Personalized prediction of immunotherapy response in lung cancer patients using advanced radiomics and deep learning.

BACKGROUND: Lung cancer (LC) is a leading cause of cancer-related mortality, and immunotherapy (IO) has shown promise in treating advanced-stage LC. However, identifying patients likely to benefit from IO and monitoring treatment response remains challenging. This study aims to develop a predictive model for progression-free survival (PFS) in LC patients with IO based on clinical features and advanced imaging biomarkers. MATERIALS AND METHODS: A retrospective analysis was conducted on a cohort of 206 LC patients receiving IO treatment. Pre-treatment computed tomography images were used to extract advanced imaging biomarkers, including intratumoral and peritumoral-vasculature radiomics. Clinical features, including age, gene status, hematology, and staging, were also collected. Key radiomic and clinical features for predicting IO outcomes were identified using a two-step feature selection process, including univariate Cox regression and chi-squared test, followed by sequential forward selection. The DeepSurv model was constructed to predict PFS based on clinical and radiomic features. Model performance was evaluated using the area under the time-dependent receiver operating characteristic curve (AUC) and concordance index (C-index). RESULTS: Combining radiomics of intratumoral heterogeneity and peritumoral-vasculature with clinical features demonstrated a significant enhancement (p < 0.001) in predicting IO response. The proposed DeepSurv model exhibited a prediction performance with AUCs ranging from 0.76 to 0.80 and a C-index of 0.83. Furthermore, the predicted personalized PFS curves revealed a significant difference (p < 0.05) between patients with favorable and unfavorable prognoses. CONCLUSIONS: Integrating intratumoral and peritumoral-vasculature radiomics with clinical features enabled the development of a predictive model for PFS in LC patients with IO. The proposed model's capability to estimate individualized PFS probability and differentiate the prognosis status held promise to facilitate personalized medicine and improve patient outcomes in LC.

Systematic review and meta-analysis of deep learning applications in computed tomography lung cancer segmentation.

BACKGROUND: Accurate segmentation of lung tumors on chest computed tomography (CT) scans is crucial for effective diagnosis and treatment planning. Deep Learning (DL) has emerged as a promising tool in medical imaging, particularly for lung cancer segmentation. However, its efficacy across different clinical settings and tumor stages remains variable. METHODS: We conducted a comprehensive search of PubMed, Embase, and Web of Science until November 7, 2023. We assessed the quality of these studies by using the Checklist for Artificial Intelligence in Medical Imaging and the Quality Assessment of Diagnostic Accuracy Studies-2 tools. This analysis included data from various clinical settings and stages of lung cancer. Key performance metrics, such as the Dice similarity coefficient, were pooled, and factors affecting algorithm performance, such as clinical setting, algorithm type, and image processing techniques, were examined. RESULTS: Our analysis of 37 studies revealed a pooled Dice score of 79 % (95 % CI: 76 %-83 %), indicating moderate accuracy. Radiotherapy studies had a slightly lower score of 78 % (95 % CI: 74 %-82 %). A temporal increase was noted, with recent studies (post-2022) showing improvement from 75 % (95 % CI: 70 %-81 %). to 82 % (95 % CI: 81 %-84 %). Key factors affecting performance included algorithm type, resolution adjustment, and image cropping. QUADAS-2 assessments identified ambiguous risks in 78 % of studies due to data interval omissions and concerns about generalizability in 8 % due to nodule size exclusions, and CLAIM criteria highlighted areas for improvement, with an average score of 27.24 out of 42. CONCLUSION: This meta-analysis demonstrates DL algorithms' promising but varied efficacy in lung cancer segmentation, particularly higher efficacy noted in early stages. The results highlight the critical need for continued development of tailored DL models to improve segmentation accuracy across diverse clinical settings, especially in advanced cancer stages with greater challenges. As recent studies demonstrate, ongoing advancements in algorithmic approaches are crucial for future applications.

Progress in Serial Imaging for Prognostic Stratification of Lung Cancer Patients Receiving Immunotherapy: A Systematic Review and Meta-Analysis.

Immunotherapy, particularly with checkpoint inhibitors, has revolutionized non-small cell lung cancer treatment. Enhancing the selection of potential responders is crucial, and researchers are exploring predictive biomarkers. Delta radiomics, a derivative of radiomics, holds promise in this regard. For this study, a meta-analysis was conducted that adhered to PRISMA guidelines, searching PubMed, Embase, Web of Science, and the Cochrane Library for studies on the use of delta radiomics in stratifying lung cancer patients receiving immunotherapy. Out of 223 initially collected studies, 10 were included for qualitative synthesis. Stratifying patients using radiomic models, the pooled analysis reveals a predictive power with an area under the curve of 0.81 (95% CI 0.76-0.86, p < 0.001) for 6-month response, a pooled hazard ratio of 4.77 (95% CI 2.70-8.43, p < 0.001) for progression-free survival, and 2.15 (95% CI 1.73-2.66, p < 0.001) for overall survival at 6 months. Radiomics emerges as a potential prognostic predictor for lung cancer, but further research is needed to compare traditional radiomics and deep-learning radiomics.

Evaluating the Potential of Delta Radiomics for Assessing Tyrosine Kinase Inhibitor Treatment Response in Non-Small Cell Lung Cancer Patients.

Our study aimed to harness the power of CT scans, observed over time, in predicting how lung adenocarcinoma patients might respond to a treatment known as EGFR-TKI. Analyzing scans from 322 advanced stage lung cancer patients, we identified distinct image-based patterns. By integrating these patterns with comprehensive clinical information, such as gene mutations and treatment regimens, our predictive capabilities were significantly enhanced. Interestingly, the precision of these predictions, particularly related to radiomics features, diminished when data from various centers were combined, suggesting that the approach requires standardization across facilities. This novel method offers a potential pathway to anticipate disease progression in lung adenocarcinoma patients treated with EGFR-TKI, laying the groundwork for more personalized treatments. To further validate this approach, extensive studies involving a larger cohort are pivotal.

Federated Learning: A Cross-Institutional Feasibility Study of Deep Learning Based Intracranial Tumor Delineation Framework for Stereotactic Radiosurgery.

BACKGROUND: Deep learning-based segmentation algorithms usually required large or multi-institute data sets to improve the performance and ability of generalization. However, protecting patient privacy is a key concern in the multi-institutional studies when conventional centralized learning (CL) is used. PURPOSE: To explores the feasibility of a proposed lesion delineation for stereotactic radiosurgery (SRS) scheme for federated learning (FL), which can solve decentralization and privacy protection concerns. STUDY TYPE: Retrospective. SUBJECTS: 506 and 118 vestibular schwannoma patients aged 15-88 and 22-85 from two institutes, respectively; 1069 and 256 meningioma patients aged 12-91 and 23-85, respectively; 574 and 705 brain metastasis patients aged 26-92 and 28-89, respectively. FIELD STRENGTH/SEQUENCE: 1.5T, spin-echo, and gradient-echo [Correction added after first online publication on 21 August 2023. Field Strength has been changed to "1.5T" from "5T" in this sentence.]. ASSESSMENT: The proposed lesion delineation method was integrated into an FL framework, and CL models were established as the baseline. The effect of image standardization strategies was also explored. The dice coefficient was used to evaluate the segmentation between the predicted delineation and the ground truth, which was manual delineated by neurosurgeons and a neuroradiologist. STATISTICAL TESTS: The paired t-test was applied to compare the mean for the evaluated dice scores (p < 0.05). RESULTS: FL performed the comparable mean dice coefficient to CL for the testing set of Taipei Veterans General Hospital regardless of standardization and parameter; for the Taichung Veterans General Hospital data, CL significantly (p < 0.05) outperformed FL while using bi-parameter, but comparable results while using single-parameter. For the non-SRS data, FL achieved the comparable applicability to CL with mean dice 0.78 versus 0.78 (without standardization), and outperformed to the baseline models of two institutes. DATA CONCLUSION: The proposed lesion delineation successfully implemented into an FL framework. The FL models were applicable on SRS data of each participating institute, and the FL exhibited comparable mean dice coefficient to CL on non-SRS dataset. Standardization strategies would be recommended when FL is used. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: Stage 1.

Application of Radiomics in Prognosing Lung Cancer Treated with Epidermal Growth Factor Receptor Tyrosine Kinase Inhibitors: A Systematic Review and Meta-Analysis.

In the context of non-small cell lung cancer (NSCLC) patients treated with EGFR tyrosine kinase inhibitors (TKIs), this research evaluated the prognostic value of CT-based radiomics. A comprehensive systematic review and meta-analysis of studies up to April 2023, which included 3111 patients, was conducted. We utilized the Quality in Prognosis Studies (QUIPS) tool and radiomics quality scoring (RQS) system to assess the quality of the included studies. Our analysis revealed a pooled hazard ratio for progression-free survival of 2.80 (95% confidence interval: 1.87-4.19), suggesting that patients with certain radiomics features had a significantly higher risk of disease progression. Additionally, we calculated the pooled Harrell's concordance index and area under the curve (AUC) values of 0.71 and 0.73, respectively, indicating good predictive performance of radiomics. Despite these promising results, further studies with consistent and robust protocols are needed to confirm the prognostic role of radiomics in NSCLC.

Predicting survival after radiosurgery in patients with lung cancer brain metastases using deep learning of radiomics and EGFR status.

The early prediction of overall survival (OS) in patients with lung cancer brain metastases (BMs) after Gamma Knife radiosurgery (GKRS) can facilitate patient management and outcome improvement. However, the disease progression is influenced by multiple factors, such as patient characteristics and treatment strategies, and hence satisfactory performance of OS prediction remains challenging. Accordingly, we proposed a deep learning approach based on comprehensive predictors, including clinical, imaging, and genetic information, to accomplish reliable and personalized OS prediction in patients with BMs after receiving GKRS. Overall 1793 radiomic features extracted from pre-GKRS magnetic resonance images (MRI), clinical information, and epidermal growth factor receptor (EGFR) mutation status were retrospectively collected from 237 BM patients who underwent GKRS. DeepSurv, a multi-layer perceptron model, with 4 different aggregation methods of radiomics was applied to predict personalized survival curves and survival status at 3, 6, 12, and 24 months. The model combining clinical features, EGFR status, and radiomics from the largest BM showed the best prediction performance with concordance index of 0.75 and achieved areas under the curve of 0.82, 0.80, 0.84, and 0.92 for predicting survival status at 3, 6, 12, and 24 months, respectively. The DeepSurv model showed a significant improvement (p < 0.001) in concordance index compared to the validated lung cancer BM prognostic molecular markers. Furthermore, the model provided a novel estimate of the risk-of-death period for patients. The personalized survival curves generated by the DeepSurv model effectively predicted the risk-of-death period which could facilitate personalized management of patients with lung cancer BMs.

A radiomics-based deep learning approach to predict progression free-survival after tyrosine kinase inhibitor therapy in non-small cell lung cancer.

BACKGROUND: The epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors (TKIs) are a first-line therapy for non-small cell lung cancer (NSCLC) with EGFR mutations. Approximately half of the patients with EGFR-mutated NSCLC are treated with EGFR-TKIs and develop disease progression within 1 year. Therefore, the early prediction of tumor progression in patients who receive EGFR-TKIs can facilitate patient management and development of treatment strategies. We proposed a deep learning approach based on both quantitative computed tomography (CT) characteristics and clinical data to predict progression-free survival (PFS) in patients with advanced NSCLC after EGFR-TKI treatment. METHODS: A total of 593 radiomic features were extracted from pretreatment chest CT images. The DeepSurv models for the progression risk stratification of EGFR-TKI treatment were proposed based on CT radiomic and clinical features from 270 stage IIIB-IV EGFR-mutant NSCLC patients. Time-dependent PFS predictions at 3, 12, 18, and 24 months and estimated personalized PFS curves were calculated using the DeepSurv models. RESULTS: The model combining clinical and radiomic features demonstrated better prediction performance than the clinical model. The model achieving areas under the curve of 0.76, 0.77, 0.76, and 0.86 can predict PFS at 3, 12, 18, and 24 months, respectively. The personalized PFS curves showed significant differences (p < 0.003) between groups with good (PFS > median) and poor (PFS < median) tumor control. CONCLUSIONS: The DeepSurv models provided reliable multi-time-point PFS predictions for EGFR-TKI treatment. The personalized PFS curves can help make accurate and individualized predictions of tumor progression. The proposed deep learning approach holds promise for improving the pre-TKI personalized management of patients with EGFR-mutated NSCLC.

Application of artificial intelligence to stereotactic radiosurgery for intracranial lesions: detection, segmentation, and outcome prediction.

BACKGROUND: Rapid evolution of artificial intelligence (AI) prompted its wide application in healthcare systems. Stereotactic radiosurgery served as a good candidate for AI model development and achieved encouraging result in recent years. This article aimed at demonstrating current AI application in radiosurgery. METHODS: Literatures published in PubMed during 2010-2022, discussing AI application in stereotactic radiosurgery were reviewed. RESULTS: AI algorithms, especially machine learning/deep learning models, have been administered to different aspect of stereotactic radiosurgery. Spontaneous tumor detection and automated lesion delineation or segmentation were two of the promising application, which could be further extended to longitudinal treatment follow-up. Outcome prediction utilized machine learning algorithms with radiomic-based analysis was another well-established application. CONCLUSIONS: Stereotactic radiosurgery has taken a lead role in AI development. Current achievement, limitation, and further investigation was summarized in this article.

Lesion delineation framework for vestibular schwannoma, meningioma and brain metastasis for gamma knife radiosurgery using stereotactic magnetic resonance images.

BACKGROUND AND OBJECTIVE: GKRS is an effective treatment for smaller intracranial tumors with a high control rate and low risk of complications. Target delineation in medical MR images is essential in the planning of GKRS and follow-up. A deep learning-based algorithm can effectively segment the targets from medical images and has been widely explored. However, state-of-the-art deep learning-based target delineation uses fixed sizes, and the isotropic voxel size may not be suitable for stereotactic MR images which use different anisotropic voxel sizes and numbers of slices according to the lesion size and location for clinical GKRS planning. This study developed an automatic deep learning-based segmentation scheme for stereotactic MR images. METHODS: We retrospectively collected stereotactic MR images from 506 patients with VS, 1,069 patients with meningioma and 574 patients with BM who had been treated using GKRS; the lesion contours and individual T1W+C and T2W MR images were extracted from the GammaPlan system. The three-dimensional patching-based training strategy and dual-pathway architecture were used to manage inconsistent FOVs and anisotropic voxel size. Furthermore, we used two-parametric MR image as training input to segment the regions with different image characteristics (e.g., cystic lesions) effectively. RESULTS: Our results for VS and BM demonstrated that the model trained using two-parametric MR images significantly outperformed the model trained using single-parametric images with median Dice coefficients (0.91, 0.05 versus 0.90, 0.06, and 0.82, 0.23 versus 0.78, 0.34, respectively), whereas predicted delineations in meningiomas using the dual-pathway model were dominated by single-parametric images (median Dice coefficients 0.83, 0.17 versus 0.84, 0.22). Finally, we combined three data sets to train the models, achieving the comparable or even higher testing median Dice (VS: 0.91, 0.07; meningioma: 0.83, 0.22; BM: 0.84, 0.23) in three diseases while using two-parametric as input. CONCLUSIONS: Our proposed deep learning-based tumor segmentation scheme was successfully applied to multiple types of intracranial tumor (VS, meningioma and BM) undergoing GKRS and for segmenting the tumor effectively from stereotactic MR image volumes for use in GKRS planning.

Radiomics-Based Deep Learning Prediction of Overall Survival in Non-Small-Cell Lung Cancer Using Contrast-Enhanced Computed Tomography.

Patient outcomes of non-small-cell lung cancer (NSCLC) vary because of tumor heterogeneity and treatment strategies. This study aimed to construct a deep learning model combining both radiomic and clinical features to predict the overall survival of patients with NSCLC. To improve the reliability of the proposed model, radiomic analysis complying with the Image Biomarker Standardization Initiative and the compensation approach to integrate multicenter datasets were performed on contrast-enhanced computed tomography (CECT) images. Pretreatment CECT images and the clinical data of 492 patients with NSCLC from two hospitals were collected. The deep neural network architecture, DeepSurv, with the input of radiomic and clinical features was employed. The performance of survival prediction model was assessed using the C-index and area under the curve (AUC) 8, 12, and 24 months after diagnosis. The performance of survival prediction that combined eight radiomic features and five clinical features outperformed that solely based on radiomic or clinical features. The C-index values of the combined model achieved 0.74, 0.75, and 0.75, respectively, and AUC values of 0.76, 0.74, and 0.73, respectively, 8, 12, and 24 months after diagnosis. In conclusion, combining the traits of pretreatment CECT images, lesion characteristics, and treatment strategies could effectively predict the survival of patients with NSCLC using a deep learning model.

Radiomics-Based Predictive Model of Radiation-Induced Liver Disease in Hepatocellular Carcinoma Patients Receiving Stereo-Tactic Body Radiotherapy.

(1) Background: The application of stereotactic body radiation therapy (SBRT) in hepatocellular carcinoma (HCC) limited the risk of the radiation-induced liver disease (RILD) and we aimed to predict the occurrence of RILD more accurately. (2) Methods: 86 HCC patients were enrolled. We identified key predictive factors from clinical, radiomic, and dose-volumetric parameters using a multivariate analysis, sequential forward selection (SFS), and a K-nearest neighbor (KNN) algorithm. We developed a predictive model for RILD based on these factors, using the random forest or logistic regression algorithms. (3) Results: Five key predictive factors in the training set were identified, including the albumin-bilirubin grade, difference average, strength, V5, and V30. After model training, the F1 score, sensitivity, specificity, and accuracy of the final random forest model were 0.857, 100, 93.3, and 94.4% in the test set, respectively. Meanwhile, the logistic regression model yielded an F1 score, sensitivity, specificity, and accuracy of 0.8, 66.7, 100, and 94.4% in the test set, respectively. (4) Conclusions: Based on clinical, radiomic, and dose-volumetric factors, our models achieved satisfactory performance on the prediction of the occurrence of SBRT-related RILD in HCC patients. Before undergoing SBRT, the proposed models may detect patients at high risk of RILD, allowing to assist in treatment strategies accordingly.

Radiomics-based Prediction of Re-hemorrhage in Cerebral Cavernous Malformation after Gamma Knife Radiosurgery.

We conducted a retrospective study of long-term follow-ups in patients with cerebral cavernous malformation (CCM) treated by Gamma Knife radiosurgery (GKRS). CCM is one of the common cerebral vascular diseases. Hemorrhage is a common and dangerous symptom of CCMs, and re-hemorrhage may still occur in 30% of patients after the treatment of GKRS. We aim to identify the reliable imaging biomarkers using radiomics of magnetic resonance images (MRI) to predict the re-hemorrhage after GKRS.Clinical Relevance- This study reported the longitudinal changes of MRI radiomic features in CCM after GKRS. Combining machine-learning approach with the longitudinal radiomic features can predict the re-hemorrhage of CCM after GKRS to guide the clinical management.

Comparison of Conventional and Radiomic Features between 18F-FBPA PET/CT and PET/MR.

Boron-10-containing positron emission tomography (PET) radio-tracer, 18F-FBPA, has been used to evaluate the feasibility and treatment outcomes of Boron neutron capture therapy (BNCT). The clinical use of PET/MR is increasing and reveals its benefit in certain applications. However, the PET/CT is still the most widely used modality for daily PET practice due to its high quantitative accuracy and relatively low cost. Considering the different attenuation correction maps between PET/CT and PET/MR, comparison of derived image features from these two modalities is critical to identify quantitative imaging biomarkers for diagnosis and prognosis. This study aimed to investigate the comparability of image features extracted from 18F-FBPA PET/CT and PET/MR. A total of 15 patients with malignant brain tumor who underwent 18F-FBPA examinations using both PET/CT and PET/MR on the same day were retrospectively analyzed. Overall, four conventional imaging characteristics and 449 radiomic features were calculated from PET/CT and PET/MR, respectively. A linear regression model and intraclass correlation coefficient (ICC) were estimated to evaluate the comparability of derived features between two modalities. Features were classified into strong, moderate, and weak comparability based on coefficient of determination (r2) and ICC. All of the conventional features, 81.2% of histogram, 37.5% of geometry, 51.5% of texture, and 25% of wavelet-based features, showed strong comparability between PET/CT and PET/MR. With regard to the wavelet filtering, radiomic features without filtering (61.2%) or with low-pass filtering (59.2%) along three axes produced strong comparability between the two modalities. However, only 8.2% of the features with high-pass filtering showed strong comparability. The linear regression models were provided for the features with strong and moderate consensus to interchange the quantitative features between the PET/CT and the PET/MR. All of the conventional and 71% of the radiomic (mostly histogram and texture) features were sufficiently stable and could be interchanged between 18F-FBPA PET with different hybrid modalities using the proposed equations. Our findings suggested that the image features high interchangeability may facilitate future studies in comparing PET/CT and PET/MR.

Fractionated deep-inspiration breath-hold ZTE Compared with Free-breathing four-dimensional ZTE for detecting pulmonary nodules in oncological patients underwent PET/MRI.

The zero echo time (ZTE) technique has improved the detection of lung nodules in PET/MRI but respiratory motion remains a challenge in lung scan. We investigated the feasibility and performance of fractionated deep-inspiration breath-hold (FDIBH) three-dimensional (3D) ZTE FDG PET/MRI for assessing lung nodules in patients with proved malignancy. Sixty patients who had undergone ZTE FDG PET/MRI and chest CT within a three-day interval were retrospectively included. Lung nodules less than 2 mm were excluded for analysis. Two physicians checked the adequacy of FDIBH ZTE and compared the lung nodule detection rates of FDIBH 3D ZTE and free-breathing (FB) four-dimensional (4D) ZTE, with chest CT as the reference standard. FDIBH resolved the effect of respiratory motion in 49 patients. The mean number and size of the pulmonary nodules identified in CT were 15 ± 31.3 per patient and 5.9 ± 4.6 mm in diameter. The overall nodule detection rate was 71% for FDIBH 3D ZTE and 70% for FB 4D ZTE (p = 0.73). FDIBH 3D ZTE significantly outperformed FB 4DZTE in detecting lung base nodules (72% and 68%; p = 0.03), especially for detecting those less than 6 mm (61% and 55%; p = 0.03). High inter-rater reliability for FDIBH 3D ZTE and FB 4D ZTE (k = 0.9 and 0.92) was noted. In conclusion, the capability of FDIBH 3D ZTE in respiratory motion resolution was limited with a technical failure rate of 18%. However, it could provide full expansion of the lung in a shorter scan time which enabled better detection of nodules (< 6 mm) in basal lungs, compared to FB 4D ZTE.

Enhancement of Radiosurgical Treatment Outcome Prediction Using MRI Radiomics in Patients with Non-Small Cell Lung Cancer Brain Metastases.

The diagnosis of brain metastasis (BM) is commonly observed in non-small cell lung cancer (NSCLC) with poor outcomes. Accordingly, developing an approach to early predict BM response to Gamma Knife radiosurgery (GKRS) may benefit the patient treatment and monitoring. A total of 237 NSCLC patients with BMs (for survival prediction) and 256 patients with 976 BMs (for prediction of local tumor control) treated with GKRS were retrospectively analyzed. All the survival data were recorded without censoring, and the status of local tumor control was determined by comparing the last MRI follow-up in patients' lives with the pre-GKRS MRI. Overall 1763 radiomic features were extracted from pre-radiosurgical magnetic resonance images. Three prediction models were constructed, using (1) clinical data, (2) radiomic features, and (3) clinical and radiomic features. Support vector machines with a 30% hold-out validation approach were constructed. For treatment outcome predictions, the models derived from both the clinical and radiomics data achieved the best results. For local tumor control, the combined model achieved an area under the curve (AUC) of 0.95, an accuracy of 90%, a sensitivity of 91%, and a specificity of 89%. For patient survival, the combined model achieved an AUC of 0.81, an accuracy of 77%, a sensitivity of 78%, and a specificity of 80%. The pre-radiosurgical radiomics data enhanced the performance of local tumor control and survival prediction models in NSCLC patients with BMs treated with GRKS. An outcome prediction model based on radiomics combined with clinical features may guide therapy in these patients.

Magnetic resonance radiomics features and prognosticators in different molecular subtypes of pediatric Medulloblastoma.

PURPOSE: Medulloblastoma (MB) is a highly malignant pediatric brain tumor. In the latest classification, medulloblastoma is divided into four distinct groups: wingless (WNT), sonic hedgehog (SHH), Group 3, and Group 4. We analyzed the magnetic resonance imaging radiomics features to find the imaging surrogates of the 4 molecular subgroups of MB. MATERIAL AND METHODS: Frozen tissue, imaging data, and clinical data of 38 patients with medulloblastoma were included from Taipei Medical University Hospital and Taipei Veterans General Hospital. Molecular clustering was performed based on the gene expression level of 22 subgroup-specific signature genes. A total 253 magnetic resonance imaging radiomic features were generated from each subject for comparison between different molecular subgroups. RESULTS: Our cohort consisted of 7 (18.4%) patients with WNT medulloblastoma, 12 (31.6%) with SHH tumor, 8 (21.1%) with Group 3 tumor, and 11 (28.9%) with Group 4 tumor. 8 radiomics gray-level co-occurrence matrix texture (GLCM) features were significantly different between 4 molecular subgroups of MB. In addition, for tumors with higher values in a gray-level run length matrix feature-Short Run Low Gray-Level Emphasis, patients have shorter survival times than patients with low values of this feature (p = 0.04). The receiver operating characteristic analysis revealed optimal performance of the preliminary prediction model based on GLCM features for predicting WNT, Group 3, and Group 4 MB (area under the curve = 0.82, 0.72, and 0.78, respectively). CONCLUSION: The preliminary result revealed that 8 contrast-enhanced T1-weighted imaging texture features were significantly different between 4 molecular subgroups of MB. Together with the prediction models, the radiomics features may provide suggestions for stratifying patients with MB into different risk groups.

Applying artificial intelligence to longitudinal imaging analysis of vestibular schwannoma following radiosurgery.

Artificial intelligence (AI) has been applied with considerable success in the fields of radiology, pathology, and neurosurgery. It is expected that AI will soon be used to optimize strategies for the clinical management of patients based on intensive imaging follow-up. Our objective in this study was to establish an algorithm by which to automate the volumetric measurement of vestibular schwannoma (VS) using a series of parametric MR images following radiosurgery. Based on a sample of 861 consecutive patients who underwent Gamma Knife radiosurgery (GKRS) between 1993 and 2008, the proposed end-to-end deep-learning scheme with automated pre-processing pipeline was applied to a series of 1290 MR examinations (T1W+C, and T2W parametric MR images). All of which were performed under consistent imaging acquisition protocols. The relative volume difference (RVD) between AI-based volumetric measurements and clinical measurements performed by expert radiologists were + 1.74%, - 0.31%, - 0.44%, - 0.19%, - 0.01%, and + 0.26% at each follow-up time point, regardless of the state of the tumor (progressed, pseudo-progressed, or regressed). This study outlines an approach to the evaluation of treatment responses via novel volumetric measurement algorithm, and can be used longitudinally following GKRS for VS. The proposed deep learning AI scheme is applicable to longitudinal follow-up assessments following a variety of therapeutic interventions.

Prediction of pseudoprogression and long-term outcome of vestibular schwannoma after Gamma Knife radiosurgery based on preradiosurgical MR radiomics.

BACKGROUND AND PURPOSE: Gamma Knife radiosurgery (GKRS) is a safe and effective treatment modality with a long-term tumor control rate over 90% for vestibular schwannoma (VS). However, numerous tumors may undergo a transient pseudoprogression during 6-18 months after GKRS followed by a long-term volume reduction. The aim of this study is to determine whether the radiomics analysis based on preradiosurgical MRI data could predict the pseudoprogression and long-term outcome of VS after GKRS. MATERIALS AND METHODS: A longitudinal dataset of patients with VS treated by single GKRS were retrospectively collected. Overall 336 patients with no previous craniotomy for tumor removal and a median of 65-month follow-up period after radiosurgery were finally included in this study. In total 1763 radiomic features were extracted from the multiparameteric MRI data before GKRS followed by the machine-learning classification. RESULTS: We constructed a two-level machine-learning model to predict the long-term outcome and the occurrence of transient pseudoprogression after GKRS separately. The prediction of long-term outcome achieved an accuracy of 88.4% based on five radiomic features describing the variation of T2-weighted intensity and inhomogeneity of contrast enhancement in tumor. The prediction of transient pseudoprogression achieved an accuracy of 85.0% based on another five radiomic features associated with the inhomogeneous hypointensity pattern of contrast enhancement and the variation of T2-weighted intensity. CONCLUSION: The proposed machine-learning model based on the preradiosurgical MR radiomics provides a potential to predict the pseudoprogression and long-term outcome of VS after GKRS, which can benefit the treatment strategy in clinical practice.

Combining analysis of multi-parametric MR images into a convolutional neural network: Precise target delineation for vestibular schwannoma treatment planning.

Manual delineation of vestibular schwannoma (VS) by magnetic resonance (MR) imaging is required for diagnosis, radiosurgery dose planning, and follow-up tumor volume measurement. A rapid and objective automatic segmentation method is required, but problems have been encountered due to the low through-plane resolution of standard VS MR scan protocols and because some patients have non-homogeneous cystic areas within their tumors. In this study, we retrospectively collected multi-parametric MR images from 516 patients with VS; these were extracted from the Gamma Knife radiosurgery planning system and consisted of T1-weighted (T1W), T2-weighted (T2W), and T1W with contrast (T1W + C) images. We developed an end-to-end deep-learning-based method via an automatic preprocessing pipeline. A two-pathway U-Net model involving two sizes of convolution kernel (i.e., 3 × 3 × 1 and 1 × 1 × 3) was used to extract the in-plane and through-plane features of the anisotropic MR images. A single-pathway model that adopted the same architecture as the two-pathway model, but used a kernel size of 3 × 3 × 3, was also developed for comparison purposes. In addition, we used multi-parametric MR images with different image contrasts as the model training input in order to effectively segment tumors with solid as well as cystic parts. The results of the automatic segmentation demonstrated that (1) the two-pathway model outperformed single-pathway model in terms of dice scores (0.90 ± 0.05 versus 0.87 ± 0.07); both of them having been trained using the T1W, T1W + C and T2W anisotropic MR images, (2) the optimal single-parametric two-pathway model (dice score: 0.88 ± 0.06) was then trained using the T1W + C images, and (3) the two-pathway models trained using bi-parametric (T1W + C and T2W) and tri-parametric (T1W, T2W, and T1W + C) images outperformed the model trained using the single-parametric (T1W + C) images (dice scores: 0.89 ± 0.05 and 0.90 ± 0.05, respectively, larger than 0.88 ± 0.06) because it showed improved segmentation of the non-homogeneous parts of the tumors. The proposed two-pathway U-Net model outperformed the single-pathway U-Net model when segmenting VS using anisotropic MR images. The multi-parametric models effectively improved on the defective segmentation obtained using the single-parametric models by separating the non-homogeneous tumors into their solid and cystic parts.