國立虎尾科技大學 |

An Artificial Intelligence Driven Framework for Medical Imaging.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	An Artificial Intelligence Driven Framework for Medical Imaging./
作者:	Sanghvi, Harshal A.
面頁冊數:	1 online resource (172 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-02, Section: B.
Contained By:	Dissertations Abstracts International85-02B.
標題:	Computer engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9798380138499

An Artificial Intelligence Driven Framework for Medical Imaging.
Sanghvi, Harshal A.

An Artificial Intelligence Driven Framework for Medical Imaging. - 1 online resource (172 pages)

Source: Dissertations Abstracts International, Volume: 85-02, Section: B.

Thesis (Ph.D.)--Florida Atlantic University, 2023.

Includes bibliographical references

The major objective of this dissertation was to create a framework which is used for medical image diagnosis. In this diagnosis, we brought classification and diagnosing of diseases through an Artificial Intelligence based framework, including COVID, Pneumonia, and Melanoma cancer through medical images. The algorithm ran on multiple datasets. A model was developed which detected the medical images through changing hyper-parameters.The aim of this work was to apply the new transfer learning framework DenseNet-201 for the diagnosis of the diseases and compare the results with the other deep learning models. The novelty in the proposed work was modifying the Dense Net 201 Algorithm, changing hyper parameters (source weights, Batch Size, Epochs, Architecture (number of neurons in hidden layer), learning rate and optimizer) to quantify the results. The novelty also included the training of the model by quantifying weights and in order to get more accuracy. During the data selection process, the data were cleaned, removing all the outliers. Data augmentation was used for the novel architecture to overcome overfitting and hence not producing false absurd results the computational performance was also observed. The proposed model results were also compared with the existing deep learning models and the algorithm was also tested on multiple datasets.In the proposed deep learning model, DenseNet-201, a convolutional neural network was used which was trained on the ImageNet dataset. Each layer was getting more accurate information from the previous layer. Since each layer receives feature maps from all preceding layers, the network was thinner and more compact. The growth rate k was the additional number of channels for each layer to have higher computational efficiency and memory efficiency. In the present work, composite learning factor strategy and data augmentation were included in the developed model. The graphical user interface (GUI) which was developed assisted in computational experience and adhered to the HIPAA Compliance. The GUI also provided different image observations which were generated through different visualization techniques. The proposed model gave us more accurate results which was not overfitting, had better computational performance and will assist clinicians with more visual data representation. The parameters were tuned, and the model complexity was calculated. The present work was validated by the medical fraternity.

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

Mode of access: World Wide Web

ISBN: 9798380138499Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

DenseNet-201Index Terms--Genre/Form:

554714
Electronic books.

An Artificial Intelligence Driven Framework for Medical Imaging.
LDR:03882ntm a22003977 4500 001 1146623
005 20240812064659.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380138499
035 $a (MiAaPQ)AAI30575869
035 $a AAI30575869
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Sanghvi, Harshal A. $3 1472047
245 1 3 $a An Artificial Intelligence Driven Framework for Medical Imaging.
264 0 $c 2023
300 $a 1 online resource (172 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: Dissertations Abstracts International, Volume: 85-02, Section: B.
500 $a Advisor: Agarwal, Ankur;Alhalabi, Bassem.
502 $a Thesis (Ph.D.)--Florida Atlantic University, 2023.
504 $a Includes bibliographical references
520 $a The major objective of this dissertation was to create a framework which is used for medical image diagnosis. In this diagnosis, we brought classification and diagnosing of diseases through an Artificial Intelligence based framework, including COVID, Pneumonia, and Melanoma cancer through medical images. The algorithm ran on multiple datasets. A model was developed which detected the medical images through changing hyper-parameters.The aim of this work was to apply the new transfer learning framework DenseNet-201 for the diagnosis of the diseases and compare the results with the other deep learning models. The novelty in the proposed work was modifying the Dense Net 201 Algorithm, changing hyper parameters (source weights, Batch Size, Epochs, Architecture (number of neurons in hidden layer), learning rate and optimizer) to quantify the results. The novelty also included the training of the model by quantifying weights and in order to get more accuracy. During the data selection process, the data were cleaned, removing all the outliers. Data augmentation was used for the novel architecture to overcome overfitting and hence not producing false absurd results the computational performance was also observed. The proposed model results were also compared with the existing deep learning models and the algorithm was also tested on multiple datasets.In the proposed deep learning model, DenseNet-201, a convolutional neural network was used which was trained on the ImageNet dataset. Each layer was getting more accurate information from the previous layer. Since each layer receives feature maps from all preceding layers, the network was thinner and more compact. The growth rate k was the additional number of channels for each layer to have higher computational efficiency and memory efficiency. In the present work, composite learning factor strategy and data augmentation were included in the developed model. The graphical user interface (GUI) which was developed assisted in computational experience and adhered to the HIPAA Compliance. The GUI also provided different image observations which were generated through different visualization techniques. The proposed model gave us more accurate results which was not overfitting, had better computational performance and will assist clinicians with more visual data representation. The parameters were tuned, and the model complexity was calculated. The present work was validated by the medical fraternity.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer engineering. $3 569006
650 4 $a Medical imaging. $3 1180167
653 $a DenseNet-201
653 $a Deep learning model
653 $a Graphical user interface
653 $a Visual data representation
653 $a Medical fraternity
655 7 $a Electronic books. $2 local $3 554714
690 $a 0464
690 $a 0574
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Florida Atlantic University. $b Computer Engineering. $3 1241314
773 0 $t Dissertations Abstracts International $g 85-02B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30575869 $z click for full text (PQDT)