Abstract 1250P
Background
We conducted a retrospective analysis to evaluate the volume of the lungs and determine the presence of infiltration and consolidation. To accurately interpret anisotropies and voxel spacings and to maintain resilience even when dealing with unbalanced class distributions, we used nnU-Net with quantitative and qualitative assessments to detect Lung infiltration. Utilizing TCGA-LUAD data (Lung Adenocarcinoma) and TCGA-LUSC (Lung Squamous cell carcinoma) this retrospective study on segmentation for volumetric and consolidation assessments are conducted. Chest OMX is a diagnostic tool that can assess lung volume, which in turn enables various applications such as monitoring recurrence from the changes in Lung volume; identifying infiltration and response to the treatment from Lung Volume and lobes, and detecting abnormalities in the lung from Consolidation. By providing quantitative score values, it assists in tracking changes over time and facilitating decision-making in clinical diagnosis.
Methods
We used nnU-Net, a popular deep-learning framework designed for medical image segmentation tasks. By analyzing the volume, infiltration, and consolidation characteristics of a lung carcinoma on CT scans, we can assess the tumor's behavior and response to treatment. From regional lung segmentation invasion, the burden is calculated. Additionally, measurements of discovered lung lesions and dedication to the relevant lung lobe are performed, along with fully automated lung lobe segmentation. Lobe 3D uses a deep learning system to measure the volume of the five lobes of the lung. HAA is also analyzed towards the end. Patient cases are selected irrespective of their ages from the TCGA cohort group. The primary outcome was the assessment of lung volume and the extent of the infiltration.
Results
Table: 1250P
Chest OMX: Generated diagnosis report for the case TCGA-LUSC
Left lung (LL) cm3 | 1429.50 |
Right lung (RL) cm3 | 1516.38 |
Left upper lobe (LUL) cm3 | 807.24 |
Left lower lobe (LLL) cm3 | 603.17 |
Right upper lobe (RUL) cm3 | 618.34 |
Right middle lobe (RML) cm3 | 276.84 |
Right lower lobe (RLL) cm3 | 611.89 |
Left upper lobe (HAA) cm3 | 170.16 |
Left lower lobe (HAA) cm3 | 378.00 |
Right upper lobe (HAA) cm3 | 128.18 |
Right middle lobe (HAA) cm3 | 59.05 |
Right lower lobe (HAA) cm3 | 394.12 |
Volume (LUL, LLL, RUL, RML, RLL) cm3 | (807.24, 603.17, 618.34, 276.84, 611.89) |
Involvement (LUL, LLL, RUL, RML, RLL) cm3 | (378.00, 128.18, 59.05, 394.12) |
Infiltration percentage (LUL, LLL, RUL, RML, RLL) % | (21.08, 62.67, 20.73, 21.33, 64.41) |
Conclusions
The diagnostic tool, Chest OMX can analyze the lung tissue from CT scans to determine the volume, consolidation and extent of infiltration by cancerous cells.
Clinical trial identification
Editorial acknowledgement
The dataset acknowledgment for,
1.Albertina, B., Watson, M., Holback, C., Jarosz, R., Kirk, S., Lee, Y., Rieger-Christ, K., & Lemmerman, J. (2016). The Cancer Genome Atlas Lung Adenocarcinoma Collection (TCGA-LUAD) (Version 4) [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/K9/TCIA.2016.JGNIHEP5.[Data Citation]
2. Clark, K., Vendt, B., Smith, K., Freymann, J., Kirby, J., Koppel, P., Moore, S., Phillips, S., Maffitt, D., Pringle, M., Tarbox, L., & Prior, F. (2013). The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. In Journal of Digital Imaging (Vol. 26, Issue 6, pp. 1045–1057). Springer Science and Business Media LLC. \https://doi.org/10.1007/s10278-013-9622-7.[TCIA Citation]
3.Kirk, S., Lee, Y., Kumar, P., Filippini, J., Albertina, B., Watson, M., Rieger-Christ, K., & Lemmerman, J. (2016). The Cancer Genome Atlas Lung Squamous Cell Carcinoma Collection (TCGA-LUSC) (Version 4) [Data set]. The Cancer Imaging Archive. \https://doi.org/10.7937/K9/TCIA.2016.TYGKKFMQ.[Data Citation]
Legal entity responsible for the study
PMX.Inc., USA and PMX, South Korea.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
1229P - Selective phenotypic and genotypic evaluation of circulating glial cells for improved diagnosis of glial malignancies
Presenter: Sewanti Limaye
Session: Poster session 14
1230P - hPG80 (circulating progastrin) is a new blood-based biomarker for diagnosis of early-stage non-small cell lung cancers
Presenter: Paul Hofman
Session: Poster session 14
1231P - Machine learning prediction of the case-fatality of COVID-19 and risk factors for adverse outcomes in patients with non-small cell lung cancer
Presenter: Yeji Jung
Session: Poster session 14
1232P - Analytic analysis of PanSeer7, a targeted bisulfite sequencing assay for blood-based multi-cancer detection for cancer early detection and tissue-of-origin identification
Presenter: Xinrong Yang
Session: Poster session 14
1233P - Accurate prediction of gastrointestinal cancer tissue of origin using comprehensive plasma cell-free DNA fragmentomics features
Presenter: Xinrong Yang
Session: Poster session 14
1234P - HistoMate: Automated preprocessing software for digital histopathology image to enhance deep learning
Presenter: Jinok Lee
Session: Poster session 14
1235P - Enrichment of rare cancers in pragmatic precision cancer medicine trial: Experience from IMPRESS-Norway
Presenter: Aaslaug Helland
Session: Poster session 14
1236P - Feasibility of online symptom monitoring to detect lung cancer relapse in Poland
Presenter: Ewa Pawlowska
Session: Poster session 14
1237P - Design and validation of a custom next-generation sequencing panel in melanoma, glioma and gastrointestinal stromal tumor
Presenter: Xiaoyan Zhou
Session: Poster session 14
1238P - Detecting driver mutations by AmoyDx 11-gene PCR with high concordance with next-generation sequencing in Chinese non-small cell lung cancer patients
Presenter: Dongmei Lin
Session: Poster session 14