A cloud-based computer-aided detection system improves identification of lung nodules on computed tomography scans of patients with extra-thoracic malignancies

Lorenzo Vassallo, Alberto Traverso, Michelangelo Agnello, Christian Bracco, Delia Campanella, Gabriele Chiara, Maria Evelina Fantacci, Ernesto Lopez Torres, Antonio Manca, Marco Saletta, Valentina Giannini, Simone Mazzetti, Michele Stasi, Piergiorgio Cerello, Daniele Regge

Research output: Contribution to journalArticle

Abstract

Objectives: To compare unassisted and CAD-assisted detection and time efficiency of radiologists in reporting lung nodules on CT scans taken from patients with extra-thoracic malignancies using a Cloud-based system. Materials and methods: Three radiologists searched for pulmonary nodules in patients with extra-thoracic malignancy who underwent CT (slice thickness/spacing 2 mm/1.7 mm) between September 2015 and March 2016. All nodules detected by unassisted reading were measured and coordinates were uploaded on a cloud-based system. CAD marks were then reviewed by the same readers using the cloud-based interface. To establish the reference standard all nodules ≥ 3 mm detected by at least one radiologist were validated by two additional experienced radiologists in consensus. Reader detection rate and reporting time with and without CAD were compared. The study was approved by the local ethics committee. All patients signed written informed consent. Results: The series included 225 patients (age range 21–90 years, mean 62 years), including 75 patients having at least one nodule, for a total of 215 nodules. Stand-alone CAD sensitivity for lesions ≥ 3 mm was 85% (183/215, 95% CI: 82–91); mean false-positive rate per scan was 3.8. Sensitivity across readers in detecting lesions ≥ 3 mm was statistically higher using CAD: 65% (95% CI: 61–69) versus 88% (95% CI: 86–91, p<0.01). Reading time increased by 11% using CAD (296 s vs. 329 s; p<0.05). Conclusion: In patients with extra-thoracic malignancies, CAD-assisted reading improves detection of ≥ 3-mm lung nodules on CT, slightly increasing reading time. Key Points: • CAD-assisted reading improves the detection of lung nodules compared with unassisted reading on CT scans of patients with primary extra-thoracic tumour, slightly increasing reading time. • Cloud-based CAD systems may represent a cost-effective solution since CAD results can be reviewed while a separated cloud back-end is taking care of computations. • Early identification of lung nodules by CAD-assisted interpretation of CT scans in patients with extra-thoracic primary tumours is of paramount importance as it could anticipate surgery and extend patient life expectancy.

LanguageEnglish
Pages144-152
Number of pages9
JournalEuropean Radiology
Volume29
Issue number1
DOIs
Publication statusPublished - Jan 1 2019

Keywords

  • Lung
  • Metastases
  • Neoplasm
  • Radiologists
  • Tomography

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

A cloud-based computer-aided detection system improves identification of lung nodules on computed tomography scans of patients with extra-thoracic malignancies. / Vassallo, Lorenzo; Traverso, Alberto; Agnello, Michelangelo; Bracco, Christian; Campanella, Delia; Chiara, Gabriele; Fantacci, Maria Evelina; Lopez Torres, Ernesto; Manca, Antonio; Saletta, Marco; Giannini, Valentina; Mazzetti, Simone; Stasi, Michele; Cerello, Piergiorgio; Regge, Daniele.

In: European Radiology, Vol. 29, No. 1, 01.01.2019, p. 144-152.

Research output: Contribution to journalArticle

Vassallo, Lorenzo ; Traverso, Alberto ; Agnello, Michelangelo ; Bracco, Christian ; Campanella, Delia ; Chiara, Gabriele ; Fantacci, Maria Evelina ; Lopez Torres, Ernesto ; Manca, Antonio ; Saletta, Marco ; Giannini, Valentina ; Mazzetti, Simone ; Stasi, Michele ; Cerello, Piergiorgio ; Regge, Daniele. / A cloud-based computer-aided detection system improves identification of lung nodules on computed tomography scans of patients with extra-thoracic malignancies. In: European Radiology. 2019 ; Vol. 29, No. 1. pp. 144-152.
@article{61d1015df50d4b04abb54cd49114cacb,
title = "A cloud-based computer-aided detection system improves identification of lung nodules on computed tomography scans of patients with extra-thoracic malignancies",
abstract = "Objectives: To compare unassisted and CAD-assisted detection and time efficiency of radiologists in reporting lung nodules on CT scans taken from patients with extra-thoracic malignancies using a Cloud-based system. Materials and methods: Three radiologists searched for pulmonary nodules in patients with extra-thoracic malignancy who underwent CT (slice thickness/spacing 2 mm/1.7 mm) between September 2015 and March 2016. All nodules detected by unassisted reading were measured and coordinates were uploaded on a cloud-based system. CAD marks were then reviewed by the same readers using the cloud-based interface. To establish the reference standard all nodules ≥ 3 mm detected by at least one radiologist were validated by two additional experienced radiologists in consensus. Reader detection rate and reporting time with and without CAD were compared. The study was approved by the local ethics committee. All patients signed written informed consent. Results: The series included 225 patients (age range 21–90 years, mean 62 years), including 75 patients having at least one nodule, for a total of 215 nodules. Stand-alone CAD sensitivity for lesions ≥ 3 mm was 85{\%} (183/215, 95{\%} CI: 82–91); mean false-positive rate per scan was 3.8. Sensitivity across readers in detecting lesions ≥ 3 mm was statistically higher using CAD: 65{\%} (95{\%} CI: 61–69) versus 88{\%} (95{\%} CI: 86–91, p<0.01). Reading time increased by 11{\%} using CAD (296 s vs. 329 s; p<0.05). Conclusion: In patients with extra-thoracic malignancies, CAD-assisted reading improves detection of ≥ 3-mm lung nodules on CT, slightly increasing reading time. Key Points: • CAD-assisted reading improves the detection of lung nodules compared with unassisted reading on CT scans of patients with primary extra-thoracic tumour, slightly increasing reading time. • Cloud-based CAD systems may represent a cost-effective solution since CAD results can be reviewed while a separated cloud back-end is taking care of computations. • Early identification of lung nodules by CAD-assisted interpretation of CT scans in patients with extra-thoracic primary tumours is of paramount importance as it could anticipate surgery and extend patient life expectancy.",
keywords = "Lung, Metastases, Neoplasm, Radiologists, Tomography",
author = "Lorenzo Vassallo and Alberto Traverso and Michelangelo Agnello and Christian Bracco and Delia Campanella and Gabriele Chiara and Fantacci, {Maria Evelina} and {Lopez Torres}, Ernesto and Antonio Manca and Marco Saletta and Valentina Giannini and Simone Mazzetti and Michele Stasi and Piergiorgio Cerello and Daniele Regge",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/s00330-018-5528-6",
language = "English",
volume = "29",
pages = "144--152",
journal = "European Radiology",
issn = "0938-7994",
publisher = "Springer Verlag",
number = "1",

}

TY - JOUR

T1 - A cloud-based computer-aided detection system improves identification of lung nodules on computed tomography scans of patients with extra-thoracic malignancies

AU - Vassallo, Lorenzo

AU - Traverso, Alberto

AU - Agnello, Michelangelo

AU - Bracco, Christian

AU - Campanella, Delia

AU - Chiara, Gabriele

AU - Fantacci, Maria Evelina

AU - Lopez Torres, Ernesto

AU - Manca, Antonio

AU - Saletta, Marco

AU - Giannini, Valentina

AU - Mazzetti, Simone

AU - Stasi, Michele

AU - Cerello, Piergiorgio

AU - Regge, Daniele

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Objectives: To compare unassisted and CAD-assisted detection and time efficiency of radiologists in reporting lung nodules on CT scans taken from patients with extra-thoracic malignancies using a Cloud-based system. Materials and methods: Three radiologists searched for pulmonary nodules in patients with extra-thoracic malignancy who underwent CT (slice thickness/spacing 2 mm/1.7 mm) between September 2015 and March 2016. All nodules detected by unassisted reading were measured and coordinates were uploaded on a cloud-based system. CAD marks were then reviewed by the same readers using the cloud-based interface. To establish the reference standard all nodules ≥ 3 mm detected by at least one radiologist were validated by two additional experienced radiologists in consensus. Reader detection rate and reporting time with and without CAD were compared. The study was approved by the local ethics committee. All patients signed written informed consent. Results: The series included 225 patients (age range 21–90 years, mean 62 years), including 75 patients having at least one nodule, for a total of 215 nodules. Stand-alone CAD sensitivity for lesions ≥ 3 mm was 85% (183/215, 95% CI: 82–91); mean false-positive rate per scan was 3.8. Sensitivity across readers in detecting lesions ≥ 3 mm was statistically higher using CAD: 65% (95% CI: 61–69) versus 88% (95% CI: 86–91, p<0.01). Reading time increased by 11% using CAD (296 s vs. 329 s; p<0.05). Conclusion: In patients with extra-thoracic malignancies, CAD-assisted reading improves detection of ≥ 3-mm lung nodules on CT, slightly increasing reading time. Key Points: • CAD-assisted reading improves the detection of lung nodules compared with unassisted reading on CT scans of patients with primary extra-thoracic tumour, slightly increasing reading time. • Cloud-based CAD systems may represent a cost-effective solution since CAD results can be reviewed while a separated cloud back-end is taking care of computations. • Early identification of lung nodules by CAD-assisted interpretation of CT scans in patients with extra-thoracic primary tumours is of paramount importance as it could anticipate surgery and extend patient life expectancy.

AB - Objectives: To compare unassisted and CAD-assisted detection and time efficiency of radiologists in reporting lung nodules on CT scans taken from patients with extra-thoracic malignancies using a Cloud-based system. Materials and methods: Three radiologists searched for pulmonary nodules in patients with extra-thoracic malignancy who underwent CT (slice thickness/spacing 2 mm/1.7 mm) between September 2015 and March 2016. All nodules detected by unassisted reading were measured and coordinates were uploaded on a cloud-based system. CAD marks were then reviewed by the same readers using the cloud-based interface. To establish the reference standard all nodules ≥ 3 mm detected by at least one radiologist were validated by two additional experienced radiologists in consensus. Reader detection rate and reporting time with and without CAD were compared. The study was approved by the local ethics committee. All patients signed written informed consent. Results: The series included 225 patients (age range 21–90 years, mean 62 years), including 75 patients having at least one nodule, for a total of 215 nodules. Stand-alone CAD sensitivity for lesions ≥ 3 mm was 85% (183/215, 95% CI: 82–91); mean false-positive rate per scan was 3.8. Sensitivity across readers in detecting lesions ≥ 3 mm was statistically higher using CAD: 65% (95% CI: 61–69) versus 88% (95% CI: 86–91, p<0.01). Reading time increased by 11% using CAD (296 s vs. 329 s; p<0.05). Conclusion: In patients with extra-thoracic malignancies, CAD-assisted reading improves detection of ≥ 3-mm lung nodules on CT, slightly increasing reading time. Key Points: • CAD-assisted reading improves the detection of lung nodules compared with unassisted reading on CT scans of patients with primary extra-thoracic tumour, slightly increasing reading time. • Cloud-based CAD systems may represent a cost-effective solution since CAD results can be reviewed while a separated cloud back-end is taking care of computations. • Early identification of lung nodules by CAD-assisted interpretation of CT scans in patients with extra-thoracic primary tumours is of paramount importance as it could anticipate surgery and extend patient life expectancy.

KW - Lung

KW - Metastases

KW - Neoplasm

KW - Radiologists

KW - Tomography

UR - http://www.scopus.com/inward/record.url?scp=85048594204&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048594204&partnerID=8YFLogxK

U2 - 10.1007/s00330-018-5528-6

DO - 10.1007/s00330-018-5528-6

M3 - Article

VL - 29

SP - 144

EP - 152

JO - European Radiology

T2 - European Radiology

JF - European Radiology

SN - 0938-7994

IS - 1

ER -