Detail
Článek
Článek online
FT
Medvik - BMČ
  • Je něco špatně v tomto záznamu ?

Leveraging Deep Learning Decision-Support System in Specialized Oncology Center: A Multi-Reader Retrospective Study on Detection of Pulmonary Lesions in Chest X-ray Images

D. Kvak, A. Chromcová, R. Hrubý, E. Janů, M. Biroš, M. Pajdaković, K. Kvaková, MA. Al-Antari, P. Polášková, S. Strukov

. 2023 ; 13 (6) : . [pub] 20230309

Status neindexováno Jazyk angličtina Země Švýcarsko

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc23002715

Chest X-ray (CXR) is considered to be the most widely used modality for detecting and monitoring various thoracic findings, including lung carcinoma and other pulmonary lesions. However, X-ray imaging shows particular limitations when detecting primary and secondary tumors and is prone to reading errors due to limited resolution and disagreement between radiologists. To address these issues, we developed a deep-learning-based automatic detection algorithm (DLAD) to automatically detect and localize suspicious lesions on CXRs. Five radiologists were invited to retrospectively evaluate 300 CXR images from a specialized oncology center, and the performance of individual radiologists was subsequently compared with that of DLAD. The proposed DLAD achieved significantly higher sensitivity (0.910 (0.854-0.966)) than that of all assessed radiologists (RAD 10.290 (0.201-0.379), p < 0.001, RAD 20.450 (0.352-0.548), p < 0.001, RAD 30.670 (0.578-0.762), p < 0.001, RAD 40.810 (0.733-0.887), p = 0.025, RAD 50.700 (0.610-0.790), p < 0.001). The DLAD specificity (0.775 (0.717-0.833)) was significantly lower than for all assessed radiologists (RAD 11.000 (0.984-1.000), p < 0.001, RAD 20.970 (0.946-1.000), p < 0.001, RAD 30.980 (0.961-1.000), p < 0.001, RAD 40.975 (0.953-0.997), p < 0.001, RAD 50.995 (0.985-1.000), p < 0.001). The study results demonstrate that the proposed DLAD could be utilized as a decision-support system to reduce radiologists' false negative rate.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc23002715
003      
CZ-PrNML
005      
20230421100057.0
007      
ta
008      
230413s2023 sz f 000 0|eng||
009      
AR
024    7_
$a 10.3390/diagnostics13061043 $2 doi
035    __
$a (PubMed)36980351
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a sz
100    1_
$a Kvak, Daniel $u Carebot, Ltd., 128 00 Prague, Czech Republic $1 https://orcid.org/0000000178087773
245    10
$a Leveraging Deep Learning Decision-Support System in Specialized Oncology Center: A Multi-Reader Retrospective Study on Detection of Pulmonary Lesions in Chest X-ray Images / $c D. Kvak, A. Chromcová, R. Hrubý, E. Janů, M. Biroš, M. Pajdaković, K. Kvaková, MA. Al-Antari, P. Polášková, S. Strukov
520    9_
$a Chest X-ray (CXR) is considered to be the most widely used modality for detecting and monitoring various thoracic findings, including lung carcinoma and other pulmonary lesions. However, X-ray imaging shows particular limitations when detecting primary and secondary tumors and is prone to reading errors due to limited resolution and disagreement between radiologists. To address these issues, we developed a deep-learning-based automatic detection algorithm (DLAD) to automatically detect and localize suspicious lesions on CXRs. Five radiologists were invited to retrospectively evaluate 300 CXR images from a specialized oncology center, and the performance of individual radiologists was subsequently compared with that of DLAD. The proposed DLAD achieved significantly higher sensitivity (0.910 (0.854-0.966)) than that of all assessed radiologists (RAD 10.290 (0.201-0.379), p < 0.001, RAD 20.450 (0.352-0.548), p < 0.001, RAD 30.670 (0.578-0.762), p < 0.001, RAD 40.810 (0.733-0.887), p = 0.025, RAD 50.700 (0.610-0.790), p < 0.001). The DLAD specificity (0.775 (0.717-0.833)) was significantly lower than for all assessed radiologists (RAD 11.000 (0.984-1.000), p < 0.001, RAD 20.970 (0.946-1.000), p < 0.001, RAD 30.980 (0.961-1.000), p < 0.001, RAD 40.975 (0.953-0.997), p < 0.001, RAD 50.995 (0.985-1.000), p < 0.001). The study results demonstrate that the proposed DLAD could be utilized as a decision-support system to reduce radiologists' false negative rate.
590    __
$a NEINDEXOVÁNO
655    _2
$a časopisecké články $7 D016428
700    1_
$a Chromcová, Anna $u Carebot, Ltd., 128 00 Prague, Czech Republic
700    1_
$a Hrubý, Robert $u Carebot, Ltd., 128 00 Prague, Czech Republic $u Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University, 115 19 Prague, Czech Republic $1 https://orcid.org/0000000299858060
700    1_
$a Janů, Eva $u Department of Radiology, Masaryk Memorial Cancer Institute, 602 00 Brno, Czech Republic $1 https://orcid.org/000000020147211X
700    1_
$a Biroš, Marek $u Carebot, Ltd., 128 00 Prague, Czech Republic $u Faculty of Mathematics and Physics, Charles University, 121 16 Prague, Czech Republic $1 https://orcid.org/000000032781623X
700    1_
$a Pajdaković, Marija $u Carebot, Ltd., 128 00 Prague, Czech Republic $u Faculty of Electrical Engineering, Czech Technical University, 166 36 Prague, Czech Republic
700    1_
$a Kvaková, Karolína $u Carebot, Ltd., 128 00 Prague, Czech Republic
700    1_
$a Al-Antari, Mugahed A $u Department of Artificial Intelligence, Daeyang AI Center, Sejong University, Seoul 050 06, Republic of Korea $1 https://orcid.org/0000000244574407
700    1_
$a Polášková, Pavlína $u Department of Imaging Methods, Motol University Hospital, 150 06 Prague, Czech Republic
700    1_
$a Strukov, Sergei $u Department of Radiodiagnosis, Podripska City Hospital, 413 01 Roudnice nad Labem, Czech Republic
773    0_
$w MED00195450 $t Diagnostics (Basel, Switzerland) $x 2075-4418 $g Roč. 13, č. 6 (2023)
856    41
$u https://pubmed.ncbi.nlm.nih.gov/36980351 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y p $z 0
990    __
$a 20230413 $b ABA008
991    __
$a 20230421100049 $b ABA008
999    __
$a ok $b bmc $g 1922639 $s 1188922
BAS    __
$a 3
BAS    __
$a PreBMC-PubMed-not-MEDLINE
BMC    __
$a 2023 $b 13 $c 6 $e 20230309 $i 2075-4418 $m Diagnostics $n Diagnostics $x MED00195450
LZP    __
$a Pubmed-20230413

Najít záznam

Citační ukazatele

Pouze přihlášení uživatelé

Možnosti archivace