Dual-energy computed tomography for evaluating nodal staging in lung adenocarcinoma: correlation with surgical pathology.

PURPOSE: To ascertain the performance of dual-energy CT (DECT) with iodine quantification in differentiating malignant mediastinal and hilar lymph nodes (LNs) from benign ones, focusing on patients with lung adenocarcinoma. MATERIALS AND METHODS: In this study, patients with suspected lung cancer received a preoperative contrast-enhanced DECT scan from Jun 2018 to Dec 2020. Quantitative DECT parameters and the size were compared between metastatic and benign LNs. Their diagnostic performances were analyzed by the ROC curves and compared by using the two-sample t test. RESULTS: 72 patients (23 men, 49 women; mean age 62.5 ± 10.1 years) fulfilled the inclusion criteria. A total of 98 LNs (67 benign, 31 metastatic) were analyzed. The iodine concentration normalized by muscle (NICmuscle) was significantly higher (P < 0.001) in metastatic LNs (4.79 ± 1.70) than in benign ones (3.00 ± 1.45). The optimal threshold of NICmuscle was 3.44, which yielded AUC: 0.798, sensitivity: 83.9%, specificity: 73.1%, accuracy: 76.5%, respectively. Applying the established size parameters with 10 mm as the threshold yielded AUC: 0.600, sensitivity: 29.0%, specificity: 91.0%, accuracy: 71.4%, respectively. The diagnostic performance of NICmuscle was significantly better (P = 0.007) than the performance obtained using the established size parameters. CONCLUSIONS: For lung adenocarcinoma, the quantitative measurement of NICmuscle derived from DECT is useful for differentiating benign and metastatic mediastinal and hilar LNs before surgical intervention.

CT findings of 144 in-hospital patients with influenza pneumonia: A retrospective analysis.

BACKGROUND/PURPOSE: Patients with influenza infection during their period of admission may have worse computed tomography (CT) manifestation according to the clinical status. This study aimed to evaluate the CT findings of in-hospital patients due to clinically significant influenza pneumonia with correlation of clinical presentations. METHODS: In this retrospective, single center case series, 144 patients were included. All in-hospital patients were confirmed influenza infection and underwent CT scan. These patients were divided into three groups according to the clinical status of the most significant management: (1) without endotracheal tube and mechanical ventilator (ETTMV) or extracorporeal membrane oxygenation (ECMO); (2) with ETTMV; (3) with ETTMV and ECMO. Pulmonary opacities were scored according to extent. Spearman rank correlation analysis was used to evaluate the correlation between clinical parameters and CT scores. RESULTS: The predominant CT manifestation of influenza infection was mixed ground-glass opacity (GGO) and consolidation with both lung involvement. The CT scores were all reach significant difference among all three groups (8.73 ± 6.29 vs 12.49 ± 6.69 vs 18.94 ± 4.57, p < 0.05). The chest CT score was correlated with age, mortality, and intensive care unit (ICU) days (all p values were less than 0.05). In addition, the CT score was correlated with peak lactate dehydrogenase (LDH) level and peak C-reactive protein (CRP) level (all p values were less than 0.05). Concomitant bacterial infection had higher CT score than primary influenza pneumonia (13.02 ± 7.27 vs 8.95 ± 5.99, p < 0.05). CONCLUSION: Thin-section chest CT scores correlated with clinical and laboratory parameters in in-hospital patients with influenza pneumonia.

An improved 3-D attention CNN with hybrid loss and feature fusion for pulmonary nodule classification.

BACKGROUND AND OBJECTIVE: Lung cancer has the highest cancer-related mortality worldwide, and lung nodule usually presents with no symptom. Low-dose computed tomography (LDCT) was an important tool for lung cancer detection and diagnosis. It provided a complete three-dimensional (3-D) chest image with a high resolution.Recently, convolutional neural network (CNN) had flourished and been proven the CNN-based computer-aided diagnosis (CADx) system could extract the features and help radiologists to make a preliminary diagnosis. Therefore, a 3-D ResNeXt-based CADx system was proposed to assist radiologists for diagnosis in this study. METHODS: The proposed CADx system consists of image preprocessing and a 3-D CNN-based classification model for pulmonary nodule classification. First, the image preprocessing was executed to generate the normalized volumn of interest (VOI) only including nodule information and a few surrounding tissues. Then, the extracted VOI was forwarded to the 3-D nodule classification model. In the classification model, the RestNext was employed as the backbone and the attention scheme was embedded to focus on the important features. Moreover, a multi-level feature fusion network incorporating feature information of different scales was used to enhance the prediction accuracy of small malignant nodules. Finally, a hybrid loss based on channel optimization which make the network learn more detailed information was empolyed to replace a binary cross-entropy (BCE) loss. RESULTS: In this research, there were a total of 880 low-dose CT images including 440 benign and 440 malignant nodules from the American National Lung Screening Trial (NLST) for system evaluation. The results showed that our system could achieve the accuracy of 85.3%, the sensitivity of 86.8%, the specificity of 83.9%, and the area-under-curve (AUC) value was 0.9042. It was confirmed that the designed system had a good diagnostic ability. CONCLUSION: In this study, a CADx composed of the image preprocessing and a 3-D nodule classification model with attention scheme, feature fusion, and hybrid loss was proposed for pulmonary nodule classification in LDCT. The results indicated that the proposed CADx system had potential for achieving high performance in classifying lung nodules as benign and malignant.

Multi-energy level fusion for nodal metastasis classification of primary lung tumor on dual energy CT using deep learning.

Lymph node metastasis also called nodal metastasis (Nmet), is a clinically primary task for physicians. The survival and recurrence of lung cancer are related to the Nmet staging from Tumor-Node-Metastasis (TNM) reports. Furthermore, preoperative Nmet prediction is still a challenge for the patient in managing the surgical plan and making treatment decisions. We proposed a multi-energy level fusion model with a principal feature enhancement (PFE) block incorporating radiologist and computer science knowledge for Nmet prediction. The proposed model is custom-designed by gemstone spectral imaging (GSI) with different energy levels on dual-energy computer tomography (CT) from a primary tumor of lung cancer. In the experiment, we take three different energy level fusion datasets: lower energy level fusion (40, 50, 60, 70 keV), higher energy level fusion (110, 120, 130, 140 keV), and average energy level fusion (40, 70, 100, 140 keV). The proposed model is trained by lower energy level fusion that is 93% accurate and the value of Kappa is 86%. When we used the lower energy level images to train the fusion model, there has been a significant difference to other energy level fusion models. Hence, we apply 5-fold cross-validation, which is used to validate the performance result of the multi-keV model with different fusion datasets of energy level images in the pathology report. The cross-validation result also demonstrates that the model with the lower energy level dataset is more robust and suitable in predicting the Nmet of the primary tumor. The lower energy level shows more information of tumor angiogenesis or heterogeneity provided the proposed fusion model with a PFE block and channel attention blocks to predict Nmet from primary tumors.

Dual energy CT image prediction on primary tumor of lung cancer for nodal metastasis using deep learning.

Lymph node metastasis (LNM) identification is the most clinically important tasks related to survival and recurrence from lung cancer. However, the preoperative prediction of nodal metastasis remains a challenge to determine surgical plans and pretreatment decisions in patients with cancers. We proposed a novel deep prediction method with a size-related damper block for nodal metastasis (Nmet) identification from the primary tumor in lung cancer generated by gemstone spectral imaging (GSI) dual-energy computer tomography (CT). The best model is the proposed method trained by the 40 keV dataset achieves an accuracy of 86 % and a Kappa value of 72 % for Nmet prediction. In the experiment, we have 11 different monochromatic images from 40∼140 keV (the interval is 10 keV) for each patient. When we used the model of 40 keV dataset, there has significant difference in other energy levels (unit of keV). Therefore, we apply in 5-fold cross-validation to explain the lower keV is more efficient to predict Nmet of the primary tumor. The result shows that tumor heterogeneity and size contributed to the proposed model to estimate whether absence or presence of nodal metastasis from the primary tumor.

Computer-aided diagnosis of breast DCE-MRI using pharmacokinetic model and 3-D morphology analysis.

Three-dimensional (3-D) dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) consists of a large number of images in different enhancement phases which are used to identify and characterize breast lesions. The purpose of this study was to develop a computer-assisted algorithm for tumor segmentation and characterization using both kinetic information and morphological features of 3-D breast DCE-MRI. An integrated color map created by intersecting kinetic and area under the curve (AUC) color maps was used to detect potential breast lesions, followed by the application of a region growing algorithm to segment the tumor. Modified fuzzy c-means clustering was used to identify the most representative kinetic curve of the whole segmented tumor, which was then characterized by using conventional curve analysis or pharmacokinetic model. The 3-D morphological features including shape features (compactness, margin, and ellipsoid fitting) and texture features (based on the grey level co-occurrence matrix) of the segmented tumor were obtained to characterize the lesion. One hundred and thirty-two biopsy-proven lesions (63 benign and 69 malignant) were used to evaluate the performance of the proposed computer-aided system for breast MRI. Five combined features including rate constant (kep), volume of plasma (vp), energy (G1), entropy (G2), and compactness (C1), had the best performance with an accuracy of 91.67% (121/132), sensitivity of 91.30% (63/69), specificity of 92.06% (58/63), and Az value of 0.9427. Combining the kinetic and morphological features of 3-D breast MRI is a potentially useful and robust algorithm when attempting to differentiate benign and malignant lesions.

A 2-year follow-up of swallowing function after radiation therapy in patients with nasopharyngeal carcinoma.

OBJECTIVE: To evaluate over a 2-year period the serial swallowing function of patients with nasopharyngeal carcinoma (NPC) after completing radiotherapy (RT). DESIGN: Prospective longitudinal follow-up. SETTING: University hospital. PARTICIPANTS: Patients with NPC (N=76) referred for RT: 53 of them at 1 year after RT, and 23 at 2 years after RT. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Participants completed a questionnaire and had a video-recorded fluoroscopic swallowing study before RT and 1 month, 1 year, and 2 years after RT. RESULTS: The highest incidence of dysphagia symptoms and retropharyngeal soft tissue swelling occurred in the first month after RT and decreased over time. Pharyngeal transit time was prolonged continuously up to 1 year after RT. Epiglottic vallecular stasis and pharyngeal mucosal coating were worst in the first month after RT and stable afterwards. Aspiration was uncommon during the first 2 years after RT. CONCLUSIONS: At a 2-year follow-up after RT, patients with NPC had a progressively increasing pharyngeal transit time, although the subjectively identified symptoms of dysphagia decreased after the first month after RT.

Intrapulmonary bronchogenic cysts: computed tomography, clinical and histopathologic correlations.

BACKGROUND/PURPOSE: Bronchogenic cysts (BCs) are usually located in the mediastinum and they occur less commonly in the lung parenchyma. This study investigated the findings from computed tomography (CT) images, clinical presentation and histopathologic findings of intrapulmonary BCs. METHODS: From the last 7 years, the CT images of 20 patients (12 females, 8 males; mean age, 38.8 +/- 21.7 years; median age, 34 years) with intrapulmonary BC were available. Contrast-enhanced CT findings were characterized and correlated with clinical presentation and histopathologic findings (using Fisher's exact tests). RESULTS: The majority of intrapulmonary BCs were subpleural in location (55%), in the lower lobes (60%), symptomatic (80%), and in adults (90%). Three CT patterns were identified: cyst with content of fluid attenuation (9 patients), cyst with air and fluid content (9 patients), cyst with content of soft tissue attenuation (2 patients). Preoperative diagnosis of intrapulmonary BC was correct in only 20% using the CT criteria of cysts with fluid attenuation and without anomalous blood supply. Cysts with air component were significantly larger than those without air component (p = 0.0452), but cyst size and air component were not correlated with clinical presentation. Surrounding infiltration or thick wall on CT were significantly correlated with the presence of any clinical symptom (p = 0.014) or fever (p = 0.042). CT findings of surrounding consolidation, ground glass opacity or thick wall were significantly correlated with chronic inflammation or pneumonic change on histopathology (p = 0.0008). CONCLUSION: There is a wide spectrum of intrapulmonary BCs that have CT findings that are correlated with clinical presentations and histopathologic findings.

Dysphagia in patients with nasopharyngeal cancer after radiation therapy: a videofluoroscopic swallowing study.

This study evaluated swallowing status and the factors influencing swallowing in patients with nasopharyngeal carcinoma (NPC) after radiation therapy. During the period from July 1995 to June 1999, this cross-sectional study used videofluoroscopic swallowing study (VFSS) to evaluate 184 NPC patients who had completed radiation therapy [113 cases had completed radiation therapy < or = 12 months prior to evaluation (acute group) and 71 cases had completed radiation therapy > 12 months prior to evaluation (chronic group)]. The numbers of patients with tumors in each of the four stages were as follows: 24 in stage I, 45 in stage II, 41 in stage III, and 74 in stage IV. Swallowing abnormalities of the acute and chronic groups were correlated with multiple variables, including gender, age, the stage of the tumor, use of either neoadjuvant chemotherapy or radiosensitizer, and radiation modality. The analytical results indicated that the chronic group had a significantly higher proportion of swallowing abnormalities. Radiation modality, chemotherapy, and tumor staging were not significantly associated with swallowing dysfunction. Trend analysis revealed a progressive deterioration of most parameters of swallowing function in this group of patients. These findings indicate that swallowing function continues to deteriorate over time, even many years after radiation therapy in patients with NPC. Our results indicate that the time elapsed since radiation therapy correlates with the severity of dysphagia in NPC patients.