Peng Zhou

Background: High-risk factors of lung adenocarcinoma (LUAD), including poorly differentiated pattern, lymphovascular invasion, visceral pleural invasion, lymph node metastasis, and spread through air spaces, are associated with poor prognosis. Purpose: To construct and validate a combined model based on dual-energy computed tomography (DECT) for predicting high-risk LUAD in nodules with solid components. Material and Methods: A total of 539 pathologically confirmed LUADs were retrospectively enrolled and were randomly divided into training (n = 377) and testing cohorts (n = 162) (ratio = 7:3). DECT quantitative parameters, conventional quantitative-semantic features, and clinical characteristics were collected. Univariable and multivariable logistic regression was used to construct the conventional CT model, DECT model, and combined model. Area under the curve (AUC) was used to evaluate diagnostic performance of models. Results: The combined model (features: sex, diameter, pleural indentation, electron density in venous phase [Rho_V], and NIC_A [normalized iodine concentration in arterial phase]) showed significantly higher AUC than the DECT model (features: Rho_V and NIC_A) (0.899 vs. 0.870; P = 0.005) and the conventional CT model (features: diameter and pleural indentation) (0.899 vs. 0.742; P P P = 0.354). Conclusion: The combined model based on DECT has good diagnostic performance in predicting high-risk LUAD in nodules with solid components.

Objectives: Our objectives were to develop and validate the habitat model based on low-dose computed tomography (LDCT) for noninvasive prediction of the visceral pleural invasion (VPI) in subpleural nodules with solid component. Methods: A total of 313 patients with subpleural lung adenocarcinoma nodules from three centers were retrospectively enrolled and divided into training (n = 192), validation (n = 82), and external test (n = 39) sets. All patients underwent preoperative LDCT scan. The habitat model was constructed using unsupervised clustering to partition each tumor into three distinct habitats, from which radiomic features were extracted and selected. Its diagnostic performance was compared with a whole-lesion radiomic model and radiological model. Statistical analysis included receiver operating characteristic (ROC) analysis and DeLong test. Results: The habitat model significantly outperformed both the radiomic and radiological models across the validation and external test sets, with areas under the ROC curve of 0.893 and 0.908, respectively (all p < 0.05). In contrast, the radiomic model achieved 0.833 and 0.772, while the radiological model yielded 0.746 and 0.624. The corresponding software tool has been made publicly available to facilitate broader clinical application. Conclusions: The habitat imaging model based on LDCT effectively predicts the VPI in subpleural lung adenocarcinoma by quantifying intratumoral spatial heterogeneity and demonstrates promising diagnostic performance compared to conventional radiomic and radiological methods. This approach offers a noninvasive preoperative tool to assist in risk stratification and guide personalized therapeutic decision-making for subpleural nodules detected during lung cancer screening.

Background: Magnetic resonance imaging (MRI) is increasingly used to evaluate axillary lymph node (ALN) status in breast cancer. However, the correlation between MRI features of the primary tumor and the ALN metastasis (ALNM) burden remains poorly understood. This study aimed to develop a non-invasive MRI-based model to preoperatively distinguish between low (≤2 nodes) and high (>2 nodes) ALNM burden in T1 and T2 stage breast cancer. Methods: This retrospective single-center study included 185 patients, categorized by ALNM burden [≤ 2 nodes (n = 149) or >2 nodes (n = 36)]. The kinetic and radiomic features were extracted from the segmented whole tumor on dynamic contrast-enhanced MRI (DCE-MRI). A forward-stepwise feature selection method was employed based on the ANOVA F-score from the training cohort. Features were added according to F-values and logistical regression model was built iteratively. The final model, trained on the entire training set, was evaluated on the independent test cohort. Results: The model incorporated five kinetic and three radiomic features, demonstrating moderate predictive performance. The model achieved an area under the receiver operating characteristic curve (AUC) of 0.705 in the test cohort. It showed a sensitivity of 72.7% and a specificity of 77.8%. The negative predictive value (NPV) was 92.1%. Conclusion: The kinetic and radiomic features from DCE-MRI showed potential for predicting ALNM burden (≤2 or > 2 nodes) in T1 and T2 stage breast cancer. The high NPV particularly supported their utility as a non-invasive tool to identify candidates for less invasive axillary procedures.

Evaluation of confounding factors and the analysis of clinical applicability for the TCRnodseek plus model

Indeterminate pulmonary nodules (IPN) are increasingly detected due to increasing health awareness and widespread lung cancer screening, yet distinguishing benign from malignant nodules remains a critical challenge. Emerging evidence suggests that recognizing cancer-associated immune signatures represents a powerful approach for early-stage cancer detection. This study explored the clinical utility of T-cell receptor (TCR) repertoire analysis in IPN evaluation. By conducting large-scale TCR sequencing (6,059 blood and 988 tumor samples), we established LungTCR (https://www.lungtcr.com/), a comprehensive TCR repertoire database, and proposed a method for the quantitative assessment of tumor-related immune responses. LungTCR was leveraged to develop TCRnodseek plus, a diagnostic model integrating clinical data, CT imaging, and TCR features. A multicenter prospective study (ChiCTR2200055761) involving 1,107 patients with IPN validated the superior diagnostic performance of TCRnodseek plus over existing approaches. Mechanistic analyses revealed that the identified lung cancer–related TCR clones are enriched in non–small cell lung cancer and are predominantly present in malignant nodules and tumor tissues. This study provides a robust TCR database and an advanced diagnostic model, offering a framework for precise IPN differentiation.Significance:Construction of the largest TCR database of lung nodules enabled identification of lung cancer–specific TCR sequences and development of an advanced machine learning model to distinguish benign from malignant pulmonary nodules.This article is part of a special series: Driving Cancer Discoveries with Computational Research, Data Science, and Machine Learning/AI.

Evaluation and external validation of lung cancer-enriched TCR sequences

Clinical and TCR characteristics for LungTCR database

TCR profiling of blood samples from patients with indeterminate pulmonary nodules

Biology and Disease Annotation of Enriched CDR3-beta aaSeqs