Vedant-S / Malaria-Detection_CNN

Project includes a CNN Model which successfully classifies blood cell images into malaria infected and uninfected category with an accuracy of 95% and a recall of 93%.

Malaria Infected Cell Detection using Computer Vision and Convolutional Neural Network (CNN):

---

Built a deep learning CNN Model to differentiate between healthy and malaria infected cell images. Used Keras and Tensorflow Libraries to create a Convolutional Neural Network which successfully classifies blood cell images into malaria infected and uninfected category with an accuracy of 95% and a recall of 93%. Performed data augmentation & image preprocessing to improve predictions.

Dataset Source: https://ceb.nlm.nih.gov/repositories/malaria-datasets/

---

Reference:

(Research Papers)

---

Using of deep neural ensembles, recently report an improvement towards malaria parasite detection in thin-blood smear images and is published in the Peer Journal as cited herewith:

• Rajaraman S, Jaeger S, Antani SK. (2019) Performance evaluation of deep neural ensembles toward malaria parasite detection in thin-blood smear images. PeerJ 7:e6977: https://doi.org/10.7717/peerj.6977

---

Author:

---

+ Vedant Shrivastava | [e-mail]