본문으로 건너뛰기
← 뒤로

Performance validation of a closed loop fully automated AI model for lung nodule stratification in screening cases.

1/5 보강
Respiratory investigation 2026 Vol.64(2) p. 101373
Retraction 확인
출처

PICO 자동 추출 (휴리스틱, conf 2/4)

유사 논문
P · Population 대상 환자/모집단
2358 cases (malignant and benign nodules).
I · Intervention 중재 / 시술
추출되지 않음
C · Comparison 대조 / 비교
추출되지 않음
O · Outcome 결과 / 결론
Performance remained consistent across scanner types and slice thicknesses. [CONCLUSIONS] Bronchosolve enables accurate, fully-automated risk classification of lung nodules and may enhance non-invasive diagnostic workflows.

Taha A, Muneer MS, Kalra A, Muelly M, Reicher J

📝 환자 설명용 한 줄

[BACKGROUND] Several limitations hinder the effectiveness of human-based lung cancer screening (LCS): high false-positive rates leading to unnecessary follow-up imaging, procedures, and surgeries; int

🔬 핵심 임상 통계 (초록에서 자동 추출 — 원문 검증 권장)
  • 표본수 (n) 184
  • Sensitivity 83.6 %
  • Specificity 86.3 %

이 논문을 인용하기

↓ .bib ↓ .ris
APA Taha A, Muneer MS, et al. (2026). Performance validation of a closed loop fully automated AI model for lung nodule stratification in screening cases.. Respiratory investigation, 64(2), 101373. https://doi.org/10.1016/j.resinv.2026.101373
MLA Taha A, et al.. "Performance validation of a closed loop fully automated AI model for lung nodule stratification in screening cases.." Respiratory investigation, vol. 64, no. 2, 2026, pp. 101373.
PMID 41564843 ↗

Abstract

[BACKGROUND] Several limitations hinder the effectiveness of human-based lung cancer screening (LCS): high false-positive rates leading to unnecessary follow-up imaging, procedures, and surgeries; inter-reader variability; inconsistent Lung-RADS adherence; and fatigue-related diagnostic errors. Additionally, most artificial intelligence (AI) models address only one task (nodule detection or risk stratification) and require manual image processing, which is time-consuming and costly. We developed Bronchosolve, a closed-loop, fully-automated software that processes scans without manual input, aiming to improve consistency, accuracy, and throughput in LCS.

[METHODS] The software integrates pre-processing, analysis, and result generation, using a deep-learning convolutional neural network (CNN) for pulmonary nodule triaging. Inputs were full chest CT scans in DICOM format, without clinical or demographic data. Automated steps included: 1) optimal CT series selection, 2) normalization and preprocessing, 3) AI-based detection and classification of suspicious nodules, and 4) report generation. The model was trained on a multi-center high-prevalence set of 2358 cases (malignant and benign nodules). Validation used a U.S.-based, multi-site cohort (n = 184; 8 sites). Positive cases were biopsy-confirmed within 1 year; negatives had biopsy or ≥2-year follow-up.

[RESULTS] All cases completed automatically (100 % success). Median age was 62.5 years (IQR 58.5-66.5); 45 % former smokers, 55 % current smokers, and 40 % female. The model achieved an AUC of 0.898 [0.851-0.940], outperforming Lung-RADS (pAUC 0.669) and the Brock model (AUC 0.783). Sensitivity was 83.6 %; specificity was 86.3 %. Performance remained consistent across scanner types and slice thicknesses.

[CONCLUSIONS] Bronchosolve enables accurate, fully-automated risk classification of lung nodules and may enhance non-invasive diagnostic workflows.

🏷️ 키워드 / MeSH 📖 같은 키워드 OA만

같은 제1저자의 인용 많은 논문 (3)

🏷️ 같은 키워드 · 무료전문 — 이 논문 MeSH/keyword 기반