Detection of metastasis of mediastinal lymph nodes in lung cancer patients with an artificial intelligence model.
Ontology highlight
ABSTRACT:
SUBMITTER: Sun X
PROVIDER: S-EPMC10228471 | biostudies-literature | 2023 May
REPOSITORIES: biostudies-literature
Publications
Detection of metastasis of mediastinal lymph nodes in lung cancer patients with an artificial intelligence model.
Sun Xiao X Xin Yanlu Y Liu Dahai D Xie Boheng B Wang Yuanyong Y Lu Tong T Jiang Gang G Lin Jizheng J Jiao Wenjie W
Chinese medical journal 20230505 9
Similar Datasets
Project description:It is important to detect mediastinal lymph node metastases in patients with lung cancer to improve outcomes, and it is possible that activatable fluorescence imaging with indocyanine green (ICG) can help visualize metastatic lymph nodes. Therefore, we investigated the feasibility of applying this method to mediastinal lymph node metastases in an epidermal growth factor receptor (EGFR)-positive squamous cell carcinoma of the lung. Tumors were formed by injecting H226 (EGFR-positive) and H520 (EGFR-negative) cell lines directly in the lung parenchyma of five mice each. When computed tomography revealed tumors exceeding 8 mm at their longest or atelectasis that occupied more than half of lateral lung fields, a panitumumab (Pan)-ICG conjugate was injected in the tail vein (50 ?g/100 ?L). The mice were then sacrificed 48 hours after injection and their chests were opened for fluorescent imaging acquisition. Lymph node metastases with the five highest fluorescent signal intensities per mouse were chosen for statistical analysis of the average signal ratios against the liver. Regarding the quenching capacity, the Pan-ICG conjugate had almost no fluorescence in phosphate-buffered saline, but there was an approximate 61.8-fold increase in vitro after treatment with 1% sodium dodecyl sulfate. Both the fluorescent microscopy and the flow cytometry showed specific binding between the conjugate and H226, but almost no specific binding with H520. The EGFR-positive mediastinal lymph node metastases showed significantly higher average fluorescence signal ratios than the EGFR-negative ones (n = 25 per group) 48 hours after conjugate administration (70.1% ± 4.5% vs. 13.3% ± 1.8%; p < 0.05). Thus, activatable fluorescence imaging using the Pan-ICG conjugate detected EGFR-positive mediastinal lymph node metastases with high specificity.
| S-EPMC5983456 | biostudies-literature
Project description:PurposeThe identification of pathological mediastinal lymph nodes is an important step in the staging of lung cancer, with the presence of metastases significantly affecting survival rates. Nodes are currently identified by a physician, but this process is time-consuming and prone to errors. In this paper, we investigate the use of artificial intelligence-based methods to increase the accuracy and consistency of this process.MethodsWhole-body 18F-labelled fluoro-2-deoxyglucose ([18F]FDG) positron emission tomography/computed tomography ([18F]FDG-PET/CT) scans (Philips Gemini TF) from 134 patients were retrospectively analysed. The thorax was automatically located, and then slices were fed into a U-Net to identify candidate regions. These regions were split into overlapping 3D cubes, which were individually predicted as positive or negative using a 3D CNN. From these predictions, pathological mediastinal nodes could be identified. A second cohort of 71 patients was then acquired from a different, newer scanner (GE Discovery MI), and the performance of the model on this dataset was tested with and without transfer learning.ResultsOn the test set from the first scanner, our model achieved a sensitivity of 0.87 (95% confidence intervals [0.74, 0.94]) with 0.41 [0.22, 0.71] false positives/patient. This was comparable to the performance of an expert. Without transfer learning, on the test set from the second scanner, the corresponding results were 0.53 [0.35, 0.70] and 0.24 [0.10, 0.49], respectively. With transfer learning, these metrics were 0.88 [0.73, 0.97] and 0.69 [0.43, 1.04], respectively.ConclusionModel performance was comparable to that of an expert on data from the same scanner. With transfer learning, the model can be applied to data from a different scanner. To our knowledge it is the first study of its kind to go directly from whole-body [18F]FDG-PET/CT scans to pathological mediastinal lymph node localisation.
| S-EPMC8803782 | biostudies-literature
Project description:The presence of metastases in mediastinal lymph nodes (LNs) is essential for planning lung cancer treatment and assessing anticancer immune responses. The aim of the study was to assess LNs for the presence of neoplastic cells and evaluate lung cancer-selected antigen expression. LN aspirates were obtained during an EBUS/TBNA procedure. The cells were analyzed using a hematological analyzer and flow cytometry. It was possible to indicate the presence of cells characterized by high fluorescence connected with high metabolic activity using a hematological analyzer and to determine their non-hematopoietic origin using flow cytometry. Using these methods together, we detected very quickly a high proportion of cancer cells in LNs. We noticed that it was possible to determine a high expression of EpCAM, TTF-1, Ki67, cytokeratin, HER, and differences between non-small-cell (NSCLC) and small-cell lung cancer (SCLC) for the antigens MUC-1, CD56, HLA-DR, CD39, CD184, PD-L1, PD-L2 and CTLA-4 on tumor cells. We report, for the first time, that the detection of tumor cells in LNs with the expression of specific antigens is easy to evaluate using a hematological analyzer and flow cytometry in EBUS/TBNA samples. Such precise characteristics of non-hematopoietic cells in LNs may be of great diagnostic importance in the detection of micrometastases.
| S-EPMC11816154 | biostudies-literature
Project description:Background: Lymph node metastasis (LNM) status is critical to the treatment. Fewer studies has focused on LNM in patients with small-size non-small cell lung cancer (NSCLC). This study aims to investigate clinicopathological characteristics associated with skip N2 (SN2) and non-skip N2 (NSN2) metastasis, and their metastatic patterns in NSCLC with tumor size of 1-2 cm. Methods: We reviewed the records of NSCLC patients with tumor size of 1-2 cm who underwent lobectomy with systematic lymph node dissection (LND) between January 2013 and June 2019. Clinical, radiographical, and pathological characteristics were compared among N1, SN2, and NSN2 groups. Metastatic patterns of mediastinal lymph node were analyzed based on final pathology. Results: A total of 63 NSCLC patients with tumor size of 1-2 cm were staged as pN2, including 25 (39.7%) SN2 and 38 (60.3%) NSN2. The incidence rates of SN2 and NSN2 were 2.8% (25/884) and 4.3% (38/884), respectively. For all clinicopathological characteristics, no significant difference was observed among the groups of N1, SN2, and NSN2. For the tumor located in each lobe, specific nodal drainage stations were identified: 2R/4R for right upper lobe; 2R/4R and subcarinal node (#7) for right middle lobe and right lower lobe; 4L and subaortic node (#5) for left upper lobe; #7 for left lower lobe. However, there were still a few patients (10.9%, 5/46) had the involvement of lower zone for tumors of upper lobe and the involvement of upper zone for lower lobe. Conclusions: SN2 occurs frequently in patients with small-size NSCLC. Whether lobe-specific selective LND is suitable for all small-size patients deserves more studies to confirm. Surgeons should be more careful when performing selective LND for tumors located in the lower and upper lobes.
| S-EPMC7536402 | biostudies-literature
Project description: Not available
| S-EPMC6467302 | biostudies-literature
Project description:BackgroundIntraoperative localisation of nodal disease in non-small cell lung cancer (NSCLC) can be challenging. Lymph node localisation via radiopharmaceuticals is used in many conditions; we tested the feasibility of this approach in NSCLC.MethodsNSCLC patients were prospectively recruited. Intraoperative peri-tumoral injections of [99mTc]Tc-albumin nanocolloids were performed, followed by removing the tumour and locoregional lymph nodes. These were examined ex vivo with a gamma probe and labelled sentinel lymph nodes (SLNs) if they showed any activity or non-sentinel lymph nodes (nSLNs) if they did not. Thereafter, the surgical field was scanned with the probe; any further radioactive lymph node was removed and labelled as "extra" SLNs (eSLNs). All specimens were sent to histology, and metastatic status was recorded.Results48 patients were enrolled, and 290 nodal stations were identified: 179 SLNs, 87 nSLNs, and 24 eSLNs. A total of 44 nodal metastases were identified in 22 patients, with 36 of them (82%) located within SLNs. Patients with nSLNs metastases had at least a co-existing positive SLN. No metastases were found in eSLNs.ConclusionsThe technique shows high sensitivity for intraoperative nodal metastases identification. This information could allow selective lymphadenectomies in low-risk patients or more aggressive approaches in high-risk patients.
| S-EPMC10341198 | biostudies-literature
Project description:ObjectiveThe objective of this study was to identify the risk factors that influence metastasis and prognosis in patients with nodular melanoma (NM), as well as to develop and validate a prognostic model using artificial intelligence (AI) algorithms.MethodsThe Surveillance, Epidemiology, and End Results (SEER) database was queried for 4,727 patients with NM based on the inclusion/exclusion criteria. Their clinicopathological characteristics were retrospectively reviewed, and logistic regression analysis was utilized to identify risk factors for metastasis. This was followed by employing Multilayer Perceptron (MLP), Adaptive Boosting (AB), Bagging (BAG), logistic regression (LR), Gradient Boosting Machine (GBM), and eXtreme Gradient Boosting (XGB) algorithms to develop metastasis models. The performance of the six models was evaluated and compared, leading to the selection and visualization of the optimal model. Through integrating the prognostic factors of Cox regression analysis with the optimal models, the prognostic prediction model was constructed, validated, and assessed.ResultsLogistic regression analyses identified that marital status, gender, primary site, surgery, radiation, chemotherapy, system management, and N stage were all independent risk factors for NM metastasis. MLP emerged as the optimal model among the six models (AUC = 0.932, F1 = 0.855, Accuracy = 0.856, Sensitivity = 0.878), and the corresponding network calculator (https://shimunana-nm-distant-m-nm-m-distant-8z8k54.streamlit.app/) was developed. The following were examined as independent prognostic factors: MLP, age, marital status, sequence number, laterality, surgery, radiation, chemotherapy, system management, T stage, and N stage. System management and surgery emerged as protective factors (HR < 1). To predict 1-, 3-, and 5-year overall survival (OS), a nomogram was created. The validation results demonstrated that the model exhibited good discrimination and consistency, as well as high clinical usefulness.ConclusionThe developed prediction model more effectively reflects the prognosis of patients with NM and differentiates between the risk level of patients, serving as a useful supplement to the classical American Joint Committee on Cancer (AJCC) staging system and offering a reference for clinically stratified individualized treatment and prognosis prediction. Furthermore, the model enables clinicians to quantify the risk of metastasis in NM patients, assess patient survival, and administer precise treatments.
| S-EPMC11305581 | biostudies-literature
Project description:BackgroundAccurate diagnosis of mediastinal lymph node (LN) metastases is very important for the treatment and prognosis in lung cancer patients. Spectral computed tomography (CT), as a non-invasive approach, has good prospects for detecting mediastinal nodal metastasis. However, the diagnostic criteria of differentiating metastatic and nonmetastatic LNs have not been determined.MethodsClinical and imaging data of 64 lung cancer patients (mean age 61.3±10.3 years, 41 men) from April to December 2019 were retrospectively analyzed. The unenhanced scan and contrast enhanced arterial phase (AP) and venous phase (VP) spectral CT scans were performed. The 70 keV monochromatic image and iodine-based image in all phases were analyzed to measure the parameters of LNs. LNs were divided into the metastatic and non-metastatic groups based on confirmative pathological results, and their differences were statistically analyzed. The receiver operating characteristics curve (ROC) was used to evaluate the efficacy of the differential diagnosis.ResultsSeventy-four metastatic LNs and 152 non-metastatic LNs were obtained. Compared with non-metastatic LNs, metastatic LNs often had a larger size (P<0.001). In the unenhanced scans, the density of metastatic LNs was lower than that of non-metastatic LNs (P<0.001); however, there was no difference in CT value in AP and VP between metastatic and non-metastatic LNs (P=0.07, P=0.08, respectively). A statistically significant difference was found in iodine concentration (IC), normalized iodine concentration (NIC) and slope of the spectral curve (λHU) in unenhanced scan, IC and λHU in AP, as well as IC, NIC and λHU in VP between metastatic and non-metastatic LNs. There was no difference in NIC in AP between them.ConclusionsCombined with morphology, spectral CT quantitative parameters demonstrate certain diagnostic efficiency for differential diagnosis between metastatic and non-metastatic LNs in lung cancer patients.
| S-EPMC8411177 | biostudies-literature
Project description:PurposeLymph nodes (LNs) in the chest have a tendency to enlarge due to various pathologies, such as lung cancer or pneumonia. Clinicians routinely measure nodal size to monitor disease progression, confirm metastatic cancer, and assess treatment response. However, variations in their shapes and appearances make it cumbersome to identify LNs, which reside outside of most organs.MethodsWe propose to segment LNs in the mediastinum by leveraging the anatomical priors of 28 different structures (e.g., lung, trachea etc.) generated by the public TotalSegmentator tool. The CT volumes from 89 patients available in the public NIH CT Lymph Node dataset were used to train three 3D off-the-shelf nnUNet models to segment LNs. The public St. Olavs dataset containing 15 patients (out-of-training-distribution) was used to evaluate the segmentation performance.ResultsFor LNs with short axis diameter ≥ 8 mm, the 3D cascade nnUNet model obtained the highest Dice score of 67.9 ± 23.4 and lowest Hausdorff distance error of 22.8 ± 20.2. For LNs of all sizes, the Dice score was 58.7 ± 21.3 and this represented a ≥ 10% improvement over a recently published approach evaluated on the same test dataset.ConclusionTo our knowledge, we are the first to harness 28 distinct anatomical priors to segment mediastinal LNs, and our work can be extended to other nodal zones in the body. The proposed method has the potential for improved patient outcomes through the identification of enlarged nodes in initial staging CT scans.
| S-EPMC11329534 | biostudies-literature
Project description:Lung cancer with mediastinal lymph node metastasis is more likely to develop recurrence and metastasis after complete resection and targeted therapy is a promising treatment strategy. We performed amplification refractory mutation system (ARMS) fluorescence quantitative PCR to detect the gene status of EGFR, ALK, ROS1 and RET in resected samples from 280 patients who were confirmed to have primary lung adenocarcinomas with N1-N2 lymph node metastasis. Of the 280 patients enrolled, the frequency of EGFR mutations, ALK fusions, ROS1 fusions, RET fusions and no mutations was 42.9%, 10.7%, 1.8%, 3.6% and 42.9%, respectively. Five patients exhibited the coexistence of the EGFR and ALK alterations. ALK, ROS1 and RET fusions were mutually exclusive. The frequency of EGFR mutation was significantly lower among patients with poor differentiation, while the rates of ALK and ROS1 fusions were the opposite. RET fusions also tended to be more prevalent in poorly differentiated patients. EGFR and ALK double positive tumors were characterized by significantly smaller size compared with those had single gene alteration. Our study comprehensively analyzed the distinct and common clinicopathologic characteristics according to genotypes of the cohort, which should help in categorizing patients for efficient screening.
| S-EPMC5325401 | biostudies-literature