Glioma Grade and Molecular Markers: Comparing Machine-Learning Approaches Using VASARI (Visually AcceSAble Rembrandt Images) Radiological Assessment.

OBJECTIVES: This study aimed to leverage Visually AcceSAble Rembrandt Images (VASARI) radiological features, extracted from magnetic resonance imaging (MRI) scans, and machine-learning techniques to predict glioma grade, isocitrate dehydrogenase (IDH) mutation status, and O6-methylguanine-DNA methyltransferase (MGMT) methylation. METHODOLOGY: A retrospective evaluation was undertaken, analyzing MRI and molecular data from 107 glioma patients treated at a tertiary hospital. Patients underwent MRI scans using established protocols and were evaluated based on VASARI criteria. Tissue samples were assessed for glioma grade and underwent molecular testing for IDH mutations and MGMT methylation. Four machine learning models, namely, Random Forest, Elastic-Net, multivariate adaptive regression spline (MARS), and eXtreme Gradient Boosting (XGBoost), were trained on 27 VASARI features using fivefold internal cross-validation. The models' predictive performances were assessed using the area under the curve (AUC), sensitivity, and specificity. RESULTS: For glioma grade prediction, XGBoost exhibited the highest AUC (0.978), sensitivity (0.879), and specificity (0.964), with f6 (proportion of non-enhancing) and f12 (definition of enhancing margin) as the most important predictors. In predicting IDH mutation status, XGBoost achieved an AUC of 0.806, sensitivity of 0.364, and specificity of 0.880, with f1 (tumor location), f12, and f30 (perpendicular diameter to f29) as primary predictors. For MGMT methylation, XGBoost displayed an AUC of 0.580, sensitivity of 0.372, and specificity of 0.759, highlighting f29 (longest diameter) as the key predictor. CONCLUSIONS: This study underscores the robust potential of combining VASARI radiological features with machine learning models in predicting glioma grade, IDH mutation status, and MGMT methylation. The best and most balanced performance was achieved using the XGBoost model. While the prediction of glioma grade showed promising results, the sensitivity in discerning IDH mutations and MGMT methylation still leaves room for improvement. Follow-up studies with larger datasets and more advanced artificial intelligence techniques can further refine our understanding and management of gliomas.

CHNet: A multi-task global-local Collaborative Hybrid Network for KRAS mutation status prediction in colorectal cancer.

Accurate prediction of Kirsten rat sarcoma (KRAS) mutation status is crucial for personalized treatment of advanced colorectal cancer patients. However, despite the excellent performance of deep learning models in certain aspects, they often overlook the synergistic promotion among multiple tasks and the consideration of both global and local information, which can significantly reduce prediction accuracy. To address these issues, this paper proposes an innovative method called the Multi-task Global-Local Collaborative Hybrid Network (CHNet) aimed at more accurately predicting patients' KRAS mutation status. CHNet consists of two branches that can extract global and local features from segmentation and classification tasks, respectively, and exchange complementary information to collaborate in executing these tasks. Within the two branches, we have designed a Channel-wise Hybrid Transformer (CHT) and a Spatial-wise Hybrid Transformer (SHT). These transformers integrate the advantages of both Transformer and CNN, employing cascaded hybrid attention and convolution to capture global and local information from the two tasks. Additionally, we have created an Adaptive Collaborative Attention (ACA) module to facilitate the collaborative fusion of segmentation and classification features through guidance. Furthermore, we introduce a novel Class Activation Map (CAM) loss to encourage CHNet to learn complementary information between the two tasks. We evaluate CHNet on the T2-weighted MRI dataset, and achieve an accuracy of 88.93% in KRAS mutation status prediction, which outperforms the performance of representative KRAS mutation status prediction methods. The results suggest that our CHNet can more accurately predict KRAS mutation status in patients via a multi-task collaborative facilitation and considering global-local information way, which can assist doctors in formulating more personalized treatment strategies for patients.

Clinical, Imaging, and Pathological-Molecular Characteristics Associated with Stage IA Invasive Lung Adenocarcinoma Recurrence After Sub-lobar Resection.

RATIONALE AND OBJECTIVES: This study aimed to investigate the association of clinical, imaging, and pathological-molecular characteristics with the prediction of patient prognosis with stage IA invasive lung adenocarcinoma (ILADC) after sub-lobar resection. MATERIALS AND METHODS: This study assessed 360 patients, including 91 and 269 with and without recurrence 3 years postoperatively, respectively, with stage IA ILADC undergoing preoperative chest computed tomography (CT) scans and subsequent sub-lobar resection at our institution. Their clinical and CT features and histological subtypes and gene mutation status were compared. Binary logistic regression analysis was conducted to identify the independent risk factors for recurrence. An external validation cohort included 113 patients, used to test the model's efficiency. RESULTS: For clinical features, old age, male gender, smokers, and high age-adjusted Charlson comorbidity index (ACCI) were frequently observed in patients with recurrence than those without (all p < 0.05). For CT features, large tumor size, solid-predominant density, spiculation, peripheral fibrosis, type II pleural tag, and pleural adhesion were more common in recurrent patients than non-recurrent ones (all p < 0.05). The regression model revealed old age, large tumor size, solid-predominant density, spiculation, type II pleural tag, and pleural adhesion as independent risk factors for recurrence, with an area under the curve (AUC) of 0.942. The external validation cohort obtained an AUC of 0.958. For phological-molecular features, micropapillary/solid-predominant growth pattern, KRAS, ALK, and NRAS mutation or fusion were more common in the recurrent group, whereas EGFR mutation was more frequent in the non-recurrent group (all p < 0.05). CONCLUSION: Clinical and CT features help predict the prognosis of patients with stage IA ILADC after sub-lobar resection and decide for individualized treatment. Moreover, patients with different prognosis demonstrated different pathological-molecular features.

Accurate Early Detection and EGFR Mutation Status Prediction of Lung Cancer Using Plasma cfDNA Coverage Patterns: A Proof-of-Concept Study.

Lung cancer is a major global health concern with a low survival rate, often due to late-stage diagnosis. Liquid biopsy offers a non-invasive approach to cancer detection and monitoring, utilizing various features of circulating cell-free DNA (cfDNA). In this study, we established two models based on cfDNA coverage patterns at the transcription start sites (TSSs) from 6X whole-genome sequencing: an Early Cancer Screening Model and an EGFR mutation status prediction model. The Early Cancer Screening Model showed encouraging prediction ability, especially for early-stage lung cancer. The EGFR mutation status prediction model exhibited high accuracy in distinguishing between EGFR-positive and wild-type cases. Additionally, cfDNA coverage patterns at TSSs also reflect gene expression patterns at the pathway level in lung cancer patients. These findings demonstrate the potential applications of cfDNA coverage patterns at TSSs in early cancer screening and in cancer subtyping.

A New Perspective on the Effectiveness of FDG PET/CT in Predicting KRAS Mutation in Colon Cancer Cases.

Aim: The main aim of this study was to evaluate the effectiveness of 18F-fluorodeoxyglucose (18FDG) positron emission tomography/computerized tomography (PET/CT) parameters in predicting the Kristen rat sarcoma viral oncogene(KRAS) mutation status of patients with colon cancer. Materials and Methods: Between April 2013 and December 2020, 79 patients who were diagnosed with colon cancer by colonoscopy underwent staging 18FDG PET/CT with this diagnosis and met all the inclusion criteria were included in this study. Clinical and prognostic features and also imaging (18FDG PET/CT and magnetic resonance imaging) reports of the patients were collected and analyzed retrospectively. Results: KRAS mutation was seen in 32 of patients (40.5%). No significant difference was observed between KRAS mutant and wild-type patients in terms of clinical features (tumor location, findings regarding metastasis, T stage, and tumor differentiation grade in patients who underwent surgery) and overall survival. Progression-free survival was significantly shorter in KRAS mutant patients (p = 0.018). Primary tumor standardized uptake value (SUVmean) was significantly higher in KRAS mutant cases in the whole group (p = 0.024) and in patients in whom KRAS analysis was performed only in the primary lesion (p = 0.036). The cutoff value for predicting KRAS mutation status was 7.01 g/mL (area under the curve [AUC]: 0.650, confidence interval [CI] 95%, 0.56-0.74). Conclusions: When colon and rectal cancer cases were evaluated separately, the primary tumor SUVmean value was significantly higher in KRAS mutant colon cancer cases. However, its effectiveness in predicting KRAS mutation status was low, similar to other parameters in the literature.

Structural- and DTI- MRI enable automated prediction of IDH Mutation Status in CNS WHO Grade 2-4 glioma patients: a deep Radiomics Approach.

BACKGROUND: The role of isocitrate dehydrogenase (IDH) mutation status for glioma stratification and prognosis is established. While structural magnetic resonance image (MRI) is a promising biomarker, it may not be sufficient for non-invasive characterisation of IDH mutation status. We investigated the diagnostic value of combined diffusion tensor imaging (DTI) and structural MRI enhanced by a deep radiomics approach based on convolutional neural networks (CNNs) and support vector machine (SVM), to determine the IDH mutation status in Central Nervous System World Health Organization (CNS WHO) grade 2-4 gliomas. METHODS: This retrospective study analyzed the DTI-derived fractional anisotropy (FA) and mean diffusivity (MD) images and structural images including fluid attenuated inversion recovery (FLAIR), non-enhanced T1-, and T2-weighted images of 206 treatment-naïve gliomas, including 146 IDH mutant and 60 IDH-wildtype ones. The lesions were manually segmented by experienced neuroradiologists and the masks were applied to the FA and MD maps. Deep radiomics features were extracted from each subject by applying a pre-trained CNN and statistical description. An SVM classifier was applied to predict IDH status using imaging features in combination with demographic data. RESULTS: We comparatively assessed the CNN-SVM classifier performance in predicting IDH mutation status using standalone and combined structural and DTI-based imaging features. Combined imaging features surpassed stand-alone modalities for the prediction of IDH mutation status [area under the curve (AUC) = 0.846; sensitivity = 0.925; and specificity = 0.567]. Importantly, optimal model performance was noted following the addition of demographic data (patients' age) to structural and DTI imaging features [area under the curve (AUC) = 0.847; sensitivity = 0.911; and specificity = 0.617]. CONCLUSIONS: Imaging features derived from DTI-based FA and MD maps combined with structural MRI, have superior diagnostic value to that provided by standalone structural or DTI sequences. In combination with demographic information, this CNN-SVM model offers a further enhanced non-invasive prediction of IDH mutation status in gliomas.

Comparison of MRI Sequences to Predict IDH Mutation Status in Gliomas Using Radiomics-Based Machine Learning.

OBJECTIVES: Regarding the 2021 World Health Organization (WHO) classification of central nervous system (CNS) tumors, the isocitrate dehydrogenase (IDH) mutation status is one of the most important factors for CNS tumor classification. The aim of our study is to analyze which of the commonly used magnetic resonance imaging (MRI) sequences is best suited to obtain this information non-invasively using radiomics-based machine learning models. We developed machine learning models based on different MRI sequences and determined which of the MRI sequences analyzed yields the highest discriminatory power in predicting the IDH mutation status. MATERIAL AND METHODS: In our retrospective IRB-approved study, we used the MRI images of 106 patients with histologically confirmed gliomas. The MRI images were acquired using the T1 sequence with and without administration of a contrast agent, the T2 sequence, and the Fluid-Attenuated Inversion Recovery (FLAIR) sequence. To objectively compare performance in predicting the IDH mutation status as a function of the MRI sequence used, we included only patients in our study cohort for whom MRI images of all four sequences were available. Seventy-one of the patients had an IDH mutation, and the remaining 35 patients did not have an IDH mutation (IDH wild-type). For each of the four MRI sequences used, 107 radiomic features were extracted from the corresponding MRI images by hand-delineated regions of interest. Data partitioning into training data and independent test data was repeated 100 times to avoid random effects associated with the data partitioning. Feature preselection and subsequent model development were performed using Random Forest, Lasso regression, LDA, and Naïve Bayes. The performance of all models was determined with independent test data. RESULTS: Among the different approaches we examined, the T1-weighted contrast-enhanced sequence was found to be the most suitable for predicting IDH mutations status using radiomics-based machine learning models. Using contrast-enhanced T1-weighted MRI images, our seven-feature model developed with Lasso regression achieved a mean area under the curve (AUC) of 0.846, a mean accuracy of 0.792, a mean sensitivity of 0.847, and a mean specificity of 0.681. The administration of contrast agents resulted in a significant increase in the achieved discriminatory power. CONCLUSIONS: Our analyses show that for the prediction of the IDH mutation status using radiomics-based machine learning models, among the MRI images acquired with the commonly used MRI sequences, the contrast-enhanced T1-weighted images are the most suitable.

Predictive nomograms of repeat intrahepatic recurrence and overall survival after radiofrequency ablation of recurrent colorectal liver metastases.

OBJECTIVES: This study was conducted to develop nomograms for predicting repeat intrahepatic recurrence (rIHR) and overall survival (OS), after radiofrequency ablation (RFA), treatment in patients with recurrent colorectal liver metastases (CLMs) after hepatectomy based on clinicopathologic features. METHODS: A total of 160 consecutive patients with recurrent CLMs after hepatectomy who were treated with ultrasound-guided percutaneous RFA from 2012 to 2022 were retrospectively included. Patients were randomly divided into a training cohort and a validation cohort, with a ratio of 8:2. Potential prognostic factors associated with rIHR and OS, after RFA, were identified by using the competing-risks and Cox proportional hazard models, respectively, and were used to construct the nomogram. The nomogram was evaluated by Harrell's C-index and a calibration curve. RESULTS: The 1-, 2-, and 3-year rIHR rates after RFA were 58.8%, 70.2%, and 74.2%, respectively. The 1-, 3- and 5-year OS rates were 96.3%, 60.4%, and 38.5%, respectively. In the multivariate analysis, mutant RAS, interval from hepatectomy to intrahepatic recurrence ≤ 12 months, CEA level >5 ng/ml, and ablation margin <5 mm were the independent predictive factors for rIHR. Mutant RAS, largest CLM at hepatectomy >3 cm, CEA level >5 ng/ml, and extrahepatic disease were independent predictors of poor OS. Two nomograms for rIHR and OS were constructed using the respective significant variables. In both cohorts, the nomogram demonstrated good discrimination and calibration. CONCLUSIONS: The established nomograms can predict individual risk of rIHR and OS after RFA for recurrent CLMs and contribute to improving individualized management.

Development of End-to-End AI-Based MRI Image Analysis System for Predicting IDH Mutation Status of Patients with Gliomas: Multicentric Validation.

Radiogenomics has shown potential to predict genomic phenotypes from medical images. The development of models using standard-of-care pre-operative MRI images, as opposed to advanced MRI images, enables a broader reach of such models. In this work, a radiogenomics model for IDH mutation status prediction from standard-of-care MRIs in patients with glioma was developed and validated using multicentric data. A cohort of 142 (wild-type: 32.4%) patients with glioma retrieved from the TCIA/TCGA was used to train a logistic regression model to predict the IDH mutation status. The model was evaluated using retrospective data collected in two distinct hospitals, comprising 36 (wild-type: 63.9%) and 53 (wild-type: 75.5%) patients. Model development utilized ROC analysis. Model discrimination and calibration were used for validation. The model yielded an AUC of 0.741 vs. 0.716 vs. 0.938, a sensitivity of 0.784 vs. 0.739 vs. 0.875, and a specificity of 0.657 vs. 0.692 vs. 1.000 on the training, test cohort 1, and test cohort 2, respectively. The assessment of model fairness suggested an unbiased model for age and sex, and calibration tests showed a p < 0.05. These results indicate that the developed model allows the prediction of the IDH mutation status in gliomas using standard-of-care MRI images and does not appear to hold sex and age biases.

Functional Homologous Recombination (HR) Screening Shows the Majority of BRCA1/2-Mutant Breast and Ovarian Cancer Cell Lines Are HR-Proficient.

Tumors with a pathogenic BRCA1/2 mutation are homologous recombination (HR)-deficient (HRD) and consequently sensitive to platinum-based chemotherapy and Poly-[ADP-Ribose]-Polymerase inhibitors (PARPi). We hypothesized that functional HR status better reflects real-time HR status than BRCA1/2 mutation status. Therefore, we determined the functional HR status of 53 breast cancer (BC) and 38 ovarian cancer (OC) cell lines by measuring the formation of RAD51 foci after irradiation. Discrepancies between functional HR and BRCA1/2 mutation status were investigated using exome sequencing, methylation and gene expression data from 50 HR-related genes. A pathogenic BRCA1/2 mutation was found in 10/53 (18.9%) of BC and 7/38 (18.4%) of OC cell lines. Among BRCA1/2-mutant cell lines, 14/17 (82.4%) were HR-proficient (HRP), while 1/74 (1.4%) wild-type cell lines was HRD. For most (80%) cell lines, we explained the discrepancy between functional HR and BRCA1/2 mutation status. Importantly, 12/14 (85.7%) BRCA1/2-mutant HRP cell lines were explained by mechanisms directly acting on BRCA1/2. Finally, functional HR status was strongly associated with COSMIC single base substitution signature 3, but not BRCA1/2 mutation status. Thus, the majority of BRCA1/2-mutant cell lines do not represent a suitable model for HRD. Moreover, exclusively determining BRCA1/2 mutation status may not suffice for platinum-based chemotherapy or PARPi patient selection.

Association of Cytogenetics Aberrations and IGHV Mutations with Outcome in Chronic Lymphocytic Leukemia Patients in a Real-World Clinical Setting.

Immunoglobulin heavy chain variable ( IGHV ) region mutations, TP53 mutation, fluorescence in situ hybridization (FISH), and cytogenetic analysis are the most important prognostic biomarkers used in chronic lymphocytic leukemia (CLL) patients in our daily practice. In real-life environment, there are scarce studies that analyze the correlation of these factors with outcome, mainly referred to time to first treatment (TTFT) and overall survival (OS). This study aimed to typify IGHV mutation status, family usage, FISH aberrations, and complex karyotype (CK) and to analyze the prognostic impact in TTFT and OS in retrospective study of 375 CLL patients from a Spanish cohort. We found unmutated CLL (U-CLL) was associated with more aggressive disease, shorter TTFT (48 vs. 133 months, p < 0.0001), and shorter OS (112 vs. 246 months, p < 0.0001) than the mutated CLL. IGHV3 was the most frequently used IGHV family (46%), followed by IGHV1 (30%) and IGHV4 (16%). IGHV5-51 and IGHV1-69 subfamilies were associated with poor prognosis, while IGHV4 and IGHV2 showed the best outcomes. The prevalence of CK was 15% and was significantly associated with U-CLL. In the multivariable analysis, IGHV2 gene usage and del13q were associated with longer TTFT, while VH1-02, +12, del11q, del17p, and U-CLL with shorter TTFT. Moreover, VH1-69 usage, del11q, del17p, and U-CLL were significantly associated with shorter OS. A comprehensive analysis of genetic prognostic factors provides a more precise information on the outcome of CLL patients. In addition to FISH cytogenetic aberrations, IGHV and TP53 mutations, IGHV gene families, and CK information could help clinicians in the decision-making process.

Enhancing predictability of IDH mutation status in glioma patients at initial diagnosis: a comparative analysis of radiomics from MRI, [18F]FET PET, and TSPO PET.

PURPOSE: According to the World Health Organization classification for tumors of the central nervous system, mutation status of the isocitrate dehydrogenase (IDH) genes has become a major diagnostic discriminator for gliomas. Therefore, imaging-based prediction of IDH mutation status is of high interest for individual patient management. We compared and evaluated the diagnostic value of radiomics derived from dual positron emission tomography (PET) and magnetic resonance imaging (MRI) data to predict the IDH mutation status non-invasively. METHODS: Eighty-seven glioma patients at initial diagnosis who underwent PET targeting the translocator protein (TSPO) using [18F]GE-180, dynamic amino acid PET using [18F]FET, and T1-/T2-weighted MRI scans were examined. In addition to calculating tumor-to-background ratio (TBR) images for all modalities, parametric images quantifying dynamic [18F]FET PET information were generated. Radiomic features were extracted from TBR and parametric images. The area under the receiver operating characteristic curve (AUC) was employed to assess the performance of logistic regression (LR) classifiers. To report robust estimates, nested cross-validation with five folds and 50 repeats was applied. RESULTS: TBRGE-180 features extracted from TSPO-positive volumes had the highest predictive power among TBR images (AUC 0.88, with age as co-factor 0.94). Dynamic [18F]FET PET reached a similarly high performance (0.94, with age 0.96). The highest LR coefficients in multimodal analyses included TBRGE-180 features, parameters from kinetic and early static [18F]FET PET images, age, and the features from TBRT2 images such as the kurtosis (0.97). CONCLUSION: The findings suggest that incorporating TBRGE-180 features along with kinetic information from dynamic [18F]FET PET, kurtosis from TBRT2, and age can yield very high predictability of IDH mutation status, thus potentially improving early patient management.

Conditional survival to assess prognosis in patients with chronic lymphocytic leukemia.

Biomarkers in chronic lymphocytic leukemia (CLL) allow assessment of prognosis. However, the validity of current prognostic biomarkers based on a single assessment point remains unclear for patients who have survived one or more years. Conditional survival (CS) studies that address how prognosis may change over time, especially in prognostic subgroups, are still rare. We performed CS analyses to estimate 5-year survival in 1-year increments, stratified by baseline disease characteristics and known risk factors in two community-based cohorts of CLL patients (Freiburg University Hospital (n = 316) and Augsburg University Hospital (n = 564)) diagnosed between 1984 and 2021. We demonstrate that 5-year CS probability is stable (app. 75%) for the entire CLL patient cohort over 10 years. While age, sex, and stage have no significant impact on CS, patients with high-risk disease features such as non-mutated IGHV, deletion 17p, and high-risk CLL-IPI have a significantly worse prognosis at diagnosis, and 5-year CS steadily decreases with each additional year survived. Our results confirm that CLL patients have a stable survival probability with excess mortality and that the prognosis of high-risk CLL patients declines over time. We infer that CS-based prognostic information is relevant for disease management and counseling of CLL patients.

Development and external validation of MRI-based RAS mutation status prediction model for liver metastases of colorectal cancer.

BACKGROUND: The mutation status of rat sarcoma viral oncogene homolog (RAS) has prognostic significance and serves as a key predictive biomarker for the effectiveness of antiepidermal growth factor receptor (EGFR) therapy. However, there remains a lack of effective models for predicting RAS mutation status in colorectal liver metastases (CRLMs). This study aimed to construct and validate a diagnostic model for predicting RAS mutation status among patients undergoing hepatic resection for CRLMs. METHODS: A diagnostic multivariate prediction model was developed and validated in patients with CRLMs who had undergone hepatectomy between 2014 and 2020. Patients from Institution A were assigned to the model development group (i.e., Development Cohort), while patients from Institutions B and C were assigned to the external validation groups (i.e., Validation Cohort_1 and Validation Cohort_2). The presence of CRLMs was determined by examination of surgical specimens. RAS mutation status was determined by genetic testing. The final predictors, identified by a group of oncologists and radiologists, included several key clinical, demographic, and radiographic characteristics derived from magnetic resonance images. Multiple imputation was performed to estimate the values of missing non-outcome data. A penalized logistic regression model using the adaptive least absolute shrinkage and selection operator penalty was implemented to select appropriate variables for the development of the model. A single nomogram was constructed from the model. The performance of the prediction model, discrimination, and calibration were estimated and reported by the area under the receiver operating characteristic curve (AUC) and calibration plots. Internal validation with a bootstrapping procedure and external validation of the nomogram were assessed. Finally, decision curve analyses were used to characterize the clinical outcomes of the Development and Validation Cohorts. RESULTS: A total of 173 patients were enrolled in this study between January 2014 and May 2020. Of the 173 patients, 117 patients from Institution A were assigned to the Model Development group, while 56 patients (33 from Institution B and 23 from Institution C) were assigned to the Model Validation groups. Forty-six (39.3%) patients harbored RAS mutations in the Development Cohort compared to 14 (42.4%) in Validation Cohort_1 and 8 (34.8%) in Validation Cohort_2. The final model contained the following predictor variables: time of occurrence of CRLMs, location of primary lesion, type of intratumoral necrosis, and early enhancement of liver parenchyma. The diagnostic model based on clinical and MRI data demonstrated satisfactory predictive performance in distinguishing between mutated and wild-type RAS, with AUCs of 0.742 (95% confidence interval [CI]: 0.651─0.834), 0.741 (95% CI: 0.649─0.836), 0.703 (95% CI: 0.514─0.892), and 0.708 (95% CI: 0.452─0.964) in the Development Cohort, bootstrapping internal validation, external Validation Cohort_1 and Validation Cohort_2, respectively. The Hosmer-Lemeshow goodness-of-fit values for the Development Cohort, Validation Cohort_1 and Validation Cohort_2 were 2.868 (p = 0.942), 4.616 (p = 0.465), and 6.297 (p = 0.391), respectively. CONCLUSIONS: Integrating clinical, demographic, and radiographic modalities with a magnetic resonance imaging-based approach may accurately predict the RAS mutation status of CRLMs, thereby aiding in triage and possibly reducing the time taken to perform diagnostic and life-saving procedures. Our diagnostic multivariate prediction model may serve as a foundation for prognostic stratification and therapeutic decision-making.

Treatment Patterns and Prognosis of Palliative Chemotherapy Combined With Targeting Agents in Patients With Unresectable Metastatic Colorectal Cancer: CHOICE, A Multicenter Longitudinal Observational Study.

BACKGROUND/AIM: This study investigated the treatment patterns and prognosis of patients with metastatic or unresectable colorectal cancer (mCRC) treated with chemotherapy with targeting agents. PATIENTS AND METHODS: This longitudinal multicenter study included 963 patients with mCRC who were treated in Korea between 2016 and 2020. Treatment patterns and efficacy were compared according to the mutation status and clinical factors. RESULTS: As first-line therapy, most of the patients (83.5%) received FOLFOX plus bevacizumab (35.4%), followed by FOLFIRI plus bevacizumab (18.8%), FOLFIRI plus cetuximab (17.0%), and FOLFOX plus cetuximab (12.3%). Bevacizumab was the most frequent agent (78.8%) combined with chemotherapy in RAS-mutated CRC, while cetuximab (57.2%) in RAS wild-type CRC. Cetuximab was frequently combined with a doublet regimen in patients with left-sided CRC than in those with right-sided CRC (34.4% vs. 16%). As second-line therapy, most patients (63.4%) also received doublet regimens with bevacizumab, and FOLFIRI plus aflibercept was administered in 15.1%. The objective response rate with FOLFIRI plus cetuximab was significantly higher in patients with left-sided CRC than in those with right-sided CRC (59.2% vs. 30.8%, p=0.008) and marginally higher in patients with RAS wild-type CRC than in those with RAS-mutated CRC (55.6% vs. 0.0%, p=0.092). Progression-free survival (PFS) with FOLFOX plus bevacizumab was significantly shorter than that with FOLFIRI plus bevacizumab (p=0.030) in RAS-mutated CRC, whereas there were no significant differences between regimens in RAS wild-type CRC. CONCLUSION: In patients with unresectable metastatic colorectal cancer, doublet chemotherapy with targeting agents is the most common therapy and efficacy depends on the mutation status as well as clinical factors.

Diagnostic Workup, Treatment Patterns, and Clinical Outcomes in Early-Stage IB-IIIA Non-Small-Cell Lung Cancer Patients in Denmark.

Despite recent improvements in early-stage non-small-cell lung cancer (NSCLC), disease relapse remains challenging. Moreover, real-world evidence on long-term follow-up of disease-free survival (DFS) and recurrence patterns in a large, unselected cohort of early-stage NSCLC patients is lacking. This cohort study aimed to assess clinical characteristics, diagnostic workup, treatment, survival, and risk of disease relapse among early-stage NSCLC patients. Adult patients with stage IB, II, or IIIA NSCLC diagnosed and/or treated at Aarhus University Hospital in Denmark from January 2010 to December 2020 were included and followed-up until May 2021. Comprehensive clinical data were collected from electronic medical records of eligible patients and linked to Danish register data. The study population comprised 1341 early-stage NSCLC patients: 22%, 40%, and 38% were diagnosed with stage IB, II, and IIIA disease, respectively. In total, 42% of patients were tested for epidermal growth factor receptor (EGFR), of whom 10% were EGFR-mutation-positive (EGFRm+). Half of all patients received surgery, and nine percent of patients received stereotactic body radiation therapy (SBRT). Disease-free survival 5 years post-diagnosis was 49%, 42%, and 22% for stage IB, II, and stage IIIA patients, respectively. DFS improved over time both for patients treated with surgery and SBRT. However, disease relapse remained a challenge, with approximately 40% of stage IIIA having relapsed 3 years post-diagnosis. This study contributes important knowledge that puts clinical trials on new perioperative treatment modalities for early-stage NSCLC patients into perspective. Our findings cover an essential evidence gap on real-world DFS and recurrence dynamics, confirming that despite an improvement in DFS over time and across different treatment modalities, disease relapse remains a monumental challenge. Therefore, better treatment strategies are needed.

Deep wavelet scattering orthogonal fusion network for glioma IDH mutation status prediction.

Accurately predicting the isocitrate dehydrogenase (IDH) mutation status of gliomas is greatly significant for formulating appropriate treatment plans and evaluating the prognoses of gliomas. Although existing studies can accurately predict the IDH mutation status of gliomas based on multimodal magnetic resonance (MR) images and machine learning methods, most of these methods cannot fully explore multimodal information and effectively predict IDH status for datasets acquired from multiple centers. To address this issue, a novel wavelet scattering (WS)-based orthogonal fusion network (WSOFNet) was proposed in this work to predict the IDH mutation status of gliomas from multiple centers. First, transformation-invariant features were extracted from multimodal MR images with a WS network, and then the multimodal WS features were used instead of the original images as the inputs of WSOFNet and were fully fused through an adaptive multimodal feature fusion module (AMF2M) and an orthogonal projection module (OPM). Finally, the fused features were input into a fully connected classifier to predict IDH mutation status. In addition, to achieve improved prediction accuracy, four auxiliary losses were also used in the feature extraction modules. The comparison results showed that the prediction area under the curve (AUC) of WSOFNet on a single-center dataset was 0.9966 and that on a multicenter dataset was approximately 0.9655, which was at least 3.9% higher than that of state-of-the-art methods. Moreover, the ablation experimental results also proved that the adaptive multimodal feature fusion strategy based on orthogonal projection could effectively improve the prediction performance of the model, especially for an external validation dataset.

Mutation status analysis of 58 patients with advanced ALK fusion gene positive non small cell lung cancer.

PURPOSE: To analyze the characteristics and prognostic values of Anaplastic Lymphoma Kinase (ALK) fusion gene partner, gene subtype and abundance in tumor tissues of advanced Non Small Cell Lung Cancer (NSCLC) patients with positive ALK fusion gene and to explore the best treatment mode of ALK-Tyrosine Kinase Inhibitors(TKIs). METHODS: Cases of advanced NSCLC patients with ALK positive confirmed by both Next Generation Sequencing (NGS) and immunohistochemistry were retrospectively collected. The relationships of Overall Survival (OS)/Progression Free Survival (PFS) between different mutation subtypes, mutation abundance, clinicopathological features were analyzed. OS/PFS between different treatment mode of ALK inhibitors were compared. RESULTS: Fifty-eight patients were enrolled. There were diverse fusion partners. Five subtypes of Echinoderm Microtubule-associated protein-Like 4 gene (EML4)-ALK fusion mutation were detected: V1,V2,V3,V5 and V7. The mutation abundance ranged from 0.13 to 27.77%, with a median of 5.34%. The abundance of V2 and V5 was higher than V1 and V3 respectively. There was no difference in OS between the low abundance group(≤ 5.34%) and the high abundance group(>5.34%) (P = 0.434). PFS of second-generation ALK inhibitors as first-line treatment was longer than that of Crizotinib as first-line (P<0.001). Never smokers had longer OS than current smokers(P = 0.001). CONCLUSIONS: There are differences in abundance between different fusion partners and subtypes in advanced NSCLC with positive ALK. OS is not associated with subtypes, mutation abundance and first line treatment option of either generation of ALK inhibitors. Smoking is a poor prognostic factor.

Differential Distribution of Brain Metastases from Non-Small Cell Lung Cancer Based on Mutation Status.

Non-small cell lung cancer (NSCLC) has a high rate of brain metastasis. The purpose of this study was to assess the differential distribution of brain metastases from primary NSCLC based on mutation status. Brain MRI scans of patients with brain metastases from primary NSCLC were retrospectively analyzed. Brain metastatic tumors were grouped according to mutation status of their primary NSCLC and the neuroimaging features of these brain metastases were analyzed. A total of 110 patients with 1386 brain metastases from primary NSCLC were included in this study. Gray matter density at the tumor center peaked at ~0.6 for all mutations. The median depths of tumors were 7.9 mm, 8.7 mm and 9.1 mm for EGFR, ALK and KRAS mutation groups, respectively (p = 0.044). Brain metastases for the EGFR mutation-positive group were more frequently located in the left cerebellum, left cuneus, left precuneus and right precentral gyrus. In the ALK mutation-positive group, brain metastases were more frequently located in the right middle occipital gyrus, right posterior cingulate, right precuneus, right precentral gyrus and right parietal lobe. In the KRAS mutation-positive patient group, brain metastases were more frequently located in the posterior left cerebellum. Our study showed differential spatial distribution of brain metastases in patients with NSCLC according to their mutation status. Information regarding distribution of brain metastases is clinically relevant as it could be helpful to guide treatment planning for targeted therapy, and for predicting prognosis.

Systematic Review, Meta-Analysis and Radiomics Quality Score Assessment of CT Radiomics-Based Models Predicting Tumor EGFR Mutation Status in Patients with Non-Small-Cell Lung Cancer.

Assessment of the quality and current performance of computed tomography (CT) radiomics-based models in predicting epidermal growth factor receptor (EGFR) mutation status in patients with non-small-cell lung carcinoma (NSCLC). Two medical literature databases were systematically searched, and articles presenting original studies on CT radiomics-based models for predicting EGFR mutation status were retrieved. Forest plots and related statistical tests were performed to summarize the model performance and inter-study heterogeneity. The methodological quality of the selected studies was assessed via the Radiomics Quality Score (RQS). The performance of the models was evaluated using the area under the curve (ROC AUC). The range of the Risk RQS across the selected articles varied from 11 to 24, indicating a notable heterogeneity in the quality and methodology of the included studies. The average score was 15.25, which accounted for 42.34% of the maximum possible score. The pooled Area Under the Curve (AUC) value was 0.801, indicating the accuracy of CT radiomics-based models in predicting the EGFR mutation status. CT radiomics-based models show promising results as non-invasive alternatives for predicting EGFR mutation status in NSCLC patients. However, the quality of the studies using CT radiomics-based models varies widely, and further harmonization and prospective validation are needed before the generalization of these models.