國立虎尾科技大學 |

Augmented Dual Input CNN (DI-CNN) for the Diagnostic Classification of Lung Nodule Malignancy from CT Scans.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Augmented Dual Input CNN (DI-CNN) for the Diagnostic Classification of Lung Nodule Malignancy from CT Scans./
作者:	Jain, Arshita.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	60 p.
附註:	Source: Masters Abstracts International, Volume: 82-05.
Contained By:	Masters Abstracts International82-05.
標題:	Bioinformatics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28028937
ISBN:	9798678176745

Augmented Dual Input CNN (DI-CNN) for the Diagnostic Classification of Lung Nodule Malignancy from CT Scans.
Jain, Arshita.

Augmented Dual Input CNN (DI-CNN) for the Diagnostic Classification of Lung Nodule Malignancy from CT Scans. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 60 p.

Source: Masters Abstracts International, Volume: 82-05.

Thesis (M.S.)--University of Maryland, Baltimore County, 2020.

This item must not be sold to any third party vendors.

We demonstrate that Image Augmentation with a Dual-Input CNN architecture can greatly improve the diagnostic classification performance of a model for AI-based lung nodule malignancy classification from CT scan images.  Lung cancer is the leading cause of cancer-related death worldwide, but early detection can improve prognosis. Lung cancer screening using Low Dose Computed Tomography (LDCT) has become a standard practice as a way of determining which pulmonary nodules are likely benign and which nodules require biopsy to determine malignancy. In recent years many studies have investigated the use of CNNs for malignancy estimation using LIDC-IDRI. Recent progress has shown that hybrid algorithms that combine CNNs with Radiomic features can achieve a high accuracy.  Furthermore, additional studies have shown that  Multi-Path CNN (MP-CNN) architectures are more accurate for this task than CNN architectures using a single input path. We present a novel approach using a special case of the MP-CNN in which both inputs are of the same dimensions, for which we coin Dual Input - CNN (DI-CNN). Furthermore, we greatly increase the labeled data volume of the LIDC-IDRI by incorporating rotation-based augmentation.  We observe that the DI-CNN is the most accurate version of MP-CNN of several input dimensions in our comparison, thereby demonstrating that it is not necessary for both input paths to take imagery of different dimensions as was previously thought.  Furthermore, we show that through data augmentation, it is possible to substantially increase the labeled data volume thereby allowing the DI-CNN algorithm to outperform a state-of-the-art hybrid CNN/Radiomic algorithm for classification of nodule malignancy.

ISBN: 9798678176745Subjects--Topical Terms:

583857
Bioinformatics.
Subjects--Index Terms:

Dual Input CNN

Augmented Dual Input CNN (DI-CNN) for the Diagnostic Classification of Lung Nodule Malignancy from CT Scans.
LDR:02977nam a2200385 4500 001 1038007
005 20210910100653.5
008 211029s2020 ||||||||||||||||| ||eng d
020 $a 9798678176745
035 $a (MiAaPQ)AAI28028937
035 $a AAI28028937
040 $a MiAaPQ $c MiAaPQ
100 1 $a Jain, Arshita. $3 1335330
245 1 0 $a Augmented Dual Input CNN (DI-CNN) for the Diagnostic Classification of Lung Nodule Malignancy from CT Scans.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 60 p.
500 $a Source: Masters Abstracts International, Volume: 82-05.
500 $a Advisor: Chapman, David.
502 $a Thesis (M.S.)--University of Maryland, Baltimore County, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a We demonstrate that Image Augmentation with a Dual-Input CNN architecture can greatly improve the diagnostic classification performance of a model for AI-based lung nodule malignancy classification from CT scan images.  Lung cancer is the leading cause of cancer-related death worldwide, but early detection can improve prognosis. Lung cancer screening using Low Dose Computed Tomography (LDCT) has become a standard practice as a way of determining which pulmonary nodules are likely benign and which nodules require biopsy to determine malignancy. In recent years many studies have investigated the use of CNNs for malignancy estimation using LIDC-IDRI. Recent progress has shown that hybrid algorithms that combine CNNs with Radiomic features can achieve a high accuracy.  Furthermore, additional studies have shown that  Multi-Path CNN (MP-CNN) architectures are more accurate for this task than CNN architectures using a single input path. We present a novel approach using a special case of the MP-CNN in which both inputs are of the same dimensions, for which we coin Dual Input - CNN (DI-CNN). Furthermore, we greatly increase the labeled data volume of the LIDC-IDRI by incorporating rotation-based augmentation.  We observe that the DI-CNN is the most accurate version of MP-CNN of several input dimensions in our comparison, thereby demonstrating that it is not necessary for both input paths to take imagery of different dimensions as was previously thought.  Furthermore, we show that through data augmentation, it is possible to substantially increase the labeled data volume thereby allowing the DI-CNN algorithm to outperform a state-of-the-art hybrid CNN/Radiomic algorithm for classification of nodule malignancy.
590 $a School code: 0434.
650 4 $a Bioinformatics. $3 583857
650 4 $a Medical imaging. $3 1180167
650 4 $a Neurosciences. $3 593561
650 4 $a Computer science. $3 573171
653 $a Dual Input CNN
653 $a Convolutional neural network
653 $a Diagnostic classification
653 $a Lung nodule malignancy
653 $a CT Scan
690 $a 0984
690 $a 0574
690 $a 0317
690 $a 0715
710 2 $a University of Maryland, Baltimore County. $b Computer Science. $3 1179407
773 0 $t Masters Abstracts International $g 82-05.
790 $a 0434
791 $a M.S.
792 $a 2020
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28028937