PrecisionLymphoNet: Advancing Malignant Lymphoma Diagnosis via Ensemble Transfer Learning with CNNs

Abstract

Malignant lymphoma, which impacts the lymphatic system, presents diverse challenges in accurate diagnosis due to its varied subtypes-chronic lymphocytic leukemia (CLL), follicular lymphoma (FL), and mantle cell lymphoma (MCL). Lymphoma is a form of cancer that begins in the lymphatic system, impacting lymphocytes, which are a specific type of white blood cell. This research addresses these challenges by proposing ensemble and non-ensemble transfer learning models employing pre-trained weights from VGG16, VGG19, DenseNet201, InceptionV3, and Xception. For the ensemble technique, this paper adopts a stack-based ensemble approach. It is a two-level classification approach and best suited for accuracy improvement. Testing on a multiclass dataset of CLL, FL, and MCL reveals exceptional diagnostic accuracy, with DenseNet201, InceptionV3, and Xception exceeding 90% accuracy. The proposed ensemble model, leveraging InceptionV3 and Xception, achieves an outstanding 99% accuracy over 300 epochs, surpassing previous prediction methods. This study demonstrates the feasibility and efficiency of the proposed approach, showcasing its potential in real-world medical applications for precise lymphoma diagnosis.

Keywords: DenseNet201; Inceptionv3; Xception; chronic lymphocytic leukemia (CLL); ensemble technique; follicular lymphoma (FL); malignant lymphoma; mantle cell lymphoma (MCL); transfer learning.

Figure 1

Hodgkin lymphoma and non-Hodgkin lymphoma (NHL).

Figure 2

The malignant lymphoma image samples of CLL, FL, and MCL.

Figure 3

Non-ensemble transfer learning architecture.

Figure 4

Ensemble transfer learning architecture. (a) Proposed method of Stacked Ensemble Technique steps.

Figure 5

VGG16 architecture summary.

Figure 6

Accuracy, loss, MAE, MSE, MAPE, and confusion matrix of VGG16.

Figure 7

VGG19 architecture summary.

Figure 8

Accuracy, loss, MAE, MSE, MAPE, and confusion matrix of VGG19.

Figure 9

DenseNet201 architecture summary.

Figure 10

Accuracy, loss, MAE, MSE, MAPE, and confusion matrix of DenseNet201.

Figure 11

Inceptionv3 architecture summary.

Figure 12

Accuracy, loss, MAE, MSE, MAPE, and confusion matrix of Inceptionv3.

Figure 13

Xception architecture summary.

Figure 14

Accuracy, loss, MAE, MSE, MAPE, and confusion matrix of Xception.

Figure 15

The proposed method level-0 classifier (Inception and Xception) output.

Figure 16

Accuracy, loss, and confusion matrix of ensemble model Inceptionv3 and Xception.