TWI840828B - System, computer program and computer-readable medium for assisting in recognition of periodontitis and dental caries by using image processing and deep learning object detection model - Google Patents
System, computer program and computer-readable medium for assisting in recognition of periodontitis and dental caries by using image processing and deep learning object detection model Download PDFInfo
- Publication number
- TWI840828B TWI840828B TW111121076A TW111121076A TWI840828B TW I840828 B TWI840828 B TW I840828B TW 111121076 A TW111121076 A TW 111121076A TW 111121076 A TW111121076 A TW 111121076A TW I840828 B TWI840828 B TW I840828B
- Authority
- TW
- Taiwan
- Prior art keywords
- image
- tooth
- periodontal disease
- object detection
- caries
- Prior art date
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 44
- 208000002925 dental caries Diseases 0.000 title claims abstract description 41
- 238000012545 processing Methods 0.000 title claims abstract description 41
- 238000013135 deep learning Methods 0.000 title claims abstract description 15
- 238000004590 computer program Methods 0.000 title claims abstract description 8
- 201000001245 periodontitis Diseases 0.000 title abstract 7
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims abstract description 4
- 208000028169 periodontal disease Diseases 0.000 claims description 48
- 230000003044 adaptive effect Effects 0.000 claims description 14
- 238000012935 Averaging Methods 0.000 claims description 12
- 230000002146 bilateral effect Effects 0.000 claims description 11
- 239000002131 composite material Substances 0.000 claims description 7
- 208000002679 Alveolar Bone Loss Diseases 0.000 claims description 2
- 206010044038 Tooth erosion Diseases 0.000 claims description 2
- 238000009434 installation Methods 0.000 claims description 2
- 208000036595 non-bacterial tooth erosion Diseases 0.000 claims description 2
- 230000003862 health status Effects 0.000 abstract description 2
- 238000002372 labelling Methods 0.000 abstract 1
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 230000037123 dental health Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 208000018035 Dental disease Diseases 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 208000014151 Stomatognathic disease Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
Description
本發明係有關於一種利用影像處理與深度學習之物件偵測模型輔助辨識牙周病及齲齒之系統、電腦程式及電腦可讀取媒體，特別是指將數據資料庫中牙齒的根尖X光影像結合影像處理模組及物件偵測模型而建立牙周病及齲齒輔助辨識模型的發明，藉以輔助檢測牙齒健康狀態。 The present invention relates to a system, computer program and computer-readable medium that utilizes image processing and deep learning object detection models to assist in the identification of periodontal disease and caries, and in particular to an invention that combines the root apex X-ray images of teeth in a database with an image processing module and an object detection model to establish a periodontal disease and caries auxiliary identification model, thereby assisting in the detection of tooth health status.
一般神經網路及卷積神經網路(Convolutional Neural Network,CNN)通常適用於單顆牙齒之檢測辨別。 General neural networks and convolutional neural networks (CNN) are usually applicable to the detection and identification of a single tooth.
Hu.Chen等人於2021年提出之文獻「Dental Disease Detection on Periapical Radiographs Based on Deep Convolutional Neural Networks」，係將牙齒的根尖X光影像使用較快速的基於區域的卷積神經網路(Faster Region-based Convolutional Neural Network,Faster R-CNN)物件偵測模型進行學習，藉以能夠在根尖X光影像辨識齲齒、根尖周圍炎及牙周病等病徵之程度與位置。 The paper "Dental Disease Detection on Periapical Radiographs Based on Deep Convolutional Neural Networks" proposed by Hu.Chen et al. in 2021 uses a faster region-based convolutional neural network (Faster R-CNN) object detection model to learn the apical X-ray images of teeth, so as to identify the extent and location of symptoms such as caries, periapical inflammation and periodontal disease in apical X-ray images.
有別於上述前案，本發明提出一種利用影像處理與深度學習之物件偵測模型輔助辨識牙周病及齲齒之系統，準確判別病患的牙齒健康狀況。 Different from the above-mentioned previous case, the present invention proposes a system that uses image processing and deep learning object detection models to assist in the identification of periodontal disease and caries, and accurately judge the patient's dental health status.
本發明之系統包括有：一數據資料庫，儲存有複數根尖X光影像，上述根尖X光影像中之複數單顆牙齒影像上各自標註為一正常牙齒影像、一牙周病牙齒影像、一齲齒牙齒影像或一牙周病/齲齒複合牙齒影像。一電腦，連結該數據資料庫，該電腦安裝有一影像處理模組及深度學習之一物件偵測模型。 The system of the present invention includes: a database storing a plurality of apical X-ray images, wherein the plurality of single tooth images in the apical X-ray images are respectively labeled as a normal tooth image, a periodontal disease tooth image, a carious tooth image, or a periodontal disease/carious combined tooth image. A computer connected to the database, the computer is equipped with an image processing module and an object detection model of deep learning.
該電腦取得上述根尖X光影像，並透過該影像處理模組將上述根尖X光影像進行影像處理，以強化上述根尖X光影像的特徵，之後輸入該物件偵測模型進行訓練，而獲得一牙周病及齲齒輔助辨識模型。輸入一待檢測根尖X光影像至該電腦，透過該牙周病及齲齒輔助辨識模型將該待檢測根尖X光影像進行牙齒檢測，其中包含先透過該影像處理模組將上述待檢測根尖X光影像進行影像處理，再以該物件偵測模型自該待檢測根尖X光影像辨識出複數待檢測單顆牙齒影像而獲得不同牙齒位置以及將上述待檢測單顆牙齒影像歸類於該正常牙齒影像、該牙周病牙齒影像、該齲齒牙齒影像或該牙周病/齲齒複合牙齒影像。 The computer obtains the above-mentioned apical X-ray image, and processes the above-mentioned apical X-ray image through the image processing module to enhance the characteristics of the above-mentioned apical X-ray image, and then inputs the object detection model for training to obtain a periodontal disease and caries auxiliary identification model. Input a root apex X-ray image to be detected into the computer, and perform tooth detection on the root apex X-ray image to be detected through the periodontal disease and caries auxiliary identification model, which includes first processing the root apex X-ray image to be detected through the image processing module, and then using the object detection model to identify multiple single tooth images to be detected from the root apex X-ray image to be detected to obtain different tooth positions and classify the single tooth image to be detected into the normal tooth image, the periodontal disease tooth image, the caries tooth image or the periodontal disease/caries composite tooth image.
進一步，該物件偵測模型係YOLOv4一階段物件偵測模型(One-stage Object Detection Model)。 Furthermore, the object detection model is a YOLOv4 one-stage object detection model (One-stage Object Detection Model).
進一步，該影像處理模組包括對比限制自適應直方圖均化(Contrast Limited Adaptive Histogram Equalization,CLAHE)及雙邊濾波器(Bilateral Filter)；上述根尖X光影像之影像處理結果為先由該對比限制自適應直方圖均化進行影像處理以增強局部對比度，再由該雙邊濾波器再次進行影像處理以保留影像邊緣之結果。 Furthermore, the image processing module includes contrast limited adaptive histogram equalization (CLAHE) and a bilateral filter; the image processing result of the above-mentioned apical X-ray image is first processed by the contrast limited adaptive histogram equalization to enhance the local contrast, and then processed again by the bilateral filter to retain the image edge.
進一步，將上述待檢測根尖X光影像之待檢測單顆牙齒影像以不同標記符號標記為該正常牙齒影像、該牙周病牙齒影像、該齲齒牙齒影像或該牙周病/齲齒複合牙齒影像。 Furthermore, the single tooth image to be tested of the above-mentioned apical X-ray image to be tested is marked with different marking symbols as the normal tooth image, the periodontal disease tooth image, the decayed tooth image or the periodontal disease/decayed tooth image.
本發明再提供一種電腦程式，用於安裝在前述利用影像處理與深度學習之物件偵測模型輔助辨識牙周病及齲齒之系統。 The present invention further provides a computer program for installation in the aforementioned system that uses image processing and deep learning object detection models to assist in the identification of periodontal disease and caries.
本發明再提供一種電腦可讀取媒體，係儲存有前述電腦程式。 The present invention further provides a computer-readable medium that stores the aforementioned computer program.
根據上述技術特徵可達成以下功效： Based on the above technical features, the following effects can be achieved:
1.本發明之系統所建立的牙周病及齲齒輔助辨識模型於進行影像訓練時係結合影像處理模組及深度學習之物件偵測模型。所述影像處理模組為使用對比限制自適應直方圖均化進行影像處理以增強局部對比度，再使用雙邊濾波器進行影像處理以保留影像邊緣。實際進行人工智慧檢測時，相比於單獨利用物件偵測模型進行訓練，本發明之系統能有效提升檢測結果之效能。 1. The periodontal disease and caries auxiliary recognition model established by the system of the present invention combines the image processing module and the deep learning object detection model during image training. The image processing module uses contrast-limited adaptive histogram averaging to perform image processing to enhance local contrast, and then uses a bilateral filter to perform image processing to retain image edges. When performing actual artificial intelligence detection, compared with training using the object detection model alone, the system of the present invention can effectively improve the performance of the detection results.
2.本發明之牙周病及齲齒輔助辨識模型能夠在根尖X光影像上辨識不同的單顆牙齒影像而獲得不同牙齒位置，並且能夠在根尖X光影像上同時檢測不同牙齒上的齲齒、牙周病與牙周病/齲齒複合等病徵。 2. The periodontal disease and caries auxiliary identification model of the present invention can identify different single tooth images on the apical X-ray image to obtain different tooth positions, and can simultaneously detect caries, periodontal disease, and periodontal disease/caries combined symptoms on different teeth on the apical X-ray image.
1:數據資料庫 1:Database
2:電腦 2: Computer
21:影像處理模組 21: Image processing module
211:對比限制自適應直方圖均化 211: Contrast-limited adaptive histogram averaging
212:雙邊濾波器 212: Double-sided filter
22:物件偵測模型 22: Object detection model
23:牙周病及齲齒輔助辨識模型 23: Periodontal disease and caries auxiliary identification model
A:根尖X光影像 A: Periapical X-ray image
A1:正常牙齒影像 A1: Normal tooth image
A2:牙周病牙齒影像 A2: Periodontal disease tooth image
A3:齲齒牙齒影像 A3: Tooth decay image
A4:牙周病/齲齒複合牙齒影像 A4: Periodontal disease/cavity compound tooth images
B:待檢測根尖X光影像 B: X-ray image of the apex to be tested
[第一圖]係為本發明實施例之系統架構示意圖。 [Figure 1] is a schematic diagram of the system architecture of an embodiment of the present invention.
[第二圖]係為本發明實施例之影像流程圖。 [Figure 2] is an image flow chart of an embodiment of the present invention.
[第三圖]係為本發明實施例中，經過對比限制自適應直方圖均化以及依序經過對比限制自適應直方圖均化及雙邊濾波器處理後的牙齒影像之比較。 [Figure 3] is a comparison of tooth images after contrast-limited adaptive histogram averaging and after contrast-limited adaptive histogram averaging and bilateral filter processing in sequence in an embodiment of the present invention.
[第四圖]係為本發明實施例中以不同標記符號標記所檢測之不同牙齒影像。 [Figure 4] shows different tooth images detected using different marking symbols in the embodiment of the present invention.
綜合上述技術特徵，本發明利用影像處理與深度學習之物件偵測模型輔助辨識牙周病及齲齒之系統、電腦程式及電腦可讀取媒體的主要功效將可於下述實施例清楚呈現。 Combining the above technical features, the main functions of the system, computer program and computer-readable medium of the present invention that utilizes image processing and deep learning object detection models to assist in the identification of periodontal disease and caries will be clearly presented in the following embodiments.
參閱第一圖所示，本實施例包括：一數據資料庫1，儲存有複數根尖X光影像A，上述根尖X光影像A中之複數單顆牙齒影像上各自標註為一正常牙齒影像A1、一牙周病牙齒影像A2、一齲齒牙齒影像A3及一牙周病/齲齒複合牙齒影像A4之一。一電腦2，連結該數據資料庫1，該電腦安裝有一影像處理模組21及深度學習之一物件偵測模型22。 Referring to the first figure, the present embodiment includes: a database 1 storing a plurality of apical X-ray images A, wherein the plurality of single tooth images in the apical X-ray images A are respectively labeled as one of a normal tooth image A1, a periodontal disease tooth image A2, a carious tooth image A3, and a periodontal disease/carious composite tooth image A4. A computer 2 connected to the database 1, the computer is equipped with an image processing module 21 and an object detection model 22 of deep learning.
本實施例試驗時，每張根尖X光影像A皆經由牙醫師標註，而取得上述正常牙齒影像A1、牙周病牙齒影像A2、齲齒牙齒影像A3及牙周病/齲齒複合牙齒影像A4。 During the trial of this embodiment, each apex X-ray image A was annotated by a dentist to obtain the above-mentioned normal tooth image A1, periodontal disease tooth image A2, carious tooth image A3 and periodontal disease/carious combined tooth image A4.
參閱第一圖至第三圖所示，該電腦取得上述根尖X光影像A，透過該影像處理模組21將上述根尖X光影像A進行影像處理，以強化上述根尖X光影像A的特徵。具體的，該影像處理模組21包括一對比限制自適應直方圖均化211及一雙邊濾波器212；上述根尖X光影像A先由該對比限制自適應直方圖均化211進行影像處理以增強局部對比度，再由該雙邊濾波器212再次進行影像處理以保留影像邊緣。 Referring to the first to third figures, the computer obtains the above-mentioned apical X-ray image A, and processes the above-mentioned apical X-ray image A through the image processing module 21 to enhance the characteristics of the above-mentioned apical X-ray image A. Specifically, the image processing module 21 includes a contrast-limited adaptive histogram averaging 211 and a bilateral filter 212; the above-mentioned apical X-ray image A is first processed by the contrast-limited adaptive histogram averaging 211 to enhance the local contrast, and then processed again by the bilateral filter 212 to retain the image edge.
參閱第三圖所示，顯示經過該對比限制自適應直方圖均化211處理後的單顆牙齒影像A，相較原始的單顆牙齒影像A能夠有效的增強局部對比 度；再經過該雙邊濾波器212處理後的單顆牙齒影像A能有效降低影像雜訊，保留用來診斷牙周病與齲齒的特徵如齒槽骨流失或牙齒受侵蝕的影像邊緣等資訊。本實施例結合上述對比限制自適應直方圖均化211及雙邊濾波器212而能夠強化該根尖X光影像A的疾病特徵，有利於深度學習模型之訓練，具體係由該對比限制自適應直方圖均化211增加局部對比度而強化牙周病與齲齒疾病的局部特徵，但增加該根尖X光影像A的對比後可能會有細節雜訊，該雙邊濾波器212則讓該根尖X光影像A保持原本的輪廓並降低雜訊。 Referring to the third figure, the single tooth image A after the contrast-limited adaptive histogram averaging 211 processing is shown, which can effectively enhance the local contrast compared to the original single tooth image A; the single tooth image A after the bilateral filter 212 processing can effectively reduce the image noise, and retain the features used for diagnosing periodontal disease and tooth decay, such as alveolar bone loss or tooth erosion image edge information. This embodiment combines the above-mentioned contrast-limited adaptive histogram averaging 211 and the bilateral filter 212 to enhance the disease characteristics of the apical X-ray image A, which is beneficial to the training of the deep learning model. Specifically, the contrast-limited adaptive histogram averaging 211 increases the local contrast and enhances the local characteristics of periodontal disease and caries. However, increasing the contrast of the apical X-ray image A may cause detail noise. The bilateral filter 212 allows the apical X-ray image A to maintain its original outline and reduce noise.
參閱第一圖所示，將透過該影像處理模組21處理後之上述根尖X光影像A輸入該物件偵測模型22進行訓練，藉以獲得一牙周病及齲齒輔助辨識模型23，其中本實施例之物件偵測模型22係使用YOLOv4一階段物件偵測模型(One-stage Object Detection Model)。 Referring to the first figure, the apical X-ray image A processed by the image processing module 21 is input into the object detection model 22 for training to obtain a periodontal disease and caries auxiliary recognition model 23, wherein the object detection model 22 of this embodiment uses the YOLOv4 one-stage object detection model (One-stage Object Detection Model).
實際用於檢測時，輸入一待檢測根尖X光影像B至該電腦2，該電腦2透過該牙周病及齲齒輔助辨識模型23將該待檢測根尖X光影像B進行牙齒檢測，其中包含先透過該影像處理模組21將上述待檢測根尖X光影像B進行影像處理，再以該物件偵測模型22自該待檢測根尖X光影像B辨識出複數待檢測單顆牙齒影像而獲得不同牙齒位置並分類，並將該待檢測單顆牙齒影像檢測歸類於該正常牙齒影像A1、該牙周病牙齒影像A2、該齲齒牙齒影像A3或該牙周病/齲齒複合牙齒影像A4。其中，可將上述待檢測根尖X光影像B之待檢測單顆牙齒影像以不同標記符號標記為該正常牙齒影像A1、該牙周病牙齒影像A2、該齲齒牙齒影像A3或該牙周病/齲齒複合牙齒影像A4，所述以不同標記符號標記例如第四圖所示係以不同線形框。 When actually used for detection, an apex X-ray image B to be detected is input to the computer 2, and the computer 2 performs tooth detection on the apex X-ray image B to be detected through the periodontal disease and caries auxiliary identification model 23, which includes first performing image processing on the apex X-ray image B to be detected through the image processing module 21, and then using the object detection model 22 to identify a plurality of single tooth images to be detected from the apex X-ray image B to be detected to obtain different tooth positions and classify them, and the single tooth image to be detected is detected and classified into the normal tooth image A1, the periodontal disease tooth image A2, the caries tooth image A3 or the periodontal disease/caries composite tooth image A4. Among them, the single tooth image to be detected of the above-mentioned apex X-ray image B to be detected can be marked with different marking symbols as the normal tooth image A1, the periodontal disease tooth image A2, the carious tooth image A3 or the periodontal disease/carious composite tooth image A4. The marking with different marking symbols is, for example, different linear frames as shown in the fourth figure.
根據前述說明，本發明提供了一種人工智慧辨識系統，用以更準確判別病患的牙齒健康狀況。 According to the above description, the present invention provides an artificial intelligence recognition system to more accurately determine the patient's dental health condition.
綜合上述實施例之說明，當可充分瞭解本發明之操作、使用及本發明產生之功效，惟以上所述實施例僅係為本發明之較佳實施例，當不能以此限定本發明實施之範圍，即依本發明申請專利範圍及發明說明內容所作簡單的等效變化與修飾，皆屬本發明涵蓋之範圍內。 Combined with the description of the above embodiments, the operation, use and effects of the present invention can be fully understood. However, the above embodiments are only preferred embodiments of the present invention and cannot be used to limit the scope of implementation of the present invention. In other words, simple equivalent changes and modifications made according to the scope of the patent application and the content of the invention description are all within the scope of the present invention.
1:數據資料庫 1:Database
2:電腦 2: Computer
21:影像處理模組 21: Image processing module
211:對比限制自適應直方圖均化 211: Contrast-limited adaptive histogram averaging
212:雙邊濾波器 212: Double-sided filter
22:物件偵測模型 22: Object detection model
23:牙周病及齲齒輔助辨識模型 23: Periodontal disease and caries auxiliary identification model
A:根尖X光影像 A: Periapical X-ray image
A1:正常牙齒影像 A1: Normal tooth image
A2:牙周病牙齒影像 A2: Periodontal disease tooth image
A3:齲齒牙齒影像 A3: Tooth decay image
A4:牙周病/齲齒複合牙齒影像 A4: Periodontal disease/cavity compound tooth images
B:待檢測根尖X光影像 B: X-ray image of the apex to be tested
Claims (5)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW111121076A TWI840828B (en) | 2022-06-07 | 2022-06-07 | System, computer program and computer-readable medium for assisting in recognition of periodontitis and dental caries by using image processing and deep learning object detection model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW111121076A TWI840828B (en) | 2022-06-07 | 2022-06-07 | System, computer program and computer-readable medium for assisting in recognition of periodontitis and dental caries by using image processing and deep learning object detection model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| TW202349411A TW202349411A (en) | 2023-12-16 |
| TWI840828B true TWI840828B (en) | 2024-05-01 |
Family
ID=90039204
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| TW111121076A TWI840828B (en) | 2022-06-07 | 2022-06-07 | System, computer program and computer-readable medium for assisting in recognition of periodontitis and dental caries by using image processing and deep learning object detection model |
Country Status (1)
| Country | Link |
|---|---|
| TW (1) | TWI840828B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101513366A (en) * | 2009-03-18 | 2009-08-26 | 天津大学 | PS-OCT-based three dimension visual nonnasality decayed tooth checking device and checking method thereof |
| US20170325910A1 (en) * | 2014-10-27 | 2017-11-16 | Dental Monitoring S.A.S. | Method for monitoring dentition |
| CN113469987A (en) * | 2021-07-13 | 2021-10-01 | 山东大学 | Dental X-ray image lesion area positioning system based on deep learning |
| CN113888535A (en) * | 2021-11-23 | 2022-01-04 | 北京羽医甘蓝信息技术有限公司 | Method and system for identifying impacted wisdom tooth types |
| CN114586069A (en) * | 2019-10-22 | 2022-06-03 | 牙科监测公司 | Method for generating dental images |
-
2022
- 2022-06-07 TW TW111121076A patent/TWI840828B/en active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101513366A (en) * | 2009-03-18 | 2009-08-26 | 天津大学 | PS-OCT-based three dimension visual nonnasality decayed tooth checking device and checking method thereof |
| US20170325910A1 (en) * | 2014-10-27 | 2017-11-16 | Dental Monitoring S.A.S. | Method for monitoring dentition |
| CN114586069A (en) * | 2019-10-22 | 2022-06-03 | 牙科监测公司 | Method for generating dental images |
| CN113469987A (en) * | 2021-07-13 | 2021-10-01 | 山东大学 | Dental X-ray image lesion area positioning system based on deep learning |
| CN113888535A (en) * | 2021-11-23 | 2022-01-04 | 北京羽医甘蓝信息技术有限公司 | Method and system for identifying impacted wisdom tooth types |
Also Published As
| Publication number | Publication date |
|---|---|
| TW202349411A (en) | 2023-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113516639B (en) | Training method and device for oral cavity abnormality detection model based on panoramic X-ray film | |
| CN113888535A (en) | Method and system for identifying impacted wisdom tooth types | |
| Kieu et al. | COVID-19 detection using integration of deep learning classifiers and contrast-enhanced canny edge detected X-ray images | |
| CN111738997A (en) | A deep learning-based method for calculating the proportion of lesions in new coronary pneumonia | |
| Yüksel et al. | Evaluation of dental plaque area with artificial intelligence model | |
| CN113160151B (en) | Panoramic sheet decayed tooth depth identification method based on deep learning and attention mechanism | |
| TWI840828B (en) | System, computer program and computer-readable medium for assisting in recognition of periodontitis and dental caries by using image processing and deep learning object detection model | |
| CN110084810B (en) | A pulmonary nodule image detection method, model training method, device and storage medium | |
| Tobias et al. | Android application for chest X-ray health classification from a CNN deep learning TensorFlow model | |
| CN115908361A (en) | Dental caries identification method for oral panorama film | |
| CN111652837B (en) | An AI-based method for locating left and right lobes of thyroid nodules and correcting errors in ultrasound reports | |
| CN117274757B (en) | Automatic assessment method and device for abnormal central cusp based on convolutional neural network | |
| CN113313722A (en) | Tooth root image interactive annotation method | |
| CN110097080B (en) | Construction method and device of classification label | |
| CN111667500A (en) | Tongue picture segmentation algorithm based on image block prior | |
| CN112102234A (en) | Ear sclerosis focus detection and diagnosis system based on target detection neural network | |
| TWI807809B (en) | System, computer program and computer-readable medium for assisting in the recognition of periodontitis and dental caries by using the convolutional neural network of deep learning | |
| CN118334429A (en) | Method for quickly marking industrial radiographic inspection defect pictures by combining Deeplabv plus network | |
| CN118864838A (en) | Multi-pathology instance segmentation method for oral panoramic X-ray images based on deep learning | |
| CN118279282A (en) | Panoramic sheet tooth disorder recognition and detection method and system based on deep learning | |
| CN113222984B (en) | X-ray COVID-19 recognition and detection method based on fine-grained image recognition and target detection algorithm | |
| Arafin et al. | Enhanced tooth classification and numbering using YOLOv8 in bitewing dental images | |
| CN112700445B (en) | Image processing method, device and system | |
| bin Keram et al. | Covid-19 detection from chest X-Ray images using convolutional neural network | |
| Hansen et al. | Automated tooth instance segmentation and pathology annotation pipeline for panoramic radiographs |