Exploiting probability density function of deep convolutional autoencoders’ latent space for reliable COVID-19 detection on CT scans

We present a probabilistic method for classifying chest computed tomography (CT) scans into COVID-19 and non-COVID-19. To this end, we design and train, in an unsupervised manner, a deep convolutional autoencoder (DCAE) on a selected training data set, which is composed only of COVID-19 CT scans. On...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The Journal of supercomputing Ročník 78; číslo 9; s. 12024 - 12045
Hlavní autoři: Sarv Ahrabi, Sima, Piazzo, Lorenzo, Momenzadeh, Alireza, Scarpiniti, Michele, Baccarelli, Enzo
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.06.2022
Springer Nature B.V
Témata:
Coders
Compilers
Computed tomography
Computer Science
Coronaviruses
COVID-19
Datasets
Interpreters
Medical imaging
Probabilistic methods
Probability density functions
Processor Architectures
Programming Languages
Representations
Statistical analysis
Training
COVID-19
Deep convolutional autoEencoder
Hidden representation
Kernel density estimation
Reconstruction error
ISSN:0920-8542, 1573-0484
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We present a probabilistic method for classifying chest computed tomography (CT) scans into COVID-19 and non-COVID-19. To this end, we design and train, in an unsupervised manner, a deep convolutional autoencoder (DCAE) on a selected training data set, which is composed only of COVID-19 CT scans. Once the model is trained, the encoder can generate the compact hidden representation (the hidden feature vectors) of the training data set. Afterwards, we exploit the obtained hidden representation to build up the target probability density function (PDF) of the training data set by means of kernel density estimation (KDE). Subsequently, in the test phase, we feed a test CT into the trained encoder to produce the corresponding hidden feature vector, and then, we utilise the target PDF to compute the corresponding PDF value of the test image. Finally, this obtained value is compared to a threshold to assign the COVID-19 label or non-COVID-19 to the test image. We numerically check our approach’s performance (i.e. test accuracy and training times) by comparing it with those of some state-of-the-art methods.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-022-04349-y