RESUMEN
PURPOSE: This study proposed a three-dimensional (3D) multi-modal learning-based model for the automated prediction and classification of lymph node metastasis in patients with non-small cell lung cancer (NSCLC) using computed tomography (CT) images and clinical information. METHODS: We utilized clinical information and CT image data from 4239 patients with NSCLC across multiple institutions. Four deep learning algorithm-based multi-modal models were constructed and evaluated for lymph node classification. To further enhance classification performance, a soft-voting ensemble technique was applied to integrate the outcomes of multiple multi-modal models. RESULTS: A comparison of the classification performance revealed that the multi-modal model, which integrated CT images and clinical information, outperformed the single-modal models. Among the four multi-modal models, the Xception model demonstrated the highest classification performance, with an area under the curve (AUC) of 0.756 for the internal test dataset and 0.736 for the external validation dataset. The ensemble model (SEResNet50_DenseNet121_Xception) exhibited even better performance, with an AUC of 0.762 for the internal test dataset and 0.751 for the external validation dataset, surpassing the multi-modal model's performance. CONCLUSIONS: Integrating CT images and clinical information improved the performance of the lymph node metastasis prediction models in patients with NSCLC. The proposed 3D multi-modal lymph node prediction model can serve as an auxiliary tool for evaluating lymph node metastasis in patients with non-pretreated NSCLC, aiding in patient screening and treatment planning.
RESUMEN
Background: Epithelioid hemangioendothelioma (EHE) is a rare vascular tumor with limited clinical data that can guide treatment choices. The diagnosis of EHE is based on its unique histological, immunohistochemical, and molecular characteristics. Differential diagnoses are broad and include autoimmune diseases. Treatments include hepatic resection, liver transplantation, systemic/regional chemotherapy, and radiotherapy. Case Description: We describe EHE in a patient with weight loss and general weakness. The prognosis of EHE is variable, with few cases demonstrating an indolent clinical course, whereas others tend to metastasize. In our case, hepatic EHE had metastasized to the lungs and brain. Histopathological examination of the liver tissue revealed an epithelial hemangioendothelioma. On CK7 staining, hepatocytes were clearly reactive and arranged in the plates (CK7: negative), with positive immunohistochemical staining for CD34 (CD34: positive) alone. Surveillance was conducted and the clinical course was better than expected, probably due to her relatively good general condition, the lack of genetic factors associated with her familial medical history, and normal levels of tumor markers such as α-fetoprotein and carcinoembryonic antigen (CEA). During a follow-up examination, she was asymptomatic with a healthy general appearance. Conclusions: The prognosis of EHE is variable, with few cases demonstrating an indolent clinical course, whereas others tend to metastasize. The treatment method for EHE should be determined according to the patient's condition.
RESUMEN
OBJECTIVES: To estimate the pooled prevalence and progression rate of ILAs and identify the risk factors for radiological progression. MATERIALS AND METHODS: An EMBASE and PubMed search was undertaken, identifying all studies meeting the inclusion criteria performed before May 10, 2023. Random effect models were used to estimate pooled prevalence, ILA progression rates, and odds ratio for radiological progression based on radiological subtype. Subgroup analyses were performed to compare the general and high-risk populations for lung cancer. The quality of the included studies was evaluated using the risk of bias assessment tool for non-randomized studies. RESULTS: We analyzed 19 studies (241,541 patients) and 10 studies (1317 patients) for the pooled prevalence and progression rate of ILA, respectively. The pooled ILA prevalence was 9.7% (95% CI, 6.1-13.9%). The pooled prevalence was 6.8% (95% CI, 3.1-11.6%) and 7.1% (95% CI, 2.2-14.4%) in the general (six studies) and high-risk population for lung cancer (six studies), respectively. The pooled progression rate was 47.1% (95% CI, 29.1-65.5%). The pooled progression rate was 64.2% (95% CI, 45.0-81.2%, five studies) and 31.0% (95% CI, 8.2-60.5%, five studies) for longer (≥ 4.5 years) and shorter follow-up periods (< 4.5 years), respectively (p = 0.009). Fibrotic ILAs were significantly associated with a higher progression probability (combined OR, 5.55; 95% CI, 1.95-15.82). CONCLUSIONS: The prevalence of ILAs was approximately 9.7%. Approximately half of the patients exhibited radiological progression, with the rate increasing over a longer follow-up period. Fibrotic ILA was a significant risk factor for radiological progression. CLINICAL RELEVANCE STATEMENT: The prevalence of interstitial lung abnormalities (ILAs) is approximately 9.7%, with about half exhibiting progression; a longer follow-up duration and fibrotic ILAs are associated with a higher progression rate. KEY POINTS: ILAs are increasingly recognized as important, but few population data are available. ILAs exhibited a pooled prevalence of 9.7% with a progression rate of 47.1%. Fibrotic ILAs were associated with increased progression likelihood.
RESUMEN
This study focused on a novel strategy that combines deep learning and radiomics to predict epidermal growth factor receptor (EGFR) mutations in patients with non-small cell lung cancer (NSCLC) using computed tomography (CT). A total of 1280 patients with NSCLC who underwent contrast-enhanced CT scans and EGFR mutation testing before treatment were selected for the final study. Regions of interest were segmented from the CT images to extract radiomics features and obtain tumor images. These tumor images were input into a convolutional neural network model to extract 512 image features, which were combined with radiographic features and clinical data to predict the EGFR mutation. The generalization performance of the model was evaluated using external institutional data. The internal and external datasets contained 324 and 130 EGFR mutants, respectively. Sex, height, weight, smoking history, and clinical stage were significantly different between the EGFR-mutant patient groups. The EGFR mutations were predicted by combining the radiomics and clinical features, and an external validation dataset yielded an area under the curve (AUC) value of 0.7038. The model utilized 1280 tumor images, radiomics features, and clinical characteristics as input data and exhibited an AUC of approximately 0.81 and 0.78 during the primary cohort and external validation, respectively. These results indicate the feasibility of integrating radiomics analysis with deep learning for predicting EGFR mutations. CT-image-based genetic testing is a simple EGFR mutation prediction method, which can improve the prognosis of NSCLC patients and help establish personalized treatment strategies.