Explainable AI in Diagnosing and Anticipating Leukemia Using Transfer Learning Method

Abstract

White blood cells (WBCs) are blood cells that fight infections and diseases as a part of the immune system. They are also known as “defender cells.” But the imbalance in the number of WBCs in the blood can be hazardous. Leukemia is the most common blood cancer caused by an overabundance of WBCs in the immune system. Acute lymphocytic leukemia (ALL) usually occurs when the bone marrow creates many immature WBCs that destroy healthy cells. People of all ages, including children and adolescents, can be affected by ALL. The rapid proliferation of atypical lymphocyte cells can cause a reduction in new blood cells and increase the chances of death in patients. Therefore, early and precise cancer detection can help with better therapy and a higher survival probability in the case of leukemia. However, diagnosing ALL is time-consuming and complicated, and manual analysis is expensive, with subjective and error-prone outcomes. Thus, detecting normal and malignant cells reliably and accurately is crucial. For this reason, automatic detection using computer-aided diagnostic models can help doctors effectively detect early leukemia. The entire approach may be automated using image processing techniques, reducing physicians’ workload and increasing diagnosis accuracy. The impact of deep learning (DL) on medical research has recently proven quite beneficial, offering new avenues and possibilities in the healthcare domain for diagnostic techniques. However, to make that happen soon in DL, the entire community must overcome the explainability limit. Because of the black box operation’s shortcomings in artificial intelligence (AI) models’ decisions, there is a lack of liability and trust in the outcomes. But explainable artificial intelligence (XAI) can solve this problem by interpreting the predictions of AI systems. This study emphasizes leukemia, specifically ALL. The proposed strategy recognizes acute lymphoblastic leukemia as an automated procedure that applies different transfer learning models to classify ALL. Hence, using local interpretable model-agnostic explanations (LIME) to assure validity and reliability, this method also explains the cause of a specific classification. The proposed method achieved 98.38% accuracy with the InceptionV3 model. Experimental results were found between different transfer learning methods, including ResNet101V2, VGG19, and InceptionResNetV2, later verified with the LIME algorithm for XAI, where the proposed method performed the best. The obtained results and their reliability demonstrate that it can be preferred in identifying ALL, which will assist medical examiners.

Utilization of model-agnostic explainable artificial intelligence frameworks in oncology: a narrative review

“…These overlays permitted the authors to biologically validate results by comparing highlighted areas of interest with clinical intuition. This technique has also been applied to diagnosing leukemia (accuracy of 98.38%) ( 38 ). Examination of individual patients has also been used on structured data to help classify primary and metastatic cancers using origin-based DNA methylation profiles ( 39 ).…”

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

“…Only 1% of blood is made up of White blood cells because white blood cells are essential to the human immune system. Even small changes significantly impact (Sharif et al, 2020 ; Winter et al, 2021 ; Abir et al, 2022 ).…”

“…Any variation in the white blood cell count is cause for concern. Leukemia is the most frequently associated with a low White Blood cell (WBCs) count (Ghanem et al, 2019 ; Abir et al, 2022 ). It can be harmful and a factor in disease when our bodies have an unusually high quantity of WBC (Hegde et al, 2019 ).…”

Biomedical Diagnosis of Leukemia Using a Deep Learner Classifier

“…Abir et al in [ 23 ] developed a method to detect ALL using a transfer learning model. This method achieved nearly 98.3% of accuracy, while our presented algorithm achieves nearly over 99% of accuracy.…”

“…However, these four models detected only ALL, while our algorithm detects and classifies ALL and AML as well. Additional information is found in [ 23 ].…”