Autokeras Approach: A Robust Automated Deep Learning Network for Diagnosis Disease Cases in Medical Images

Article Computer Science, Artificial Intelligence

A Novel Data Augmentation Convolutional Neural Network for Detecting Malaria Parasite in Blood Smear Images

David Opeoluwa Oyewola et al.

Summary: Malaria fever, caused by the Plasmodium parasite, is a potentially fatal disease. This paper proposes a novel deep learning model called DACNN, trained by reinforcement learning, to rapidly and accurately diagnose malaria by identifying Plasmodium parasites in blood smear images.

APPLIED ARTIFICIAL INTELLIGENCE (2022)

Add to Collection

Article Chemistry, Multidisciplinary

IMNets: Deep Learning Using an Incremental Modular Network Synthesis Approach for Medical Imaging Applications

Redha Ali et al.

Summary: The study introduces a novel deep learning approach, IMNS, that incrementally builds larger and more powerful IMNets using SubNets, achieving high classification accuracies in malaria, diabetic retinopathy, and tuberculosis cases.

APPLIED SCIENCES-BASEL (2022)

Add to Collection

Article Medicine, General & Internal

Evaluating the Performance of Deep Learning Frameworks for Malaria Parasite Detection Using Microscopic Images of Peripheral Blood Smears

Dilber Uzun Ozsahin et al.

Summary: This study aims to automate and accurately classify malaria parasites using a deep learning framework, report the most appropriate peripheral blood smear, and evaluate model performance. The proposed model performs best when using thick peripheral blood smears, providing important insights for improved accuracy and rapid diagnosis.

DIAGNOSTICS (2022)

Add to Collection

Article Chemistry, Analytical

Explainable Transformer-Based Deep Learning Model for the Detection of Malaria Parasites from Blood Cell Images

Md. Robiul Islam et al.

Summary: This article proposes a multiheaded attention-based transformer model for diagnosing malaria parasite from blood cell images. The effectiveness of the model is demonstrated using the Grad-CAM technique to identify the parts of the image that the model pays more attention to. The proposed model achieves high accuracy, precision, recall, F1-score, and AUC score for both the original and modified datasets, outperforming existing methods.

SENSORS (2022)

Add to Collection

Article Telecommunications

Image analysis and machine learning-based malaria assessment system

Kyle Manning et al.

Summary: Malaria is a significant and worldwide fatal disease that requires an automated solution for diagnosis. This study aims to create a design tool for diagnosing malaria from blood sample images. The proposed techniques have achieved an accuracy of 92% in detecting malaria.

DIGITAL COMMUNICATIONS AND NETWORKS (2022)

Add to Collection

Article Chemistry, Multidisciplinary

Deep Malaria Parasite Detection in Thin Blood Smear Microscopic Images

Asma Maqsood et al.

Summary: Malaria is a deadly disease spread by infected mosquito bites, with quick diagnosis being crucial for patients. Deep learning approaches like Convolutional Neural Networks offer superior performance in detecting malaria, improving accuracy and efficiency in diagnosis.

APPLIED SCIENCES-BASEL (2021)

Add to Collection

Article Medicine, General & Internal

Diagnosing Malaria Patients with Plasmodium falciparum and vivax Using Deep Learning for Thick Smear Images

Yasmin M. Kassim et al.

Summary: A new framework PlasmodiumVF-Net is proposed for malaria diagnosis using thick smear microscopy images, achieving over 90% accuracy on both image and patient-level analysis.

DIAGNOSTICS (2021)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

Malaria detection through digital microscopic imaging using Deep Greedy Network with transfer learning

Sumagna Dey et al.

Summary: This study proposes a comprehensive computer-aided diagnosis scheme for automating the detection of malaria parasites in thin blood smear images using deep CNN, with transfer learning optimizing the feature selection process and layer embeddings serving as an extra layer of security. The hybrid model's performance is promising compared to other deep learning algorithms based on accuracy metrics evaluation.

JOURNAL OF MEDICAL IMAGING (2021)

Add to Collection

Article Computer Science, Information Systems

DeepFMD: Computational Analysis for Malaria Detection in Blood-Smear Images Using Deep-Learning Features

Aliyu Abubakar et al.

Summary: Malaria is a highly infectious disease, especially prevalent in developing continents. This study proposes the use of machine-learning models to detect the malaria parasite, achieving an accuracy of over 94% with automated processes.

APPLIED SYSTEM INNOVATION (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Pre-trained Deep Convolutional Neural Network for Detecting Malaria on the Human Blood Smear Images

Gede Susrama Mas Diyasa et al.

Summary: Malaria, caused by the Plasmodium falciparum parasite carried by female Anopheles mosquitoes, remains a severe threat in eastern Indonesia. However, utilizing a data-driven computer-aided diagnostic approach can improve accuracy, with the ShuffleNet V2 model achieving higher accuracy in shorter training times compared to the GoogLeNet model.

3RD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE IN INFORMATION AND COMMUNICATION (IEEE ICAIIC 2021) (2021)

Add to Collection

Article Engineering, Electrical & Electronic

A Novel Implementation of Deep-Learning Approach on Malaria Parasite Detection from Thin Blood Cell Images

Emrah Irmak

Summary: Malaria is an acute febrile disease caused by female Anopheles mosquitoes, diagnosed manually through microscopic examinations. Deep learning methods have shown great potential in medical diagnosis, with the ability to be applied in malaria detection.

ELECTRICA (2021)

Add to Collection

Article Computer Science, Information Systems