ALL-Net: integrating CNN and explainable-AI for enhanced diagnosis and interpretation of acute lymphoblastic leukemia
This article presents a new model, ALL-Net, for the detection of acute lymphoblastic leukemia (ALL) using a custom convolutional neural network (CNN) architecture and explainable Artificial Intelligence (XAI). A dataset consisting of 3,256 peripheral blood smear (PBS) images belonging to four classe...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-01-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-2600.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832574354382127104 |
|---|---|
| author | Abhiram Thiriveedhi Swetha Ghanta Sujit Biswas Ashok K. Pradhan |
| author_facet | Abhiram Thiriveedhi Swetha Ghanta Sujit Biswas Ashok K. Pradhan |
| author_sort | Abhiram Thiriveedhi |
| collection | DOAJ |
| description | This article presents a new model, ALL-Net, for the detection of acute lymphoblastic leukemia (ALL) using a custom convolutional neural network (CNN) architecture and explainable Artificial Intelligence (XAI). A dataset consisting of 3,256 peripheral blood smear (PBS) images belonging to four classes—benign (hematogones), and the other three Early B, Pre-B, and Pro-B, which are subtypes of ALL, are utilized for training and evaluation. The ALL-Net CNN is initially designed and trained on the PBS image dataset, achieving an impressive test accuracy of 97.85%. However, data augmentation techniques are applied to augment the benign class and address the class imbalance challenge. The augmented dataset is then used to retrain the ALL-Net, resulting in a notable improvement in test accuracy, reaching 99.32%. Along with accuracy, we have considered other evaluation metrics and the results illustrate the potential of ALLNet with an average precision of 99.35%, recall of 99.33%, and F1 score of 99.58%. Additionally, XAI techniques, specifically the Local Interpretable Model-Agnostic Explanations (LIME) algorithm is employed to interpret the model’s predictions, providing insights into the decision-making process of our ALL-Net CNN. These findings highlight the effectiveness of CNNs in accurately detecting ALL from PBS images and emphasize the importance of addressing data imbalance issues through appropriate preprocessing techniques at the same time demonstrating the usage of XAI in solving the black box approach of the deep learning models. The proposed ALL-Net outperformed EfficientNet, MobileNetV3, VGG-19, Xception, InceptionV3, ResNet50V2, VGG-16, and NASNetLarge except for DenseNet201 with a slight variation of 0.5%. Nevertheless, our ALL-Net model is much less complex than DenseNet201, allowing it to provide faster results. This highlights the need for a more customized and streamlined model, such as ALL-Net, specifically designed for ALL classification. The entire source code of our proposed CNN is publicly available at https://github.com/Abhiram014/ALL-Net-Detection-of-ALL-using-CNN-and-XAI. |
| format | Article |
| id | doaj-art-192b27affe1e41a4a61abe4bd12fb2a3 |
| institution | Kabale University |
| issn | 2376-5992 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj-art-192b27affe1e41a4a61abe4bd12fb2a32025-02-01T15:05:14ZengPeerJ Inc.PeerJ Computer Science2376-59922025-01-0111e260010.7717/peerj-cs.2600ALL-Net: integrating CNN and explainable-AI for enhanced diagnosis and interpretation of acute lymphoblastic leukemiaAbhiram Thiriveedhi0Swetha Ghanta1Sujit Biswas2Ashok K. Pradhan3Department of Computer Science and Engineering, School of Engineering and Sciences, SRM University, AP, Guntur, Andhra Pradesh, IndiaDepartment of Computer Science and Engineering, School of Engineering and Sciences, SRM University, AP, Guntur, Andhra Pradesh, IndiaComputer Science, University of London, London, United KingdomDepartment of Computer Science and Engineering, School of Engineering and Sciences, SRM University, AP, Guntur, Andhra Pradesh, IndiaThis article presents a new model, ALL-Net, for the detection of acute lymphoblastic leukemia (ALL) using a custom convolutional neural network (CNN) architecture and explainable Artificial Intelligence (XAI). A dataset consisting of 3,256 peripheral blood smear (PBS) images belonging to four classes—benign (hematogones), and the other three Early B, Pre-B, and Pro-B, which are subtypes of ALL, are utilized for training and evaluation. The ALL-Net CNN is initially designed and trained on the PBS image dataset, achieving an impressive test accuracy of 97.85%. However, data augmentation techniques are applied to augment the benign class and address the class imbalance challenge. The augmented dataset is then used to retrain the ALL-Net, resulting in a notable improvement in test accuracy, reaching 99.32%. Along with accuracy, we have considered other evaluation metrics and the results illustrate the potential of ALLNet with an average precision of 99.35%, recall of 99.33%, and F1 score of 99.58%. Additionally, XAI techniques, specifically the Local Interpretable Model-Agnostic Explanations (LIME) algorithm is employed to interpret the model’s predictions, providing insights into the decision-making process of our ALL-Net CNN. These findings highlight the effectiveness of CNNs in accurately detecting ALL from PBS images and emphasize the importance of addressing data imbalance issues through appropriate preprocessing techniques at the same time demonstrating the usage of XAI in solving the black box approach of the deep learning models. The proposed ALL-Net outperformed EfficientNet, MobileNetV3, VGG-19, Xception, InceptionV3, ResNet50V2, VGG-16, and NASNetLarge except for DenseNet201 with a slight variation of 0.5%. Nevertheless, our ALL-Net model is much less complex than DenseNet201, allowing it to provide faster results. This highlights the need for a more customized and streamlined model, such as ALL-Net, specifically designed for ALL classification. The entire source code of our proposed CNN is publicly available at https://github.com/Abhiram014/ALL-Net-Detection-of-ALL-using-CNN-and-XAI.https://peerj.com/articles/cs-2600.pdfAcute lymphoblastic leukemiaPeripheral blood smear imagesConvolutional neural networksExplainable AIData augmentation |
| spellingShingle | Abhiram Thiriveedhi Swetha Ghanta Sujit Biswas Ashok K. Pradhan ALL-Net: integrating CNN and explainable-AI for enhanced diagnosis and interpretation of acute lymphoblastic leukemia PeerJ Computer Science Acute lymphoblastic leukemia Peripheral blood smear images Convolutional neural networks Explainable AI Data augmentation |
| title | ALL-Net: integrating CNN and explainable-AI for enhanced diagnosis and interpretation of acute lymphoblastic leukemia |
| title_full | ALL-Net: integrating CNN and explainable-AI for enhanced diagnosis and interpretation of acute lymphoblastic leukemia |
| title_fullStr | ALL-Net: integrating CNN and explainable-AI for enhanced diagnosis and interpretation of acute lymphoblastic leukemia |
| title_full_unstemmed | ALL-Net: integrating CNN and explainable-AI for enhanced diagnosis and interpretation of acute lymphoblastic leukemia |
| title_short | ALL-Net: integrating CNN and explainable-AI for enhanced diagnosis and interpretation of acute lymphoblastic leukemia |
| title_sort | all net integrating cnn and explainable ai for enhanced diagnosis and interpretation of acute lymphoblastic leukemia |
| topic | Acute lymphoblastic leukemia Peripheral blood smear images Convolutional neural networks Explainable AI Data augmentation |
| url | https://peerj.com/articles/cs-2600.pdf |
| work_keys_str_mv | AT abhiramthiriveedhi allnetintegratingcnnandexplainableaiforenhanceddiagnosisandinterpretationofacutelymphoblasticleukemia AT swethaghanta allnetintegratingcnnandexplainableaiforenhanceddiagnosisandinterpretationofacutelymphoblasticleukemia AT sujitbiswas allnetintegratingcnnandexplainableaiforenhanceddiagnosisandinterpretationofacutelymphoblasticleukemia AT ashokkpradhan allnetintegratingcnnandexplainableaiforenhanceddiagnosisandinterpretationofacutelymphoblasticleukemia |