Preoperative CT findings and prognosis of pulmonary sarcomatoid carcinoma: comparison with conventional NSCLC of similar tumor size

Tang, Wenjian; Wen, Chunju; Pei, Yixiu; Zhang, Wu; Zhong, Junyuan; Peng, Jidong; Zhong, Jianping

doi:10.1186/s12880-023-01065-8

Cited by 3 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conventional imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET) provide insights into tumor extent, lymph node involvement, and distant metastases. However, the radiological features of PSC are not entirely specific and can resemble other subtypes of NSCLC or even benign entities (9). Therefore, a comprehensive pathological assessment is necessary for a definitive diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Computed Tomography-Based Radiomics Analysis of Different Machine Learning Approaches for Differentiating Pulmonary Sarcomatoid Carcinoma and Pulmonary Inflammatory Pseudotumor

Zhang,

Fu,

2024

I J Radiol

View full text Add to dashboard Cite

Background: Differentiating between pulmonary sarcomatoid carcinoma (PSC) and pulmonary inflammatory pseudotumor (PIP) is challenging using current conventional diagnostic methods. This lack of distinction significantly impacts subsequent clinical treatment decisions. Objectives: This study was conducted to construct an effective method to distinguish between PSC and PIP based on commonly used computed tomography (CT) images. Patients and Methods: A total of 14 patients with PSC and 76 patients with PIP were retrospectively included in the study for CT imaging. Radiomics features were extracted from non-enhanced CT images, and canonical correlation analysis was performed to reduce redundancy. The final radiomics signature was then identified using the least absolute shrinkage and selection operator (LASSO). Logistic regression (LR), classification and regression trees (CART), support vector machine (SVM), k-nearest neighbors (KNN), and gradient boosting machine (GBM) were used to construct the radiomics models. The performance of these different radiomics models was evaluated using the receiver operating characteristic curve. Results: A total of 1186 radiomics features were extracted from non-enhanced CT images. After dimensionality reduction and selection, 7 valuable features were identified. The performance of 5 machine learning models was evaluated to differentiate between PSC and PIP, and the GBM-based radiomics model demonstrated the best performance. The GBM-based radiomics model achieved an accuracy of 0.922, area under the curve (AUC) of 0.98, F1 score of 0.967, and log loss of 0.161. Compared to conventional clinical-radiological diagnosis, the GBM-based radiomics model showed a significant association (odds ratio [OR] = 8.119; P = 0.006). Conclusion: The implementation of the GBM-based radiomics model has the potential to improve the ability to differentiate between PSC and PIP, thereby influencing the timeliness of subsequent surgical interventions and even the prognosis of patients.

show abstract

Section: Introductionmentioning

confidence: 99%

Computed Tomography-Based Radiomics Analysis of Different Machine Learning Approaches for Differentiating Pulmonary Sarcomatoid Carcinoma and Pulmonary Inflammatory Pseudotumor

Zhang,

Fu,

2024

I J Radiol

View full text Add to dashboard Cite

show abstract

Sotorasib in KRAS p.G12C-Mutated Pulmonary Sarcomatoid Carcinoma: Therapeutic Efficacy of a KRAS Inhibitor in Symptomatic Brain Metastases

Schmidt,

Entz,

Brasch

et al. 2024

Case Rep Oncol

View full text Add to dashboard Cite

Introduction: Pulmonary sarcomatoid carcinomas (PSCs) are a rare subgroup of non-small cell lung cancer (NSCLC). In contrast to other NSCLCs, PSCs have a poor prognosis due to limited efficacy of radiation and chemotherapy. Therefore, other therapeutic approaches are needed. KRAS mutations occur in PSC with a significant proportion of 30%, and most of them are G12C with the therapeutic option of sotorasib. Case Report: Here, we describe the case of a patient with PSC and pleural metastases. After first-line chemotherapy, the patient presented with new neurological symptoms such as a hemiparesis of the right arm and focal seizures. Following the detection of new brain metastases, we switched the therapy to sotorasib due to the presence of a KRAS G12C mutation. During treatment with sotorasib, the patient’s condition worsened progressively and his neurological symptoms got more severe. A CCT performed during the course of treatment showed progression of the brain metastases. After 48 days being on drug, decision to discontinuate therapy with sotorasib due to patient’s inability to take oral medication and change to a best supportive care concept was made. The patient died few weeks after termination of therapy with rapidly progressive disease. Discussion/Conclusion: This case emphasizes the poor prognosis of patients with PSC due to a lack of therapeutic response to chemotherapy, radiation, and, as seen in this case, current targeted therapy as well. Our case emphasizes the need to further evaluate therapeutic responses of targeted therapy in this rare subtype of NSCLC.

show abstract

Clinicoradiological findings associated with prognostic indicators of sarcomatoid-NSCLC: A multicenter analysis of 135 patients

Tang,

Yin,

Wen

et al. 2024

Preprint

View full text Add to dashboard Cite

Purpose: To assess clinical data and preoperative CT findings associated with prognosis in sarcomatoid-NSCLC (s-NSCLC) patients. Material and Methods: In this retrospective study, s-NSCLC patients who underwent contrast enhanced thoracic CT or PET/CT from January 2013 to June 2023 at three centers were enrolled. Clinicoradiological data, including sex, age, smoking history, TNM classification, tumor size, tumor location, calcification, vacuole/cavity, pleural invasion, low-attenuation area (LAA) ratio, hydrothorax, peritumoral ground-glass opacity (GGO), nodule or atelectasis and SUVmax were calculated. Clinicoradiological findings associated with overall survival were evaluated by a multivariate Cox regression model. Results: A total of 135 with s-NSCLC were included. The s-NSCLC patients were more likely to be elderly male smokers. The mean age and tumor size at diagnosis was 62 years and 5.8 cm. The median survival time of patients with s-NSCLC was 9 (95% CI: 7, 11) months. The 1-, 3- and 5-year overall survival (OS) rates of the s-NSCLC patients were 28.9%, 11.9% and 5.9%, respectively. s-NSCLC is often peripherally locate (98/135, 70.4%). Calcification (19/135, 14.1%) and Vacuole/cavity (22/135, 16.2%) were rare in s-NSCLC lesions. Pleural invasion and hydrothorax was present in 75/135 (55.6%) and 36/135 (26.7%) of s-NSCLC patients. The s-NSCLC lesions usually present with LAA (87/135, 80.6%), the median LAA ratio was 30.8% (IQR: 10.6%, 50.7%). The SUVmax of s-NSCLC lesions were 20.2 (IQR: 14.0, 23.9). Surgical treatment [hazard ratio (HR) = 0.518] was associated with decreased mortality, while peritumoral GGO, nodule or atelectasis (HR = 1.995) were associated with increased mortality. Conclusions: Peritumoral GGO, nodule or atelectasis is an independent risk indicator associated with poor prognosis, while complete surgical resection is essential for improving the prognosis in s-NSCLC patients.

show abstract

Preoperative CT findings and prognosis of pulmonary sarcomatoid carcinoma: comparison with conventional NSCLC of similar tumor size

Cited by 3 publications

References 22 publications

Computed Tomography-Based Radiomics Analysis of Different Machine Learning Approaches for Differentiating Pulmonary Sarcomatoid Carcinoma and Pulmonary Inflammatory Pseudotumor

Computed Tomography-Based Radiomics Analysis of Different Machine Learning Approaches for Differentiating Pulmonary Sarcomatoid Carcinoma and Pulmonary Inflammatory Pseudotumor

Sotorasib in KRAS p.G12C-Mutated Pulmonary Sarcomatoid Carcinoma: Therapeutic Efficacy of a KRAS Inhibitor in Symptomatic Brain Metastases

Clinicoradiological findings associated with prognostic indicators of sarcomatoid-NSCLC: A multicenter analysis of 135 patients

Contact Info

Product

Resources

About