Lightweight Advanced Deep Neural Network (DNN) Model for Early-Stage Lung Cancer Detection
<b>Background:</b> Lung cancer, also known as lung carcinoma, has a high mortality rate; however, an early prediction helps to reduce the risk. In the current literature, various approaches have been developed for the prediction of lung carcinoma (at an early stage), but these still have...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/14/21/2356 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846173502263001088 |
|---|---|
| author | Isha Bhatia Aarti Syed Immamul Ansarullah Farhan Amin Amerah Alabrah |
| author_facet | Isha Bhatia Aarti Syed Immamul Ansarullah Farhan Amin Amerah Alabrah |
| author_sort | Isha Bhatia |
| collection | DOAJ |
| description | <b>Background:</b> Lung cancer, also known as lung carcinoma, has a high mortality rate; however, an early prediction helps to reduce the risk. In the current literature, various approaches have been developed for the prediction of lung carcinoma (at an early stage), but these still have various issues, such as low accuracy, high noise, low contrast, poor recognition rates, and a high false-positive rate, etc. Thus, in this research effort, we have proposed an advanced algorithm and combined two different types of deep neural networks to make it easier to spot lung melanoma in the early phases. <b>Methods:</b> We have used WDSI (weakly supervised dense instance-level lung segmentation) for laborious pixel-level annotations. In addition, we suggested an SS-CL (deep continuous learning-based deep neural network) that can be applied to the labeled and unlabeled data to improve efficiency. This work intends to evaluate potential lightweight, low-memory deep neural net (DNN) designs for image processing. <b>Results:</b> Our experimental results show that, by combining WDSI and LSO segmentation, we can achieve super-sensitive, specific, and accurate early detection of lung cancer. For experiments, we used the lung nodule (LUNA16) dataset, which consists of the patients’ 3D CT scan images. We confirmed that our proposed model is lightweight because it uses less memory. We have compared them with state-of-the-art models named PSNR and SSIM. The efficiency is 32.8% and 0.97, respectively. The proposed lightweight deep neural network (DNN) model archives a high accuracy of 98.2% and also removes noise more effectively. <b>Conclusions:</b> Our proposed approach has a lot of potential to help medical image analysis to help improve the accuracy of test results, and it may also prove helpful in saving patients’ lives. |
| format | Article |
| id | doaj-art-08d1de84567d43e7b578b93e05f3c127 |
| institution | Kabale University |
| issn | 2075-4418 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-08d1de84567d43e7b578b93e05f3c1272024-11-08T14:34:39ZengMDPI AGDiagnostics2075-44182024-10-011421235610.3390/diagnostics14212356Lightweight Advanced Deep Neural Network (DNN) Model for Early-Stage Lung Cancer DetectionIsha Bhatia0Aarti1Syed Immamul Ansarullah2Farhan Amin3Amerah Alabrah4Department of Computer Science and Engineering, Lovely Professional University, Phagwara 144411, Punjab, IndiaDepartment of Computer Science and Engineering, Lovely Professional University, Phagwara 144411, Punjab, IndiaDepartment of Management Studies, University of Kashmir, North Campus, Delina, Baramulla 193103, Jammu & Kashmir, IndiaSchool of Computer Science and Engineering, Yeungnam University, Gyeongsan 38541, Republic of KoreaDepartment of Information Systems, College of Computer and Information Science, King Saud University, Riyadh 11543, Saudi Arabia<b>Background:</b> Lung cancer, also known as lung carcinoma, has a high mortality rate; however, an early prediction helps to reduce the risk. In the current literature, various approaches have been developed for the prediction of lung carcinoma (at an early stage), but these still have various issues, such as low accuracy, high noise, low contrast, poor recognition rates, and a high false-positive rate, etc. Thus, in this research effort, we have proposed an advanced algorithm and combined two different types of deep neural networks to make it easier to spot lung melanoma in the early phases. <b>Methods:</b> We have used WDSI (weakly supervised dense instance-level lung segmentation) for laborious pixel-level annotations. In addition, we suggested an SS-CL (deep continuous learning-based deep neural network) that can be applied to the labeled and unlabeled data to improve efficiency. This work intends to evaluate potential lightweight, low-memory deep neural net (DNN) designs for image processing. <b>Results:</b> Our experimental results show that, by combining WDSI and LSO segmentation, we can achieve super-sensitive, specific, and accurate early detection of lung cancer. For experiments, we used the lung nodule (LUNA16) dataset, which consists of the patients’ 3D CT scan images. We confirmed that our proposed model is lightweight because it uses less memory. We have compared them with state-of-the-art models named PSNR and SSIM. The efficiency is 32.8% and 0.97, respectively. The proposed lightweight deep neural network (DNN) model archives a high accuracy of 98.2% and also removes noise more effectively. <b>Conclusions:</b> Our proposed approach has a lot of potential to help medical image analysis to help improve the accuracy of test results, and it may also prove helpful in saving patients’ lives.https://www.mdpi.com/2075-4418/14/21/2356deep learninglung carcinomaCT imagelung cancerconvolutional neural networksimage classification |
| spellingShingle | Isha Bhatia Aarti Syed Immamul Ansarullah Farhan Amin Amerah Alabrah Lightweight Advanced Deep Neural Network (DNN) Model for Early-Stage Lung Cancer Detection Diagnostics deep learning lung carcinoma CT image lung cancer convolutional neural networks image classification |
| title | Lightweight Advanced Deep Neural Network (DNN) Model for Early-Stage Lung Cancer Detection |
| title_full | Lightweight Advanced Deep Neural Network (DNN) Model for Early-Stage Lung Cancer Detection |
| title_fullStr | Lightweight Advanced Deep Neural Network (DNN) Model for Early-Stage Lung Cancer Detection |
| title_full_unstemmed | Lightweight Advanced Deep Neural Network (DNN) Model for Early-Stage Lung Cancer Detection |
| title_short | Lightweight Advanced Deep Neural Network (DNN) Model for Early-Stage Lung Cancer Detection |
| title_sort | lightweight advanced deep neural network dnn model for early stage lung cancer detection |
| topic | deep learning lung carcinoma CT image lung cancer convolutional neural networks image classification |
| url | https://www.mdpi.com/2075-4418/14/21/2356 |
| work_keys_str_mv | AT ishabhatia lightweightadvanceddeepneuralnetworkdnnmodelforearlystagelungcancerdetection AT aarti lightweightadvanceddeepneuralnetworkdnnmodelforearlystagelungcancerdetection AT syedimmamulansarullah lightweightadvanceddeepneuralnetworkdnnmodelforearlystagelungcancerdetection AT farhanamin lightweightadvanceddeepneuralnetworkdnnmodelforearlystagelungcancerdetection AT amerahalabrah lightweightadvanceddeepneuralnetworkdnnmodelforearlystagelungcancerdetection |