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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00064203%3A_____%2F23%3A10458480" target="_blank" >RIV/00064203:_____/23:10458480 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/00216208:11320/23:10458480 RIV/00209805:_____/23:00079208

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=DEq.3Pva3h" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=DEq.3Pva3h</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/diagnostics13061043" target="_blank" >10.3390/diagnostics13061043</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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 &lt; 0.001, RAD 20.450 (0.352-0.548), p &lt; 0.001, RAD 30.670 (0.578-0.762), p &lt; 0.001, RAD 40.810 (0.733-0.887), p = 0.025, RAD 50.700 (0.610-0.790), p &lt; 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 &lt; 0.001, RAD 20.970 (0.946-1.000), p &lt; 0.001, RAD 30.980 (0.961-1.000), p &lt; 0.001, RAD 40.975 (0.953-0.997), p &lt; 0.001, RAD 50.995 (0.985-1.000), p &lt; 0.001). The study results demonstrate that the proposed DLAD could be utilized as a decision-support system to reduce radiologists&apos; false negative rate.

Název v anglickém jazyce

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

Popis výsledku anglicky

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 &lt; 0.001, RAD 20.450 (0.352-0.548), p &lt; 0.001, RAD 30.670 (0.578-0.762), p &lt; 0.001, RAD 40.810 (0.733-0.887), p = 0.025, RAD 50.700 (0.610-0.790), p &lt; 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 &lt; 0.001, RAD 20.970 (0.946-1.000), p &lt; 0.001, RAD 30.980 (0.961-1.000), p &lt; 0.001, RAD 40.975 (0.953-0.997), p &lt; 0.001, RAD 50.995 (0.985-1.000), p &lt; 0.001). The study results demonstrate that the proposed DLAD could be utilized as a decision-support system to reduce radiologists&apos; false negative rate.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

30204 - Oncology

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Diagnostics

ISSN

2075-4418

e-ISSN

2075-4418

Svazek periodika

13

Číslo periodika v rámci svazku

6

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

16

Strana od-do

1043

Kód UT WoS článku

000955949800001

EID výsledku v databázi Scopus

2-s2.0-85152356552