Pulmonary Foreign Body Granulomatosis after Cosmetic Injection.

INTRODUCTION: We occasionally encounter irregular marginated masses discovered incidentally in young individuals. In most cases, further investigations are conducted to assess the presence of a primary malignancy, as these masses often raise suspicions of malignancy. However, rare exceptional cases leave us perplexed. Granulomas arising from common lung infections and those induced by foreign substances can often pose challenge in distinguishing them from lung cancer. Therefore, we aimed to present a case of multiple pulmonary granulomatosis following cosmetic procedure. CASE PRESENTATION: A 55-year-old woman visited the hospital after an incidental discovery of an abnormal chest radiograph during a routine health check-up. Subsequent computed tomography (CT) scans showed worrisome lung nodules, leading to biopsies and positron emission tomography CT scans. Histological examination of the biopsied specimens revealed a chronic inflammatory reaction surrounded by multinucleated foreign body giant cells. Upon sharing the biopsy results with the patient and conducting additional history-taking, she had undergone various cosmetic procedures (botox injection, dermal filler treatments, and thread lifts) around the face and neck, approximately 5-6 months ago. It was hypothesized that these cosmetic materials might have led to the observed pulmonary granulomatosis. After 3 months of conservative care, a follow-up CT showed no change in the lesions. CONCLUSION: We present this case to underscore the importance of considering pulmonary foreign body granulomatosis as a potential differential diagnosis, especially when it closely resembles lung cancer, particularly following cosmetic injections.

A Challenge for Emphysema Quantification Using a Deep Learning Algorithm With Low-dose Chest Computed Tomography.

PURPOSE: We aimed to identify clinically relevant deep learning algorithms for emphysema quantification using low-dose chest computed tomography (LDCT) through an invitation-based competition. MATERIALS AND METHODS: The Korean Society of Imaging Informatics in Medicine (KSIIM) organized a challenge for emphysema quantification between November 24, 2020 and January 26, 2021. Seven invited research teams participated in this challenge. In total, 558 pairs of computed tomography (CT) scans (468 pairs for the training set, and 90 pairs for the test set) from 9 hospitals were collected retrospectively or prospectively. CT acquisition followed the hospitals' protocols to reflect the real-world clinical setting. Using the training set, each team developed an algorithm that generated converted LDCT by changing the pixel values of LDCT to simulate those of standard-dose CT (SDCT). The agreement between SDCT and LDCT was evaluated using the intraclass correlation coefficient (ICC; 2-way random effects, absolute agreement, and single rater) for the percentage of low-attenuated area below -950 HU (LAA-950 HU), κ value for emphysema categorization (LAA-950 HU, <5%, 5% to 10%, and ≥10%) and cosine similarity of LAA-950 HU. RESULTS: The mean LAA-950 HU of the test set was 14.2%±10.5% for SDCT, 25.4%±10.2% for unconverted LDCT, and 12.9%±10.4%, 11.7%±10.8%, and 12.4%±10.5% for converted LDCT (top 3 teams). The agreement between the SDCT and converted LDCT of the first-place team was 0.94 (95% confidence interval: 0.90, 0.97) for ICC, 0.71 (95% confidence interval: 0.58, 0.84) for categorical agreement, and 0.97 (interquartile range: 0.94 to 0.99) for cosine similarity. CONCLUSIONS: Emphysema quantification with LDCT was feasible through deep learning-based CT conversion strategies.

Tracheobronchopathia Osteochondroplastica Associated with Fibrotic Interstitial Lung Disease.

Tracheobronchopathia osteochondroplastica (TPO) is a very rare, benign disorder involving the lumen of the trachea-bronchial tree. However, its etiology is unknown. In our first case, observation for several years showed that TPO worsened as interstitial lung disease was aggravated. In the second case, the lung parenchymal lesion on computed tomography (CT) was found to be compatible with interstitial lung abnormality (ILA). We believe that our cases suggest a common pathogenetic relationship between TPO and fibrotic interstitial lung disease. TGF-ß is likely a common factor in the pathogenesis of TPO and fibrotic interstitial lung disease.

DeepCUBIT: Predicting Lymphovascular Invasion or Pathological Lymph Node Involvement of Clinical T1 Stage Non-Small Cell Lung Cancer on Chest CT Scan Using Deep Cubical Nodule Transfer Learning Algorithm.

The prediction of lymphovascular invasion (LVI) or pathological nodal involvement of tumor cells is critical for successful treatment in early stage non-small cell lung cancer (NSCLC). We developed and validated a Deep Cubical Nodule Transfer Learning Algorithm (DeepCUBIT) using transfer learning and 3D Convolutional Neural Network (CNN) to predict LVI or pathological nodal involvement on chest CT images. A total of 695 preoperative CT images of resected NSCLC with tumor size of less than or equal to 3 cm from 2008 to 2015 were used to train and validate the DeepCUBIT model using five-fold cross-validation method. We also used tumor size and consolidation to tumor ratio (C/T ratio) to build a support vector machine (SVM) classifier. Two-hundred and fifty-four out of 695 samples (36.5%) had LVI or nodal involvement. An integrated model (3D CNN + Tumor size + C/T ratio) showed sensitivity of 31.8%, specificity of 89.8%, accuracy of 76.4%, and AUC of 0.759 on external validation cohort. Three single SVM models, using 3D CNN (DeepCUBIT), tumor size or C/T ratio, showed AUCs of 0.717, 0.630 and 0.683, respectively on external validation cohort. DeepCUBIT showed the best single model compared to the models using only C/T ratio or tumor size. In addition, the DeepCUBIT model could significantly identify the prognosis of resected NSCLC patients even in stage I. DeepCUBIT using transfer learning and 3D CNN can accurately predict LVI or nodal involvement in cT1 size NSCLC on CT images. Thus, it can provide a more accurate selection of candidates who will benefit from limited surgery without increasing the risk of recurrence.

Effectiveness of radiologist training in improving reader agreement for Lung-RADS 4X categorization.

OBJECTIVES: To identify the agreement on Lung CT Screening Reporting and Data System 4X categorization between radiologists and an expert-adjudicated reference standard and to investigate whether training led to improvement of the agreement measures and diagnostic potential for lung cancer. METHODS: Category 4 nodules in the Korean Lung Cancer Screening Project were identified retrospectively, and each 4X nodule was matched with one 4A or 4B nodule. An expert panel re-evaluated the categories and determined the reference standard. Nineteen radiologists were asked to determine the presence of CT features of malignancy and 4X categorization for each nodule. A review was performed in two sessions, and training material was given after session 1. Agreement on 4X categorization between radiologists and the expert-adjudicated reference standard and agreement between radiologist-assessed 4X categorization and lung cancer diagnosis were evaluated. RESULTS: The 48 expert-adjudicated 4X nodules and 64 non-4X nodules were evenly distributed in each session. The proportion of category 4X decreased after training (56.4% ± 16.9% vs. 33.4% ± 8.0%; p < 0.001). Cohen's κ indicated poor agreement (0.39 ± 0.16) in session 1, but agreement improved in session 2 (0.47 ± 0.09; p = 0.03). The increase in agreement in session 2 was observed among inexperienced radiologists (p < 0.05), and experienced and inexperienced reviewers exhibited comparable agreement performance in session 2 (p > 0.05). All agreement measures between radiologist-assessed 4X categorization and lung cancer diagnosis increased in session 2 (p < 0.05). CONCLUSION: Radiologist training can improve reader agreement on 4X categorization, leading to enhanced diagnostic performance for lung cancer. KEY POINTS: • Agreement on 4X categorization between radiologists and an expert-adjudicated reference standard was initially poor, but improved significantly after training. • The mean proportion of 4X categorization by 19 radiologists decreased from 56.4% ± 16.9% in session 1 to 33.4% ± 8.0% in session 2. • All agreement measures between the 4X categorization and lung cancer diagnosis increased significantly in session 2, implying that appropriate training and guidance increased the diagnostic potential of category 4X.

The implications of clinical risk factors, CAR index, and compositional changes of immune cells on hyperprogressive disease in non-small cell lung cancer patients receiving immunotherapy.

BACKGROUND: Immune checkpoint blockades (ICBs) are characterized by a durable clinical response and better tolerability in patients with a variety of advanced solid tumors. However, we not infrequently encounter patients with hyperprogressive disease (HPD) exhibiting paradoxically accelerated tumor growth with poor clinical outcomes. This study aimed to investigate implications of clinical factors and immune cell composition on different tumor responses to immunotherapy in patients with non-small cell lung cancer (NSCLC). METHODS: This study evaluated 231 NSCLC patients receiving ICBs between January 2014 and May 2018. HPD was defined as a > 2-fold tumor growth kinetics ratio during ICB therapy and time-to-treatment failure of ≤2 months. We analyzed clinical data, imaging studies, periodic serologic indexes, and immune cell compositions in tumors and stromata using multiplex immunohistochemistry. RESULTS: Of 231 NSCLC patients, PR/CR and SD were observed in 50 (21.6%) and 79 (34.2%) patients, respectively and 26 (11.3%) patients met the criteria for HPD. Median overall survival in poor response groups (HPD and non-HPD PD) was extremely shorter than disease-controlled group (SD and PR/CR) (5.5 and 6.1 months vs. 16.2 and 18.3 months, respectively, P = 0.000). In multivariate analysis, HPD were significantly associated with heavy smoker (p = 0.0072), PD-L1 expression ≤1% (p = 0.0355), and number of metastatic site ≥3 (p = 0.0297). Among the serologic indexes including NLR, PLR, CAR, and LDH, only CAR had constantly significant correlations with HPD at the beginning of prior treatment and immunotherapy, and at the 1st tumor assessment. The number of CD4+ effector T cells and CD8+ cytotoxic T cells, and CD8+/PD-1+ tumor-infiltrating lymphocytes (TIL) tended to be smaller, especially in stromata of HPD group. More M2-type macrophages expressing CD14, CD68 and CD163 in the stromal area and markedly fewer CD56+ NK cells in the intratumoral area were observed in HPD group. CONCLUSIONS: Our study suggests that not only clinical factors including heavy smoker, very low PD-L1 expression, multiple metastasis, and CAR index, but also fewer CD8+/PD-1+ TIL and more M2 macrophages in the tumor microenvironment are significantly associated with the occurrence of HPD in the patients with advanced/metastatic NSCLC receiving immunotherapy.

DeepBTS: Prediction of Recurrence-free Survival of Non-small Cell Lung Cancer Using a Time-binned Deep Neural Network.

Accurate prediction of non-small cell lung cancer (NSCLC) prognosis after surgery remains challenging. The Cox proportional hazard (PH) model is widely used, however, there are some limitations associated with it. In this study, we developed novel neural network models called binned time survival analysis (DeepBTS) models using 30 clinico-pathological features of surgically resected NSCLC patients (training cohort, n = 1,022; external validation cohort, n = 298). We employed the root-mean-square error (in the supervised learning model, s- DeepBTS) or negative log-likelihood (in the semi-unsupervised learning model, su-DeepBTS) as the loss function. The su-DeepBTS algorithm achieved better performance (C-index = 0.7306; AUC = 0.7677) than the other models (Cox PH: C-index = 0.7048 and AUC = 0.7390; s-DeepBTS: C-index = 0.7126 and AUC = 0.7420). The top 14 features were selected using su-DeepBTS model as a selector and could distinguish the low- and high-risk groups in the training cohort (p = 1.86 × 10-11) and validation cohort (p = 1.04 × 10-10). When trained with the optimal feature set for each model, the su-DeepBTS model could predict the prognoses of NSCLC better than the traditional model, especially in stage I patients. Follow-up studies using combined radiological, pathological imaging, and genomic data to enhance the performance of our model are ongoing.

Detection of Leptomeningeal Metastasis by Contrast-Enhanced 3D T1-SPACE: Comparison with 2D FLAIR and Contrast-Enhanced 2D T1-Weighted Images.

INTRODUCTION: To compare the diagnostic accuracy of contrast-enhanced 3D(dimensional) T1-weighted sampling perfection with application-optimized contrasts by using different flip angle evolutions (T1-SPACE), 2D fluid attenuated inversion recovery (FLAIR) images and 2D contrast-enhanced T1-weighted image in detection of leptomeningeal metastasis except for invasive procedures such as a CSF tapping. MATERIALS AND METHODS: Three groups of patients were included retrospectively for 9 months (from 2013-04-01 to 2013-12-31). Group 1 patients with positive malignant cells in CSF cytology (n = 22); group 2, stroke patients with steno-occlusion in ICA or MCA (n = 16); and group 3, patients with negative results on MRI, whose symptom were dizziness or headache (n = 25). A total of 63 sets of MR images are separately collected and randomly arranged: (1) CE 3D T1-SPACE; (2) 2D FLAIR; and (3) CE T1-GRE using a 3-Tesla MR system. A faculty neuroradiologist with 8-year-experience and another 2nd grade trainee in radiology reviewed each MR image- blinded by the results of CSF cytology and coded their observations as positives or negatives of leptomeningeal metastasis. The CSF cytology result was considered as a gold standard. Sensitivity and specificity of each MR images were calculated. Diagnostic accuracy was compared using a McNemar's test. A Cohen's kappa analysis was performed to assess inter-observer agreements. RESULTS: Diagnostic accuracy was not different between 3D T1-SPACE and CSF cytology by both raters. However, the accuracy test of 2D FLAIR and 2D contrast-enhanced T1-weighted GRE was inconsistent by the two raters. The Kappa statistic results were 0.657 (3D T1-SPACE), 0.420 (2D FLAIR), and 0.160 (2D contrast-enhanced T1-weighted GRE). The 3D T1-SPACE images showed the highest inter-observer agreements between the raters. CONCLUSIONS: Compared to 2D FLAIR and 2D contrast-enhanced T1-weighted GRE, contrast-enhanced 3D T1 SPACE showed a better detection rate of leptomeningeal metastasis.