Symptom Based Explainable Artificial Intelligence Model for Leukemia Detection

Hossain, Mohammad Akter; Islam, A. K. M. Muzahidul; Islam, Salekul; Shatabda, Swakkhar; Ahmed, Ashir

doi:10.1109/access.2022.3176274

Cited by 18 publications

(17 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The F1 score, accuracy, precision, recall, and other metrics for all kind of Leukaemia were determined using the standard dataset mentioned in the dataset description section image bank. To demonstrate their effectiveness, the proposed models are compared to earlier approaches such as Apriori [20], ALNett [13], and CNN [35][36][37]. AML, ALL, and healthy samples are identified using GA with SVM, and the kind of Leukaemia present in each sample is identified using CNN.…”

Section: Precisionmentioning

confidence: 99%

“…To demonstrate their effectiveness on blurred images, the proposed models are compared to earlier approaches such as Apriori [20], ALNett [13], and CNN [35][36][37]. Figure 17 and Table 3 shows that ODRNN achieves 91.23% accuracy, while current techniques such as Apriori, ALNett, and CNN achieve 83.66%, 84.75%, and 85.86%, respectively.…”

Section: Figure 16 F1 Score Comparison Of Leukaemia Classifiermentioning

confidence: 99%

See 1 more Smart Citation

RETRACTED: ODRNN: Optimized Deep Recurrent Neural Networks for Automatic Detection of Leukaemia

Shree,a,

Logeswari,

2024

Egyptian Informatics Journal

View full text Add to dashboard Cite

Section: Precisionmentioning

confidence: 99%

Section: Figure 16 F1 Score Comparison Of Leukaemia Classifiermentioning

confidence: 99%

RETRACTED: ODRNN: Optimized Deep Recurrent Neural Networks for Automatic Detection of Leukaemia

Shree,a,

Logeswari,

2024

Egyptian Informatics Journal

View full text Add to dashboard Cite

“…Two feature selection and analysis steps are executed on the dataset to increase the model performance. The proposed model outperforms with 97.45% accuracy, 0.63 Mathew's Correlation Coefficient (MCC), and 0.783 of the area under the Receiver Operating Characteristic (ROC) curve (Hossain et al, 2022 ).…”

Section: Literature Reviewmentioning

confidence: 99%

An efficient computer vision-based approach for acute lymphoblastic leukemia prediction

Almadhor

Sattar

Hejaili

et al. 2022

Front. Comput. Neurosci.

View full text Add to dashboard Cite

Leukemia (blood cancer) diseases arise when the number of White blood cells (WBCs) is imbalanced in the human body. When the bone marrow produces many immature WBCs that kill healthy cells, acute lymphocytic leukemia (ALL) impacts people of all ages. Thus, timely predicting this disease can increase the chance of survival, and the patient can get his therapy early. Manual prediction is very expensive and time-consuming. Therefore, automated prediction techniques are essential. In this research, we propose an ensemble automated prediction approach that uses four machine learning algorithms K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest (RF), and Naive Bayes (NB). The C-NMC leukemia dataset is used from the Kaggle repository to predict leukemia. Dataset is divided into two classes cancer and healthy cells. We perform data preprocessing steps, such as the first images being cropped using minimum and maximum points. Feature extraction is performed to extract the feature using pre-trained Convolutional Neural Network-based Deep Neural Network (DNN) architectures (VGG19, ResNet50, or ResNet101). Data scaling is performed by using the MinMaxScaler normalization technique. Analysis of Variance (ANOVA), Recursive Feature Elimination (RFE), and Random Forest (RF) as feature Selection techniques. Classification machine learning algorithms and ensemble voting are applied to selected features. Results reveal that SVM with 90.0% accuracy outperforms compared to other algorithms.

show abstract

“…Experimental results revealed that the proposed method achieved 97.78 percent accuracy. M. A. Hossain el al [15] have employed Apriori algorithm for generating explainable rules for leukemia prediction. The decision tree model proposed in their experiments has achieved 0.63 of Mathew's Correlation Coefficient (MCC) and 0.783 of area under Receiver Operating Characteristic (ROC) curve on the test set.…”

Section: Related Workmentioning

confidence: 99%

Detection and Classification of Acute Lymphoblastic Leukemia (ALL) from Blood Smear Microscopic Images

Kohok¹

2022

IJSREM

View full text Add to dashboard Cite

Abstract—White blood cells (WBC) which are also known as leukocytes, are a crucial part of the human body’s immune system. Leukaemia is a haematological disorder that starts from the bone marrow and affects white blood cells (WBCs) due to mutations in DNA causing blood cell production to become out of control. This prevents the development of healthy blood cells. Acute lymphocytic leukemia (ALL) is a kind of cancer where the bone marrow forms many more lymphocytes. ALL can further be classified into L1, L2 and L3 based on the structure of nucleus and cytoplasm. Automatic detection of leukemia or detection of blood cancer is a tough job and it is very much essential in healthcare centres. ALL identification and interpretation using peripheral blood smear (PBS) pictures plays an important role in early identification in screening and treatment. Conventionally, the method was achieved manually by a skilled technician during a considerable amount of time however the examination of those PBS pictures by laboratory users typically contains diagnostic errors owing to the nonspecific nature of ALL signs and symptoms that usually results in misdiagnosis. So, to achieve more accurate classification results we use powerful segmentation and deep learning techniques to train the model on these images. Firstly, we pre-process the images to apply segmentation methods on them. The proposed model will attempt to eradicate the probability of errors in the manual process and it can be used as a supporting analysis tool for pathologists. So, various Artificial Intelligence-based ALL classification methods and approaches are analysed in a well-defined manner with advantages and disadvantages. Keywords—Acute Lymphoblastic Leukemia, Classification, Detection, Deep Learning Techniques.

show abstract

Symptom Based Explainable Artificial Intelligence Model for Leukemia Detection

Cited by 18 publications

References 34 publications

RETRACTED: ODRNN: Optimized Deep Recurrent Neural Networks for Automatic Detection of Leukaemia

RETRACTED: ODRNN: Optimized Deep Recurrent Neural Networks for Automatic Detection of Leukaemia

An efficient computer vision-based approach for acute lymphoblastic leukemia prediction

Detection and Classification of Acute Lymphoblastic Leukemia (ALL) from Blood Smear Microscopic Images

Contact Info

Product

Resources

About