東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Accuracy of Rule-Based Algorithm and...

Alsaffar, Alaa,

FindBook

Google Book

Amazon

博客來

Accuracy of Rule-Based Algorithm and Deep-Learning Platform in Diagnosis of Periodontal Disease /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Accuracy of Rule-Based Algorithm and Deep-Learning Platform in Diagnosis of Periodontal Disease // Alaa Alsaffar.
作者:	Alsaffar, Alaa,
面頁冊數:	1 electronic resource (76 pages)
附註:	Source: Masters Abstracts International, Volume: 85-12.
Contained By:	Masters Abstracts International85-12.
標題:	Dentistry. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31331793
ISBN:	9798382830735

Accuracy of Rule-Based Algorithm and Deep-Learning Platform in Diagnosis of Periodontal Disease /
Alsaffar, Alaa,

Accuracy of Rule-Based Algorithm and Deep-Learning Platform in Diagnosis of Periodontal Disease /Alaa Alsaffar. - 1 electronic resource (76 pages)

Source: Masters Abstracts International, Volume: 85-12.

Purpose: This study aims to evaluate the accuracy of computer-aided periodontal diagnostic tools, including the rule-based (RB) algorithm and deep learning-based (DL) platform, in assigning periodontal diagnoses compared to clinicians' diagnoses with different levels of knowledge and experience.Methods: A total of 302 cases (periodontitis and non-periodontitis) were randomly selected from the electronic health record system. The clinical data and radiographic images during 2019-2023 were extracted. All de-identified data were used to assign a standardized periodontal diagnosis by two calibrated experts. The RB algorithm was developed and validated based on a periodontal diagnosis decision tree following the 2017 World Workshop Classification. The RB algorithm uses clinical data only to assign a periodontal diagnosis. The validated end-to-end DL platform integrates segmentation networks and image analysis to calculate and assign a periodontal diagnosis from a full-mouth series of periapical radiographs and age only. The reliability of the assigned diagnosis by the RB algorithm, DL platform, and clinicians were compared to expert reference diagnoses using the accuracy, weighted kappa coefficient, sensitivity, specificity, positive predictive value, negative predictable value, and F1 Score. An independent sample test for proportions was used to determine any variation in the accuracy and dental provider group.Results: Compared to the expert, the sensitivity/specificity of Stage for the RB algorithm, DL platform, and clinicians was 0.81/0.93, 0.79/0.87, and 0.62/0.85, respectively. The sensitivity/specificity of Grade for the RB algorithm, DL platform, and clinicians was 0.75/0.76, 0.91/0.95, and 0.65/0.80, respectively. The sensitivity/specificity of Extent for the RB algorithm, DL platform, and clinicians was 0.82/0.86, 0.78/0.80, and 0.63/0.77, respectively. For sensitivity, all the three groups performed worse in Stage I/II, Grade A, and Generalized than the other categories, and the clinician group performed the worst in all categories. Among the clinicians, the dentists' diagnosis was more accurate than the students and residents.Conclusion: Computer-aided diagnostic tools demonstrated reliable performance in assigning the periodontal diagnosis. Considering the strengths and weakness of the two tools, using both the RB algorithm and DL platform together should assist clinicians in arriving at a more accurate diagnosis than using a single tool.

English

ISBN: 9798382830735Subjects--Topical Terms:

828971
Dentistry.
Subjects--Index Terms:

Computer-aided diagnositc tools

Accuracy of Rule-Based Algorithm and Deep-Learning Platform in Diagnosis of Periodontal Disease /
LDR:04052nmm a22004573i 4500 001 2431602
005 20250616055537.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798382830735
035 $a (MiAaPQD)AAI31331793
035 $a AAI31331793
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Alsaffar, Alaa, $e author. $3 3820493
245 1 0 $a Accuracy of Rule-Based Algorithm and Deep-Learning Platform in Diagnosis of Periodontal Disease / $c Alaa Alsaffar.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (76 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 85-12.
500 $a Advisors: Lee, Chun-Teh Committee members: Jiang, Xiaoqain; Tokede, Oluwabunmi; Ayilavarapu, Srinivas.
502 $b M.Sc.D. $c The University of Texas School of Dentistry at Houston $d 2024.
520 $a Purpose: This study aims to evaluate the accuracy of computer-aided periodontal diagnostic tools, including the rule-based (RB) algorithm and deep learning-based (DL) platform, in assigning periodontal diagnoses compared to clinicians' diagnoses with different levels of knowledge and experience.Methods: A total of 302 cases (periodontitis and non-periodontitis) were randomly selected from the electronic health record system. The clinical data and radiographic images during 2019-2023 were extracted. All de-identified data were used to assign a standardized periodontal diagnosis by two calibrated experts. The RB algorithm was developed and validated based on a periodontal diagnosis decision tree following the 2017 World Workshop Classification. The RB algorithm uses clinical data only to assign a periodontal diagnosis. The validated end-to-end DL platform integrates segmentation networks and image analysis to calculate and assign a periodontal diagnosis from a full-mouth series of periapical radiographs and age only. The reliability of the assigned diagnosis by the RB algorithm, DL platform, and clinicians were compared to expert reference diagnoses using the accuracy, weighted kappa coefficient, sensitivity, specificity, positive predictive value, negative predictable value, and F1 Score. An independent sample test for proportions was used to determine any variation in the accuracy and dental provider group.Results: Compared to the expert, the sensitivity/specificity of Stage for the RB algorithm, DL platform, and clinicians was 0.81/0.93, 0.79/0.87, and 0.62/0.85, respectively. The sensitivity/specificity of Grade for the RB algorithm, DL platform, and clinicians was 0.75/0.76, 0.91/0.95, and 0.65/0.80, respectively. The sensitivity/specificity of Extent for the RB algorithm, DL platform, and clinicians was 0.82/0.86, 0.78/0.80, and 0.63/0.77, respectively. For sensitivity, all the three groups performed worse in Stage I/II, Grade A, and Generalized than the other categories, and the clinician group performed the worst in all categories. Among the clinicians, the dentists' diagnosis was more accurate than the students and residents.Conclusion: Computer-aided diagnostic tools demonstrated reliable performance in assigning the periodontal diagnosis. Considering the strengths and weakness of the two tools, using both the RB algorithm and DL platform together should assist clinicians in arriving at a more accurate diagnosis than using a single tool.
546 $a English
590 $a School code: 1707
650 4 $a Dentistry. $3 828971
650 4 $a Biomedical engineering. $3 535387
650 4 $a Computer science. $3 523869
650 4 $a Medical imaging. $3 3172799
653 $a Computer-aided diagnositc tools
653 $a Convolutional neural networks
653 $a Deep learning
653 $a Periodontal disease diagnosis
653 $a Rule-based algorithm
690 $a 0567
690 $a 0800
690 $a 0984
690 $a 0574
690 $a 0541
710 2 $a The University of Texas School of Dentistry at Houston. $b Periodontics. $e degree granting institution. $3 3820494
720 1 $a Lee, Chun-Teh $e degree supervisor.
773 0 $t Masters Abstracts International $g 85-12.
790 $a 1707
791 $a M.Sc.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31331793