[Advanced Pneumonic-type Lung Carcinoma: A Retrospective Study of Clinical-radiological-pathological Characteristics with Survival Analysis in A Single Chinese Hospital]

Pulmonary invasive mucinous adenocarcinoma mimicking pulmonary actinomycosis

Background

Primary pulmonary invasive mucinous adenocarcinoma is a rare and distinct subtype of lung adenocarcinoma.

Case presentation

A 72-year-old woman presented with productive cough for two months and fever for six days. Chest computed tomography (CT) showed a mass in the left lower lobe. Sputum culture tested negative for bacteria, but the sequence of Actinomyces meyeri was detected by metagenomic next generation sequencing from the bronchoalveolar lavage fluid. It was considered a pathogenic bacterium as the normalized number of DNA sequencing reads was 10 times higher than the normal level. The patient’s symptoms alleviated quickly, and the chest CT lesion shrank to a third of the original size following treatment with penicillin for two months. However, a repeat chest CT performed after four months of treatment revealed that the lesion had expanded. Positron emission tomography/CT revealed that fluorodeoxyglucose metabolism was increased in the mass with surrounding ground glass density of the left lower lobe. Furthermore, CT-guided percutaneous lung biopsy was performed, and hematoxylin–eosin staining showed columnar tumor cells with abundant mucin in the cytoplasm with a basal nucleus. Finally, the patient was diagnosed with pulmonary invasive mucinous adenocarcinoma and agreed to undergo a thoracoscopic surgery.

Conclusions

Pulmonary invasive mucinous adenocarcinoma is a subset of lung adenocarcinoma with low incidence rate. The clinical features and CT findings are non-specific. A histopathological diagnosis is of fundamental importance in preventing misdiagnosis.

A Practical Deep Learning Model in Differentiating Pneumonia-Type Lung Carcinoma from Pneumonia on CT Images: ResNet Added with Attention Mechanism

Objective

We aim to develop a deep neural network model to differentiate pneumonia-type lung carcinoma from pneumonia based on chest CT scanning and evaluate its performance.

Materials and Methods

We retrospectively analyzed 131 patients diagnosed with pneumonia-type lung carcinoma and 171 patients with pneumonia treated in Beijing Hospital from October 2019 to February 2021. The average age was 68 (±15) years old, and the proportion of men (162/302) was slightly more than that of women (140/302). In this study, a deep learning based model UNet was applied to extract lesion areas from chest CT images. Lesion areas were extracted and classified by a designed spatial attention mechanism network. The model AUC and diagnostic accuracy were analyzed based on the results of the model. We analyzed the accuracy rate, sensitivity, and specificity and compared the results of the model to the junior and senior radiologists and radiologists based on the model.

Results

The model has a good efficiency in detecting pneumonia-like lesions (6.31 seconds/case). The model accuracy rate, sensitivity, and specificity were 74.20%, 60.37%, and 89.36%, respectively. The junior radiologist's accuracy rate, sensitivity, and specificity were 61.00%, 48.08%, and 75.00%, respectively. The senior radiologist's accuracy rate, sensitivity, and specificity were 65.00%, 51.92%, and 79.17%, respectively. The results of junior radiologists based on the model were improved (76.00% for accuracy rate, 62.75% for sensitivity, and 89.80% for specificity). The results of senior radiologists based on the model were also improved (78.00% for accuracy rate, 64.71% for sensitivity, and 91.84% for specificity) and the diagnostic accuracy of which was statistically higher than other groups (P < 0.05). Based on the lesion texture diversity and the lesion boundary ambiguity, the algorithm produced false-positive samples (13.51%).

Conclusion

This deep learning model could detect pneumonia-type lung carcinoma and differentiate it from pneumonia accurately and efficiently.

Pneumonic-type lung adenocarcinoma with different ranges exhibiting different clinical, imaging, and pathological characteristics

Background

Pneumonic-type lung adenocarcinoma (PLADC) with different ranges might exhibit different imaging and clinicopathological features. This study divided PLADC into localized PLADC (L-PLADC) and diffuse PLADC (D-PLADC) based on imaging and aimed to clarify the differences in clinical, imaging, and pathologic characteristics between the two new subtypes.

Results

The data of 131 patients with L-PLADC and 117 patients with D-PLADC who were pathologically confirmed and underwent chest computed tomography (CT) at our institute from December 2014 to December 2020 were retrospectively collected. Patients with L-PLADC were predominantly female, non-smokers, and without respiratory symptoms and elevated white blood cell count and C-reactive protein level, whereas those with D-PLADC were predominantly male, smokers, and had respiratory symptoms and elevated white blood cell count and C-reactive protein level (all p < 0.05). Pleural retraction was more common in L-PLADC, whereas interlobular fissure bulging, hypodense sign, air space, CT angiogram sign, coexisting nodules, pleural effusion, and lymphadenopathy were more frequent in D-PLADC (all p < 0.001). Among the 129 patients with surgically resected PLADC, the most common histological subtype of L-PLADC was acinar-predominant growth pattern (76.7%, 79/103), whereas that of D-PLADC was invasive mucinous adenocarcinoma (80.8%, 21/26). Among the 136 patients with EGFR mutation status, L-PLADC had a significantly higher EGFR mutation rate than D-PLADC (p < 0.001).

Conclusions

L-PLADC and D-PLADC have different clinical, imaging, and pathological characteristics. This new imaging-based classification may help improve our understanding of PLADC and develop personalized treatment plans, with concomitant implications for patient outcomes.