Hierarchical approach for pulmonary-nodule identification from CT images using YOLO model and a 3D neural network classifier
Saved in:
| Title: | Hierarchical approach for pulmonary-nodule identification from CT images using YOLO model and a 3D neural network classifier |
|---|---|
| Authors: | Ahmadyar, Yashar, Kamali-Asl, Alireza, Arabi, Hossein, Samimi, Rezvan, Zaidi, Habib |
| Source: | Radiological Physics and Technology. 17:124-134 |
| Publisher Information: | Springer Science and Business Media LLC, 2023. |
| Publication Year: | 2023 |
| Subject Terms: | CT scan, 616.8, Lung Neoplasms, Neural Networks, 616.0757, Object detection, Radiographic Image Interpretation, Solitary Pulmonary Nodule, Lung Neoplasms/diagnostic imaging, Classification, X-Ray Computed/methods, Lung/diagnostic imaging, 3. Good health, Computer, Solitary Pulmonary Nodule/diagnostic imaging, Computer-Assisted/methods, Humans, Radiographic Image Interpretation, Computer-Assisted, Neural Networks, Computer, Lung cancer, Tomography, X-Ray Computed, Tomography, Lung, Pulmonary nodules |
| Description: | This study aimed to assist doctors in detecting early-stage lung cancer. To achieve this, a hierarchical system that can detect nodules in the lungs using computed tomography (CT) images was developed. In the initial phase, a preexisting model (YOLOv5s) was used to detect lung nodules. A 0.3 confidence threshold was established for identifying nodules in this phase to enhance the model's sensitivity. The primary objective of the hierarchical model was to locate and categorize all lung nodules while minimizing the false-negative rate. Following the analysis of the results from the first phase, a novel 3D convolutional neural network (CNN) classifier was developed to examine and categorize the potential nodules detected by the YOLOv5s model. The objective was to create a detection framework characterized by an extremely low false positive rate and high accuracy. The Lung Nodule Analysis 2016 (LUNA 16) dataset was used to evaluate the effectiveness of this framework. This dataset comprises 888 CT scans that include the positions of 1186 nodules and 400,000 non-nodular regions in the lungs. The YOLOv5s technique yielded numerous incorrect detections owing to its low confidence level. Nevertheless, the addition of a 3D classification system significantly enhanced the precision of nodule identification. By integrating the outcomes of the YOLOv5s approach using a 30% confidence limit and the 3D CNN classification model, the overall system achieved 98.4% nodule detection accuracy and an area under the curve of 98.9%. Despite producing some false negatives and false positives, the suggested method for identifying lung nodules from CT scans is promising as a valuable aid in decision-making for nodule detection. |
| Document Type: | Article |
| File Description: | application/pdf |
| Language: | English |
| ISSN: | 1865-0341 1865-0333 |
| DOI: | 10.1007/s12194-023-00756-9 |
| Access URL: | https://pubmed.ncbi.nlm.nih.gov/37980315 https://research.rug.nl/en/publications/4da3c418-2c7d-445a-9c35-69683e2948df https://hdl.handle.net/11370/4da3c418-2c7d-445a-9c35-69683e2948df https://doi.org/10.1007/s12194-023-00756-9 https://archive-ouverte.unige.ch/unige:174986 https://doi.org/10.1007/s12194-023-00756-9 https://portal.findresearcher.sdu.dk/da/publications/6cbb7396-80b5-4b91-bdd7-6ff3eb810564 https://doi.org/10.1007/s12194-023-00756-9 |
| Rights: | Springer Nature TDM taverne |
| Accession Number: | edsair.doi.dedup.....c17612f00aa0bcc9c08e108f65721043 |
| Database: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | This study aimed to assist doctors in detecting early-stage lung cancer. To achieve this, a hierarchical system that can detect nodules in the lungs using computed tomography (CT) images was developed. In the initial phase, a preexisting model (YOLOv5s) was used to detect lung nodules. A 0.3 confidence threshold was established for identifying nodules in this phase to enhance the model's sensitivity. The primary objective of the hierarchical model was to locate and categorize all lung nodules while minimizing the false-negative rate. Following the analysis of the results from the first phase, a novel 3D convolutional neural network (CNN) classifier was developed to examine and categorize the potential nodules detected by the YOLOv5s model. The objective was to create a detection framework characterized by an extremely low false positive rate and high accuracy. The Lung Nodule Analysis 2016 (LUNA 16) dataset was used to evaluate the effectiveness of this framework. This dataset comprises 888 CT scans that include the positions of 1186 nodules and 400,000 non-nodular regions in the lungs. The YOLOv5s technique yielded numerous incorrect detections owing to its low confidence level. Nevertheless, the addition of a 3D classification system significantly enhanced the precision of nodule identification. By integrating the outcomes of the YOLOv5s approach using a 30% confidence limit and the 3D CNN classification model, the overall system achieved 98.4% nodule detection accuracy and an area under the curve of 98.9%. Despite producing some false negatives and false positives, the suggested method for identifying lung nodules from CT scans is promising as a valuable aid in decision-making for nodule detection. |
|---|---|
| ISSN: | 18650341 18650333 |
| DOI: | 10.1007/s12194-023-00756-9 |