A computer-aided diagnosis system for HEp-2 fluorescence intensity classification.
Computer-aided diagnosis
Deep learning
HEp-2 samples
Indirect immunofluorescence
Invariant Scattering Convolutional Networks
Journal
Artificial intelligence in medicine
ISSN: 1873-2860
Titre abrégé: Artif Intell Med
Pays: Netherlands
ID NLM: 8915031
Informations de publication
Date de publication:
06 2019
06 2019
Historique:
received:
19
02
2018
revised:
08
09
2018
accepted:
06
11
2018
pubmed:
7
12
2018
medline:
29
8
2020
entrez:
4
12
2018
Statut:
ppublish
Résumé
The indirect immunofluorescence (IIF) on HEp-2 cells is the recommended technique for the detection of antinuclear antibodies. However, it is burdened by some limitations, as it is time consuming and subjective, and it requires trained personnel. In other fields the adoption of deep neural networks has provided an effective high-level abstraction of the raw data, resulting in the ability to automatically generate optimized high-level features. To alleviate IIF limitations, this paper presents a computer-aided diagnosis (CAD) system classifying HEp-2 fluorescence intensity: it represents each image using an Invariant Scattering Convolutional Network (Scatnet), which is locally translation invariant and stable to deformations, a characteristic useful in case of HEp-2 samples. To cope with the inter-observer discrepancies found in the dataset, we also introduce a method for gold standard computation that assigns a label and a reliability score to each HEp-2 sample on the basis of annotations provided by expert physicians. Features by Scatnet and gold standard information are then used to train a Support Vector Machine. The proposed CAD is tested on a new dataset of 1771 images annotated by three independent medical centers. The performances achieved by our CAD in recognizing positive, weak positive and negative samples are also compared against those obtained by other two approaches presented so far in the literature. The same system trained on this new dataset is then tested on two public datasets, namely MIVIA and I3Asel. The results confirm the effectiveness of our proposal, also revealing that it achieves the same performance as medical experts.
Sections du résumé
BACKGROUND AND OBJECTIVE
The indirect immunofluorescence (IIF) on HEp-2 cells is the recommended technique for the detection of antinuclear antibodies. However, it is burdened by some limitations, as it is time consuming and subjective, and it requires trained personnel. In other fields the adoption of deep neural networks has provided an effective high-level abstraction of the raw data, resulting in the ability to automatically generate optimized high-level features.
METHODS
To alleviate IIF limitations, this paper presents a computer-aided diagnosis (CAD) system classifying HEp-2 fluorescence intensity: it represents each image using an Invariant Scattering Convolutional Network (Scatnet), which is locally translation invariant and stable to deformations, a characteristic useful in case of HEp-2 samples. To cope with the inter-observer discrepancies found in the dataset, we also introduce a method for gold standard computation that assigns a label and a reliability score to each HEp-2 sample on the basis of annotations provided by expert physicians. Features by Scatnet and gold standard information are then used to train a Support Vector Machine.
RESULTS
The proposed CAD is tested on a new dataset of 1771 images annotated by three independent medical centers. The performances achieved by our CAD in recognizing positive, weak positive and negative samples are also compared against those obtained by other two approaches presented so far in the literature. The same system trained on this new dataset is then tested on two public datasets, namely MIVIA and I3Asel.
CONCLUSIONS
The results confirm the effectiveness of our proposal, also revealing that it achieves the same performance as medical experts.
Identifiants
pubmed: 30503016
pii: S0933-3657(18)30100-3
doi: 10.1016/j.artmed.2018.11.002
pii:
doi:
Substances chimiques
Antibodies, Antinuclear
0
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
71-78Informations de copyright
Copyright © 2018 Elsevier B.V. All rights reserved.