國立虎尾科技大學 |

Using Generative Models to Create Synthetic Medical Imaging Data to Boost Model Performance on Sparse Demographic Groups.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Using Generative Models to Create Synthetic Medical Imaging Data to Boost Model Performance on Sparse Demographic Groups./
作者:	Fitzpatrick, Ryan S.
面頁冊數:	1 online resource (31 pages)
附註:	Source: Masters Abstracts International, Volume: 85-12.
Contained By:	Masters Abstracts International85-12.
標題:	Biomedical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9798383112229

Using Generative Models to Create Synthetic Medical Imaging Data to Boost Model Performance on Sparse Demographic Groups.
Fitzpatrick, Ryan S.

Using Generative Models to Create Synthetic Medical Imaging Data to Boost Model Performance on Sparse Demographic Groups. - 1 online resource (31 pages)

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

Thesis (M.S.)--University of Hawai'i at Manoa, 2024.

Includes bibliographical references

Recent advancements in deep generative models, specifically Generative Adversarial Networks (GANs) and Diffusion Models, have introduced new methods for generating synthetic medical imaging data. These models can produce highly realistic images, particularly for underrepresented demographic groups, thereby enhancing the diversity of existing medical datasets without incur- ring significant data collection costs. This research utilizes GANs and Diffusion Models to generate synthetic medical images, aiming to address biases in diagnostic models towards majority populations. The study assesses the impact of these augmented datasets on the performance of a conventional Convolutional Neural Network (CNN) by comparing its classification accuracy on the original imbalanced dataset with that on a dataset enhanced with synthetic images. Specifically, the performance metrics focus on the accuracy of classifying conditions such as edema, no findings, and pneumonia across combined minority groups versus each majority demographic group. The results from experimentation demonstrated that CNNs trained on the supplemented datasets did not achieve a higher Area Under the Receiver Operating Characteristic (AUROC) curve score compared to those trained on the original dataset. We fail to reject the null hypothesis and can- not say that the CNNs trained on the supplemented data have a significant difference in AUROC performance.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798383112229Subjects--Topical Terms:

588770
Biomedical engineering.
Subjects--Index Terms:

Generative Adversarial NetworksIndex Terms--Genre/Form:

554714
Electronic books.

Using Generative Models to Create Synthetic Medical Imaging Data to Boost Model Performance on Sparse Demographic Groups.
LDR:02801ntm a22003737 4500 001 1150160
005 20241022111603.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798383112229
035 $a (MiAaPQ)AAI31143308
035 $a AAI31143308
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Fitzpatrick, Ryan S. $3 1476595
245 1 0 $a Using Generative Models to Create Synthetic Medical Imaging Data to Boost Model Performance on Sparse Demographic Groups.
264 0 $c 2024
300 $a 1 online resource (31 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 Advisor: Washington, Peter.
502 $a Thesis (M.S.)--University of Hawai'i at Manoa, 2024.
504 $a Includes bibliographical references
520 $a Recent advancements in deep generative models, specifically Generative Adversarial Networks (GANs) and Diffusion Models, have introduced new methods for generating synthetic medical imaging data. These models can produce highly realistic images, particularly for underrepresented demographic groups, thereby enhancing the diversity of existing medical datasets without incur- ring significant data collection costs. This research utilizes GANs and Diffusion Models to generate synthetic medical images, aiming to address biases in diagnostic models towards majority populations. The study assesses the impact of these augmented datasets on the performance of a conventional Convolutional Neural Network (CNN) by comparing its classification accuracy on the original imbalanced dataset with that on a dataset enhanced with synthetic images. Specifically, the performance metrics focus on the accuracy of classifying conditions such as edema, no findings, and pneumonia across combined minority groups versus each majority demographic group. The results from experimentation demonstrated that CNNs trained on the supplemented datasets did not achieve a higher Area Under the Receiver Operating Characteristic (AUROC) curve score compared to those trained on the original dataset. We fail to reject the null hypothesis and can- not say that the CNNs trained on the supplemented data have a significant difference in AUROC performance.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Biomedical engineering. $3 588770
650 4 $a Computer science. $3 573171
653 $a Generative Adversarial Networks
653 $a Convolutional Neural Network
653 $a Deep generative models
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0541
690 $a 0800
710 2 $a University of Hawai'i at Manoa. $b Computer Science. $3 1476571
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Masters Abstracts International $g 85-12.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31143308 $z click for full text (PQDT)