Differentiating spinal pathologies by deep learning approach.

BACKGROUND CONTEXT: Spinal pathologies are diverse in nature and, excluding trauma and degenerative diseases, includes infectious, neoplastic (either extradural or intradural), and inflammatory conditions. The preoperative diagnosis is made with clinical judgment incorporating lab findings and radiological studies. When the diagnosis is uncertain, a biopsy is almost always mandatory since the treatment is dictated by the type of pathology. This is an invasive, timely, and costly process. PURPOSE: The aim of this study was to develop a deep learning (DL) algorithm, based on preoperative MRI and post-operative pathological results, to differentiate between leading spinal pathologies. STUDY DESIGN: We retrospectively collected and analyzed clinical, radiological, and pathological data of patients who underwent spinal surgery or biopsy for various spinal pathologies between 2008 and 2022 at a tertiary center. The patients were stratified according to their pathological reports (the threshold for inclusion was set to 25 patients per diagnosis). METHODS: Preoperative MRI, clinical data, and pathological results were processed by a deep learning model built on the Fast.ai framework on top of the PyTorch environment. RESULTS: A total of 231 patients diagnosed with carcinoma (80), infection (57), meningioma (52), or schwannoma (42), were included in our model. The mean overall accuracy was 0.78±0.06 for the validation, and 0.93±0.03 for the test dataset. CONCLUSION: Deep learning algorithm for differentiation between the aforementioned spinal pathologies, based solely on clinical MRI, proves as a feasible primary diagnostic modality. Larger studies should be performed to validate and improve this algorithm for clinical use. CLINICAL SIGNIFICANCE: This study provides a proof-of-concept for predicting spinal pathologies solely by MRI based DL technology, allowing for a rapid, targeted, and cost-effective work-up and subsequent treatment.

The clinical significance of radiological changes associated with gliadel implantation in patients with recurrent high grade glioma.

Gliadel occasionally induces edema following its implantation. We aimed to correlate such post-surgical radiological changes to its efficacy and subsequent survival. Fifty-six patients with recurrent high grade glioma were treated between 2005 and 2016 with Gliadel implantation. Volumetric measurements of MRI features, including FLAIR abnormalities, tumor bulk (volume of gadolinium enhancement on T1) and resection cavity volumes over time were conducted. To assess dynamics over time, linear regression trendlines for each of these were calculated and examined to correlate with survival. Median follow-up after resection was 21.5 months. Median survival post-Gliadel implantation and overall survival since diagnosis were 12 months and 22 months, respectively. A subgroup of patients (n = 6) with a transient increase in FLAIR changes volume over time survived significantly longer post-Gliadel compared to those who did not demonstrate such change (36 vs 12 months, p = .03). Positive trends, representing overall growth in volume over time, of tumor bulk and resection cavity predicted survival in multivariate analyses (hazard ratios 7.9 and 84, p = .003 and .002, respectively). Increase in tumor bulk and resection cavity over time were associated with decreased survival, while transient FLAIR increase was a favorable prognostic factor. This may represent a transient inflammatory process in the tumor, possibly stemming from a presumed immune-mediated anti-tumor response.

Predicting EGFR mutation status by a deep learning approach in patients with non-small cell lung cancer brain metastases.

PURPOSE: Non-small cell lung cancer (NSCLC) tends to metastasize to the brain. Between 10 and 60% of NSCLCs harbor an activating mutation in the epidermal growth-factor receptor (EGFR), which may be targeted with selective EGFR inhibitors. However, due to a high discordance rate between the molecular profile of the primary tumor and the brain metastases (BMs), identifying an individual patient's EGFR status of the BMs necessitates tissue diagnosis via an invasive surgical procedure. We employed a deep learning (DL) method with the aim of noninvasive detection of the EGFR mutation status in NSCLC BM. METHODS: We retrospectively collected clinical, radiological, and pathological-molecular data of all the NSCLC patients who had been diagnosed with BMs and underwent resection of their BM during 2009-2019. The study population was then divided into two groups based upon EGFR mutational status. We further employed a DL technique to classify the two groups according to their preoperative magnetic resonance imaging features. Augmentation techniques, transfer learning approach, and post-processing of the predicted results were applied to overcome the relatively small cohort. Finally, we established the accuracy of our model in predicting EGFR mutation status of BM of NSCLC. RESULTS: Fifty-nine patients were included in the study, 16 patients harbored EGFR mutations. Our model predicted mutational status with mean accuracy of 89.8%, sensitivity of 68.7%, specificity of 97.7%, and a receiver operating characteristic curve value of 0.91 across the 5 validation datasets. CONCLUSION: DL-based noninvasive molecular characterization is feasible, has high accuracy and should be further validated in large prospective cohorts.

T Cells Retain Pivotal Antitumoral Functions under Tumor-Treating Electric Fields.

Tumor-treating fields (TTFields) are a localized, antitumoral therapy using alternating electric fields, which impair cell proliferation. Combining TTFields with tumor immunotherapy constitutes a rational approach; however, it is currently unknown whether TTFields' locoregional effects are compatible with T cell functionality. Healthy donor PBMCs and viably dissociated human glioblastoma samples were cultured under either standard or TTFields conditions. Select pivotal T cell functions were measured by multiparametric flow cytometry. Cytotoxicity was evaluated using a chimeric Ag receptor (CAR)-T-based assay. Glioblastoma patient samples were acquired before and after standard chemoradiation or standard chemoradiation + TTFields treatment and examined by immunohistochemistry and by RNA sequencing. TTFields reduced the viability of proliferating T cells, but had little or no effect on the viability of nonproliferating T cells. The functionality of T cells cultured under TTFields was retained: they exhibited similar IFN-γ secretion, cytotoxic degranulation, and PD1 upregulation as controls with similar polyfunctional patterns. Glioblastoma Ag-specific T cells exhibited unaltered viability and functionality under TTFields. CAR-T cells cultured under TTFields exhibited similar cytotoxicity as controls toward their CAR target. Transcriptomic analysis of patients' glioblastoma samples revealed a significant shift in the TTFields-treated versus the standard-treated samples, from a protumoral to an antitumoral immune signature. Immunohistochemistry of samples before and after TTFields treatment showed no reduction in T cell infiltration. T cells were found to retain key antitumoral functions under TTFields settings. Our data provide a mechanistic insight and a rationale for ongoing and future clinical trials that combine TTFields with immunotherapy.

Differentiating Small-Cell Lung Cancer From Non-Small-Cell Lung Cancer Brain Metastases Based on MRI Using Efficientnet and Transfer Learning Approach.

Differentiation between small-cell lung cancer (SCLC) from non-small-cell lung cancer (NSCLC) brain metastases is crucial due to the different clinical behaviors of the two tumor types. We propose the use of a deep learning and transfer learning approach based on conventional magnetic resonance imaging (MRI) for non-invasive classification of SCLC vs. NSCLC brain metastases. Sixty-nine patients with brain metastasis of lung cancer origin were included. Of them, 44 patients had NSCLC and 25 patients had SCLC. Classification was performed with EfficientNet architecture on crop images of lesion areas and based on post-contrast T1-weighted, T2-weighted and FLAIR imaging input data. Evaluation of the model was carried out in a 5-fold cross-validation manner, and based on accuracy, precision, recall, F1 score and area under the receiver operating characteristic curve. The best classification results were obtained with multiparametric MRI input data (T1WI+c+FLAIR+T2WI), with a mean overall accuracy of 0.90 ± 0.04, and F1 score of 0.92 ± 0.05 for NSCLC and 0.87 ± 0.08 for SCLC for the validation data and an accuracy of 0.87 ± 0.05, with an F1 score of 0.88 ± 0.05 for NSCLC and 0.85 ± 0.05 for SCLC for the test dataset. The proposed method provides an automatic noninvasive method for the classification of brain metastasis with high sensitivity and specificity for differentiation between NSCLC vs. SCLC brain metastases. It may be used as a diagnostic tool for improving decision-making in the treatment of patients with these metastases. Further studies on larger patient samples are required to validate the current results.

Impact of repeated operations for progressive low-grade gliomas.

BACKGROUND: Maximal, aggressive resection of diffuse low-grade gliomas (DLGG) is well established as the standard of care in neuro-oncology. The role of repeat resection for tumor progression is unclear. OBJECTIVE: To assess the role of repeated operation for DLGG, and the effect on malignant transformation and survival. METHODS: We conducted a historical cohort study in which all patients undergoing multiple resections of DLGG between the years 1995-2019 were evaluated for overall survival (OS) and time to transformation (TTT). We then compared the outcome of this group with that of a matched control group comprised of patients who underwent only one operation despite being eligible for repeat surgery at tumor progression, but had received non-surgical oncological therapy or declined additional treatment. RESULTS: Of 607 patients in our departmental DLGG database, 93 patients underwent 2 or more surgeries and had sufficient follow-up and imaging data to be included in the study group. Thirty-eight patients were included in the matched control group. Early (less than 1 year) progression was associated with decreased survival and shorter TTT in the study group. Patients undergoing multiple resections had significantly longer TTT and OS compared to patients who underwent a single surgery. This effect was especially noted in patients who had radiological evidence of tumor transformation. CONCLUSIONS: Repeated resections of LGG are safe and offer survival benefit in select patients. Early progression following resection is associated with worse prognosis. Patients with evidence of radiological transformation may benefit the most from re-resection.

Virtual biopsy using MRI radiomics for prediction of BRAF status in melanoma brain metastasis.

Brain metastases are common in patients with advanced melanoma and constitute a major cause of morbidity and mortality. Between 40% and 60% of melanomas harbor BRAF mutations. Selective BRAF inhibitor therapy has yielded improvement in clinical outcome; however, genetic discordance between the primary lesion and the metastatic tumor has been shown to occur. Currently, the only way to characterize the genetic landscape of a brain metastasis is by tissue sampling, which carries risks and potential complications. The aim of this study was to investigate the use of radiomics analysis for non-invasive identification of BRAF mutation in patients with melanoma brain metastases, based on conventional magnetic resonance imaging (MRI) data. We applied a machine-learning method, based on MRI radiomics features for noninvasive characterization of the BRAF status of brain metastases from melanoma (BMM) and applied it to BMM patients from two tertiary neuro-oncological centers. All patients underwent surgical resection for BMM, and their BRAF mutation status was determined as part of their oncological work-up. Their routine preoperative MRI study was used for radiomics-based analysis in which 195 features were extracted and classified according to their BRAF status via a support vector machine. The BRAF status of 53 study patients, with 54 brain metastases (25 positive, 29 negative for BRAF mutation) was predicted with mean accuracy = 0.79 ± 0.13, mean precision = 0.77 ± 0.14, mean sensitivity = 0.72 ± 0.20, mean specificity = 0.83 ± 0.11 and with a 0.78 area under the receiver operating characteristic curve for positive BRAF mutation prediction. Radiomics-based noninvasive genetic characterization is feasible and should be further verified using large prospective cohorts.

5-ALA-assisted stereotactic brain tumor biopsy improve diagnostic yield.

BACKGROUND: Abnormal tissue in stereotactic brain biopsies (SBB) is traditionally identified intraoperatively via pathological frozen section (FS), a time-consuming and error-prone process. The objective of this study was to assess the efficacy of 5-aminolevulinic acid (5-ALA) administration on SBB operation time, diagnostic yield, and the associated complication rate. METHODS: We retrospectively evaluated all consecutive patients undergoing SBB with preoperative 5-ALA administration and intraoperative assessment of fluorescence (5-ALA group) between 2010 and 2017 in a single center. They were compared to all consecutive patients who underwent traditional brain biopsy with FS (control group). Demographics, clinical data, diagnostic yield of biopsies, and complication rates were documented. RESULTS: In all, 376 patients underwent SBB for suspected oncological pathology during the study period. All 34 of the 5-ALA-assisted SBB were diagnostic compared to 96.8% of the control group. The mean operative time was the same for both groups, but it was significantly shorter for the 5-ALA patients with florescent samples compared to patients with negative fluorescence (61 ±â€¯25 min vs. 136 ±â€¯54 min, P = 0.003) and compared to the control group (74 ±â€¯34 min vs. 61 ±â€¯25 min, P = 0.03). Symptomatic bleed was absent in the 5-ALA group and present in 5.4% of the controls. No adverse events were associated with preoperative 5-ALA administration. CONCLUSIONS: Preoperative administration of 5-ALA may improve the diagnostic yield of SBB and shortens operation time in cases of fluorescent pathological tissue. In addition, it may reduce the risk for associated postoperative symptomatic bleed. 5-ALA-assisted SBB is a viable alternative to traditional biopsies with FS.

MRI radiomics analysis of molecular alterations in low-grade gliomas.

PURPOSE: Low-grade gliomas (LGG) are classified into three distinct groups based on their IDH1 mutation and 1p/19q codeletion status, each of which is associated with a different clinical expression. The genomic sub-classification of LGG requires tumor sampling via neurosurgical procedures. The aim of this study was to evaluate the radiomics approach for noninvasive classification of patients with LGG and IDH mutation, based on their 1p/19q codeletion status, by testing different classifiers and assessing the contribution of the different MR contrasts. METHODS: Preoperative MRI scans of 47 patients diagnosed with LGG with IDH1-mutated tumors and a genetic analysis for 1p/19q deletion status were included in this study. A total of 152 features, including size, location and texture, were extracted from fluid-attenuated inversion recovery images, [Formula: see text]-weighted images (WI) and post-contrast [Formula: see text]. Classification was performed using 17 machine learning classifiers. Results were evaluated by a fivefold cross-validation analysis. RESULTS: Radiomic analysis differentiated tumors with 1p/19q intact ([Formula: see text]; astrocytomas) from those with 1p/19q codeleted ([Formula: see text]; oligodendrogliomas). Best classification was obtained using the Ensemble Bagged Trees classifier, with sensitivity [Formula: see text] 92%, specificity [Formula: see text] 83% and accuracy [Formula: see text] 87%, and with area under the curve [Formula: see text] 0.87. Tumors with 1p/19q intact were larger than those with 1p/19q codeleted ([Formula: see text] vs. [Formula: see text] cc, respectively; [Formula: see text]) and predominantly located to the left insula ([Formula: see text]). CONCLUSION: The proposed method yielded good discrimination between LGG with and without 1p/19q codeletion. Results from this study demonstrate the great potential of this method to aid decision-making in the clinical management of patients with LGG.

Impact of Onyx Embolization on Radiosurgical Management of Cerebral Arteriovenous Malformations: Treatment and Outcome.

BACKGROUND: Stereotactic radiosurgery (SRS) is a well-established treatment modality for cerebral arteriovenous malformations (AVMs). The main limiting factor in the radiosurgical treatment of AVMs is the volume of the nidus, with high-grade lesions often requiring combined treatment to reduce the SRS target volume. To overcome this limitation, we have been using a combined treatment approach consisting of endovascular embolization with Onyx followed by SRS. OBJECTIVE: To evaluate our clinical experience for safety and feasibility of this multimodality treatment approach. METHODS: This is a retrospective review of all adult patients with cerebral AVMs who received SRS treatment to their AVM after endovascular embolization with Onyx between June 2007 and June 2014. RESULTS: Thirty-five consecutive patients were identified. The mean follow-up period was 52.4 ± 22.6 months (range 18-97 months). We confirmed 18 (51.4%) complete nidus closures at a median time of 49.5 months (range 6.5-81 months) from SRS. High-resolution Magnetic resonance imaging/magnetic resonance angiography was performed routinely in all patients until closure of the nidus. Digital subtraction angiography was performed to confirm complete obliteration in 5 of the patients (28%); 13 patients are either planned for digital subtraction angiography or have refused it. In 6 patients (17%) a significant flow reduction was noted after a mean of 32 ± 16 months. No significant improvement was observed in 9 patients (26%) during the follow-up period. Two patients were lost to follow-up. CONCLUSIONS: The multimodality treatment of cerebral AVMs using embolization with Onyx followed by SRS is feasible and safe. The use of Onyx significantly reduced the SRS treatment target volume.