Comparing attenuations of malignant and benign solitary pulmonary nodule using semi-automated region of interest selection on contrast-enhanced CT

New developments in the imaging of lung cancer

Radiological and nuclear medicine methods play a fundamental role in the diagnosis and staging of patients with lung cancer. Imaging is essential in the detection, characterisation, staging and follow-up of lung cancer. Due to the increasing evidence, low-dose chest computed tomography (CT) screening for the early detection of lung cancer is being introduced to the clinical routine in several countries. Radiomics and radiogenomics are emerging fields reliant on artificial intelligence to improve diagnosis and personalised risk stratification. Ultrasound- and CT-guided interventions are minimally invasive methods for the diagnosis and treatment of pulmonary malignancies. In this review, we put more emphasis on the new developments in the imaging of lung cancer.

Artificial intelligence system-based histogram analysis of computed tomography features to predict tumor invasiveness of ground-glass nodules

Background

The use of an artificial intelligence (AI)-based diagnostic system can significantly aid in analyzing the histogram of pulmonary nodules. The aim of our study was to evaluate the value of computed tomography (CT) histogram indicators analyzed by AI in predicting the tumor invasiveness of ground-glass nodules (GGNs) and to determine the added value of contrast-enhanced CT (CECT) compared with nonenhanced CT (NECT) in this prediction.

Methods

This study enrolled patients with persistent GGNs who underwent preoperative NECT and CECT scanning. AI-based histogram analysis was performed for pathologically confirmed GGNs, which was followed by screening invasiveness-related factors via univariable analysis. Multivariable logistic models were developed based on candidate CT histogram indicators measured on either NECT or CECT. Receiver operating characteristic (ROC) curve and precision-recall (PR) curve were used to evaluate the models' performance.

Results

A total of 116 patients comprising 121 GGNs were included and divided into the precancerous lesion and adenocarcinoma groups based on invasiveness. In the AI-based histogram analysis, the mean CT value [NECT: odds ratio (OR) =1.009; 95% confidence interval (CI): 1.004-1.013; P<0.001] and solid component volume (NECT: OR =1.005; 95% CI: 1.000-1.010; P=0.032) were associated with the adenocarcinoma and used for multivariable logistic modeling. The area under ROC curve (AUC) and PR curve (AUPR) were not significantly different between the NECT model (AUC =0.765, 95% CI: 0.679-0.837; AUPR =0.907, 95% CI: 0.825-0.953) and the optimal CECT model (delayed phase: AUC =0.772, 95% CI: 0.687-0.843; AUPR =0.895, 95% CI: 0.812-0.944). No significantly different metrics were observed between the NECT and CECT models (precision: 0.707 vs. 0.742; P=0.616).

Conclusions

The AI diagnostic system can help in the diagnosis of GGNs. The system displayed decent performance in GGN detection and alert to malignancy. Mean CT value and solid component volume were independent predictors of tumor invasiveness. CECT provided no additional improvement in diagnostic performance as compared with NECT.

Pulmonary metastases from mucinous colorectal cancers and their appearance on CT: a case series

Mucinous colorectal adenocarcinoma represents a small proportion of all colorectal cancers, characterised by mucinous tumour components. While its pattern of metastatic spread differs from that of conventional colorectal adenocarcinoma, pulmonary metastases are commonly seen in both mucinous and non-mucinous types. The assessment of pulmonary nodules in the context of malignancy is a commonly encountered problem for the radiologist given the high prevalence of benign pulmonary lesions. Low density of a pulmonary nodule on CT evaluation is one of the recognised and well-documented features of benignity that is used in the radiological assessment of such nodules. We present three cases of patients with histologically proven mucinous colorectal adenocarcinoma with evidence of pulmonary metastases. In all cases, the metastases were of low density on CT and in one case were initially suspected to represent benign hamartomatous lesions. There has been little documented about the density of mucinous pulmonary metastases on CT. We suspect the low density seen in the metastases in each case is accounted for by their high internal mucinous components. The cases presented here demonstrate the importance of recognising that mucinous colorectal metastases can be of low density and therefore mimic benign pathology. This review may help the radiologist to consider shorter interval follow-up of such lesions in the context of known mucinous neoplasms, or to investigate for an extrathoracic mucinous carcinoma in the presence of multiple low-density pulmonary nodules.

The adding value of contrast-enhanced CT radiomics: Differentiating tuberculosis from non-tuberculous infectious lesions presenting as solid pulmonary nodules or masses

Purpose

To compare the value of contrast-enhanced CT (CECT) and non-contrast-enhanced CT (NCECT) radiomics models in differentiating tuberculosis (TB) from non-tuberculous infectious lesions (NTIL) presenting as solid pulmonary nodules or masses, and develop a combine radiomics model (RM).

Materials and methods

This study was a retrospective analysis of 101 lesions in 95 patients, including 49 lesions (from 45 patients) in the TB group and 52 lesions (from 50 patients) in the NTIL group. Lesions were randomly divided into training and test sets in the ratio of 7:3. Conventional imaging features were used to construct a conventional imaging model (IM). Radiomics features screening and NCECT or CECT RM construction were carried out by correlation analysis and gradient boosting decision tree, and logistic regression. Finally, conventional IM, NCECT RM, and CECT RM were used for combine RM construction. Additionally, we recruited three radiologists for independent diagnosis. The differential diagnostic performance of each model was assessed using the areas under the receiver operating characteristic curve (AUCs).

Results

The CECT RM (training AUC, 0.874; test AUC, 0.796) outperformed the conventional IM (training AUC, 0.792; test AUC, 0.708), the NCECT RM (training AUC, 0.835; test AUC, 0.704), and three radiologists. The diagnostic efficacy of the combine RM (training AUC, 0.922; test AUC, 0.833) was best in the training and test sets.

Conclusions

The diagnostic efficacy of the CECT RM was superior to that of the NCECT RM in identifying TB from NTIL presenting as solid pulmonary nodules or masses. The combine RM had the best performance and may outperform expert radiologists.

Application of CT Postprocessing Reconstruction Technique in Differential Diagnosis of Benign and Malignant Solitary Pulmonary Nodules and Analysis of Risk Factors

Objective

To evaluate the application of CT postprocessing reconstruction technique in differential diagnosis of benign and malignant solitary pulmonary nodules and analysis of risk factors.

Methods

A total of 150 solitary pulmonary nodules (SPN) patients admitted to our hospital from January 2020 to January 2022 were selected and divided into the benign SPN group (n = 64) and the malignant SPN group (n = 86) according to pathological results. All subjects underwent CT plain scan and CT postprocessing reconstruction, and the general information of the subjects was collected. The diagnostic value of CT plain scan and CT postprocessing reconstruction techniques for benign and malignant SPN was compared; and the CT signs of benign and malignant SPN were compared, and the risk factors of malignant SPN were analyzed.

Results

The pathological results of this study showed that there were 64 cases with benign SPN and 86 cases with malignant SPN. The sensitivity, specificity, accuracy, positive predictive rate, and negative predictive rate of CT postprocessing reconstruction technology in diagnosing malignant SPN were 73.44%, 89.53%, 82.67%, 83.39%, and 81.91%, respectively, which were higher than 56.25%, 65.12%, 61.33%, 54.55%, and 66.67% of CT plain scan, and the difference was statistically significant (P < 0.05). There were no significant differences in nodule location, nodule density, vacuole sign, vessel convergence, and pleural depression sign between the two groups (P > 0.05). There were statistically significant differences in age, nodule diameter, lobulation sign, burr sign, calcification components, and ground-glass components between the two groups (P < 0.05). Multivariate analysis showed that age ≥ 60 years, nodule diameter ≥ 15 mm, the presence of lobulation sign, burr sign, ground-glass components, and noncalcification components were independent risk factors for malignant SPN.

Conclusion

CT postprocessing reconstruction technique has high diagnostic value in the differentiation of benign and malignant SPN, age ≥ 60 years, nodule diameter ≥ 15 mm, lobulation signs, burr signs, ground-glass components, and noncalcification components are independent risk factors for malignant SPN.

CT review of ovarian fibrothecoma

Objective:

The aim of this study was to investigate the CT imaging characteristics of ovarian fibrothecoma which may aid in the differentiation from early stage epithelial tumours.

Methods:

Comparison of 36 patients (41 lesions) with pathologically proven ovarian fibrothecoma tumours and 36 (52 lesions) serous papillary carcinomas (SPCs) lesions. We noted their laterality, size, density, calcifications, Hounsfield units (HUs) and introduced a novel HU comparison technique with the psoas muscle or the uterus. Patients’ clinical findings such as ascites, pleural effusion, carbohydrate antigen-125 levels, and lymphadenopathy findings were also included.

Results:

Average age was 67.8 and 66 across the fibrothecoma and SPC cohort respectively. Fibrothecoma tumours had diameters ranging from 24 to 207 mm (Median: 94 mm). 80.6% of the fibrothecoma cohort had ascites which was comparable to the 72.2% in the SPC cohort. 70.7% of fibrothecoma tumour favour a purely to predominantly solid structural configuration (p < 0.001). The average HU value for the fibrothecoma solid component was 44 ± 11.7 contrasting the SPC HU value of 66.8 ± 15. The psoas:tumour mass ratio demonstrated a median of 0.7, whereas SPCs shows a median of 1.1 (p < 0.001).

Conclusion:

Suspicion of ovarian fibrothecoma should be considered through interrogation of their structural density configuration, low psoas to mass HU ratio and a presence of ascites.

Advances in knowledge:

CT imaging can be a useful tool in diagnosing fibrothecoma tumours and subsequently reducing oncogynaecological tertiary centre referrals, financial burden and patient operative morbidity and mortality.

A contrast-enhanced-CT-based classification tree model for classifying malignancy of solid lung tumors in a Chinese clinical population

Background

To develop and validate a contrast-enhanced CT based classification tree model for classifying solid lung tumors in clinical patients into malignant or benign.

Methods

Between January 2015 and October 2017, 827 pathologically confirmed solid lung tumors (487 malignant, 340 benign; median size, 27.0 mm, IQR 18.0–39.0 mm) from 827 patients from a dedicated Chinese cancer hospital were identified. Nodules were divided randomly into two groups, a training group (575 cases) and a testing group (252 cases). CT characteristics were collected by two radiologists, and analyzed using a classification and regression tree (CART) model. For validation, we used the decision analysis threshold to evaluate the classification performance of the CART model and radiologist’s diagnosis (benign; malignant) in the testing group.

Results

Three out of 19 characteristics [margin (smooth; slightly lobulated/lobulated/spiculated), and shape (round/oval; irregular), subjective enhancement (no/uniform enhancement; heterogeneous enhancement)] were automatically generated by the CART model for classifying solid lung tumors. The sensitivity, specificity, PPV, NPV, and diagnostic accuracy of the CART model is 98.5%, 58.1%, 80.6%, 98.6%, 79.8%, and 90.4%, 54.7%, 82.4% 98.5%, 74.2% for the radiologist’s diagnosis by using three-threshold decision analysis.

Conclusions

Tumor margin and shape, and subjective tumor enhancement were the most important CT characteristics in the CART model for classifying solid lung tumors as malignant. The CART model had higher discriminatory power than radiologist’s diagnosis. The CART model could help radiologists making recommendations regarding follow-up or surgery in clinical patients with a solid lung tumor.