Pleomorphic carcinoma of the lung: Prognostic models of semantic, radiomics and combined features from CT and PET/CT in 85 patients

Pulmonary pleomorphic carcinoma associated with cystic airspace and recurrent spontaneous pneumothorax: A case report

Pulmonary pleomorphic carcinoma (PPC), classified as the predominant subtype of pulmonary sarcomatoid carcinoma under the current World Health Organization (WHO) criteria, accounts for 0.1-0.4% of all non-small cell lung carcinoma cases and typically manifests radiologically as solid masses with peripheral infiltration. In the present report, a novel clinicopathological manifestation of PPC presenting as a primary solitary cystic airspace with recurrent spontaneous pneumothorax (SP), challenging conventional diagnostic paradigms, is described. A 66-year-old man with recurrent SP was initially misdiagnosed with pulmonary bullae based on the peripheral cystic airspaces observed on computed tomography. Persistent air leakage prompted video-assisted thoracoscopic wedge resection, which revealed biphasic histology: Malignant spindle cell proliferations (vimentin-positive) mixed with conventional adenocarcinoma components (transcription termination factor 1-positive/napsin A-positive), consistent with the WHO 2021 diagnostic criteria for PPC. The patient reached sustained remission without adjuvant therapy, and disease-free survival was maintained for 29 months. The present case highlights three critical implications: First, primary cystic airspaces represent a rare but clinically significant radiological phenotype of PPC that mimic benign bullous lesions, particularly when obscured by pneumothorax; second, recurrent SP may serve as the initial manifestation of occult pulmonary malignancy, necessitating rigorous evaluation of cystic lung lesions; third, early surgical intervention offers dual diagnostic and therapeutic value, even in patients with compromised pulmonary function. These findings expand the recognized spectrum of the imaging heterogeneity of PPC and underscore the need for heightened clinical suspicion of cystic lung cancer in high-risk populations.

Non-invasive, fast, and high-performance EGFR gene mutation prediction method based on deep transfer learning and model stacking for patients with Non-Small Cell Lung Cancer

Purpose

To propose an intelligent, non-invasive, highly precise, and rapid method to predict the mutation status of the Epidermal Growth Factor Receptor (EGFR) to accelerate treatment with Tyrosine Kinase Inhibitor (TKI) for patients with untreated adenocarcinoma Non-Small Cell Lung Cancer.

Materials and methods

Real-world data from 521 patients with adenocarcinoma NSCLC who performed a CT scan and underwent surgery or pathological biopsy to determine EGFR gene mutation between January 2021 and July 2022, is collected. Solutions to the problems that prevent the model from achieving very high precision, namely: human errors made during the annotation of the database and the low precision of the output decision of the model, are proposed. Thus, among the 521 analyzed cases, only 40 were selected as patients with EGFR gene mutation and 98 cases with wild-type EGFR.

Results

The proposed model is trained, validated, and tested on 12,040 2D images extracted from the 138 CT scans images where patients were randomly partitioned into training (80 %) and test (20 %) sets. The performance obtained for EGFR gene mutation prediction was 95.22 % for accuracy, 960.2 for F1_score, 95.89 % for precision, 96.92 % for sensitivity, 94.01 % for Cohen kappa, and 98 % for AUC.

Conclusion

An EGFR gene mutation status prediction method, with high-performance thanks to an intelligent prediction model entrained by highly accurate annotated data is proposed. The outcome of this project will facilitate rapid decision-making when applying a TKI as an initial treatment.

Case report: Long remission and survival following immunotherapy in a case of pulmonary pleomorphic carcinoma

In 2020, we reported on a case involving a 68-year-old male patient with a rare instance of pulmonary pleomorphic carcinoma exhibiting high PD-L1 expression. The patient experienced significant therapeutic success with the use of pembrolizumab, achieving partial tumor remission. Following the publication of that report, the patient continued on pembrolizumab at a dose of 200 mg/dl for 27 cycles, subsequently transitioning to a combination of pembrolizumab and bevacizumab for eight cycles. Due to elevated blood pressure, the regimen was adjusted back to monotherapy with pembrolizumab. As of July 9, 2024, the patient remains alive with a satisfactory quality of life. This follow-up report, coupled with a review of the literature from 2021 to 2024 on pulmonary pleomorphic carcinoma and its immunotherapeutic approaches, aims to present new insights and innovative strategies for treating this rare form of cancer.

Prognostic Factors among Patients with Resected Non-Adenocarcinoma of the Lung

INTRODUCTION

Few studies have investigated the prognostic factors for non-adenocarcinoma of the lung. We retrospectively evaluated the prognostic factors on the basis of histological type of non-adenocarcinoma of the lung treated by pulmonary resection.

METHODS

We enrolled 266 patients with non-adenocarcinoma of the lung in this retrospective study: 196 with squamous cell carcinoma (SCC) and 70 with non-SCC.

RESULTS

Relapse-free survival (RFS) did not differ significantly between SCC and non-SCC patients (p = 0.33). For SCC patients, RFS differed significantly between patients who underwent wedge resection and non-wedge resection (p < 0.01) and between patients with Clavien-Dindo grade ≥3a and 0-2 postoperative complications (p < 0.01). For non-SCC patients, RFS rates were significantly different in the groups divided at neutrophil-to-lymphocyte ratio = 2.40 (p = 0.02), maximum standardized uptake value (SUVmax) = 8.39 (p < 0.01), between patients with pathological stage (pStage) 0-I and with pStage more than II (p < 0.01). For SCC patients, male sex (p = 0.04), wedge resection (p = 0.01), and Clavien-Dindo grade ≥3a (p = 0.02) were significant factors for RFS in multivariate analysis. For non-SCC patients, neutrophil-to-lymphocyte ratio >2.40 (p < 0.01), SUVmax >8.39 (p = 0.01), and pStage ≥II (p = 0.03) were significant factors for RFS in multivariate analysis.

CONCLUSION

RFS did not differ significantly differently between SCC and non-SCC patients. It is necessary to perform more than segmentectomy and to avoid severe postoperative complications for SCC patients. SUVmax might be an adaptation criterion of adjuvant chemotherapy for patients with non-adenocarcinoma and non-SCC of the lung.

Radiomics in Oncological PET Imaging: A Systematic Review-Part 1, Supradiaphragmatic Cancers

Radiomics is an upcoming field in nuclear oncology, both promising and technically challenging. To summarize the already undertaken work on supradiaphragmatic neoplasia and assess its quality, we performed a literature search in the PubMed database up to 18 February 2022. Inclusion criteria were: studies based on human data; at least one specified tumor type; supradiaphragmatic malignancy; performing radiomics on PET imaging. Exclusion criteria were: studies only based on phantom or animal data; technical articles without a clinically oriented question; fewer than 30 patients in the training cohort. A review database containing PMID, year of publication, cancer type, and quality criteria (number of patients, retrospective or prospective nature, independent validation cohort) was constructed. A total of 220 studies met the inclusion criteria. Among them, 119 (54.1%) studies included more than 100 patients, 21 studies (9.5%) were based on prospectively acquired data, and 91 (41.4%) used an independent validation set. Most studies focused on prognostic and treatment response objectives. Because the textural parameters and methods employed are very different from one article to another, it is complicated to aggregate and compare articles. New contributions and radiomics guidelines tend to help improving quality of the reported studies over the years.

The Challenge of Choosing the Best Classification Method in Radiomic Analyses: Recommendations and Applications to Lung Cancer CT Images

Radiomics uses high-dimensional sets of imaging features to predict biological characteristics of tumors and clinical outcomes. The choice of the algorithm used to analyze radiomic features and perform predictions has a high impact on the results, thus the identification of adequate machine learning methods for radiomic applications is crucial. In this study we aim to identify suitable approaches of analysis for radiomic-based binary predictions, according to sample size, outcome balancing and the features-outcome association strength. Simulated data were obtained reproducing the correlation structure among 168 radiomic features extracted from Computed Tomography images of 270 Non-Small-Cell Lung Cancer (NSCLC) patients and the associated to lymph node status. Performances of six classifiers combined with six feature selection (FS) methods were assessed on the simulated data using AUC (Area Under the Receiver Operating Characteristics Curves), sensitivity, and specificity. For all the FS methods and regardless of the association strength, the tree-based classifiers Random Forest and Extreme Gradient Boosting obtained good performances (AUC ≥ 0.73), showing the best trade-off between sensitivity and specificity. On small samples, performances were generally lower than in large-medium samples and with larger variations. FS methods generally did not improve performances. Thus, in radiomic studies, we suggest evaluating the choice of FS and classifiers, considering specific sample size, balancing, and association strength.