A computer-aided diagnosis system for the assessment and characterization of low-to-high suspicion thyroid nodules on ultrasound

Salvatore Gitto, Giorgia Grassi, Chiara De Angelis, Cristian Giuseppe Monaco, Silvana Sdao, Francesco Sardanelli, Luca Maria Sconfienza, Giovanni Mauri

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Aim of the study: To compare the diagnostic performance of a commercially available computer-aided diagnosis (CAD) system for thyroid ultrasound (US) with that of a non-computer-aided radiologist in the characterization of low-to-high suspicion thyroid nodules. Methods: This retrospective study included a consecutive series of adult patients referred for US-guided fine-needle aspiration biopsy (FNAB) of a thyroid nodule. All patients were eligible for thyroid nodule FNAB according to the current international guidelines. An interventional radiologist experienced in thyroid imaging acquired the US images subsequently used for post-processing, performed FNAB and provided the US features of each nodule. A radiology resident and an endocrinology resident in consensus performed post-processing using the CAD system to assess the same nodule characteristics. The diagnostic performance and agreement of US features between the CAD system and the radiologist were compared. Results: Sixty-two patients (50 F; age 60 ± 12 years) were enrolled: 77.4% (48/62) of thyroid nodules were benign, 22.6% (14/62) were undetermined to malignant and required follow-up or surgery. Interobserver agreement between the CAD system and the radiologist was substantial for orientation (K = 0.69), fair for composition (K = 0.36), echogenicity (K = 0.36), K-TIRADS (K = 0.29), and slight for margins (K = 0.03). The radiologist demonstrated a significantly higher sensitivity than the CAD system (78.6% vs. 21.4%; P = 0.008), while there was no statistical difference in specificity (66.7% vs. 81.3%; P = 0.065). Conclusion: This CAD system is less sensitive than an experienced radiologist and showed slight-to-substantial agreement with the radiologist for the characterization of thyroid nodules. Although it is an innovative tool with good potential, additional efforts are needed to improve its diagnostic performance.

Original languageEnglish
Pages (from-to)118-125
JournalRadiologia Medica
Volume124
Issue number2
DOIs
Publication statusPublished - 2019

Fingerprint

Thyroid Nodule
Fine Needle Biopsy
Thyroid Gland
Endocrinology
Radiologists
Radiology
Ultrasonography
Retrospective Studies
Guidelines

Keywords

  • Computer-aided diagnosis
  • Nodule
  • Thyroid
  • Ultrasound

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

A computer-aided diagnosis system for the assessment and characterization of low-to-high suspicion thyroid nodules on ultrasound. / Gitto, Salvatore; Grassi, Giorgia; De Angelis, Chiara; Monaco, Cristian Giuseppe; Sdao, Silvana; Sardanelli, Francesco; Sconfienza, Luca Maria; Mauri, Giovanni.

In: Radiologia Medica, Vol. 124, No. 2, 2019, p. 118-125.

Research output: Contribution to journalArticle

Gitto, Salvatore ; Grassi, Giorgia ; De Angelis, Chiara ; Monaco, Cristian Giuseppe ; Sdao, Silvana ; Sardanelli, Francesco ; Sconfienza, Luca Maria ; Mauri, Giovanni. / A computer-aided diagnosis system for the assessment and characterization of low-to-high suspicion thyroid nodules on ultrasound. In: Radiologia Medica. 2019 ; Vol. 124, No. 2. pp. 118-125.
@article{c4802d1b7121452883d7d14a3396e62a,
title = "A computer-aided diagnosis system for the assessment and characterization of low-to-high suspicion thyroid nodules on ultrasound",
abstract = "Aim of the study: To compare the diagnostic performance of a commercially available computer-aided diagnosis (CAD) system for thyroid ultrasound (US) with that of a non-computer-aided radiologist in the characterization of low-to-high suspicion thyroid nodules. Methods: This retrospective study included a consecutive series of adult patients referred for US-guided fine-needle aspiration biopsy (FNAB) of a thyroid nodule. All patients were eligible for thyroid nodule FNAB according to the current international guidelines. An interventional radiologist experienced in thyroid imaging acquired the US images subsequently used for post-processing, performed FNAB and provided the US features of each nodule. A radiology resident and an endocrinology resident in consensus performed post-processing using the CAD system to assess the same nodule characteristics. The diagnostic performance and agreement of US features between the CAD system and the radiologist were compared. Results: Sixty-two patients (50 F; age 60 ± 12 years) were enrolled: 77.4{\%} (48/62) of thyroid nodules were benign, 22.6{\%} (14/62) were undetermined to malignant and required follow-up or surgery. Interobserver agreement between the CAD system and the radiologist was substantial for orientation (K = 0.69), fair for composition (K = 0.36), echogenicity (K = 0.36), K-TIRADS (K = 0.29), and slight for margins (K = 0.03). The radiologist demonstrated a significantly higher sensitivity than the CAD system (78.6{\%} vs. 21.4{\%}; P = 0.008), while there was no statistical difference in specificity (66.7{\%} vs. 81.3{\%}; P = 0.065). Conclusion: This CAD system is less sensitive than an experienced radiologist and showed slight-to-substantial agreement with the radiologist for the characterization of thyroid nodules. Although it is an innovative tool with good potential, additional efforts are needed to improve its diagnostic performance.",
keywords = "Computer-aided diagnosis, Nodule, Thyroid, Ultrasound",
author = "Salvatore Gitto and Giorgia Grassi and {De Angelis}, Chiara and Monaco, {Cristian Giuseppe} and Silvana Sdao and Francesco Sardanelli and Sconfienza, {Luca Maria} and Giovanni Mauri",
year = "2019",
doi = "10.1007/s11547-018-0942-z",
language = "English",
volume = "124",
pages = "118--125",
journal = "Radiologia Medica",
issn = "0033-8362",
publisher = "Springer-Verlag Italia s.r.l.",
number = "2",

}

TY - JOUR

T1 - A computer-aided diagnosis system for the assessment and characterization of low-to-high suspicion thyroid nodules on ultrasound

AU - Gitto, Salvatore

AU - Grassi, Giorgia

AU - De Angelis, Chiara

AU - Monaco, Cristian Giuseppe

AU - Sdao, Silvana

AU - Sardanelli, Francesco

AU - Sconfienza, Luca Maria

AU - Mauri, Giovanni

PY - 2019

Y1 - 2019

N2 - Aim of the study: To compare the diagnostic performance of a commercially available computer-aided diagnosis (CAD) system for thyroid ultrasound (US) with that of a non-computer-aided radiologist in the characterization of low-to-high suspicion thyroid nodules. Methods: This retrospective study included a consecutive series of adult patients referred for US-guided fine-needle aspiration biopsy (FNAB) of a thyroid nodule. All patients were eligible for thyroid nodule FNAB according to the current international guidelines. An interventional radiologist experienced in thyroid imaging acquired the US images subsequently used for post-processing, performed FNAB and provided the US features of each nodule. A radiology resident and an endocrinology resident in consensus performed post-processing using the CAD system to assess the same nodule characteristics. The diagnostic performance and agreement of US features between the CAD system and the radiologist were compared. Results: Sixty-two patients (50 F; age 60 ± 12 years) were enrolled: 77.4% (48/62) of thyroid nodules were benign, 22.6% (14/62) were undetermined to malignant and required follow-up or surgery. Interobserver agreement between the CAD system and the radiologist was substantial for orientation (K = 0.69), fair for composition (K = 0.36), echogenicity (K = 0.36), K-TIRADS (K = 0.29), and slight for margins (K = 0.03). The radiologist demonstrated a significantly higher sensitivity than the CAD system (78.6% vs. 21.4%; P = 0.008), while there was no statistical difference in specificity (66.7% vs. 81.3%; P = 0.065). Conclusion: This CAD system is less sensitive than an experienced radiologist and showed slight-to-substantial agreement with the radiologist for the characterization of thyroid nodules. Although it is an innovative tool with good potential, additional efforts are needed to improve its diagnostic performance.

AB - Aim of the study: To compare the diagnostic performance of a commercially available computer-aided diagnosis (CAD) system for thyroid ultrasound (US) with that of a non-computer-aided radiologist in the characterization of low-to-high suspicion thyroid nodules. Methods: This retrospective study included a consecutive series of adult patients referred for US-guided fine-needle aspiration biopsy (FNAB) of a thyroid nodule. All patients were eligible for thyroid nodule FNAB according to the current international guidelines. An interventional radiologist experienced in thyroid imaging acquired the US images subsequently used for post-processing, performed FNAB and provided the US features of each nodule. A radiology resident and an endocrinology resident in consensus performed post-processing using the CAD system to assess the same nodule characteristics. The diagnostic performance and agreement of US features between the CAD system and the radiologist were compared. Results: Sixty-two patients (50 F; age 60 ± 12 years) were enrolled: 77.4% (48/62) of thyroid nodules were benign, 22.6% (14/62) were undetermined to malignant and required follow-up or surgery. Interobserver agreement between the CAD system and the radiologist was substantial for orientation (K = 0.69), fair for composition (K = 0.36), echogenicity (K = 0.36), K-TIRADS (K = 0.29), and slight for margins (K = 0.03). The radiologist demonstrated a significantly higher sensitivity than the CAD system (78.6% vs. 21.4%; P = 0.008), while there was no statistical difference in specificity (66.7% vs. 81.3%; P = 0.065). Conclusion: This CAD system is less sensitive than an experienced radiologist and showed slight-to-substantial agreement with the radiologist for the characterization of thyroid nodules. Although it is an innovative tool with good potential, additional efforts are needed to improve its diagnostic performance.

KW - Computer-aided diagnosis

KW - Nodule

KW - Thyroid

KW - Ultrasound

UR - http://www.scopus.com/inward/record.url?scp=85053761207&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053761207&partnerID=8YFLogxK

U2 - 10.1007/s11547-018-0942-z

DO - 10.1007/s11547-018-0942-z

M3 - Article

AN - SCOPUS:85053761207

VL - 124

SP - 118

EP - 125

JO - Radiologia Medica

JF - Radiologia Medica

SN - 0033-8362

IS - 2

ER -