What question did this study set out to answer?

The research aims to enhance malaria detection through a modified AlexNet deep learning model for cell screening.

May 9, 2026Iconic Research and Engineering Journals0 citations

Malaria Detection Using an Improved AlexNet-Based Deep Learning Model

MPM. Phanindra KSK. Venkata Siva Sai Sreeja PNP. Nikhil

Key Points

The research aims to enhance malaria detection through a modified AlexNet deep learning model for cell screening.
Developed a modified AlexNet CNN for binary malaria classification using the NIH/Kaggle dataset.
Applied live augmentation and trained with techniques including batch normalization and dropout.
Evaluated model performance using confusion matrices, ROC-AUC, and precision-recall curves.
The model achieved high accuracy in detecting malaria cells.
Evaluation metrics indicated strong performance with positive predictive values and AUC scores.
Comparison with YOLOv4/DenseNet-121 highlighted improved specificity in binary classification.

Abstract

Diagnosing malaria still relies heavily on microscope examination of blood smears — which works, but is slow, hard to scale, and only as good as the person doing it. This paper describes a deep learning pipeline for binary malaria cell screening built on a modified AlexNet CNN. We used the public NIH/Kaggle malaria cell-image dataset, resized everything to 100×100 RGB patches, applied live augmentation, and trained a regularized CNN with batch normalization and dropout. Beyond just reporting accuracy, we evaluated the model with confusion matrices, ROC-AUC, precision-recall curves, calibration plots, and Grad-CAM heatmaps. We also compare the approach against a recent two-stage YOLOv4/DenseNet-121 system. This model doesn't do whole-slide detection or species identification — it's a clean, reproducible infected-vs-uninfected screener that can be understood, explained, and built on.

Ask AI

Helpful

Bookmark

View Full Paper