Toward Robust Lung Cancer Diagnosis: Integrating Multiple CT Datasets, Curriculum Learning, and Explainable AI
<b>Background and Objectives:</b> Computer-aided diagnostic systems have achieved remarkable success in the medical field, particularly in diagnosing malignant tumors, and have done so at a rapid pace. However, the generalizability of the results remains a challenge for researchers and d...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/1/1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549273197445120 |
|---|---|
| author | Amira Bouamrane Makhlouf Derdour Akram Bennour Taiseer Abdalla Elfadil Eisa Abdel-Hamid M. Emara Mohammed Al-Sarem Neesrin Ali Kurdi |
| author_facet | Amira Bouamrane Makhlouf Derdour Akram Bennour Taiseer Abdalla Elfadil Eisa Abdel-Hamid M. Emara Mohammed Al-Sarem Neesrin Ali Kurdi |
| author_sort | Amira Bouamrane |
| collection | DOAJ |
| description | <b>Background and Objectives:</b> Computer-aided diagnostic systems have achieved remarkable success in the medical field, particularly in diagnosing malignant tumors, and have done so at a rapid pace. However, the generalizability of the results remains a challenge for researchers and decreases the credibility of these models, which represents a point of criticism by physicians and specialists, especially given the sensitivity of the field. This study proposes a novel model based on deep learning to enhance lung cancer diagnosis quality, understandability, and generalizability. <b>Methods:</b> The proposed approach uses five computed tomography (CT) datasets to assess diversity and heterogeneity. Moreover, the mixup augmentation technique was adopted to facilitate the reliance on salient characteristics by combining features and CT scan labels from datasets to reduce their biases and subjectivity, thus improving the model’s generalization ability and enhancing its robustness. Curriculum learning was used to train the model, starting with simple sets to learn complicated ones quickly. <b>Results:</b> The proposed approach achieved promising results, with an accuracy of 99.38%; precision, specificity, and area under the curve (AUC) of 100%; sensitivity of 98.76%; and F1-score of 99.37%. Additionally, it scored a 00% false positive rate and only a 1.23% false negative rate. An external dataset was used to further validate the proposed method’s effectiveness. The proposed approach achieved optimal results of 100% in all metrics, with 00% false positive and false negative rates. Finally, explainable artificial intelligence (XAI) using Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to better understand the model. <b>Conclusions:</b> This research proposes a robust and interpretable model for lung cancer diagnostics with improved generalizability and validity. Incorporating mixup and curriculum training supported by several datasets underlines its promise for employment as a diagnostic device in the medical industry. |
| format | Article |
| id | doaj-art-6804dfc236234b47aae8ad5744cf4166 |
| institution | Kabale University |
| issn | 2075-4418 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-6804dfc236234b47aae8ad5744cf41662025-01-10T13:16:24ZengMDPI AGDiagnostics2075-44182024-12-01151110.3390/diagnostics15010001Toward Robust Lung Cancer Diagnosis: Integrating Multiple CT Datasets, Curriculum Learning, and Explainable AIAmira Bouamrane0Makhlouf Derdour1Akram Bennour2Taiseer Abdalla Elfadil Eisa3Abdel-Hamid M. Emara4Mohammed Al-Sarem5Neesrin Ali Kurdi6LIAOA Laboratory, University of Oum El-Bouaghi-Larbi Benmhidi, Oum El-Bouaghi 04000, AlgeriaLIAOA Laboratory, University of Oum El-Bouaghi-Larbi Benmhidi, Oum El-Bouaghi 04000, AlgeriaLAMIS Laboratory, Echahid Cheikh Larbi Tebessi University, Tebessa 12002, AlgeriaApplied College, King Khalid University, Mahayil 62529, Saudi ArabiaDepartment of Computers and Systems Engineering, Faculty of Engineering, Al-Azhar University, Cairo 11884, EgyptDepartment of Information Technology, Aylol University College, Yarim 547, YemenCollege of Computer Science and Engineering, Taibah University, Medina 41477, Saudi Arabia<b>Background and Objectives:</b> Computer-aided diagnostic systems have achieved remarkable success in the medical field, particularly in diagnosing malignant tumors, and have done so at a rapid pace. However, the generalizability of the results remains a challenge for researchers and decreases the credibility of these models, which represents a point of criticism by physicians and specialists, especially given the sensitivity of the field. This study proposes a novel model based on deep learning to enhance lung cancer diagnosis quality, understandability, and generalizability. <b>Methods:</b> The proposed approach uses five computed tomography (CT) datasets to assess diversity and heterogeneity. Moreover, the mixup augmentation technique was adopted to facilitate the reliance on salient characteristics by combining features and CT scan labels from datasets to reduce their biases and subjectivity, thus improving the model’s generalization ability and enhancing its robustness. Curriculum learning was used to train the model, starting with simple sets to learn complicated ones quickly. <b>Results:</b> The proposed approach achieved promising results, with an accuracy of 99.38%; precision, specificity, and area under the curve (AUC) of 100%; sensitivity of 98.76%; and F1-score of 99.37%. Additionally, it scored a 00% false positive rate and only a 1.23% false negative rate. An external dataset was used to further validate the proposed method’s effectiveness. The proposed approach achieved optimal results of 100% in all metrics, with 00% false positive and false negative rates. Finally, explainable artificial intelligence (XAI) using Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to better understand the model. <b>Conclusions:</b> This research proposes a robust and interpretable model for lung cancer diagnostics with improved generalizability and validity. Incorporating mixup and curriculum training supported by several datasets underlines its promise for employment as a diagnostic device in the medical industry.https://www.mdpi.com/2075-4418/15/1/1CT scanpulmonary nodulesDLdiagnosisXAIcurriculum learning |
| spellingShingle | Amira Bouamrane Makhlouf Derdour Akram Bennour Taiseer Abdalla Elfadil Eisa Abdel-Hamid M. Emara Mohammed Al-Sarem Neesrin Ali Kurdi Toward Robust Lung Cancer Diagnosis: Integrating Multiple CT Datasets, Curriculum Learning, and Explainable AI Diagnostics CT scan pulmonary nodules DL diagnosis XAI curriculum learning |
| title | Toward Robust Lung Cancer Diagnosis: Integrating Multiple CT Datasets, Curriculum Learning, and Explainable AI |
| title_full | Toward Robust Lung Cancer Diagnosis: Integrating Multiple CT Datasets, Curriculum Learning, and Explainable AI |
| title_fullStr | Toward Robust Lung Cancer Diagnosis: Integrating Multiple CT Datasets, Curriculum Learning, and Explainable AI |
| title_full_unstemmed | Toward Robust Lung Cancer Diagnosis: Integrating Multiple CT Datasets, Curriculum Learning, and Explainable AI |
| title_short | Toward Robust Lung Cancer Diagnosis: Integrating Multiple CT Datasets, Curriculum Learning, and Explainable AI |
| title_sort | toward robust lung cancer diagnosis integrating multiple ct datasets curriculum learning and explainable ai |
| topic | CT scan pulmonary nodules DL diagnosis XAI curriculum learning |
| url | https://www.mdpi.com/2075-4418/15/1/1 |
| work_keys_str_mv | AT amirabouamrane towardrobustlungcancerdiagnosisintegratingmultiplectdatasetscurriculumlearningandexplainableai AT makhloufderdour towardrobustlungcancerdiagnosisintegratingmultiplectdatasetscurriculumlearningandexplainableai AT akrambennour towardrobustlungcancerdiagnosisintegratingmultiplectdatasetscurriculumlearningandexplainableai AT taiseerabdallaelfadileisa towardrobustlungcancerdiagnosisintegratingmultiplectdatasetscurriculumlearningandexplainableai AT abdelhamidmemara towardrobustlungcancerdiagnosisintegratingmultiplectdatasetscurriculumlearningandexplainableai AT mohammedalsarem towardrobustlungcancerdiagnosisintegratingmultiplectdatasetscurriculumlearningandexplainableai AT neesrinalikurdi towardrobustlungcancerdiagnosisintegratingmultiplectdatasetscurriculumlearningandexplainableai |