Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Dec 5;14(12):8988-8998.
doi: 10.21037/qims-24-1328. Epub 2024 Nov 29.

Exploring the optimal threshold of 3D consolidation tumor ratio value segmentation based on artificial intelligence for predicting the invasive degree of T1 lung adenocarcinoma

Wensong Shi  1   2 , Yuzhui Hu  3 , Yingli Sun  4 , Guotao Chang  2 , Yulun Yang  2 , He Qian  2 , Zhengpan Wei  1 , Liang Zhao  5 , Ming Li  4 , Huiyu Zheng #  2 , Xiangnan Li #  1
Affiliations

Exploring the optimal threshold of 3D consolidation tumor ratio value segmentation based on artificial intelligence for predicting the invasive degree of T1 lung adenocarcinoma

Wensong Shi et al. Quant Imaging Med Surg. .

Abstract

Background: The assessment of lung adenocarcinoma significantly depends on the proportion of solid components in lung nodules. Traditional one-dimensional consolidation tumor ratio (1D CTR) based on ideal, uniformly dense solid components lacks precision. There is no consensus on the CT threshold for evaluating invasiveness using the threshold segmentation method. This study aimed to explore the effectiveness of the three-dimensional CTR (3D CTR) calculated by the artificial intelligence threshold segmentation method in predicting invasive stage T1 lung adenocarcinoma and to identify its optimal threshold and cut-off point.

Methods: Data from 1,056 patients with 1,179 pulmonary nodules confirmed by postoperative pathology were collected retrospectively from two centers, Zhengzhou People's Hospital and Huadong Hospital of Fudan University. Patients were divided into non-invasive [atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA)] and invasive groups [invasive adenocarcinoma (IAC)]. Seven computed tomography (CT) threshold settings (-550 to 0 HU) were used to calculate the 3D CTR via the threshold segmentation method, and differences between the groups were analyzed. Receiver operating characteristic (ROC) curves were plotted to compare predictive performance for invasiveness of stage T1 lung adenocarcinoma, and the optimal threshold and corresponding cut-off value were determined. Subgroup analyses based on nodule size-T1a (≤10 mm), T1b (>10 to 20 mm), and T1c (>20 to 30 mm)-were also conducted.

Results: The CT threshold of -150 Housefield unit (HU) showed the highest predictive efficacy for invasiveness of stage T1 lung adenocarcinoma, with an area under the curve (AUC) of 0.901 [95% confidence interval (CI): 0.883-0.919], sensitivity of 86.878%, and specificity of 77.883%. The optimal cut-off point for 3D CTR was 2.75%. In subgroup analyses, -150 HU remained optimal, with predictive performance increasing with nodule size. For the T1a group, the AUC was 0.887 (95% CI: 0.885-0.919), cut-off value was 2.75%, sensitivity was 77.620%, and specificity was 85.714%. For the T1b group, values were 0.903 (95% CI: 0.875-0.931), cut-off value was 5.4%, sensitivity was 87.671%, and specificity was 80.296%. For the T1c group, values were 0.928 (95% CI: 0.893-0.963), cut-off value was 7.1%, sensitivity was 88.043%, and specificity was 81.176%.

Conclusions: This study suggests that setting the CT threshold at -150 HU and using the AI-based threshold segmentation method to calculate the 3D CTR effectively distinguishes whether stage T1 lung adenocarcinoma is invasive, with an optimal cut-off point at 2.75%. Under this threshold, for varying nodule sizes, criteria are proposed: for nodules ≤10 mm with a 3D CTR <2.75%; >10 to 20 mm with a 3D CTR <5.4%; and >20 to 30 mm with a 3D CTR <7.1%, these partially solid nodules can be treated as non-IAC.

Keywords: Artificial intelligence (AI); T1 stage lung adenocarcinoma; invasive adenocarcinoma (IAC); three-dimensional consolidation tumor ratio (3D CTR); threshold segmentation method.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://qims.amegroups.com/article/view/10.21037/qims-24-1328/coif). L.Z. is an employee of Shukun (Beijing) Technology Co. The other authors have no conflicts of interest to declare.

Figures

Figure 1
Figure 1
Flow diagram of this study and the technical roadmap detailing the process of predicting the invasiveness of stage T1 lung adenocarcinoma using the 3D CTR derived from threshold segmentation at various CT thresholds. AI, artificial intelligence; CT, computed tomography; AAH, atypical adenomatous hyperplasia; AIS, adenocarcinoma in situ; MIA, minimally invasive adenocarcinoma; IAC, invasive adenocarcinoma; ROC, receiver operating characteristic; 3D CTR, three-dimensional consolidation tumor ratio.
Figure 2
Figure 2
Clinical Example Analysis: This figure illustrates the comparison of solid components in partially solid pulmonary nodules on chest CT images using artificial intelligence-based threshold segmentation at seven different CT threshold settings. The observations reveal the diversity and uneven density of solid components, specifically including: (A) threshold at −550 HU, (B) threshold at −450 HU, (C) threshold at −350 HU, (D) threshold at −250 HU, (E) threshold at −150 HU, (F) threshold at −50 HU, and (G) threshold at 0 HU. The green areas represent the solid parts within the lung nodules, indicating regions of high density within the nodules without air or fluid-filled spaces. The red circles denote the boundaries of the lung nodules, which are the edges that distinguish the nodules from the surrounding lung tissue. CT, computed tomography.
Figure 3
Figure 3
The ROC curves for predicting the invasiveness of stage T1 lung adenocarcinoma using the 3D CTR obtained from artificial intelligence-based threshold segmentation at seven distinct CT threshold settings. ROC, receiver operating characteristic; CT, computed tomography; CI, confidence interval; 3D CTR, three-dimensional consolidation tumor ratio.
Figure 4
Figure 4
The 3D CTR distribution of the non-invasive group and the invasive group when the threshold is −150 HU. 3D CTR, three-dimensional consolidation tumor ratio.
Figure 5
Figure 5
The ROC curves for predicting the invasiveness of T1a group lung adenocarcinoma based on the 3D CTR measured by artificial intelligence threshold segmentation at seven different CT threshold settings. ROC, receiver operating characteristic; CT, computed tomography; CI, confidence interval; 3D CTR, three-dimensional consolidation tumor ratio.
Figure 6
Figure 6
The ROC curves for predicting the invasiveness of T1b group lung cancer, based on the 3D CTR measured by artificial intelligence threshold segmentation across seven distinct CT threshold settings. ROC, receiver operating characteristic; CT, computed tomography; CI, confidence interval; 3D CTR, three-dimensional consolidation tumor ratio.
Figure 7
Figure 7
The ROC curves for predicting the invasiveness of T1c group lung adenocarcinoma, based on the 3D CTR as measured by artificial intelligence threshold segmentation at seven different CT threshold settings. ROC, receiver operating characteristic; CT, computed tomography; CI, confidence interval; 3D CTR, three-dimensional consolidation tumor ratio.
See this image and copyright information in PMC

References

    1. Ginsberg RJ, Rubinstein LV. Randomized trial of lobectomy versus limited resection for T1 N0 non-small cell lung cancer. Lung Cancer Study Group. Ann Thorac Surg 1995;60:615-22; discussion 622-3. 10.1016/0003-4975(95)00537-u - DOI - PubMed
    1. Suzuki K, Koike T, Asakawa T, Kusumoto M, Asamura H, Nagai K, Tada H, Mitsudomi T, Tsuboi M, Shibata T, Fukuda H, Kato H, Japan Lung Cancer Surgical Study Group (JCOG LCSSG). A prospective radiological study of thin-section computed tomography to predict pathological noninvasiveness in peripheral clinical IA lung cancer (Japan Clinical Oncology Group 0201). J Thorac Oncol 2011;6:751-6. 10.1097/JTO.0b013e31821038ab - DOI - PubMed
    1. Suzuki K, Watanabe SI, Wakabayashi M, Saji H, Aokage K, Moriya Y, Yoshino I, Tsuboi M, Nakamura S, Nakamura K, Mitsudomi T, Asamura H, West Japan Oncology Group and Japan Clinical Oncology Group . A single-arm study of sublobar resection for ground-glass opacity dominant peripheral lung cancer. J Thorac Cardiovasc Surg 2022;163:289-301.e2. 10.1016/j.jtcvs.2020.09.146 - DOI - PubMed
    1. Saji H, Okada M, Tsuboi M, Nakajima R, Suzuki K, Aokage K, et al. Segmentectomy versus lobectomy in small-sized peripheral non-small-cell lung cancer (JCOG0802/WJOG4607L): a multicentre, open-label, phase 3, randomised, controlled, non-inferiority trial. Lancet 2022;399:1607-17. 10.1016/S0140-6736(21)02333-3 - DOI - PubMed
    1. Aokage K, Suzuki K, Saji H, Wakabayashi M, Kataoka T, Sekino Y, et al. Segmentectomy for ground-glass-dominant lung cancer with a tumour diameter of 3 cm or less including ground-glass opacity (JCOG1211): a multicentre, single-arm, confirmatory, phase 3 trial. Lancet Respir Med 2023;11:540-9. 10.1016/S2213-2600(23)00041-3 - DOI - PubMed

LinkOut - more resources