A 178-clinical-center experiment of integrating AI solutions for lung pathology diagnosis
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
A 178-clinical-center experiment of integrating AI solutions for lung pathology diagnosis. / Ibragimov, Bulat; Arzamasov, Kirill; Maksudov, Bulat; Kiselev, Semen; Mongolin, Alexander; Mustafaev, Tamerlan; Ibragimova, Dilyara; Evteeva, Ksenia; Andreychenko, Anna; Morozov, Sergey.
In: Scientific Reports, Vol. 13, No. 1, 1135, 12.2023.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - A 178-clinical-center experiment of integrating AI solutions for lung pathology diagnosis
AU - Ibragimov, Bulat
AU - Arzamasov, Kirill
AU - Maksudov, Bulat
AU - Kiselev, Semen
AU - Mongolin, Alexander
AU - Mustafaev, Tamerlan
AU - Ibragimova, Dilyara
AU - Evteeva, Ksenia
AU - Andreychenko, Anna
AU - Morozov, Sergey
N1 - Publisher Copyright: © 2023, The Author(s).
PY - 2023/12
Y1 - 2023/12
N2 - In 2020, an experiment testing AI solutions for lung X-ray analysis on a multi-hospital network was conducted. The multi-hospital network linked 178 Moscow state healthcare centers, where all chest X-rays from the network were redirected to a research facility, analyzed with AI, and returned to the centers. The experiment was formulated as a public competition with monetary awards for participating industrial and research teams. The task was to perform the binary detection of abnormalities from chest X-rays. For the objective real-life evaluation, no training X-rays were provided to the participants. This paper presents one of the top-performing AI frameworks from this experiment. First, the framework used two EfficientNets, histograms of gradients, Haar feature ensembles, and local binary patterns to recognize whether an input image represents an acceptable lung X-ray sample, meaning the X-ray is not grayscale inverted, is a frontal chest X-ray, and completely captures both lung fields. Second, the framework extracted the region with lung fields and then passed them to a multi-head DenseNet, where the heads recognized the patient’s gender, age and the potential presence of abnormalities, and generated the heatmap with the abnormality regions highlighted. During one month of the experiment from 11.23.2020 to 12.25.2020, 17,888 cases have been analyzed by the framework with 11,902 cases having radiological reports with the reference diagnoses that were unequivocally parsed by the experiment organizers. The performance measured in terms of the area under receiving operator curve (AUC) was 0.77. The AUC for individual diseases ranged from 0.55 for herniation to 0.90 for pneumothorax.
AB - In 2020, an experiment testing AI solutions for lung X-ray analysis on a multi-hospital network was conducted. The multi-hospital network linked 178 Moscow state healthcare centers, where all chest X-rays from the network were redirected to a research facility, analyzed with AI, and returned to the centers. The experiment was formulated as a public competition with monetary awards for participating industrial and research teams. The task was to perform the binary detection of abnormalities from chest X-rays. For the objective real-life evaluation, no training X-rays were provided to the participants. This paper presents one of the top-performing AI frameworks from this experiment. First, the framework used two EfficientNets, histograms of gradients, Haar feature ensembles, and local binary patterns to recognize whether an input image represents an acceptable lung X-ray sample, meaning the X-ray is not grayscale inverted, is a frontal chest X-ray, and completely captures both lung fields. Second, the framework extracted the region with lung fields and then passed them to a multi-head DenseNet, where the heads recognized the patient’s gender, age and the potential presence of abnormalities, and generated the heatmap with the abnormality regions highlighted. During one month of the experiment from 11.23.2020 to 12.25.2020, 17,888 cases have been analyzed by the framework with 11,902 cases having radiological reports with the reference diagnoses that were unequivocally parsed by the experiment organizers. The performance measured in terms of the area under receiving operator curve (AUC) was 0.77. The AUC for individual diseases ranged from 0.55 for herniation to 0.90 for pneumothorax.
UR - http://www.scopus.com/inward/record.url?scp=85146601731&partnerID=8YFLogxK
U2 - 10.1038/s41598-023-27397-7
DO - 10.1038/s41598-023-27397-7
M3 - Journal article
C2 - 36670118
AN - SCOPUS:85146601731
VL - 13
JO - Scientific Reports
JF - Scientific Reports
SN - 2045-2322
IS - 1
M1 - 1135
ER -
ID: 335693492