Impact of Misclassification Rates on Compression Efficiency of Red Blood Cell Images of Malaria Infection Using Deep Learning
Malaria is a severe public health problem worldwide, with some developing countries being most affected. Reliable remote diagnosis of malaria infection will benefit from efficient compression of high-resolution microscopic images. This paper addresses a lossless compression of malaria-infected red b...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/21/11/1062 |
| _version_ | 1818040965164695552 |
|---|---|
| author | Yuhang Dong W. David Pan Dongsheng Wu |
| author_facet | Yuhang Dong W. David Pan Dongsheng Wu |
| author_sort | Yuhang Dong |
| collection | DOAJ |
| description | Malaria is a severe public health problem worldwide, with some developing countries being most affected. Reliable remote diagnosis of malaria infection will benefit from efficient compression of high-resolution microscopic images. This paper addresses a lossless compression of malaria-infected red blood cell images using deep learning. Specifically, we investigate a practical approach where images are first classified before being compressed using stacked autoencoders. We provide probabilistic analysis on the impact of misclassification rates on compression performance in terms of the information-theoretic measure of entropy. We then use malaria infection image datasets to evaluate the relations between misclassification rates and actually obtainable compressed bit rates using Golomb−Rice codes. Simulation results show that the joint pattern classification/compression method provides more efficient compression than several mainstream lossless compression techniques, such as JPEG2000, JPEG-LS, CALIC, and WebP, by exploiting common features extracted by deep learning on large datasets. This study provides new insight into the interplay between classification accuracy and compression bitrates. The proposed compression method can find useful telemedicine applications where efficient storage and rapid transfer of large image datasets is desirable. |
| first_indexed | 2024-12-10T08:22:54Z |
| format | Article |
| id | doaj.art-da0f16c9056248e2b17c3f4e4afe0e1d |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-12-10T08:22:54Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-da0f16c9056248e2b17c3f4e4afe0e1d2022-12-22T01:56:18ZengMDPI AGEntropy1099-43002019-10-012111106210.3390/e21111062e21111062Impact of Misclassification Rates on Compression Efficiency of Red Blood Cell Images of Malaria Infection Using Deep LearningYuhang Dong0W. David Pan1Dongsheng Wu2Department of Electrical and Computer Engineering, University of Alabama in Huntsville, Huntsville, AL 35899, USADepartment of Electrical and Computer Engineering, University of Alabama in Huntsville, Huntsville, AL 35899, USADepartment of Mathematical Sciences, University of Alabama in Huntsville, Huntsville, AL 35899, USAMalaria is a severe public health problem worldwide, with some developing countries being most affected. Reliable remote diagnosis of malaria infection will benefit from efficient compression of high-resolution microscopic images. This paper addresses a lossless compression of malaria-infected red blood cell images using deep learning. Specifically, we investigate a practical approach where images are first classified before being compressed using stacked autoencoders. We provide probabilistic analysis on the impact of misclassification rates on compression performance in terms of the information-theoretic measure of entropy. We then use malaria infection image datasets to evaluate the relations between misclassification rates and actually obtainable compressed bit rates using Golomb−Rice codes. Simulation results show that the joint pattern classification/compression method provides more efficient compression than several mainstream lossless compression techniques, such as JPEG2000, JPEG-LS, CALIC, and WebP, by exploiting common features extracted by deep learning on large datasets. This study provides new insight into the interplay between classification accuracy and compression bitrates. The proposed compression method can find useful telemedicine applications where efficient storage and rapid transfer of large image datasets is desirable.https://www.mdpi.com/1099-4300/21/11/1062lossless compressionpattern classificationmachine learningmalaria infectionentropygolomb–rice codes |
| spellingShingle | Yuhang Dong W. David Pan Dongsheng Wu Impact of Misclassification Rates on Compression Efficiency of Red Blood Cell Images of Malaria Infection Using Deep Learning Entropy lossless compression pattern classification machine learning malaria infection entropy golomb–rice codes |
| title | Impact of Misclassification Rates on Compression Efficiency of Red Blood Cell Images of Malaria Infection Using Deep Learning |
| title_full | Impact of Misclassification Rates on Compression Efficiency of Red Blood Cell Images of Malaria Infection Using Deep Learning |
| title_fullStr | Impact of Misclassification Rates on Compression Efficiency of Red Blood Cell Images of Malaria Infection Using Deep Learning |
| title_full_unstemmed | Impact of Misclassification Rates on Compression Efficiency of Red Blood Cell Images of Malaria Infection Using Deep Learning |
| title_short | Impact of Misclassification Rates on Compression Efficiency of Red Blood Cell Images of Malaria Infection Using Deep Learning |
| title_sort | impact of misclassification rates on compression efficiency of red blood cell images of malaria infection using deep learning |
| topic | lossless compression pattern classification machine learning malaria infection entropy golomb–rice codes |
| url | https://www.mdpi.com/1099-4300/21/11/1062 |
| work_keys_str_mv | AT yuhangdong impactofmisclassificationratesoncompressionefficiencyofredbloodcellimagesofmalariainfectionusingdeeplearning AT wdavidpan impactofmisclassificationratesoncompressionefficiencyofredbloodcellimagesofmalariainfectionusingdeeplearning AT dongshengwu impactofmisclassificationratesoncompressionefficiencyofredbloodcellimagesofmalariainfectionusingdeeplearning |