Non-enhancing Core Research Articles

Deep Machine Learning Algorithms in Glioblastoma (GBM) MRI evaluation (PL4.005)

<h3>Objective:</h3> To test the reliability of automatic segmentation models on post-operative MRIs in glioblastoma evaluation. <h3>Background:</h3> The extent of tumor resection in glioblastoma is an independent prognostic factor associated with clinical outcomes. Because radiological assessment to identify residual tumoral components can be time-consuming and subject to inter-rater variability, the implementation of artificial intelligence (AI) may improve radiological assessment. Hereby, we evaluate performance of different automatic brain tumor segmentation algorithms trained on pre-operative MRI datasets, on post-operative MRI scans of patients with glioblastoma. <h3>Design/Methods:</h3> We evaluated the performance of ten different deep-learning models designed for automated brain tumor segmentation. Models were trained using a publicly available dataset from the Brain Tumor Segmentation (BRaTS) Challenge 2020 and was tested in our institutional MRI scans including pre-operative and post-operative MRI examinations. Semiautomatic segmentation was performed in the institutional scans and was used as the ground truth. Dice Similarity Coefficient (DSC) was used to compare each model’s performance against the ground truth. <h3>Results:</h3> A total of 329 MR examinations were used for training purposes and a separate 100 scans were used to test the deep-learning algorithms. Overall, models demonstrated better performance on pre-operative scans. Among post-operative MRI studies, Knowledge Distillation algorithm exhibited the best performance with a DSC score of 0.836 for whole tumor segmentation. When evaluating specific regions within the tumor, Knowledge Distillation demonstrated a DSC of 0.82 for the FLAIR hyperintense region, 3D Dilated Multi-Fiber Network achieved a DSC of 0.88 in the contrast-enhancing tumoral region, and 3D U-Net exhibited the highest DCS for the non-enhancing core (0.84). <h3>Conclusions:</h3> Deep machine learning has the potential to quantify enhancing and FLAIR volumes in brain MRI from glioblastoma patients with high accuracy. Current automatic segmentation models can perform automatic segmentation on post-operative MRI scans with an 88% accuracy. Further investigations are needed to improve this promising AI technology. <b>Disclosure:</b> An immediate family member of Dr. Zhu has stock in Abbott lab. The institution of Dr. Zhu has received research support from NRG NIH. The institution of Dr. Zhu has received research support from Novocure, Inc. The institution of Dr. Zhu has received research support from Five Prime pharmaceutical. The institution of Dr. Zhu has received research support from Denovo, inc. The institution of Dr. Zhu has received research support from Boston Biomedical Sumitomo Dainippon Pharma Global Oncology. The institution of Dr. Zhu has received research support from CNS pharmaceutical. Mr. HSIEH has nothing to disclose. Ms. Kabir has nothing to disclose. Dr. Nunez has nothing to disclose. Carlos Rodriguez Quintero has nothing to disclose. Dr. Cai has nothing to disclose. Dr. Hsu has nothing to disclose. Dr. Arevalo has nothing to disclose. Kangyi Zhao has nothing to disclose. Jackie Jiaqi Zhang has nothing to disclose. Roy Riascos-Castaneda has nothing to disclose. The institution of Dr. Jiang has received research support from NIH. The institution of Dr. Jiang has received research support from CPRIT. The institution of Dr. Jiang has received research support from NSF. shayan shams has nothing to disclose.

Abstract LB067: A confident and operator-independent deep segmentation model to measure residual tumor volume in the follow-up MRIs for glioblastoma

Abstract Introduction: Magnetic resonance imaging (MRI) is the most common tool to examine glioblastoma. Preoperative MRI can be used to initial diagnosis, and surgery planning, while follow-up MRIs can be used to evaluate treatment responses, identify recurrency, and detect side effects. The follow-up MRIs are usually taken after the first-line therapy, such as maximal safe resection. In the past, radiologists manually segment the tumor regions from normal brain tissue on follow-up MRIs, which is time-consuming, error-prone, and challenging. Several deep-learning (DL) models have been developed utilizing preoperative images, but their performance has yet to be evaluated on follow-up MRIs. In this research, we built the largest follow-up MRI cohort (311 patients) to assess these DL models and their generalizability and performance on independent preoperative and follow-up images. We also made the first follow-up-based deep learning models for this specific task. Methods: All evaluation deep learning models (10 models) were trained by the Brain Tumor Segmentation challenge 2020 (BraTS’20) and evaluated by fifty pairs of preoperative and follow-up scans from our institution. The segmentation form our institution is evaluated by board certified radiologist. MRIs in the BraTS’20 dataset were all preoperative scans. After the evaluation, we randomly assigned 264 patients’ scans from our institution to the training dataset and 47 patients’ scans to the testing dataset. We compared three types of models in our follow-up deep learning model, including 1) UNet-3D, 2) UNet-3D+transfer-learning, and 3) UNet-3D+transfer-learning+baysian-learning. The benchmark for all models was the Dice similarity coefficient (DSC). DSC can measure the spatial overlap between model prediction and ground truth. The value of DSC is between zero to one. Zero means no overlap and one indicates complete overlap. Results: Our study demonstrates that the BraTS'20 trained models' performance decreased by 13.05% in independent preoperative MRI scans and 19.04% in follow-up MRI scans. The most significant mismatch regions were FLAIR hyperintense regions (3.68% drop in independent preoperative scans and 10.61% drop in independent follow-up scans) and Non-enhancing core (5.20% drop in independent preoperative scans and 11.99% drop in independent follow-up scans). Our best model can achieve the best DSC among three tumor regions compared to all evaluation models (FLAIR hyperintense regions: DSC 0.77 V.S. DSC 0.58; Enhancing tumor region: DSC 0.87 V.S. DSC 0.68; Non-enhancing tumor region: DSC 0.92 V.S. DSC 0.55). Conclusion: Maximal safe resection induced brain structure change, decreasing the performance of the preoperative-based DL model. Implementing a follow-up MRI-based segmentation model is essential to make accurate and generalizable results to address structural changes after maximal safe resection. Our follow-up DL model demonstrates the DSC score can be recovered. We commit to further developing the tool to assist radiologists in handling follow-up MRIs for glioblastoma patients. Citation Format: Kang Lin Hsieh, Tanjida Kabir, Luis Nunez-Rubiano, Yu-Chun Hsu, Yu Cai, Juan Rodriguez Quintero, Octavio Arevalo, Kangyi Zhao, Jackie Zhang, Jiguang Zhu Zhu, Roy Riascos, Xioaqian Jiang, Shayan Shams. A confident and operator-independent deep segmentation model to measure residual tumor volume in the follow-up MRIs for glioblastoma [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 2 (Clinical Trials and Late-Breaking Research); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(8_Suppl):Abstract nr LB067.

Quantification of tumor microenvironment acidity in glioblastoma using principal component analysis of dynamic susceptibility contrast enhanced MR imaging

Glioblastoma (GBM) has high metabolic demands, which can lead to acidification of the tumor microenvironment. We hypothesize that a machine learning model built on temporal principal component analysis (PCA) of dynamic susceptibility contrast-enhanced (DSC) perfusion MRI can be used to estimate tumor acidity in GBM, as estimated by pH-sensitive amine chemical exchange saturation transfer echo-planar imaging (CEST-EPI). We analyzed 78 MRI scans in 32 treatment naïve and post-treatment GBM patients. All patients were imaged with DSC-MRI, and pH-weighting that was quantified from CEST-EPI estimation of the magnetization transfer ratio asymmetry (MTRasym) at 3 ppm. Enhancing tumor (ET), non-enhancing core (NC), and peritumoral T2 hyperintensity (namely, edema, ED) were used to extract principal components (PCs) and to build support vector machines regression (SVR) models to predict MTRasym values using PCs. Our predicted map correlated with MTRasym values with Spearman’s r equal to 0.66, 0.47, 0.67, 0.71, in NC, ET, ED, and overall, respectively (p < 0.006). The results of this study demonstrates that PCA analysis of DSC imaging data can provide information about tumor pH in GBM patients, with the strongest association within the peritumoral regions.

Inflammatory lesions and brain tumors: is it possible to differentiate them based on texture features in magnetic resonance imaging?

Background:Neuroimaging strategies are essential to locate, to elucidate the etiology, and to the follow up of brain disease patients. Magnetic resonance imaging (MRI) provides good cerebral soft-tissue contrast detection and diagnostic sensitivity. Inflammatory lesions and tumors are common brain diseases that may present a similar pattern of a cerebral ring enhancing lesion on MRI, and non-enhancing core (which may reflect cystic components or necrosis) leading to misdiagnosis. Texture analysis (TA) and machine learning approaches are computer-aided diagnostic tools that can be used to assist radiologists in such decisions.Methods:In this study, we combined texture features with machine learning (ML) methods aiming to differentiate brain tumors from inflammatory lesions in magnetic resonance imaging. Retrospective examination of 67 patients, with a pattern of a cerebral ring enhancing lesion, 30 with inflammatory, and 37 with tumoral lesions were selected. Three different MRI sequences and textural features were extracted using gray level co-occurrence matrix and gray level run length. All diagnoses were confirmed by histopathology, laboratorial analysis or MRI. Results:The features extracted were processed for the application of ML methods that performed the classification. T1-weighted images proved to be the best sequence for classification, in which the differentiation between inflammatory and tumoral lesions presented high accuracy (0.827), area under ROC curve (0.906), precision (0.837), and recall (0.912). Conclusion:The algorithm obtained textures capable of differentiating brain tumors from inflammatory lesions, on T1-weghted images without contrast medium using the Random Forest machine learning classifier.

Predicting Outcome of Patients with High-grade Gliomas After Radiotherapy using Quantitative Analysis of T1-weighted Magnetic Resonance Imaging

The aim of this study was to test the hypothesis that measuring quantitative changes in signal intensity early after radiotherapy (RT) in the contrast-enhancing tumor rim and nonenhancing core may be a noninvasive marker of early treatment response in patients with high-grade gliomas. Twenty patients with high-grade gliomas had magnetic resonance imaging (MRI) performed 1 week before RT, during Weeks 1 and 3 of RT, and every 1 to 3 months after RT as part of a clinical prospective study. Regions of interest (ROI) including contrast-enhancing rim, and the nonenhancing core were defined automatically based on a calculated image of post- to precontrast T1-weighted MRI. Pretreatment T1-weighted MRI signal intensity changes were compared with Weeks 1 and 3 RT and 1 and 3 months post-RT MRI. Clinical and MRI parameters were then tested for prediction of overall survival. Regional T1-weighted signal intensity changes in both the contrast-enhancing rim and the nonenhancing core were observed in all patients during Week 1 and Week 3 of RT. Imaging parameters including signal intensity change within the nonenhancing core after Weeks 1 to 2 RT (p = 0.004), Weeks 3 to 4 RT (p = 0.002) and 1 month after completion of RT (p = 0.002) were predictive of overall survival. Using multivariate analysis including RTOG recursive partitioning analysis (RPA) and signal intensity change, only the signal intensity change in the nonenhancing core at 1 month after RT (p = 0.01) retained significance. Quantitative measurements of T1-weighted MRI signal intensity changes in the nonenhancing tumor core (using ratios of pre-post values) may provide valuable information regarding early response during treatment and improve our ability to predict posttreatment outcome.