A Transfer Learning-Based Deep CNN Approach for Classification and Diagnosis of Acute Lymphocytic Leukemia Cells

Magpantay, Leo Dominick C.; Alon, Helcy D.; Austria, Yolanda D.; Melegrito, Mark P.; Fernando, Glenn John O.

doi:10.1109/dasa54658.2022.9765000

Cited by 10 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The three models were compared using COCO evaluation metrics to determine the best model performance for the task. Magpantay et al [26] Classification + Localization…”

Section: B Single-cell Detail Explanationmentioning

confidence: 99%

“…In other words, the implementation of softmax YOLOv2 determines the probability of each value. Previous research [26] proposed the automatic detection of ALL and healthy cells to make up for an expert's lack of manual analysis. YOLOv3 is the used model, which employs a transfer learning strategy to generate low loss values and high mAP evaluation values.…”

Section: ) Yolov3mentioning

confidence: 99%

“…The object detection model is one of the deep learning models. In a single learning framework, the object detection model performs the classification and localization of objects in an image [26]. Researchers are increasingly interested in using object detection models in the medical field because they can provide disease analysis and diagnosis based on morphology and information on medical images that is useful in the initial diagnosis process.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning for the Detection of Acute Lymphoblastic Leukemia Subtypes on Microscopic Images: A Systematic Literature Review

2023

View full text Add to dashboard Cite

Computer vision research in detecting and classifying the subtype Acute Lymphoblastic Leukemia (ALL) has contributed to computer-aided diagnosis with improved accuracy. Another contribution is to serve as an assistant and second opinion for doctors and hematologists in diagnosing the ALL subtype.Early detection can also rely on computer-aided diagnosis to determine initial treatment. The purpose of this study is to review the progress of research in the detection and classification of ALL subtypes. The method's discussion focuses on the application of deep learning to the domain of object detection and classification. Motivations, challenges, and future research recommendations are thoroughly discussed to improve understanding and progress in this field of study. The study was carried out methodically by analyzing a collection of papers on the detection and classification of ALL subtypes published in science direct, IEEE, and PubMed from 2018 to 2022. The analysis of this paper field is included in the results of the selected paper. The paper selection from among 65 papers was based on inclusion and exclusion methods. Based on research methods and objectives, papers are divided into two large groups. The first group discusses the classification of ALL subtypes, while the second group discusses the detection of ALL subtypes. The discussion of prior research reveals some challenging issues and future work, such as the limited availability of the ALL subtypes dataset, the high computational complexity of the deep learning model, and further exploration of transformers in computer vision as a reference for research gaps that can contribute to future research.

show abstract

“…The three models were compared using COCO evaluation metrics to determine the best model performance for the task. Magpantay et al [26] Classification + Localization…”

Section: B Single-cell Detail Explanationmentioning

confidence: 99%

Section: ) Yolov3mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for the Detection of Acute Lymphoblastic Leukemia Subtypes on Microscopic Images: A Systematic Literature Review

2023

View full text Add to dashboard Cite

show abstract

“…Nonetheless, additional investigation is required to evaluate its performance on larger data sets and optimize the deep learning algorithms for everyday clinical applications. This research represents a significant stride in the application of terahertz imaging and spectroscopy in the healthcare domain, demonstrating the potential of deep learning algorithms to enhance classification accuracy and offering promising prospects for future advancements 11 . In the critical realm of identifying potentially life‐threatening brain tissue abnormalities and providing effective treatment for patients, accurate classification of brain tumors is of utmost importance.…”

Section: Introductionmentioning

confidence: 98%

“…This research represents a significant stride in the application of terahertz imaging and spectroscopy in the healthcare domain, demonstrating the potential of deep learning algorithms to enhance classification accuracy and offering promising prospects for future advancements. 11 In the critical realm of identifying potentially lifethreatening brain tissue abnormalities and providing effective treatment for patients, accurate classification of brain tumors is of utmost importance. Leveraging the exceptional image quality of magnetic resonance imaging (MRI), TL has emerged as a significant approach in medical imaging, enabling pre-trained models to leverage both large and small data sets, thus improving classification accuracy while reducing the required training data and enhancing overall efficiency.…”

Section: Introductionmentioning

confidence: 99%

Enhancing brain tumor classification with transfer learning: Leveraging DenseNet121 for accurate and efficient detection

Raza,

Alshehri,

Almakdi

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Brain tumors pose a serious neurological threat to human life, necessitating improved detection and classification methods. Deep transfer learning (TL), in particular in key tumor categories such as meningioma, pituitary, glioma, and instances without tumors, has shown to be a new and successful method for tumor identification and classification. In this work, the efficacy of two pre‐trained TL methods—Inceptionv3 and DenseNet121—was examined for correctly classifying certain kinds of brain tumors. The experimental findings show that the DenseNet‐121 model, using the TL approach, performed better than other models in terms of accuracy for the identification and classification of brain tumors. The classification test results were impressive, with DenseNet‐121 reaching an astounding 99.95% accuracy and precision, recall, and F1‐measure scores of 97.7%, 92.1%, and 94.8%, respectively. DenseNet‐121 demonstrated 100% and 92.42% training and validation accuracies, respectively, highlighting its potential as an effective and precise diagnosis tool for brain malignancies.

show abstract

AlexNet architecture modification to classify Acute Lymphoblastic Leukemia images

Muntasa,

Wahyuningrum,

Tuzzahra

et al. 2024

The 8th International Conference on Technology and Vocational Teachers 2022

View full text Add to dashboard Cite

A Transfer Learning-Based Deep CNN Approach for Classification and Diagnosis of Acute Lymphocytic Leukemia Cells

Cited by 10 publications

References 16 publications

Deep Learning for the Detection of Acute Lymphoblastic Leukemia Subtypes on Microscopic Images: A Systematic Literature Review

Deep Learning for the Detection of Acute Lymphoblastic Leukemia Subtypes on Microscopic Images: A Systematic Literature Review

Enhancing brain tumor classification with transfer learning: Leveraging DenseNet121 for accurate and efficient detection

AlexNet architecture modification to classify Acute Lymphoblastic Leukemia images

Contact Info

Product

Resources

About