Exploring non-invasive precision treatment in non-small cell lung cancer patients through deep learning radiomics across imaging features and molecular phenotypes.

BACKGROUND: Accurate prediction of tumor molecular alterations is vital for optimizing cancer treatment. Traditional tissue-based approaches encounter limitations due to invasiveness, heterogeneity, and molecular dynamic changes. We aim to develop and validate a deep learning radiomics framework to obtain imaging features that reflect various molecular changes, aiding first-line treatment decisions for cancer patients. METHODS: We conducted a retrospective study involving 508 NSCLC patients from three institutions, incorporating CT images and clinicopathologic data. Two radiomic scores and a deep network feature were constructed on three data sources in the 3D tumor region. Using these features, we developed and validated the 'Deep-RadScore,' a deep learning radiomics model to predict prognostic factors, gene mutations, and immune molecule expression levels. FINDINGS: The Deep-RadScore exhibits strong discrimination for tumor molecular features. In the independent test cohort, it achieved impressive AUCs: 0.889 for lymphovascular invasion, 0.903 for pleural invasion, 0.894 for T staging; 0.884 for EGFR and ALK, 0.896 for KRAS and PIK3CA, 0.889 for TP53, 0.895 for ROS1; and 0.893 for PD-1/PD-L1. Fusing features yielded optimal predictive power, surpassing any single imaging feature. Correlation and interpretability analyses confirmed the effectiveness of customized deep network features in capturing additional imaging phenotypes beyond known radiomic features. INTERPRETATION: This proof-of-concept framework demonstrates that new biomarkers across imaging features and molecular phenotypes can be provided by fusing radiomic features and deep network features from multiple data sources. This holds the potential to offer valuable insights for radiological phenotyping in characterizing diverse tumor molecular alterations, thereby advancing the pursuit of non-invasive personalized treatment for NSCLC patients.

Non-invasive decision support for clinical treatment of non-small cell lung cancer using a multiscale radiomics approach.

BACKGROUND: Selecting therapeutic strategies for cancer patients is typically based on key target-molecule biomarkers that play an important role in cancer onset, progression, and prognosis. Thus, there is a pressing need for novel biomarkers that can be utilized longitudinally to guide treatment selection. METHODS: Using data from 508 non-small cell lung cancer (NSCLC) patients across three institutions, we developed and validated a comprehensive predictive biomarker that distinguishes six genotypes and infiltrative immune phenotypes. These features were analyzed to establish the association between radiological phenotypes and tumor genotypes/immune phenotypes and to create a radiological interpretation of molecular features. In addition, we assessed the sensitivity of the models by evaluating their performance at five different voxel intervals, resulting in improved generalizability of the proposed approach. FINDINGS: The radiomics model we developed, which integrates clinical factors and multi-regional features, outperformed the conventional model that only uses clinical and intratumoral features. Our combined model showed significant performance for EGFR, KRAS, ALK, TP53, PIK3CA, and ROS1 mutation status with AUCs of 0.866, 0.874, 0.902, 0.850, 0.860, and 0.900, respectively. Additionally, the predictive performance for PD-1/PD-L1 was 0.852. Although the performance of all models decreased to different degrees at five different voxel space resolutions, the performance advantage of the combined model did not change. CONCLUSIONS: We validated multiscale radiomic signatures across tumor genotypes and immunophenotypes in a multi-institutional cohort. This imaging-based biomarker offers a non-invasive approach to select patients with NSCLC who are sensitive to targeted therapies or immunotherapy, which is promising for developing personalized treatment strategies during therapy.

Application of clinical and CT imaging features in the evaluation of disease progression in patients with COVID-19.

BACKGROUND: The Corona Virus Disease 2019(COVID-19) pandemic has strained healthcare systems worldwide, necessitating the early prediction of patients requiring critical care. This study aimed to analyze the laboratory examination indicators, CT features, and prognostic risk factors in COVID-19 patients. METHODS: A retrospective study was conducted on 90 COVID-19 patients at the First Affiliated Hospital of Gannan Medical University between December 17, 2022, and March 17, 2023. Clinical data, laboratory examination results, and computed tomography (CT) imaging data were collected. Logistic multivariate regression analysis was performed to identify independent risk factors, and the predictive ability of each risk factor was assessed using the area under the receiver operating characteristic (ROC) curve. RESULTS: Multivariate logistic regression analysis revealed that comorbid diabetes (odds ratio [OR] = 526.875, 95%CI = 1.384-1960.84, P = 0.053), lymphocyte count reduction (OR = 8.773, 95%CI = 1.432-53.584, P = 0.064), elevated D-dimer level (OR = 362.426, 95%CI = 1.228-984.995, P = 0.023), and involvement of five lung lobes (OR = 0.926, 95%CI = 0.026-0.686, P = 0.025) were risk factors for progression to severe COVID-19. ROC curve analysis showed the highest predictive value for 5 lung lobes (AUC = 0.782). Oxygen saturation was positively correlated with normally aerated lung volume and the proportion of normally aerated lung volume (P < 0.05). CONCLUSIONS: The study demonstrated that comorbid diabetes, lymphocyte count reduction, elevated D-dimer levels, and involvement of the five lung lobes are significant risk factors for severe COVID-19. In CT lung volume quantification, normal aerated lung volume and the proportion of normal aerated lung volume correlated with blood oxygen saturation.

Radiomics under 2D regions, 3D regions, and peritumoral regions reveal tumor heterogeneity in non-small cell lung cancer: a multicenter study.

PURPOSE: Lung cancer has significant genetic and phenotypic heterogeneity, leading to poor prognosis. Radiomic features have emerged as promising predictors of the tumor phenotype. However, the role of underlying information surrounding the cancer remains unclear. MATERIALS AND METHODS: We conducted a retrospective study of 508 patients with NSCLC from three institutions. Radiomics models were built using features from six tumor regions and seven classifiers to predict three prognostically significant tumor phenotypes. The models were evaluated and interpreted by the mean area under the receiver operating characteristic curve (AUC) under nested cross-validation and Shapley values. The best-performing predictive models corresponding to six tumor regions and three tumor phenotypes were identified for further comparative analysis. In addition, we designed five experiments with different voxel spacing to assess the sensitivity of the experimental results to the spatial resolution of the voxels. RESULTS: Our results demonstrated that models based on 2D, 3D, and peritumoral region features yielded mean AUCs and 95% confidence intervals of 0.759 and [0.747-0.771] for lymphovascular invasion, 0.889 and [0.882-0.896] for pleural invasion, and 0.839 and [0.829-0.849] for T-staging in the testing cohort, which was significantly higher than all other models. Similar results were obtained for the model combining the three regional features at five voxel spacings. CONCLUSION: Our study revealed the predictive role of the developed methods with multi-regional features for the preoperative assessment of prognostic factors in NSCLC. The analysis of different voxel spacing and model interpretability strengthens the experimental findings and contributes to understanding the biological significance of the radiological phenotype.

Successful neoadjuvant treatment of EGFR exon 19 deletion combined with TP53 mutation in non-small cell lung cancer using aumolertinib after osimertinib-induced myocardial damage: a case report and literature review.

The development of epidermal growth factor receptor (EGFR)-tyrosine kinase inhibitors (TKIs) represents a paradigm shift in the treatment of lung cancer with EGFR mutations. Aumolertinib has been shown to be a safe agent in the registry study. However, successful rechallenge with aumolertinib following osimertinib-induced myocardial damage has not been reported. In this article, a case of neoadjuvant therapy for lung adenocarcinoma is retrospectively analyzed, and the relevant literature is reviewed. The patient was diagnosed with stage IIIA lung adenocarcinoma, and genetic testing revealed EGFR exon 19 deletion mutation combined with Tumor Protein p53 (TP53) mutation. The mutation abundance is 33.5 and 14%, respectively. One month after osimertinib treatment, the patient developed myocardial damage, and abnormal indicators such as myocardial enzyme spectrum showed abnormalities and cardiac insufficiency, followed by pulmonary hypertension and pulmonary edema. Aumolertinib was subsequently used for treatment, following which the myocardial enzyme spectrum returned to normal, and the symptoms of bilateral interstitial edema disappeared. In addition to the disappearance of adverse reactions, the therapeutic effect was excellent; the lung lesions and mediastinal lymph nodes were significantly reduced, and the operation was successfully conducted. This is the first report of successful neoadjuvant treatment of EGFR exon 19 deletion combined with TP53 mutation in NSCLC using aumolertinib after osimertinib-induced myocardial damage. The results suggested that aumolertinib had fewer adverse reactions in patients with EGFR exon 19 deletion combined with TP53 mutation, and aumolertinib may be a potential neoadjuvant therapy for stage IIIA lung cancer.

Prospective clinical research of radiomics and deep learning in oncology: A translational review.

Radiomics and deep learning (DL) hold transformative promise and substantial and significant advances in oncology; however, most methods have been tested in retrospective or simulated settings. There is considerable interest in the biomarker validation, clinical utility, and methodological robustness of these studies and their deployment in real-world settings. This review summarizes the characteristics of studies, the level of prospective validation, and the overview of research on different clinical endpoints. The discussion of methodological robustness shows the potential for independent external replication of prospectively reported results. These in-depth analyses further describe the barriers limiting the translation of radiomics and DL into primary care options and provide specific recommendations regarding clinical deployment. Finally, we propose solutions for integrating novel approaches into the treatment environment to unravel the critical process of translating AI models into the clinical routine and explore strategies to improve personalized medicine.

Deep Learning With Radiomics for Disease Diagnosis and Treatment: Challenges and Potential.

The high-throughput extraction of quantitative imaging features from medical images for the purpose of radiomic analysis, i.e., radiomics in a broad sense, is a rapidly developing and emerging research field that has been attracting increasing interest, particularly in multimodality and multi-omics studies. In this context, the quantitative analysis of multidimensional data plays an essential role in assessing the spatio-temporal characteristics of different tissues and organs and their microenvironment. Herein, recent developments in this method, including manually defined features, data acquisition and preprocessing, lesion segmentation, feature extraction, feature selection and dimension reduction, statistical analysis, and model construction, are reviewed. In addition, deep learning-based techniques for automatic segmentation and radiomic analysis are being analyzed to address limitations such as rigorous workflow, manual/semi-automatic lesion annotation, and inadequate feature criteria, and multicenter validation. Furthermore, a summary of the current state-of-the-art applications of this technology in disease diagnosis, treatment response, and prognosis prediction from the perspective of radiology images, multimodality images, histopathology images, and three-dimensional dose distribution data, particularly in oncology, is presented. The potential and value of radiomics in diagnostic and therapeutic strategies are also further analyzed, and for the first time, the advances and challenges associated with dosiomics in radiotherapy are summarized, highlighting the latest progress in radiomics. Finally, a robust framework for radiomic analysis is presented and challenges and recommendations for future development are discussed, including but not limited to the factors that affect model stability (medical big data and multitype data and expert knowledge in medical), limitations of data-driven processes (reproducibility and interpretability of studies, different treatment alternatives for various institutions, and prospective researches and clinical trials), and thoughts on future directions (the capability to achieve clinical applications and open platform for radiomics analysis).

Association of Daily Wear of Eyeglasses With Susceptibility to Coronavirus Disease 2019 Infection.

Importance: The proportion of daily wearers of eyeglasses among patients with coronavirus disease 2019 (COVID-19) is small, and the association between daily wear of eyeglasses and COVID-19 susceptibility has not been reported. Objective: To study the association between the daily wearing of eyeglasses and the susceptibility to COVID-19. Design, Setting, and Participants: This cohort study enrolled all inpatients with COVID-19 in Suizhou Zengdu Hospital, Suizhou, China, a designated hospital for COVID-19 treatment in the area, from January 27 to March 13, 2020. COVID-19 was diagnosed according to the fifth edition of Chinese COVID-19 diagnostic guidelines. The proportion of persons with myopia who wore eyeglasses in Hubei province was based on data from a previous study. Exposures: Daily wearing of eyeglasses for more than 8 hours. Main Outcomes and Measures: The main outcomes were the proportions of daily wearers of eyeglasses among patients admitted to the hospital with COVID-19 and among the local population. Data on exposure history, clinical symptoms, underlying diseases, duration of wearing glasses, and myopia status and the proportion of people with myopia who wore eyeglasses in Hubei province were collected. People who wore glasses for more than 8 hours a day were defined as long-term wearers. Results: A total of 276 patients with COVID-19 were enrolled. Of these, 155 (56.2%) were male, and the median age was 51 (interquartile range, 41-58) years. All those who wore glasses for more than 8 hours a day had myopia and included 16 of 276 patients (5.8%; 95% CI, 3.04%-8.55%). The proportion of people with myopia in Hubei province, based on a previous study, was 31.5%, which was much higher than the proportion of patients with COVID-19 who had myopia in this sample. Conclusions and Relevance: In this cohort study of patients hospitalized with COVID-19 in Suizhou, China, the proportion of inpatients with COVID-19 who wore glasses for extended daily periods (>8 h/d) was smaller than that in the general population, suggesting that daily wearers of eyeglasses may be less susceptible to COVID-19.

Clinical characteristics of 276 hospitalized patients with coronavirus disease 2019 in Zengdu District, Hubei Province: a single-center descriptive study.

BACKGROUND: We aimed to report the epidemiological and clinical characteristics of hospitalized patients with coronavirus disease-19 (COVID-19) in Zengdu District, Hubei Province, China. METHODS: Clinical data on COVID-19 inpatients in Zengdu Hospital from January 27 to March 11, 2020 were collected; this is a community hospital in an area surrounding Wuhan and supported by volunteer doctors. All hospitalized patients with COVID-19 were included in this study. The epidemiological findings, clinical features, laboratory findings, radiologic manifestations, and clinical outcomes of these patients were analyzed. The patients were followed up for clinical outcomes until March 22, 2020. Severe COVID-19 cases include severe and critical cases diagnosed according to the seventh edition of China's COVID-19 diagnostic guidelines. Severe and critical COVID-19 cases were diagnosed according to the seventh edition of China's COVID-19 diagnostic guidelines. RESULTS: All hospitalized COVID-19 patients, 276 (median age: 51.0 years), were enrolled, including 262 non-severe and 14 severe patients. The proportion of patients aged over 60 years was higher in the severe group (78.6%) than in the non-severe group (18.7%, p < 0.01). Approximately a quarter of the patients (24.6%) had at least one comorbidity, such as hypertension, diabetes, or cancer, and the proportion of patients with comorbidities was higher in the severe group (85.7%) than in the non-severe group (21.4%, p < 0.01). Common symptoms included fever (82.2% [227/276]) and cough (78.0% [218/276]). 38.4% (106/276) of the patients had a fever at the time of admission. Most patients (94.9% [204/276]) were cured and discharged; 3.6% (10/276) deteriorated to a critical condition and were transferred to another hospital. The median COVID-19 treatment duration and hospital stay were 14.0 and 18.0 days, respectively. CONCLUSIONS: Most of the COVID-19 patients in Zengdu had mild disease. Older patients with underlying diseases were at a higher risk of progression to severe disease. The length of hospital-stay and antiviral treatment duration for COVID-19 were slightly longer than those in Wuhan. This work will contribute toward an understanding of COVID-19 characteristics in the areas around the core COVID-19 outbreak region and serve as a reference for decision-making for epidemic prevention and control in similar areas.