Kasetty Lakshminarasimha, A T Priyeshkumar, M Karthikeyan, Rajalaxmi Sakthivel
{"title":"增强肺癌诊断:优化驱动的CT成像深度学习方法。","authors":"Kasetty Lakshminarasimha, A T Priyeshkumar, M Karthikeyan, Rajalaxmi Sakthivel","doi":"10.1080/07357907.2025.2518404","DOIUrl":null,"url":null,"abstract":"<p><p>Lung cancer (LC) remains a leading cause of mortality worldwide, affecting individuals across all genders and age groups. Early and accurate diagnosis is critical for effective treatment and improved survival rates. Computed Tomography (CT) imaging is widely used for LC detection and classification. However, manual identification can be time-consuming and error-prone due to the visual similarities among various LC types. Deep learning (DL) has shown significant promise in medical image analysis. Although numerous studies have investigated LC detection using deep learning techniques, the effective extraction of highly correlated features remains a significant challenge, thereby limiting diagnostic accuracy. Furthermore, most existing models encounter substantial computational complexity and find it difficult to efficiently handle the high-dimensional nature of CT images. This study introduces an optimized CBAM-EfficientNet model to enhance feature extraction and improve LC classification. EfficientNet is utilized to reduce computational complexity, while the Convolutional Block Attention Module (CBAM) emphasizes essential spatial and channel features. Additionally, optimization algorithms including Gray Wolf Optimization (GWO), Whale Optimization (WO), and the Bat Algorithm (BA) are applied to fine-tune hyperparameters and boost predictive accuracy. The proposed model, integrated with different optimization strategies, is evaluated on two benchmark datasets. The GWO-based CBAM-EfficientNet achieves outstanding classification accuracies of 99.81% and 99.25% on the Lung-PET-CT-Dx and LIDC-IDRI datasets, respectively. Following GWO, the BA-based CBAM-EfficientNet achieves 99.44% and 98.75% accuracy on the same datasets. Comparative analysis highlights the superiority of the proposed model over existing approaches, demonstrating strong potential for reliable and automated LC diagnosis. Its lightweight architecture also supports real-time implementation, offering valuable assistance to radiologists in high-demand clinical environments.</p>","PeriodicalId":9463,"journal":{"name":"Cancer Investigation","volume":" ","pages":"1-20"},"PeriodicalIF":1.8000,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Enhancing Lung Cancer Diagnosis: An Optimization-Driven Deep Learning Approach with CT Imaging.\",\"authors\":\"Kasetty Lakshminarasimha, A T Priyeshkumar, M Karthikeyan, Rajalaxmi Sakthivel\",\"doi\":\"10.1080/07357907.2025.2518404\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Lung cancer (LC) remains a leading cause of mortality worldwide, affecting individuals across all genders and age groups. Early and accurate diagnosis is critical for effective treatment and improved survival rates. Computed Tomography (CT) imaging is widely used for LC detection and classification. However, manual identification can be time-consuming and error-prone due to the visual similarities among various LC types. Deep learning (DL) has shown significant promise in medical image analysis. Although numerous studies have investigated LC detection using deep learning techniques, the effective extraction of highly correlated features remains a significant challenge, thereby limiting diagnostic accuracy. Furthermore, most existing models encounter substantial computational complexity and find it difficult to efficiently handle the high-dimensional nature of CT images. This study introduces an optimized CBAM-EfficientNet model to enhance feature extraction and improve LC classification. EfficientNet is utilized to reduce computational complexity, while the Convolutional Block Attention Module (CBAM) emphasizes essential spatial and channel features. Additionally, optimization algorithms including Gray Wolf Optimization (GWO), Whale Optimization (WO), and the Bat Algorithm (BA) are applied to fine-tune hyperparameters and boost predictive accuracy. The proposed model, integrated with different optimization strategies, is evaluated on two benchmark datasets. The GWO-based CBAM-EfficientNet achieves outstanding classification accuracies of 99.81% and 99.25% on the Lung-PET-CT-Dx and LIDC-IDRI datasets, respectively. Following GWO, the BA-based CBAM-EfficientNet achieves 99.44% and 98.75% accuracy on the same datasets. Comparative analysis highlights the superiority of the proposed model over existing approaches, demonstrating strong potential for reliable and automated LC diagnosis. Its lightweight architecture also supports real-time implementation, offering valuable assistance to radiologists in high-demand clinical environments.</p>\",\"PeriodicalId\":9463,\"journal\":{\"name\":\"Cancer Investigation\",\"volume\":\" \",\"pages\":\"1-20\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2025-06-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Cancer Investigation\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1080/07357907.2025.2518404\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cancer Investigation","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1080/07357907.2025.2518404","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ONCOLOGY","Score":null,"Total":0}
Enhancing Lung Cancer Diagnosis: An Optimization-Driven Deep Learning Approach with CT Imaging.
Lung cancer (LC) remains a leading cause of mortality worldwide, affecting individuals across all genders and age groups. Early and accurate diagnosis is critical for effective treatment and improved survival rates. Computed Tomography (CT) imaging is widely used for LC detection and classification. However, manual identification can be time-consuming and error-prone due to the visual similarities among various LC types. Deep learning (DL) has shown significant promise in medical image analysis. Although numerous studies have investigated LC detection using deep learning techniques, the effective extraction of highly correlated features remains a significant challenge, thereby limiting diagnostic accuracy. Furthermore, most existing models encounter substantial computational complexity and find it difficult to efficiently handle the high-dimensional nature of CT images. This study introduces an optimized CBAM-EfficientNet model to enhance feature extraction and improve LC classification. EfficientNet is utilized to reduce computational complexity, while the Convolutional Block Attention Module (CBAM) emphasizes essential spatial and channel features. Additionally, optimization algorithms including Gray Wolf Optimization (GWO), Whale Optimization (WO), and the Bat Algorithm (BA) are applied to fine-tune hyperparameters and boost predictive accuracy. The proposed model, integrated with different optimization strategies, is evaluated on two benchmark datasets. The GWO-based CBAM-EfficientNet achieves outstanding classification accuracies of 99.81% and 99.25% on the Lung-PET-CT-Dx and LIDC-IDRI datasets, respectively. Following GWO, the BA-based CBAM-EfficientNet achieves 99.44% and 98.75% accuracy on the same datasets. Comparative analysis highlights the superiority of the proposed model over existing approaches, demonstrating strong potential for reliable and automated LC diagnosis. Its lightweight architecture also supports real-time implementation, offering valuable assistance to radiologists in high-demand clinical environments.
期刊介绍:
Cancer Investigation is one of the most highly regarded and recognized journals in the field of basic and clinical oncology. It is designed to give physicians a comprehensive resource on the current state of progress in the cancer field as well as a broad background of reliable information necessary for effective decision making. In addition to presenting original papers of fundamental significance, it also publishes reviews, essays, specialized presentations of controversies, considerations of new technologies and their applications to specific laboratory problems, discussions of public issues, miniseries on major topics, new and experimental drugs and therapies, and an innovative letters to the editor section. One of the unique features of the journal is its departmentalized editorial sections reporting on more than 30 subject categories covering the broad spectrum of specialized areas that together comprise the field of oncology. Edited by leading physicians and research scientists, these sections make Cancer Investigation the prime resource for clinicians seeking to make sense of the sometimes-overwhelming amount of information available throughout the field. In addition to its peer-reviewed clinical research, the journal also features translational studies that bridge the gap between the laboratory and the clinic.