Enhancing early lung cancer detection with MobileNet: A comprehensive transfer learning approach
Lung cancer is the leading cause of cancer-related mortality globally, with over 2.2 million new cases diagnosed annually. Early detection is critical for improving patient outcomes but remains a significant challenge due to the intricate nature of histopathological image analysis, which requires sp...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Franklin Open |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S277318632500012X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585065709699072 |
|---|---|
| author | Raquel Ochoa-Ornelas Alberto Gudiño-Ochoa Julio Alberto García-Rodríguez Sofia Uribe-Toscano |
| author_facet | Raquel Ochoa-Ornelas Alberto Gudiño-Ochoa Julio Alberto García-Rodríguez Sofia Uribe-Toscano |
| author_sort | Raquel Ochoa-Ornelas |
| collection | DOAJ |
| description | Lung cancer is the leading cause of cancer-related mortality globally, with over 2.2 million new cases diagnosed annually. Early detection is critical for improving patient outcomes but remains a significant challenge due to the intricate nature of histopathological image analysis, which requires specialized expertise. This study investigates the application of MobileNetV2, a state-of-the-art, lightweight convolutional neural network, for the accurate classification of lung adenocarcinoma (LAC), benign lung tissue (BLT), and lung squamous cell carcinoma (LUSC). To enhance the model’s generalization capabilities, we augmented the widely used LC25000 dataset with additional histopathological images sourced from the National Cancer Institute. The final model exhibited exceptional performance, achieving a training accuracy of 99.11%, a validation accuracy of 97.25%, and a test accuracy of 97.65%. The model also delivered high precision, recall, and F1-scores, each exceeding 98% across all classes, with perfect metrics observed for BLT. These promising results highlight the potential of MobileNetV2 as a highly effective tool for the early detection of lung cancer, offering substantial support for clinical diagnosis. By facilitating more accurate and timely diagnoses, this approach has the potential to significantly enhance patient care and improve survival rates in lung cancer patients. |
| format | Article |
| id | doaj-art-5593de5124b149bcbfb4727f758f5cf4 |
| institution | Kabale University |
| issn | 2773-1863 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Franklin Open |
| spelling | doaj-art-5593de5124b149bcbfb4727f758f5cf42025-01-27T04:22:43ZengElsevierFranklin Open2773-18632025-03-0110100222Enhancing early lung cancer detection with MobileNet: A comprehensive transfer learning approachRaquel Ochoa-Ornelas0Alberto Gudiño-Ochoa1Julio Alberto García-Rodríguez2Sofia Uribe-Toscano3Systems and Computation Department, Tecnológico Nacional de México/Instituto Tecnológico de Ciudad Guzmán, Avenida Tecnológico 100, Ciudad Guzmán, 49100, Jalisco, MexicoElectronics Department, Tecnológico Nacional de México/Instituto Tecnológico de Ciudad Guzmán, Avenida Tecnológico 100, Ciudad Guzmán, 49100, Jalisco, Mexico; Corresponding author.Electronics Department, Tecnológico Nacional de México/Instituto Tecnológico de Ciudad Guzmán, Avenida Tecnológico 100, Ciudad Guzmán, 49100, Jalisco, Mexico; Centro Universitario del Sur, Departamento de Ciencias Computacionales e Innovación Tecnológica, Universidad de Guadalajara, Av. Enrique Arreola Silva No. 883, Colón, Ciudad Guzmán, 49000, Jalisco, MexicoCentro Universitario del Sur, Departamento de Ciencias Clínicas Divisón de Ciencias de la Salud, Universidad de Guadalajara, Av. Enrique Arreola Silva No. 883, Colón, Ciudad Guzmán, 49000, Jalisco, MexicoLung cancer is the leading cause of cancer-related mortality globally, with over 2.2 million new cases diagnosed annually. Early detection is critical for improving patient outcomes but remains a significant challenge due to the intricate nature of histopathological image analysis, which requires specialized expertise. This study investigates the application of MobileNetV2, a state-of-the-art, lightweight convolutional neural network, for the accurate classification of lung adenocarcinoma (LAC), benign lung tissue (BLT), and lung squamous cell carcinoma (LUSC). To enhance the model’s generalization capabilities, we augmented the widely used LC25000 dataset with additional histopathological images sourced from the National Cancer Institute. The final model exhibited exceptional performance, achieving a training accuracy of 99.11%, a validation accuracy of 97.25%, and a test accuracy of 97.65%. The model also delivered high precision, recall, and F1-scores, each exceeding 98% across all classes, with perfect metrics observed for BLT. These promising results highlight the potential of MobileNetV2 as a highly effective tool for the early detection of lung cancer, offering substantial support for clinical diagnosis. By facilitating more accurate and timely diagnoses, this approach has the potential to significantly enhance patient care and improve survival rates in lung cancer patients.http://www.sciencedirect.com/science/article/pii/S277318632500012XMobileNetTransfer learningHistopathological imagesLung cancer detection |
| spellingShingle | Raquel Ochoa-Ornelas Alberto Gudiño-Ochoa Julio Alberto García-Rodríguez Sofia Uribe-Toscano Enhancing early lung cancer detection with MobileNet: A comprehensive transfer learning approach Franklin Open MobileNet Transfer learning Histopathological images Lung cancer detection |
| title | Enhancing early lung cancer detection with MobileNet: A comprehensive transfer learning approach |
| title_full | Enhancing early lung cancer detection with MobileNet: A comprehensive transfer learning approach |
| title_fullStr | Enhancing early lung cancer detection with MobileNet: A comprehensive transfer learning approach |
| title_full_unstemmed | Enhancing early lung cancer detection with MobileNet: A comprehensive transfer learning approach |
| title_short | Enhancing early lung cancer detection with MobileNet: A comprehensive transfer learning approach |
| title_sort | enhancing early lung cancer detection with mobilenet a comprehensive transfer learning approach |
| topic | MobileNet Transfer learning Histopathological images Lung cancer detection |
| url | http://www.sciencedirect.com/science/article/pii/S277318632500012X |
| work_keys_str_mv | AT raquelochoaornelas enhancingearlylungcancerdetectionwithmobilenetacomprehensivetransferlearningapproach AT albertogudinoochoa enhancingearlylungcancerdetectionwithmobilenetacomprehensivetransferlearningapproach AT julioalbertogarciarodriguez enhancingearlylungcancerdetectionwithmobilenetacomprehensivetransferlearningapproach AT sofiauribetoscano enhancingearlylungcancerdetectionwithmobilenetacomprehensivetransferlearningapproach |