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
1219P - Artificial intelligence-based breast cancer detection facilitates automated prognosis marker assessment using multiplex fluorescence immunohistochemistry
Presenter: Tim Mandelkow
Session: Poster session 14
1220P - Comprehensive diagnose of programmed death-ligand 1 from two-dimensional to three-dimensional in breast cancer with computer-aided artificial intelligence system
Presenter: Yi-Hsuan Lee
Session: Poster session 14
1221P - The functional domain of BRCA1/2 pathogenic variants (PVs) as potential biomarkers of second tumor and domain-related sensitivity to PARP-inhibitors
Presenter: Lorena Incorvaia
Session: Poster session 14
1222P - Detection of androgen-receptor splice variant 7 messenger RNA in circulating tumor cells of prostate cancer by in vitro assay
Presenter: Hoin Kang
Session: Poster session 14
1223P - Homologous recombination deficiency (HRD) testing on ovarian cancer ascites: A feasibility study
Presenter: Alberto Ranghiero
Session: Poster session 14
1224P - Detection of circulating tumor DNA (ctDNA) in untreated patients (pts) with cancer: Implications for early cancer detection (ECD)
Presenter: Yoshiaki Nakamura
Session: Poster session 14
1225P - Combining ctDNA and tissue-based-genomic profiling in advanced cancer: A real-world evidence prospective study in non-Western patients treated at Gustave Roussy cancer campus
Presenter: Tony Ibrahim
Session: Poster session 14
1226P - Multi-site validation of a deep learning solution for HER2 profiling of breast cancer from H&E-stained pathology slides
Presenter: Salim Arslan
Session: Poster session 14
1227P - Novel in vivo photonics-immunoassay system, inPROBE, for the rapid detection of HER2 in breast cancer
Presenter: Magdalena Staniszewska
Session: Poster session 14
1228P - A circulating tumor cell (CTC) based assay for diagnostic immunocytochemistry profiling of lung cancer
Presenter: Nitesh Rohatgi
Session: Poster session 14