Morphological Abnormalities Classification of Red Blood Cells Using Fusion Method on Imbalance Datasets

Red blood cells (RBCs) or Erythrocytes are essential components of the human body and they transport oxygen <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:semantics> <mml:mrow> <mml:mfenced><mml:msub><mml:mi>O</mml:mi> <mml:mn>2</mml:mn></mml:msub> </mml:mfenced> </mml:mrow> </mml:semantics> </mml:math> from the lungs to the body's tissues, regulate <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:semantics><mml:mrow><mml:mi>pH</mml:mi></mml:mrow> </mml:semantics> </mml:math> balance, and support the immune system. Abnormalities in RBC shapes (Poikilocytosis) and sizes (Anisocytosis) can impede oxygen-carrying capacity, leading to conditions such as anemia, thalassemia, McLeod Syndrome, liver disease, and so on. Hematologists typically spend considerable time manually examining RBC's shapes and sizes using a microscope and it is time-consuming. The proposed LSTM based neural network (NN) deep-learning strategy helps to classify abnormal RBCs automatically and accurately and overcome blood-related disorders at an early stage. After data processing, traditional and high-level features are fused to clearly distinguish between abnormal RBC classes. Class imbalance favors the dominant class, resulting in biased forecasts. To address class imbalance, a custom loss function is generated by integrating class weights and loss functions before feeding fused features to the NN classifier. Specifically, the loss function is designed to assign higher penalties to the misclassification of underrepresented classes, ensuring that the model is more sensitive to these classes during training. This is achieved by integrating class weights directly into the cross-entropy loss calculation, thereby balancing the influence of each class on the model's learning process. The proposed approach's performance is evaluated using the publicly accessible Chula-PIC-Lab dataset and privately gathered dataset from the Cachar Cancer Hospital and Research Centre (CCHRC) in Assam, India. The proposed approach achieves an average of <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:semantics><mml:mrow><mml:mn>97.83</mml:mn> <mml:mo>%</mml:mo></mml:mrow> </mml:semantics> </mml:math> and <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:semantics><mml:mrow><mml:mn>98.62</mml:mn> <mml:mo>%</mml:mo></mml:mrow> </mml:semantics> </mml:math> <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:semantics> <mml:mrow><mml:msub><mml:mi>F</mml:mi> <mml:mn>1</mml:mn></mml:msub> </mml:mrow> </mml:semantics> </mml:math> -score and accuracy on the Chula-PIC-Lab dataset and an average of <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:semantics><mml:mrow><mml:mn>99.56</mml:mn> <mml:mo>%</mml:mo></mml:mrow> </mml:semantics> </mml:math> and <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:semantics><mml:mrow><mml:mn>99.65</mml:mn> <mml:mo>%</mml:mo></mml:mrow> </mml:semantics> </mml:math> <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:semantics> <mml:mrow><mml:msub><mml:mi>F</mml:mi> <mml:mn>1</mml:mn></mml:msub> </mml:mrow> </mml:semantics> </mml:math> -score and accuracy on the CCHRC dataset for <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:semantics><mml:mrow><mml:mn>12</mml:mn></mml:mrow> </mml:semantics> </mml:math> and <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:semantics><mml:mrow><mml:mn>6</mml:mn></mml:mrow> </mml:semantics> </mml:math> classes and surpasses benchmark models including Custom CNN, Custom LSTM, Efficient Net-B1, SMOTE, Hybrid NN, and HPKNN.