists between any node pair by using a threshold judging method based on the quantized value of the connection strength so as to form a brain function network, wherein the brain function network is constructed based on a sparseness threshold in the range of 0.3 to 0.34;
the extraction module is used for extracting detection indexes based on the brain function network, wherein the detection indexes comprise central node indexes and local network efficiency indexes, and the central node indexes represent the brain development condition of a neonate subject;
a prediction module that predicts the presence of hypoxic ischemic brain injury in the neonatal subject if the neonatal subject has fewer central nodes than healthy neonates and has a higher local network efficiency index than healthy neonates.
2. The diagnostic device of claim 1, wherein the detection index further comprises a small world attribute index that employs a characteristic path length.
3. The diagnostic apparatus according to claim 1, wherein the central node index is determined by an average value and a standard deviation of node degree values of all nodes in the brain function network, wherein the node degree value is a number of connection sides possessed by one node; and/or the number of the groups of groups,
the local network efficiency is determined by a value obtained by adding the reciprocal of the connection distance between all node pairs in the brain function network and the maximum number of connection edges that can exist between all nodes.
4. The diagnostic device of claim 1, wherein the network construction module is further configured to: based on a plurality of sparseness thresholds in the range of 0.3 to 0.34, a corresponding plurality of brain function networks are constructed.
5. The diagnostic device of claim 1, wherein the network construction module is further configured to:
regarding each detection channel formed by the near infrared spectrum detection device in the target area as one node of the brain function network, wherein the length of the time sequence of each node is equal, and calculating the Pearson correlation coefficient r of the time sequence of any node pair by the following formula (1):
wherein X is i And Y is equal to i The time series of detection channels X and Y are shown respectively,and->Respectively represent time series X i And Y i N represents the length of the time series;
and judging whether functional connection exists among all node pairs by using the Pearson correlation coefficient r of the time sequence of any node pair as a quantized value of the connection strength of the Pearson correlation coefficient, and forming the brain function network by using a preset threshold, wherein when the quantized value of the connection strength among the node pairs is larger than or equal to the preset threshold, the functional connection exists among the node pairs.
6. The diagnostic device of claim 1, wherein the prediction module predicts the hypoxic ischemic brain injury condition of the neonatal subject using a classification model.
7. A diagnostic device for early assisted diagnosis of a neonatal hypoxic ischemic brain injury condition, the diagnostic device comprising at least a processor and a memory, the memory having stored thereon computer executable instructions which, when executed, perform the following:
acquiring near infrared data of a target area of a brain cortex of a neonate subject in a resting state acquired by a near infrared spectrum detection device;
constructing a brain function network based on the near infrared data, the constructing the brain function network specifically includes: regarding each detection channel formed by near infrared spectrum detection equipment in the target area as one node of the brain function network, and quantifying the connection strength between any node pair; judging whether functional connection exists between any node pair by using a threshold judging method based on the quantized value of the connection strength so as to form a brain function network, wherein the brain function network is constructed based on a sparseness threshold in the range of 0.3 to 0.34;
extracting detection indexes based on the brain function network, wherein the detection indexes comprise central node indexes and local network efficiency indexes, and the central node indexes represent the brain development condition of a neonate subject;
in the event that the number of central nodes of the neonatal subject is fewer than healthy neonates and the local network efficiency index is higher relative to healthy neonates, the neonatal subject is predicted to have hypoxic ischemic brain injury.
8. A diagnostic system for early-assisted diagnosis of a neonatal hypoxic ischemic brain injury condition, characterized in that the diagnostic system comprises a near infrared spectrum detection device and a diagnostic apparatus as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011506999.9A CN112641428B (en) | 2020-12-18 | 2020-12-18 | Diagnosis device, diagnosis equipment and diagnosis system for brain injury condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011506999.9A CN112641428B (en) | 2020-12-18 | 2020-12-18 | Diagnosis device, diagnosis equipment and diagnosis system for brain injury condition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112641428A CN112641428A (en) | 2021-04-13 |
| CN112641428B true CN112641428B (en) | 2023-09-08 |
Family
ID=75355029
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011506999.9A Active CN112641428B (en) | 2020-12-18 | 2020-12-18 | Diagnosis device, diagnosis equipment and diagnosis system for brain injury condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112641428B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113367706B (en) * | 2021-06-08 | 2022-12-06 | 北京大学第一医院 | Multi-mode detection system for newborn brain function |
| CN114403812B (en) * | 2022-03-30 | 2022-07-08 | 慧创科仪(北京)科技有限公司 | Auxiliary analysis method, device and system for brain injury condition and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105559805A (en) * | 2015-12-31 | 2016-05-11 | 四川大学 | Diagnosis assessment system for post-traumatic stress disorder |
| CN107358022A (en) * | 2017-06-02 | 2017-11-17 | 常州大学 | A kind of Modularity analysis method of cerebral function network |
| CN110443798A (en) * | 2018-12-25 | 2019-11-12 | 电子科技大学 | A kind of self-closing disease detection method based on magnetic resonance image, apparatus and system |
| CN110473635A (en) * | 2019-08-14 | 2019-11-19 | 电子科技大学 | A kind of analysis method of teenager's brain structural network and brain function cyberrelationship model |
| CN110473611A (en) * | 2019-08-14 | 2019-11-19 | 电子科技大学 | A kind of tranquillization state brain signal analysis method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9480425B2 (en) * | 2008-04-17 | 2016-11-01 | Washington University | Task-less optical mapping of dynamic brain function using resting state functional connectivity |
-
2020
- 2020-12-18 CN CN202011506999.9A patent/CN112641428B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105559805A (en) * | 2015-12-31 | 2016-05-11 | 四川大学 | Diagnosis assessment system for post-traumatic stress disorder |
| CN107358022A (en) * | 2017-06-02 | 2017-11-17 | 常州大学 | A kind of Modularity analysis method of cerebral function network |
| CN110443798A (en) * | 2018-12-25 | 2019-11-12 | 电子科技大学 | A kind of self-closing disease detection method based on magnetic resonance image, apparatus and system |
| CN110473635A (en) * | 2019-08-14 | 2019-11-19 | 电子科技大学 | A kind of analysis method of teenager's brain structural network and brain function cyberrelationship model |
| CN110473611A (en) * | 2019-08-14 | 2019-11-19 | 电子科技大学 | A kind of tranquillization state brain signal analysis method |
Non-Patent Citations (1)
| Title |
|---|
| 张红，杨天亮，卿鹏.抑郁症患者脑网络拓扑属性研究分析.西南大学学报（自然科学版）.2016,第38卷(第12期),115-118. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112641428A (en) | 2021-04-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dimitriadis et al. | Random forest feature selection, fusion and ensemble strategy: Combining multiple morphological MRI measures to discriminate among healhy elderly, MCI, cMCI and alzheimer’s disease patients: From the alzheimer’s disease neuroimaging initiative (ADNI) database | |
| CN112641428B (en) | Diagnosis device, diagnosis equipment and diagnosis system for brain injury condition | |
| Giri et al. | Ischemic stroke identification based on EEG and EOG using ID convolutional neural network and batch normalization | |
| CN110840402A (en) | Atrial fibrillation signal identification method and system based on machine learning | |
| ES2960027T3 (en) | Detection of abnormalities in ECG signals | |
| WO2023104173A1 (en) | Autism classifier construction method and system based on functional magnetic resonance images of human brains | |
| WO2020168511A1 (en) | Chromosome abnormality detection model, chromosome abnormality detection system, and chromosome abnormality detection method | |
| Supakar et al. | A deep learning based model using RNN-LSTM for the Detection of Schizophrenia from EEG data | |
| Crockart et al. | Classification of intrauterine growth restriction at 34–38 weeks gestation with machine learning models | |
| CN113593708A (en) | Sepsis prognosis prediction method based on integrated learning algorithm | |
| Karim et al. | A review on predicting autism spectrum disorder (asd) meltdown using machine learning algorithms | |
| CN116312772A (en) | Early treatment effect prediction method for antidepressant for depression based on rs-fMRI and P11 gene DNA methylation | |
| Qureshi et al. | Prediction and analysis of autism spectrum disorder using machine learning techniques | |
| CN111816303B (en) | Prediction method of refractory schizophrenia risk based on machine learning | |
| Minaee et al. | Identifying mild traumatic brain injury patients from MR images using bag of visual words | |
| Zhang et al. | Application of intelligent algorithms in Down syndrome screening during second trimester pregnancy | |
| US11669970B2 (en) | System, apparatus, and method for detection of ureteropelvic junction obstruction | |
| Campaña et al. | Minor anomalies: can they predict specific major defects? A study based on 23 major and 14 minor anomalies in over 25,000 newborns with birth defects | |
| Gorji et al. | Biomarkers Selection Toward Early Detection of Alzheimer's Disease | |
| Xu et al. | ADpred: A non-invasive model for three types of dementia and mild cognitive impairment | |
| Chen et al. | Discriminating pregnancy and labour in electrohysterogram by sample entropy and support vector machine | |
| Martins et al. | Be-sys: Big data e-health system for analysis and detection of risk of septic shock in adult patients | |
| Dai et al. | Network-based classification using cortical thickness of AD patients | |
| Shetty et al. | Detection of Alzheimer's Disease Using Machine Learning | |
| Zhang et al. | Artificial intelligence system for detection and screening of cardiac abnormalities using electrocardiogram images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Wang Daifa Inventor after: Zhang Shen Inventor before: Wang Daifa |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |