Multiscale Mask R-CNN–Based Lung Tumor Detection Using PET Imaging
Positron emission tomography (PET) imaging serves as one of the most competent methods for the diagnosis of various malignancies, such as lung tumor. However, with an elevation in the utilization of PET scan, radiologists are overburdened considerably. Consequently, a new approach of “computer-aided...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2019-07-01
|
| Series: | Molecular Imaging |
| Online Access: | https://doi.org/10.1177/1536012119863531 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841563151684861952 |
|---|---|
| author | Rui Zhang PhD Chao Cheng PhD Xuehua Zhao PhD Xuechen Li PhD |
| author_facet | Rui Zhang PhD Chao Cheng PhD Xuehua Zhao PhD Xuechen Li PhD |
| author_sort | Rui Zhang PhD |
| collection | DOAJ |
| description | Positron emission tomography (PET) imaging serves as one of the most competent methods for the diagnosis of various malignancies, such as lung tumor. However, with an elevation in the utilization of PET scan, radiologists are overburdened considerably. Consequently, a new approach of “computer-aided diagnosis” is being contemplated to curtail the heavy workloads. In this article, we propose a multiscale Mask Region–Based Convolutional Neural Network (Mask R-CNN)–based method that uses PET imaging for the detection of lung tumor. First, we produced 3 models of Mask R-CNN for lung tumor candidate detection. These 3 models were generated by fine-tuning the Mask R-CNN using certain training data that consisted of images from 3 different scales. Each of the training data set included 594 slices with lung tumor. These 3 models of Mask R-CNN models were then integrated using weighted voting strategy to diminish the false-positive outcomes. A total of 134 PET slices were employed as test set in this experiment. The precision, recall, and F score values of our proposed method were 0.90, 1, and 0.95, respectively. Experimental results exhibited strong conviction about the effectiveness of this method in detecting lung tumors, along with the capability of identifying a healthy chest pattern and reducing incorrect identification of tumors to a large extent. |
| format | Article |
| id | doaj-art-7bc3ac92fefa43598ed6780dc7675db7 |
| institution | Kabale University |
| issn | 1536-0121 |
| language | English |
| publishDate | 2019-07-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Molecular Imaging |
| spelling | doaj-art-7bc3ac92fefa43598ed6780dc7675db72025-01-03T00:10:43ZengSAGE PublishingMolecular Imaging1536-01212019-07-011810.1177/1536012119863531Multiscale Mask R-CNN–Based Lung Tumor Detection Using PET ImagingRui Zhang PhD0Chao Cheng PhD1Xuehua Zhao PhD2Xuechen Li PhD3 Department of Digital Media, Shenzhen Institute of Information Technology, Shenzhen, Guangdong, China Department of Nuclear Medicine, Changhai Hospital, Shanghai, People’s Republic of China Department of Digital Media, Shenzhen Institute of Information Technology, Shenzhen, Guangdong, China College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, People’s Republic of ChinaPositron emission tomography (PET) imaging serves as one of the most competent methods for the diagnosis of various malignancies, such as lung tumor. However, with an elevation in the utilization of PET scan, radiologists are overburdened considerably. Consequently, a new approach of “computer-aided diagnosis” is being contemplated to curtail the heavy workloads. In this article, we propose a multiscale Mask Region–Based Convolutional Neural Network (Mask R-CNN)–based method that uses PET imaging for the detection of lung tumor. First, we produced 3 models of Mask R-CNN for lung tumor candidate detection. These 3 models were generated by fine-tuning the Mask R-CNN using certain training data that consisted of images from 3 different scales. Each of the training data set included 594 slices with lung tumor. These 3 models of Mask R-CNN models were then integrated using weighted voting strategy to diminish the false-positive outcomes. A total of 134 PET slices were employed as test set in this experiment. The precision, recall, and F score values of our proposed method were 0.90, 1, and 0.95, respectively. Experimental results exhibited strong conviction about the effectiveness of this method in detecting lung tumors, along with the capability of identifying a healthy chest pattern and reducing incorrect identification of tumors to a large extent.https://doi.org/10.1177/1536012119863531 |
| spellingShingle | Rui Zhang PhD Chao Cheng PhD Xuehua Zhao PhD Xuechen Li PhD Multiscale Mask R-CNN–Based Lung Tumor Detection Using PET Imaging Molecular Imaging |
| title | Multiscale Mask R-CNN–Based Lung Tumor Detection Using PET Imaging |
| title_full | Multiscale Mask R-CNN–Based Lung Tumor Detection Using PET Imaging |
| title_fullStr | Multiscale Mask R-CNN–Based Lung Tumor Detection Using PET Imaging |
| title_full_unstemmed | Multiscale Mask R-CNN–Based Lung Tumor Detection Using PET Imaging |
| title_short | Multiscale Mask R-CNN–Based Lung Tumor Detection Using PET Imaging |
| title_sort | multiscale mask r cnn based lung tumor detection using pet imaging |
| url | https://doi.org/10.1177/1536012119863531 |
| work_keys_str_mv | AT ruizhangphd multiscalemaskrcnnbasedlungtumordetectionusingpetimaging AT chaochengphd multiscalemaskrcnnbasedlungtumordetectionusingpetimaging AT xuehuazhaophd multiscalemaskrcnnbasedlungtumordetectionusingpetimaging AT xuechenliphd multiscalemaskrcnnbasedlungtumordetectionusingpetimaging |