TWI703961B - Oral image analysis system and method - Google Patents

Abstract

The present invention discloses an oral image analysis system which includes an image capturing device and a first platform. The image capturing device generates a first image. The first platform includes a first processing device and obtains the first image from the capturing device. The first processing device determines which position of the oral does the first image correspond to, and obtains several classifiers and several weight values corresponding to the classifiers. The first processing device may select a second image corresponding to a possible lesion area from the first image, and generates an analysis result according to the classifiers, the weight values and the second image.

Description

Oral image analysis system and method

The present invention relates to an oral image analysis technology, and particularly relates to an oral image analysis technology that analyzes oral images based on the oral image location, plural classifiers, and plural weight values.

Traditional oral cancer detection methods include physician visual inspection, palpation, saliva detection, tissue staining examination or brush biopsy technique and pathological tissue biopsy. Although biopsy is currently the main method of oral cancer inspection, there are still shortcomings in its application. For example, because biopsy is an invasive medical practice, wounds are prone to risk of infection. In addition, testing/sectioning performed by medical practitioners with different experience may produce considerable differences in the diagnosis results.

Therefore, in order to reduce the diagnostic error caused by the difference in manual operation, how to achieve a more accurate and efficient oral image analysis method is a topic worthy of research.

In view of the above-mentioned problems of the prior art, the present invention provides an oral image analysis system and method for analyzing oral images according to the oral image capturing position, the complex classifier, and the complex weight value.

According to an embodiment of the present invention, an oral image analysis system is provided. The aforementioned oral image analysis system includes an image capturing device and a first platform. The image capturing device generates a first image. The first platform includes a first processing device, and obtains the first image from the image capturing device. The first processing device determines that the first image corresponds to a position of the oral cavity, and obtains a complex classifier and a complex weight value corresponding to the complex classifier according to the position. The first processing device selects a second image corresponding to a possible lesion area from the first image, and generates an analysis result according to the complex classifier, the complex weight value, and the second image.

According to an embodiment of the present invention, the aforementioned oral image analysis system further includes a second platform. The second platform includes a second processing device, and obtains the first image from the first platform through a cloud network, or obtains the first image directly from the first platform. The second processing device determines that the first image corresponds to the position of the oral cavity, and obtains the complex classifier and the complex weight value corresponding to the complex classifier according to the position. The second processing device selects the second image corresponding to the possible lesion area from the first image, and generates the analysis result according to the complex classifier, the complex weight value, and the second image.

According to another embodiment of the present invention, an oral image analysis method is provided. The steps of the oral image analysis method include: generating a first image by an image capturing device; obtaining the first image from the image capturing device by a platform, wherein the platform is a first platform or a second platform Platform, and the computing power of the second platform is better than that of the first platform; judging that the first image corresponds to a position of the oral cavity; according to the position, obtaining a complex classifier and obtaining a complex weight corresponding to the complex classifier Value; select a second image corresponding to a possible lesion area from the first image; and generate an analysis result according to the complex classifier, the complex weight value, and the second image.

With regard to other additional features and advantages of the present invention, those skilled in the art, without departing from the spirit and scope of the present invention, can make some changes and changes based on the oral image analysis system and method disclosed in the implementation method of this case. Retouched.

100‧‧‧Oral Image Analysis System

110‧‧‧Image capture device

120‧‧‧First Platform

121、141‧‧‧Processing device

122、142‧‧‧Storage device

123、143‧‧‧Display device

130‧‧‧Cloud Network

140‧‧‧Second Platform

210, 410‧‧‧Part Judgment Module

220、420‧‧‧Select module

230、430‧‧‧Computer module

310‧‧‧Weight Determinator

440‧‧‧Optimization Module

FIG. 1 is a block diagram of the oral image analysis system 100 according to an embodiment of the invention.

FIG. 2A is a block diagram of the first platform 120 according to an embodiment of the present invention.

FIG. 2B is a block diagram of the processing device 121 according to an embodiment of the invention.

Figure 3A is a schematic diagram of a classifier according to an embodiment of the present invention.

Figure 3B is a schematic diagram of classification according to sub-classifier A according to an embodiment of the present invention.

FIG. 4A is a block diagram of the second platform 140 according to an embodiment of the present invention.

FIG. 4B is a block diagram of the processing device 141 according to an embodiment of the invention.

Figure 5 is a flowchart of the oral image analysis method according to an embodiment of the present disclosure.

The description in this chapter is one of the best ways to implement the present invention. The purpose is to explain the spirit of the present invention and not to limit the scope of protection of the present invention. The scope of protection of the present invention shall be defined as the appended patent quasi.

FIG. 1 is a block diagram of the oral image analysis system 100 according to an embodiment of the invention. As shown in FIG. 1, the oral image analysis system 100 includes an image capturing device 110, a first platform 120, a cloud network 130, and a second platform 140. It should be noted that the block diagram in Figure 1 is only for the convenience of describing the embodiments of the present invention, but the present invention is not limited thereto. The oral image analysis system 100 may also include other components.

In the embodiment of the present invention, the first platform 120 can be regarded as a control platform connected to the image capturing device 110, and the second platform 140 can be regarded as a remote database and processing and analysis platform. Both the first platform 120 and the second platform 140 have image processing capabilities, but the computing power of the second platform 140 is better than that of the first platform 120. Therefore, during clinical diagnosis, the user or operator (for example, a doctor) can use the image capturing device 110 to capture the oral image of the patient, and display the image captured by the image capturing device 110 according to the first platform 120 The analysis results produced by the images provide a preliminary assessment of the patient’s condition. When a disease research or discussion is to be conducted, users (for example: multiple doctors and researchers) can connect to the second platform 140 via the Internet, and the results generated by the second platform 140 against the first platform Analyze the results, conduct disease evaluation and research. In addition, according to an embodiment of the present invention, the first platform 120 can also be used only to directly transmit the image captured by the image capture device 110 to the second platform 140, or to the second platform 140 via the cloud network 130. All other operations related to image analysis are performed by the second platform 140.

According to an embodiment of the present invention, the image capturing device 110 can be coupled (or electrically connected) to the first platform 120. According to an embodiment of the present invention, the image capturing device 110 may be a handheld device. A user (for example, a doctor) uses the image capturing device 110 to capture an image of the position (location) of the oral cavity to be imaged to generate an image corresponding to the position.

According to an embodiment of the present invention, the image capturing device 110 includes an image capturing module (not shown), a light source module (not shown), and a filter switching module (not shown), but The present invention is not limited to this.

According to an embodiment of the present invention, the image capturing module includes a lens, which can be used to capture a specific position (position) of the oral cavity to generate an image corresponding to the position. According to an embodiment of the present invention, the light source module can provide light sources of different wavelengths, such as white light (natural light), ultraviolet (Ultraviolet, UV) light, or blue light. Since the human body has many light-sensitive substances (Fluorochrome), it will emit different fluorescence when irradiated by light, which is the self-fluorescence characteristic. The difference in autofluorescence characteristics between abnormal tissues in the mouth and surrounding normal tissues can be used to identify the presence of abnormal tissues. For example, light sources of different wavelengths can be used to excite nicotine amide adenine dinucleotide (NADH), flavin adenine dinucleotide (FAD), and collagen to produce fluorescence in oral cells. . In the case of tumors, the intracellular tissue components, including the concentration of NADH, the concentration of FAD, collagen, blood volume, tissue texture, etc., will change, so fluorescent images can be used to calculate and infer the concern Whether there is any disease in the oral cavity. According to an embodiment of the present invention, the filter switching module is arranged between the image capturing module and the light source module, and it can switch different filters according to light sources of different wavelengths to capture fluorescent images of different wavelengths.

FIG. 2A is a block diagram of the first platform 120 according to an embodiment of the present invention. As shown in FIG. 2A, the first platform 120 may include a processing device 121, a storage device 122, and a display device 123. It should be noted that the block diagram in Figure 2A is only for the convenience of describing the embodiments of the present invention, but the present invention is not limited thereto. The first platform 120 may also include other components.

According to an embodiment of the present invention, the processing device 121 may be a device including one or more processors. According to an embodiment of the present invention, the storage device 122 can be used to store the complex classifier and the complex weight value. According to an embodiment of the present invention, the data such as the complex classifier and the complex weight value stored in the storage device 122 may be generated through analysis and training in advance. The first platform 120 can provide the complex classifier and the complex weight value stored in the storage device 122 to the second platform 140 via the cloud network 130. According to another embodiment of the present invention, the complex classifier and the complex weight value may also be provided by the second platform to the first platform 120. According to an embodiment of the present invention, the display device 123 may be, for example, a liquid crystal screen or a touch panel, but the present invention is not limited thereto.

The complex classifier described in the embodiment of the present invention can be based on image intensity (intensity) calculation, heterogeneity (heterogeneity) algorithm, intensity difference vector (intensity difference vector, IDV) algorithm, Gabor filter algorithm (Gabor Filter), Wavelet Transform (Wavelet Transform), and Hilbert Huang Transform (Hilbert Huang Transform) and other algorithms are one or more of which are generated by calculating the plural oral images collected in advance. In other words, the complex classifier can correspond to different image features and algorithms. According to one or more of the above algorithms, it can be used to generate the image features corresponding to each classifier. In addition, according to an embodiment of the present invention, each classifier can be further classified according to the underlying classifier calculation algorithm, such as support vector machine (support vector machine), KNN classifier, and probabilistic neural network (probabilistic neural network). neural network), convolutional neural networks (CNN), decision trees, etc., the following will take Figure 3A-3B as an example for illustration. In addition, in the embodiment of the present invention, different positions of the oral cavity corresponding to the same classifier will have different weight values.

According to an embodiment of the present invention, a machine learning method can be used to generate the weight values of different classifiers. The above-mentioned machine learning method is, for example, an adaptive boost (AdaBoost) algorithm or an ensemble algorithm, but the present invention is not limited thereto.

The concept of the adaptive enhancement (AdaBoost) algorithm is to collect multiple classifiers and aggregate them into new classifiers. The effect can be stronger than the original classifiers. It uses the complementary relationship learning between Yangchun classifiers to adjust the classifier weights during the learning process. According to an embodiment of the present invention, the processing device 121 further includes a gating, as shown in FIG. 3A. The weight determiner can determine the weight value of different classifiers based on the results obtained by testing each classifier based on the image data. A classifier with a higher accuracy rate is given a higher weight value, otherwise it is given a lower weight value.

FIG. 2B is a block diagram of the processing device 121 according to an embodiment of the invention. As shown in FIG. 2B, the processing device 121 may include a location determination module 210, a selection module 220, and an operation module 230.

According to an embodiment of the present invention, when the first platform 120 obtains the image generated by the image capturing device 110 from the image capturing device 110 (referred to as the first image below), the position determining module 210 will determine the image according to the first image , To determine the position (or part) of the oral cavity corresponding to the first image, for example: cheeks, tongue, upper jaw, under the tongue, gums and other different oral positions. In other words, the location determining module 210 determines which part of the oral cavity the user or operator of the first platform 120 currently takes based on the characteristics of the first image.

According to another embodiment of the present invention, the user or operator of the first platform 120 (for example, a doctor) can directly input (or select) the part corresponding to the first image through the first platform 120 according to the first image . For example, the user can directly input (or select) the part corresponding to the first image through the display device 123 or an operating interface of the first platform 120 (not shown).

After the position determination module 210 obtains the position of the oral cavity corresponding to the first image, it will provide this information to the calculation module 230. According to an embodiment of the present invention, the arithmetic module 230 obtains the complex classifier stored in the storage device 122 and the complex weight value from the storage device 122 according to this position. The complex classifier will have a different weight value corresponding to each position of the oral cavity. In other words, the same classifier can have different weight values corresponding to different oral positions.

According to another embodiment of the present invention, when the position determining module 210 knows the position of the oral cavity corresponding to the first image, the computing module 230 obtains one of the corresponding positions from the plural classifiers stored in the storage device 122 Group classifier, and obtain the complex weight value corresponding to the group classifier. In this embodiment, each position of the oral cavity will have a corresponding group of classifiers, and a complex weight value corresponding to the group of classifiers. It should be noted that the same classifier can have different weights corresponding to different oral positions.

According to another embodiment of the present invention, the computing module 230 can also directly calculate the weight value corresponding to each classifier based on the first image. That is to say, in this embodiment, the computing module 230 will use a machine learning method to calculate the weight value corresponding to each classifier according to the position and image feature of the oral cavity corresponding to the first image. The above-mentioned machine learning method For example, it is an adaptive enhancement (AdaBoost) algorithm or an ensemble algorithm.

According to an embodiment of the present invention, the selection module 220 can select a second image corresponding to a possible lesion area from the first image according to the first image. Specifically, the selection module 220 can use an image recognition algorithm to determine the area in the first image where the lesion may occur, and extract the image corresponding to the likely lesion area from the first image.

According to another embodiment of the present invention, the user or operator of the first platform 120 (for example, a doctor) can also directly input (or select) the disease that may occur in the first image based on the first image. Area to produce the second image. For example, the user can directly input (or select) an area in the first image that may have a lesion through one of the operating interfaces of the display device 123 or the first platform 120 to generate the second image.

After the second image is generated, the calculation module 230 generates an analysis result according to the obtained complex classifier, the complex weight value, and the second image, and transmits the analysis result to the display device 123. The display device 123 displays the analysis result for reference by the user or operator (for example, doctor) of the first platform 120.

Figure 3A is a schematic diagram of the complex classifier according to an embodiment of the present invention. It should be noted that the schematic diagram in Figure 3A is only for the convenience of describing the embodiments of the present invention, but the present invention is not limited thereto. As shown in Figure 3A, the image features used by classifier A are the results (ie, variability and image intensity) produced by the variability algorithm and image intensity algorithm, and the image features used by classifier B are through wavelet The result produced by the conversion algorithm (ie, wavelet coefficients) and the image features used by classifier C are the results produced by the Jaber filter algorithm and the image intensity algorithm (ie, Jaber coefficients and image intensity). Each classifier can also be classified according to different classifier calculation algorithms. The following will take Figure 3B as an example.

Figure 3B is a schematic diagram of classifier A performing classification according to an embodiment of the present invention. As shown in Figure 3A, the image features used by classifier A are the results (ie, variability and image intensity) produced by the variability algorithm and the image intensity algorithm. In this embodiment, the computing module 230 can use a decision tree to classify the image. As shown in FIG. 3B, the arithmetic module 230 judges an image with an image variability greater than 30 and an image intensity greater than 40 as cancer. Conversely, if the image variability is less than 30, the calculation module 230 will determine the image category as normal, and if the image variability is greater than 30 but the image intensity is lower than 40, the calculation module 230 will also determine the image category as normal. In addition, according to another embodiment of the present invention, the arithmetic module 230 can also use a support vector machine (SVM) method to implement classifiers for image classification, and calculate the image feature value used by each classifier. And load the trained boundary line, and determine which category the input image belongs to by location. The boundary line is generated by the support vector machine and based on the data collected in the past. The boundary can separate the two categories. The maximum distance between. In addition, according to another embodiment of the present invention, the computing module 230 can also use a probabilistic neural network to classify each classifier, and determine the likelihood of the image in each classification based on the similarity between the image and the training data. Therefore, the judgment result of each classifier after reclassification can be the judgment of the disease category or the possibility of the disease category.

According to an embodiment of the present invention, the analysis result generated by the calculation module 230 may include the probability of oral cancer in the oral cavity corresponding to the second image. For example, if we take Figures 3A-3B as an example, if the weight values W ₁ , W ₂ and W _M of the classifier AC corresponding to the second image generated by the weight determiner 310 are 0.2, 0.5, and 0.3, respectively, and after The result of the classifier AC judgment of the classifier calculation algorithm is that the probability of cancer is 0.8, 0.9, 0.7. The calculation module 230 can obtain the probability of cancer in the oral cavity corresponding to the first image after weighted evaluation f _en is 0.82( 82%). In addition, the analysis results generated by the calculation module 230 may also include analysis and suggestions corresponding to the probability of different oral cancers. For example, the probability of 0~10% can be set as normal, 10~50% can be set as there may be abnormalities, users are recommended to observe for a long time, 50~90% can be set as abnormalities, users are recommended to arrange inspections in the near future, and 90~ 100% can be set as obvious abnormalities as high risk. It is recommended that users seek medical assistance as soon as possible.

FIG. 4A is a block diagram of the second platform 140 according to an embodiment of the invention. As shown in FIG. 4A, the second platform 140 may include a processing device 141, a storage device 142, and a display device 143. It should be noted that the block diagram in Figure 4A is only for the convenience of describing the embodiments of the present invention, but the present invention is not limited thereto. The second platform 140 may also include other components.

According to an embodiment of the present invention, the processing device 141 may be a device including one or more processors. According to an embodiment of the present invention, the second platform 140 can directly obtain the first image, the plural classifier, and the plural weight value from the first platform 110 via the first platform 110 or the cloud network 130, and the obtained first image , The complex classifier and the complex weight value are stored in the storage device 142. According to another embodiment of the present invention, the second platform 140 only needs to obtain the first image from the first platform 110, and the complex classifier and the complex weight value can be generated by the second platform and then transmitted to the first platform. In this embodiment, the first image obtained from the first platform 110 and the complex classifier and complex weight value generated by the second platform are also stored in the storage device 142. According to an embodiment of the present invention, the display device 143 may be a liquid crystal screen or a touch panel, but the present invention is not limited thereto.

FIG. 4B is a block diagram of the processing device 141 according to an embodiment of the invention. As shown in FIG. 4, the processing device 141 may include a location determination module 410, a selection module 420, an operation module 430, and an optimization module 440.

According to an embodiment of the present invention, the oral image analysis method performed by the first platform 110 can also be applied to the second platform 140. In addition, the position determination module 410, the selection module 420, and the operation similarity position determination module 210, the selection module 220, and the operation module 230 of the operation module 430 of the processing device 141. Therefore, I will not repeat them here.

As shown in FIG. 4, compared with the processing device 121, the processing device 141 further includes an optimization module 440. The optimization module 440 can update the classifier and weight value corresponding to the part corresponding to the first image according to the analysis result generated by the calculation module 430, and store the updated information in the storage device 142. In addition, the second platform 140 can provide updated information to the first platform 120 via the cloud network 130.

FIG. 5 is a flowchart of the oral image analysis method according to an embodiment of the disclosure. This oral image analysis method can be applied to the oral image analysis system 100 of the present disclosure. In step S510, an image capturing device of the analysis system 100 generates a first image. In step S520, a platform of the analysis system 100 (a first platform or a second platform, and the computing power of the second platform is better than the computing power of the first platform) obtains the first image. In step S530, the aforementioned platform will determine that the first image corresponds to a position of the oral cavity. In step S540, according to the above position, the platform will obtain a complex classifier and obtain a complex weight value corresponding to the complex classifier. In step S550, the platform will select a second image corresponding to a possible lesion area from the first image. S560. The platform generates an analysis result according to the complex classifier, the complex weight value, and the second image.

According to some embodiments of the present invention, in the oral image analysis method, the second platform of the analysis system 100 obtains the first image from the first platform of the analysis system 100 or directly from the first platform of the analysis system 100 through a cloud network. The second platform will determine the position of the first image corresponding to the oral cavity, and obtain the complex classifier and the complex weight value of the corresponding complex classifier based on the above position. In addition, the second platform selects a second image corresponding to the possible lesion area from the first image, and generates the analysis result according to the complex classifier, the complex weight value, and the second image.

According to some embodiments of the present invention, in the oral image analysis method, the second platform will update the complex classifier and the complex weight value according to the analysis result. In addition, according to some embodiments of the present invention, in the oral image analysis method, the second platform provides the updated complex classifier and the complex weight value to the first platform via the cloud network.

According to the oral imaging system and method proposed by the embodiments of the present invention, the diagnosis error caused by the difference in human operation can be reduced, and the diagnosis of the slice position can be assisted by doctors or researchers. In addition, according to the oral imaging system and method proposed in the embodiments of the present invention, doctors or researchers can directly use the cloud database platform to conduct research or discussion of diseases based on the analysis results of the database platform.

The serial numbers in this specification and in the scope of the patent application, such as "first", "second", etc., are only for convenience of description, and there is no sequential relationship between them.

The method and algorithm steps disclosed in the specification of the present invention can be directly applied to hardware and software modules or a combination of the two directly by executing a processor. A software module (including execution commands and related data) and other data can be stored in data memory, such as random access memory (RAM), flash memory (flash memory), and read-only memory (ROM) , Erasable programmable read-only memory (EPROM), electronically erasable programmable read-only memory (EEPROM), scratchpad, hard disk, portable hard disk, optical disk read-only memory (CD- ROM), DVD, or any other computer-readable storage media format used in this field. A storage medium can be coupled to a machine device, such as a computer/processor (for the convenience of description, it is represented by a processor in this manual), and the processor can read information (such as a program Code), and write information to the storage medium. A storage medium can integrate a processor. An application-specific integrated circuit (ASIC) includes a processor and a storage medium. A user equipment includes a special application integrated circuit. In other words, the processor and the storage medium are included in the user equipment in a manner that is not directly connected to the user equipment. In addition, in some embodiments, any product suitable for computer programs includes a readable storage medium, where the readable storage medium includes code related to one or more of the disclosed embodiments. In some embodiments, the product of the computer program may include packaging materials.

The above paragraphs use multiple levels of description. Obviously, the teachings of this document can be implemented in various ways, and any specific structure or function disclosed in the example is only a representative situation. According to the teachings of this article, anyone who is familiar with this technique should understand that each level disclosed in this article can be implemented independently or two or more levels can be combined.

Although this disclosure has been disclosed in the above embodiments, it is not intended to limit the disclosure. Anyone who is familiar with this technique can make some changes and modifications without departing from the spirit and scope of this disclosure. Therefore, the protection scope of the invention The scope of the patent application attached hereafter shall prevail.

100‧‧‧Oral Image Analysis System

110‧‧‧Image capture device

120‧‧‧First Platform

130‧‧‧Cloud Network

140‧‧‧Second Platform

Claims (20)

An oral image analysis system includes: an image capture device that generates a first image; and a first platform, including a first processing device, and obtains the first image, wherein the first processing device determines the first image An image corresponds to a position in the oral cavity, and based on the above position, a complex classifier is obtained, and based on the above position, a machine learning method is used to calculate the complex weight value corresponding to the above complex classifier, wherein the same classifier corresponds to the oral cavity Different positions have different weight values; wherein the first processing device selects a second image corresponding to a possible lesion area from the first image, and generates it according to the complex classifier, the complex weight value, and the second image 1. Analysis result. According to the oral image analysis system described in claim 1, wherein the first processing device includes a first part determination module, and the first part determination module determines that the first image corresponds to the first image To the above position in the oral cavity. According to the oral image analysis system described in claim 1, wherein the first processing device includes a first selection module, and the first selection module selects from the first image based on the first image The above second image corresponding to the above possible lesion area. According to the oral image analysis system described in claim 1, wherein the first processing device includes a first arithmetic module, and the first arithmetic device is based on the complex classifier, the complex weight value, and the The second image produces the above analysis result. According to the oral image analysis system described in claim 1, wherein the first platform further includes a first storage device, and the first storage device stores the first image, the complex classifier, and the complex weight value. According to the oral image analysis system described in claim 1, wherein the first platform further includes a first display device for displaying the analysis result. For example, the oral image analysis system described in claim 1 further includes a second platform, which includes a second processing device, and obtains the first image from the first platform through a cloud network, or directly Obtain the first image from the first platform; wherein the second processing device determines that the first image corresponds to the position of the oral cavity, and according to the position, obtains the complex classifier and obtains the complex weight corresponding to the complex classifier Value; wherein the second processing device selects the second image corresponding to the possible lesion area from the first image, and generates the analysis result according to the complex classifier, the complex weight value, and the second image. According to the oral image analysis system described in claim 7, wherein the second processing device includes a second part determination module, and the second part determination module determines that the first image corresponds to the first image To the above position in the oral cavity. The oral image analysis system described in item 7 of the scope of patent application, wherein The second processing device includes a second selection module, and the second selection module selects the second image corresponding to the possible lesion area from the first image according to the first image. According to the oral image analysis system described in item 7 of the scope of patent application, the second processing device includes a second arithmetic module, and the arithmetic device generates the aforementioned complex number classifier, the aforementioned complex weight value, and the aforementioned second image. Analyze the results. According to the oral image analysis system described in claim 7, wherein the second processing device includes an optimization module, and the optimization module updates the complex classifier and the complex weight value according to the analysis result. The oral image analysis system described in claim 11, wherein the second platform provides the updated complex classifier and the complex weight value to the first platform through the cloud network. The oral image analysis system described in item 7 of the scope of patent application, wherein the second platform further includes a second storage device; the second storage device stores the first image, the complex classifier, and the complex weight value, and The complex number classifier and the complex weight value stored in the second storage device are obtained from the first platform or directly generated through the second platform. According to the oral image analysis system described in item 7 of the scope of patent application, the second platform further includes a second display device for displaying the analysis result. The oral image analysis system described in item 7 of the scope of patent application, wherein The above-mentioned complex classifier is based on the heterogeneity algorithm, the intensity difference vector (IDV) algorithm, the Gabor filter algorithm (Gabor Filter), the wavelet transform algorithm (Wavelet Transform) and Hilber Generated by one or more of the Hilbert Huang Transform algorithm. An oral image analysis method includes: generating a first image by an image capturing device; obtaining the first image by a platform, wherein the platform is a first platform or a second platform, and the second platform The computing power is better than the computing power of the first platform; it is determined that the first image corresponds to a position of the oral cavity; according to the position, a complex classifier is obtained, and based on the position, a machine learning method is used to calculate the corresponding complex number The complex weight value of the classifier, wherein the same classifier corresponds to different positions of the oral cavity with different weight values; a second image corresponding to a possible lesion area is selected from the above first image; and according to the above plural classifier, the above plural The weight value and the aforementioned second image generate an analysis result. The oral image analysis method according to the 16th patent application, wherein the first platform obtains the first image from the image capturing device, and the second platform obtains the first image from the first platform through a cloud network, or directly Obtain the first image from the first platform. Such as the oral image analysis method described in item 16 of the scope of patent application, more It includes: updating the complex classifier and the complex weight value by the second platform according to the analysis result. The oral image analysis method described in item 18 of the patent application further includes: providing the updated complex classifier and the complex weight value to the first platform through the cloud network through the second platform. According to the oral image analysis method described in item 16 of the scope of patent application, the above-mentioned complex classifier is based on the heterogeneity algorithm, the intensity difference vector (IDV) algorithm, and the Gabor filter algorithm (Gabor Filter), Wavelet Transform (Wavelet Transform), and Hilbert Huang Transform (Hilbert Huang Transform) one or more.

Images