TWI781408B - Artificial intelligence based cell detection method by using hyperspectral data analysis technology - Google Patents

Abstract

An artificial intelligence based cell detection method by using hyperspectral data analysis technology includes acquiring a plurality of cells, sampling N images of the cells from a first time point to a second time point, executing an image calibration process for generating N normalized cell hyperspectral images according to the N images of the cells, determining an observation area corresponding to a change of at least one chemical component of each cell during a development period, analyzing the N normalized cell hyperspectral images for generating a key normalized cell hyperspectral image characteristic difference value corresponding to the observation area, and inputting the key normalized cell hyperspectral image characteristic difference value and/or the N normalized cell hyperspectral images to a neural network for detecting qualities of the cells.

Description

Artificial intelligence cell detection method and system using hyperspectral data analysis technology system

The present invention describes an artificial intelligence cell detection method and system using hyperspectral data analysis technology, especially an artificial intelligence cell detection method and system with the ability to detect cell quality and identify cell functions.

With the rapid development of science and technology, women of reproductive age often suffer from infertility due to work pressure, eating habits, civilized diseases, abnormal ovulation function, hormonal imbalance or some chronic diseases. Nowadays, infertility is a high-paying treatment, and there is a huge demand in Taiwan, China and the international market, and its demand is growing rapidly every year. Many women will choose In Vitro Fertilization (IVF) to treat infertility problems. In vitro artificial fertilization is to take out eggs and sperm, carry out in vitro fertilization under artificial operation, and cultivate them into embryos, and then implant the embryos back into the mother. However, the success rate of existing infertility treatments is only 30%. The focus of infertility treatment is embryo selection. However, the existing method for selecting embryos is mainly for embryologists to use the data of embryo photos or time-lapse videos to judge the quality of embryos subjectively. As far as the current technology is concerned, due to the lack of a systematic and automated way to judge whether the embryo is good or bad, in the course of infertility treatment, the doctor subjectively selects the embryo to be implanted, and the implantation success rate is still low. Bottleneck in infertility treatment.

In other words, with current infertility treatments, doctors can only observe subjectively what happens to embryos as they divide. For example, doctors will subjectively classify embryos into several grades from good to bad according to the number of developing cells, the uniformity of cell division, and the degree of fragmentation during division. For example, embryos that divide evenly into even numbers of cells are superior, while embryos that produce incomplete odd cell divisions and more fragmentation have poorer growth potential. However, as mentioned above, since judging the quality of embryos is mainly based on the doctor's experience, the selection of better embryos is based on subjective judgment. Therefore, it is difficult to improve the success rate of the current technical treatment of infertility, and the success rate is easily affected by the subjective opinions of different doctors (such as misjudgment).

An embodiment of the present invention proposes a cell detection method using artificial intelligence of hyperspectral data analysis technology. The artificial intelligence cell detection method using hyperspectral data analysis technology includes obtaining a plurality of cells, sampling N images of these cells between the first time point and the second time point, and based on the N images of these cells, Perform image correction procedures to generate N normalized cell hyperspectral images, and determine the corresponding observation area when at least one internal chemical composition of each cell changes during development, between the first time point and the second time point, Analyze N normalized cell hyperspectral images to generate the key normalized cell hyperspectral image difference characteristic value corresponding to the observation area, and calculate the key normalized cell hyperspectral image difference characteristic value and/or N corresponding to the observation area of each cell A normalized cell hyperspectral image is input to the neural network to train the neural network, and the neural network is used to establish a cell quality detection model with an artificial intelligence program to detect cell quality and/or identify cells. The first time point is before the second time point, and N is a positive integer greater than 2.

Another embodiment of the present invention proposes a cell detection system using artificial intelligence of hyperspectral data analysis technology. The artificial intelligence cell detection system using hyperspectral data analysis technology includes a carrier, a lens module, a hyperspectral instrument, a processor, and a memory. The carrier has a receiving slot for placing complex several cells. The lens module faces the carrier and is used to enlarge the details of the cells. The hyperspectral instrument faces the lens module, and is used for obtaining images of the cells through the lens module. The processor is coupled to the lens module and the hyperspectral instrument for adjusting the magnification of the lens module and processing the images of the cells. The memory is coupled to the processor for storing training data and analysis data of image processing. After placing the cells in the holding tank of the carrier, the processor controls the hyperspectral instrument to sample N images of the cells between the first time point and the second time point through the lens module. The processor performs image correction procedures based on the N images of these cells to generate N normalized cell hyperspectral images, and determines the corresponding observation area when at least one chemical composition in each cell changes during development, and in the Between the first time point and the second time point, N normalized cell hyperspectral images are analyzed to generate key normalized cell hyperspectral image difference characteristic values corresponding to the observation area. The processor includes a neural network, and the key normalized cell hyperspectral image difference characteristic values corresponding to the observation area of each cell and/or N normalized cell hyperspectral images are used to train the neural network. The processor uses a neural network to establish a cell quality detection model with an artificial intelligence program to detect cell quality and/or identify cells. The first time point is before the second time point, and N is a positive integer greater than 2.

100: Cell detection system using artificial intelligence of hyperspectral data analysis technology

10: Vehicle

11: Lens module

12:Hyperspectrometer

13: Processor

14: Memory

S201 to S207: Steps

S301 to S302: Steps

D1: Key normalized cell hyperspectral image difference feature value

D2: N normalized cell hyperspectral images

D3: Wavelength normalized cell should be towards the edge feature data

D4: Cell quality output data

Fig. 1 is a block diagram of an embodiment of an artificial intelligence cell detection system utilizing hyperspectral data analysis technology of the present invention.

FIG. 2 is a flowchart of the cell detection method executed by the artificial intelligence cell detection system using hyperspectral data analysis technology in FIG. 1 .

Figure 3 is a schematic diagram of adding additional steps to enhance the accuracy of cell detection in the artificial intelligence cell detection system using hyperspectral data analysis technology in Figure 1 .

Figure 4 is the artificial intelligence cell detection system using hyperspectral data analysis technology in Figure 1, with Schematic diagram of the input data and output data of a neural network-like processor.

FIG. 1 is a block diagram of an embodiment of an artificial intelligence cell detection system 100 utilizing hyperspectral data analysis technology of the present invention. In order to simplify the description, the cell detection system 100 using the artificial intelligence of the hyperspectral data analysis technology is referred to as "the cell detection system 100" hereinafter. The cell detection system 100 includes a carrier 10 , a lens module 11 , a hyperspectral instrument 12 , a processor 13 and a memory 14 . The carrier 10 has an accommodating groove for placing a plurality of cells. For example, the carrier 10 can be a petri dish, and the accommodating tank inside it can contain some culture liquid. A plurality of cells can develop in the culture medium. The plurality of cells can be a plurality of germ cells, a plurality of embryos, or any number of cells that can be divided and observed. The lens module 11 faces the carrier 10 for magnifying the details of the cells. The lens module 11 can be any lens module with optical or digital zoom capability, such as a microscope module. The hyperspectral instrument 12 faces the lens module 11 for obtaining images of the cells through the lens module 11 . Therefore, in the cell detection system 100, the images of these cells captured by the hyperspectral instrument 12 can be (A) cell images corresponding to any wavelength in the hyperspectral image, (B) cell images of each wavelength in the hyperspectral image Synthesized grayscale cell images. Any reasonable image format belongs to the category disclosed by the present invention. The processor 13 is coupled to the lens module 11 and the hyperspectral instrument 12 for adjusting the magnification of the lens module 11 and processing the images of the cells. The processor 13 can be a central processing unit, a microprocessor, or any programmable processing unit. The processor 13 has a neural network, such as a deep neural network (Deep Neural Networks, DNN), which can perform machine learning and deep learning functions. Therefore, the neural network-like of the processor 13 can be trained, which can be regarded as the processing core of artificial intelligence. The memory 14 is coupled to the processor 13 for storing training data and analysis data of image processing.

In the cell detection system 100, after the cells are placed in the holding tank of the carrier 10, the processor 13 can control the hyperspectral instrument 12 to take the Sample N images of these cells. Next, the processor 13 can determine the corresponding observation area when at least one chemical composition in each cell changes during development, and analyze N normalized cell hyperspectral images between the first time point and the second time point , to generate the key normalized cell hyperspectral image difference characteristic value corresponding to the observation area. As mentioned above, the processor 13 includes a trainable neural network. Therefore, the key normalized cell hyperspectral image difference characteristic value corresponding to the observation area of each cell and/or N normalized cell hyperspectral images can be used to train the neural network. After the training of the neural network is completed, the processor 13 can use the neural network to establish a cell quality detection model with an artificial intelligence program to detect cell quality and/or identify cells. In the cell detection system 100, the first time point is before the second time point, and N is a positive integer greater than 2. In other words, the cell detection system 100 can use the time-series cell image information between two different time points to train the neural network. After the neural network-like training is completed, the cell detection system 100 has the cell detection function of artificial intelligence, and has the ability to automatically detect cell quality and/or identify cells. The details of how the cell detection system 100 trains the neural network to perform the cell detection function of artificial intelligence will be described later.

FIG. 2 is a flow chart of the cell detection method executed by the cell detection system 100 using the artificial intelligence of the hyperspectral data analysis technology. The cell detection method may include steps S201 to S207. Any reasonable step changes or technical changes belong to the scope of the disclosure of the present invention. The contents of steps S201 to S207 are described as follows: Step S201: Obtain a plurality of cells; Step S202: Sampling N images of these cells between the first time point and the second time point; Step S203: Based on the Perform image correction procedures on N images of cells to generate N normalized cell hyperspectral images; step S204: determine the corresponding observation area when at least one internal chemical composition of each cell changes during development; Step S205: Between the first time point and the second time point, analyze N normalized cell hyperspectral images to generate key normalized cell hyperspectral image difference characteristic values corresponding to the observation area; Step S206: convert each cell The key normalized cell hyperspectral image difference characteristic values corresponding to the observation area and/or N normalized cell hyperspectral images are input to the neural network to train the neural network; step S207: using the neural network to The artificial intelligence program establishes a cell quality detection model to detect cell quality and/or identify cells.

In order to simplify the description, the following "cells" are only described with "embryo" as an example, but the present invention is not limited thereto. The definition of cells can be germ cells, nerve cells, tissue cells, animal and plant cells, or any research needs and observed cells. In step S201, researchers or medical personnel can obtain multiple embryos first. In step S202, the processor 13 may control the hyperspectral instrument 12 to sample N images of the cells between the first time point and the second time point. For example, the hyperspectral instrument 12 can acquire an image set composed of multiple frames (Frames) in a video recording mode (such as 30 fps or 60 fps) within a period of time (between the first time point and the second time point). Alternatively, the hyperspectral instrument 12 can periodically take pictures of multiple embryos within a period of time (between the first time point and the second time point), so as to obtain N images of the embryos. Moreover, the first time point and the second time point can be any two time points in the observation period during which the embryos develop and divide in the culture medium. For example, the first time point and the second time point can be respectively selected as the first day and the fifth day to observe the development and division of the embryos. In other words, the hyperspectral instrument 12 can continuously take pictures of the embryos from the 0th hour to the 120th hour to obtain N images. In step S203, the processor 13 may perform an image correction procedure according to the N images of the cells to generate N normalized cell hyperspectral images. The N images may be N hyperspectral images. The processor 13 can obtain Bright Field information and Dark Field information according to the N hyperspectral images and/or ambient light parameters. Next, the processor 13 may, according to the bright field information and the dark field information, Generate light transmittance percentage values, and correct N hyperspectral images according to bright field information and/or dark field information and transmittance percentage values, so as to generate N normalized cell hyperspectral images. For example, since the ambient light of the embryos is different each time the hyperspectral instrument 12 samples (photographs), the hyperspectral images need to be normalized for consistent image processing. For example, at the time point T1, the light energy near the hyperspectrometer 12 is 100 units (eg, nits). In the normalized cell hyperspectral image generated by the hyperspectrometer 12 , the light energy of the bright field is 200 units. Therefore, for the bright field, 100 units of the light energy (200 units) of the bright field may be contributed by ambient light, so the light transmittance percentage value can be regarded as 50%. For example, at the time point T2, the light energy near the hyperspectrometer 12 is 200 units (eg, nits). In the normalized cell hyperspectral image generated by the hyperspectrometer 12 , the light energy of the bright field is 400 units. Therefore, for the bright field, 200 units of the light energy (400 units) of the bright field may be contributed by ambient light, so the light transmittance percentage value can be regarded as 50%. Therefore, the two hyperspectral images generated by the hyperspectral instrument 12 at the time point T1 and the time point T2 have the same light transmittance percentage value (bright field). Similarly, if the two hyperspectral images produced by the hyperspectral instrument 12 at the time point T1 and the time point T2 have different light transmittance percentage values (dark field), the processor 13 needs to correct the dark field image , such as increasing the brightness of the dark field so that the high contrast between the two images does not occur. In other words, during the sampling process of the hyperspectrometer, there are differences in ambient light, light intensity value, bright field and dark field information, so the cell detection system 100 needs to perform a normalization procedure to make the normalized image data have a consistent sex. Moreover, the normalized hyperspectral data may carry information of transmittance (expressed as a percentage). If the transmittance is normalized, the image brightness will be consistent. In the cell detection system 100 , any method or technique for normalizing the N hyperspectral images belongs to the scope disclosed in the present invention.

Moreover, it should be understood that the hyperspectral instrument 12 acquires N hyperspectral images of the cells, including that the hyperspectral instrument 12 acquires the hyperspectral images of the cells at at least one specific wavelength between the first time point and the second time point. N hyperspectral images. Generally speaking, in the object image of visible light, the outline, color, and polarization characteristics of the object can be seen. However, when different substances have the same visible light properties (color, shape, polarization properties, etc.), it will be difficult for the naked eye to detect them. However, the characteristics of the substance will be displayed in its spectral characteristics. Therefore, the hyperspectral instrument 12 can perform quantitative analysis on the hyperspectral signal to further analyze the difference of the substance. The number of spectral bands supported by the hyperspectral instrument 12 may be hundreds, and the spectral resolution may be at the nanometer level. Therefore, the hyperspectral instrument 12 obtains N hyperspectral images of the cells, which may include hyperspectral images at different wavelengths. The larger the number of spectral bands, the larger the number of hyperspectral images (the larger N is), and the better the image analysis capability will be. In step S204, the processor 13 determines the corresponding observation area when at least one internal chemical composition of each cell changes during development. As mentioned above, hyperspectral images can analyze the differences of substances, such as the metabolic substances (characteristic cells) of embryos or various chemical components. For example, in characteristic cells, the judgment of uniform metabolism can be determined according to the characteristics of Glucose, Radioisotope, Auto-fluorescence, ³ H ₂ O and ¹⁴ CO ₂ . For example, in healthy embryos, there are higher ribonucleic acid (RNA), protein content (Protein Content) and glycolytic dependence (Glycolytic Dependence). In other words, when in the hyperspectral image generated by the hyperspectral instrument 12, the ratio of ribonucleic acid, protein content, and glycolysis dependence of a certain embryo matches the proportion of a healthy embryo, then a certain embryo can be regarded as a healthy embryo at this time point . As mentioned above, the embryo divides several times during development, and after each division, the chemical composition ratio of a certain part of the embryo will change. Therefore, in step S204, the observation area defined by the processor 13 may be among the embryos, the blastocyst (Blastocyst) area of each embryo or the area with the greatest difference when at least one chemical composition of the embryos changes. .

Next, in step S205, the processor 13 can analyze N normalized cell hyperspectral images between the first time point and the second time point to generate key normalized cell hyperspectral image difference characteristic values corresponding to the observation area . In the cell detection system 100, the key normalized cell hyperspectral image difference characteristic values may include the proportional relationship between the normalized spectra at each wavelength, the peak and/or trough values of the normalized spectra, and the peaks and/or troughs corresponding to Wavelength data and the correlation between the wavelength data. Broadly speaking, any quantifiable feature in N normalized cellular hyperspectral images can be processed The device 13 performs quantization processing to become a two-bit digital value. Moreover, since the processor 13 includes a neural network, in step S206, the key normalized cell hyperspectral image difference characteristic value and/or N normalized cell hyperspectral images corresponding to the observation area of each cell can be input to a neural network to train a neural network. After the neural network is trained, according to step S207, the processor 13 can use an artificial intelligence program to establish a cell quality detection model to detect cell quality and/or identify cells. In the cell detection system 100 , the neural network has the capability of collecting training data for establishing a deep learning model. For example, the neural network can collect the original image data of each stage from the first day to the fifth day of the embryo, the hyperspectral data extracted by hyperspectral technology at the last stage (or any time point during development), and the Image feature data after hyperspectral data analysis, and time series data (N images) to perform deep learning training. Moreover, the neural network can also modify the cell quality detection model according to the result of embryo implantation success or implantation failure (implantation rate). Any method for training a neural network to perform the cell detection function of artificial intelligence belongs to the scope disclosed by the present invention. In other words, the cell detection system 100 using artificial intelligence to detect embryo quality and/or identify embryos may include two stages. The first stage is the training stage. The second stage is the detection stage of artificial intelligence. After the training of the neural network is completed, the processor 13 can use the trained neural network-like cell quality detection model to judge the embryo quality and identify the embryo. Therefore, the cell detection system 100 of the present invention can prevent medical personnel or researchers from judging the quality of embryos in a subjective way, so the success rate of conception can be greatly improved for the treatment of infertility.

FIG. 3 is a schematic diagram of adding additional steps to enhance the accuracy of cell detection in the cell detection system 100 using artificial intelligence of hyperspectral data analysis technology. In order to further enhance the accuracy of judging embryo quality and identifying embryos, the cell detection system 100 can also introduce morphological detection technology to enhance the neural network-like cell detection capability, as shown below.

Step S201: Obtain a plurality of cells; Step S301: Between the first time point and the second time point, according to N pieces of normalized cell highlights Spectrum image, extracting normalized cell image of at least one wavelength; Step S302: Using morphological edge detection technology, according to the normalized cell image of at least one wavelength, obtain the normalized wavelength of each time point and each wavelength The edge feature data of the cell image is normalized, and the edge feature data of the wavelength normalized cell image is input to the neural network to train the neural network.

Similarly, in order to simplify the description, the following "cell" is only described with "embryo" as an example, but the present invention is not limited thereto, and the definition of a cell can be a germ cell, a nerve cell, a tissue cell, an animal or plant cell, or Any cell that needs to be studied and observed. In order to further enhance the accuracy of judging the quality of embryos and identifying embryos, after the cell detection system 100 obtains a plurality of cells (embryos) in the aforementioned step S201, according to step S301, the processor 13 can , according to the N normalized cell hyperspectral images, extracting at least one normalized cell image with one wavelength. As mentioned above, the number of spectral bands supported by the hyperspectrometer 12 can be hundreds, so the processor 13 can obtain each wavelength after correcting (normalizing) the bright field/dark field parameters of the image generated by the hyperspectrometer 12 Normalized cell image below. Next, according to step S302, the processor 13 can use the morphological edge detection technology to obtain the edge feature data of the normalized cell image at each time point and wavelength at each wavelength according to the normalized cell image at least one wavelength , and input the edge feature data of the wavelength normalized cell image into the neural network to train the neural network. Here, the edge feature data can be the outline of the whole embryo or a specific part (such as a blastocyst), and its data format can be represented by multiple coordinates. For example, on a two-dimensional plane, the outline of a single embryo can be a closed line segment, which can be represented by (X ₁ , Y ₁ ) to (X _M , Y _M ), M is a positive integer and the larger M is, the higher the resolution will be. Compared with the cell detection method in steps S201 to S207 described in FIG. 2, the cell detection system 100 can introduce additional steps S301 to S302 to obtain more information (such as the edge feature data of the wavelength normalized cell image) ) to train a neural network. Therefore, the training of the neural network will be more optimized, thereby increasing the accuracy of the artificial intelligence to detect the quality of the cells.

FIG. 4 is a schematic diagram of the input data and output data of the processor 13 having a neural network in the artificial intelligence cell detection system 100 using the hyperspectral data analysis technology. As mentioned above, the hyperspectral instrument 12 can take pictures of multiple embryos at two different time points to generate N images. The N images can be converted into N normalized cellular hyperspectral images D2 through an image correction procedure. Moreover, by analyzing the N normalized cell hyperspectral images under the time series, the observation area can be determined, and the key normalized cell hyperspectral image difference characteristic value D1 can be further generated. The key normalized cell hyperspectral image difference feature value D1 and the normalized cell hyperspectral image D2 can be used to train the neural network in the processor 13 . After the neural network training is completed, the processor 13 can use the artificial intelligence program to judge the embryo quality and/or identify the embryo. The processor 13 can output the cell quality output data D4. It should be understood that each of the N images can be a 2D image or a 3D image. If each of the N images is a two-dimensional image, the format of the data input to the neural network can be K dimensions. For example, at the time point T and the specific wavelength λ of the hyperspectral instrument, the optical signal of the pixel S1 with two-dimensional coordinates (x, y) can be expressed as S1(λ, T, x, y). The light signal S1 (λ, T, x, y) of the pixel S1 is a four-dimensional signal format (K=4). Similarly, at the time point T and the specific wavelength λ of the hyperspectral instrument, the optical signal of the pixel S2 with three-dimensional coordinates (x, y, z) can be expressed as S2(λ, T, x, y, z). The optical signal S2 (λ, T, x, y, z) of the pixel S2 is a five-dimensional signal format (K=5). K is a positive integer greater than 2. Therefore, it is expected that when the data format of the cell detection system 100 is a higher dimension, the computational complexity will become higher. When the data format of the cell detection system 100 is a lower dimension, the computational complexity will be lower.

Moreover, as mentioned above, the neural network of the processor 13 can use the edge feature data D3 of the wavelength normalized cell image for training, and then the neural network can optimize the cell quality detection model by using artificial intelligence programs. Therefore, as shown in FIG. 4, the neural network in the processor can receive the key normalized cell hyperspectral image difference feature value D1, normalized cell hyperspectral image D2, and wavelength normalized cell image edge feature data D3. Moreover, after the neural network-like training in the processor is completed, the processor can use artificial intelligence programs to select eggs/embryos from infertile women for input Output cell quality output data D4. The cell quality output data D4 can be in any data format, such as outputting grading data of good or bad embryos, outputting the good or bad sorting percentage of at least one embryo, or outputting the cell quality of at least one embryo. Cell quality can be determined by the amount of the detailed chemical composition of the cell, the quality of the genetic gene, the quality of the developmental state of the cell within a certain period of time, or whether the cell is diseased or not. If it is a germ cell, it can also be dependent on pregnancy or not, the health of the newborn, and sex.

In summary, the present invention describes a cell detection method and system using artificial intelligence of hyperspectral data analysis technology. The application group of the cell detection system can be infertile women. Medical personnel can first establish an artificial intelligence cell quality detection model based on a large amount of cell data, and then treat infertile women with a course of treatment. Moreover, artificial intelligence-like neural networks can receive hyperspectral data at various wavelengths and various parameters related to morphology, such as key normalized cell hyperspectral image difference characteristic values, normalized cell hyperspectral images, wavelength normalized cell Image edge feature data. Therefore, the use of neural networks can prevent medical staff or researchers from judging the quality of embryos in a subjective way. Infertile women can carry out multiple embryo cultures first. The cell detection system uses the cell quality detection model of artificial intelligence to determine the best embryo, and then artificially implants into the mother's uterus to increase the success rate of conception.

The above descriptions are only preferred embodiments of the present invention, and all equivalent changes and modifications made according to the scope of the patent application of the present invention shall fall within the scope of the present invention.

100: Cell detection system using artificial intelligence of hyperspectral data analysis technology

10: Vehicle

11: Lens module

12:Hyperspectrometer

13: Processor

14: Memory

Claims (8)

A cell detection method using artificial intelligence of hyperspectral data analysis technology, comprising: obtaining a plurality of cells; a hyperspectral instrument sampling N hyperspectral images of the cells between a first time point and a second time point ; According to the N hyperspectral images and/or an ambient light parameter, obtain a Bright Field (Bright Field) information and a Dark Field (Dark Field) information; according to the Bright Field information and the Dark Field information, generate a light penetration Transmittance percentage value; according to the light transmittance percentage value, correct the N hyperspectral images to generate N normalized cell hyperspectral images; determine when at least one internal chemical composition of each cell changes during a development period A corresponding observation area; between the first time point and the second time point, analyze the N normalized cell hyperspectral images to generate a key normalized cell hyperspectral image difference characteristic value corresponding to the observation area ; Input the key normalized cell hyperspectral image difference characteristic value corresponding to the observation area of each cell and/or the N normalized cell hyperspectral images to a type of neural network to train the type of neural network; and using the neural network to establish a cell quality detection model with an artificial intelligence program to detect cell quality and/or identify cells; wherein the first time point is before the second time point, and N is greater than 2 positive integer of . The method as claimed in claim 1, wherein the cell lines are a plurality of germ cells, and the first time point and the second time point are during an observation cycle of the germ cells developing and dividing in the culture medium any two time points. The method as claimed in claim 1, wherein the cell lines are a plurality of embryos, and the observation area is a blastocyst (Blastocyst) area of each embryo in the embryos or the at least one chemical composition of the embryos When changes occur, the area with the greatest difference. The method as described in claim 1, wherein the hyperspectral instrument obtains the N hyperspectral images of the cells, including the hyperspectral instrument at least one specific wavelength between the first time point and the second time point , to obtain the N hyperspectral images of the cells. The method as described in claim 1, wherein the key normalized cell hyperspectral image difference characteristic value includes a proportional relationship between the normalized spectra at each wavelength, a peak and/or a valley value of the normalized spectrum, the peak And/or a wavelength data corresponding to the trough, and the correlation among the plurality of wavelength data. The method as described in claim 1, further comprising: capturing a normalized cell image of at least one wavelength according to the N normalized cell hyperspectral images between the first time point and the second time point; and using a morphological edge detection technique, according to the normalized cell image of the at least one wavelength, to obtain the edge feature data of the wavelength normalized cell image at each time point and at each wavelength, and convert the wavelength The edge feature data of the normalized cell image is input to the neural network to train the neural network. The method as described in Claim 6, wherein after the neural network uses the edge feature data of the wavelength normalized cell image for training, the neural network uses the artificial intelligence program to optimize the Cell quality detection model. A cell detection system based on artificial intelligence using hyperspectral data analysis technology, including: a carrier with a holding tank for placing a plurality of cells; a lens module facing the carrier for magnifying the cells Details of the cells; a hyperspectral instrument facing the lens module for obtaining images of the cells through the lens module; a processor coupled to the lens module and the hyperspectral instrument for adjusting the lens A magnification of the module and processing the image of the cells; and a memory, coupled to the processor, for storing training data and analysis data of image processing; wherein the holding tank of the carrier is placed the After some cells, the processor controls the hyperspectral instrument to sample N hyperspectral images of the cells between a first time point and a second time point through the lens module, and according to the N hyperspectral images And/or an ambient light parameter, the processor obtains a Bright Field (Bright Field) information and a Dark Field (Dark Field) information, and the processor generates a light transmittance according to the Bright Field information and the Dark Field information Percentage value, the processor corrects the N hyperspectral images according to the light transmittance percentage value to generate N normalized cell hyperspectral images, the processor determines that each cell has at least one chemical substance inside during a development period An observation area corresponding to when the composition changes, and between the first time point and the second time point, analyze the N normalized cell hyperspectral images to generate a key normalized cell hyperspectral image corresponding to the observation area Spectral image difference feature value, and the processor includes a type of neural network, the key normalized cell hyperspectral image difference feature value corresponding to the observation area of each cell and/or the N normalized cell hyperspectral image To train the neural network, the processor uses the neural network to establish a cell quality detection model with an artificial intelligence program to detect cell quality and/or identify cells, the first time point is at the second Before the time point, and N is a positive integer greater than 2.

Images