Hyperspectral Imaging (HSI) for fluorescence-guided brain tumor resection enables visualization of differences between tissues that are not distinguishable to humans. This augmentation can maximize ...brain tumor resection, improving patient outcomes. However, much of the processing in HSI uses simplified linear methods that are unable to capture the non-linear, wavelength-dependent phenomena that must be modeled for accurate recovery of fluorophore abundances. We therefore propose two deep learning models for correction and unmixing, which can account for the nonlinear effects and produce more accurate estimates of abundances. Both models use an autoencoder-like architecture to process the captured spectra. One is trained with protoporphyrin IX (PpIX) concentration labels. The other undergoes semi-supervised training, first learning hyperspectral unmixing self-supervised and then learning to correct fluorescence emission spectra for heterogeneous optical and geometric properties using a reference white-light reflectance spectrum in a few-shot manner. The models were evaluated against phantom and pig brain data with known PpIX concentration; the supervised model achieved Pearson correlation coefficients (R values) between the known and computed PpIX concentrations of 0.997 and 0.990, respectively, whereas the classical approach achieved only 0.93 and 0.82. The semi-supervised approach's R values were 0.98 and 0.91, respectively. On human data, the semi-supervised model gives qualitatively more realistic results than the classical method, better removing bright spots of specular reflectance and reducing the variance in PpIX abundance over biopsies that should be relatively homogeneous. These results show promise for using deep learning to improve HSI in fluorescence-guided neurosurgery.
This article has been retracted: please see Elsevier Policy on Article Withdrawal (http://www.elsevier.com/locate/withdrawalpolicy).
This article has been retracted at the request of the editors. ...This article was published on October 19, 2010, and Figures 4A and 7A were later corrected on August 8, 2016. In January 2021, The Ohio State University notified the Cancer Cell editors that an internal investigation concluded that Figures 1E, 4A, 4D, 5A, and 7A were falsified and that part of Figure 1E of the article is the same as part of Figure 1F in the correction of another article (Pichiorri et al., 2017, J. Exp. Med., 214, 1557, https://doi.org/10.1084/jem.2012095001172017c) and recommended retraction of the article. The editors no longer have confidence in the validity of the data and are retracting the article. S.-S. S. agrees with the retraction, and F.P., C.H., A.P., and C.M.C. disagree with the retraction; all other authors couldn't be reached or didn't respond.
Complete resection of malignant gliomas is hampered by the difficulty in distinguishing tumor cells at the infiltration zone. Fluorescence guidance with 5-ALA assists in reaching this goal. Using ...hyperspectral imaging, previous work characterized five fluorophores' emission spectra in most human brain tumors. In this paper, the effectiveness of these five spectra was explored for different tumor and tissue classification tasks in 184 patients (891 hyperspectral measurements) harboring low- (n=30) and high-grade gliomas (n=115), non-glial primary brain tumors (n=19), radiation necrosis (n=2), miscellaneous (n=10) and metastases (n=8). Four machine learning models were trained to classify tumor type, grade, glioma margins and IDH mutation. Using random forests and multi-layer perceptrons, the classifiers achieved average test accuracies of 84-87%, 96%, 86%, and 93% respectively. All five fluorophore abundances varied between tumor margin types and tumor grades (p < 0.01). For tissue type, at least four of the five fluorophore abundances were found to be significantly different (p < 0.01) between all classes. These results demonstrate the fluorophores' differing abundances in different tissue classes, as well as the value of the five fluorophores as potential optical biomarkers, opening new opportunities for intraoperative classification systems in fluorescence-guided neurosurgery.
Over recent years, αvβ6 and αvβ8 Arg-Gly-Asp (RGD) integrins have risen to prominence as interchangeable co-receptors for the cellular entry of herpes simplex virus-1 (HSV-1). In fact, the employment ...of subtype-specific integrin-neutralizing antibodies or gene-silencing siRNAs has emerged as a valuable strategy for impairing HSV infectivity. Here, we shift the focus to a more affordable pharmaceutical approach based on small RGD-containing cyclic pentapeptides. Starting from our recently developed αvβ6-preferential peptide RGD-Chg-E-CONH2 (1), a small library of N-methylated derivatives (2–6) was indeed synthesized in the attempt to increase its affinity toward αvβ8. Among the novel compounds, RGD-Chg-(NMe)E-CONH2 (6) turned out to be a potent αvβ6/αvβ8 binder and a promising inhibitor of HSV entry through an integrin-dependent mechanism. Furthermore, the renewed selectivity profile of 6 was fully rationalized by a NMR/molecular modeling combined approach, providing novel valuable hints for the design of RGD integrin ligands with the desired specificity profile.
Purpose The purpose of this study was to train a deep learning-based method for the prediction of postoperative recurrence of symptoms in Chiari malformation type 1 (CM1) patients undergoing surgery. ...Studies suggest that certain radiological and clinical features do exist in patients with treatment failure, though these are inconsistent and poorly defined. Methodology This study was a retrospective cohort study of patients who underwent primary surgical intervention for CM1 from January 2010 to May 2020. Only patients who completed pre- and postoperative 12-item short form (SF-12) surveys were included and these were used to classify the recurrence or persistence of symptoms. Forty patients had an improvement in overall symptoms while 17 had recurrence or persistence. After magnetic resonance imaging (MRI) data augmentation, a ResNet50, pre-trained on the ImageNet dataset, was used for feature extraction, and then clustering-constrained attention multiple instance learning (CLAM), a weakly supervised multi-instance learning framework, was trained for prediction of recurrence. Five-fold cross-validation was used for the development of MRI only, clinical features only, and a combined machine learning model. Results This study included 57 patients who underwent CM1 decompression. The recurrence rate was 30%. The combined model incorporating MRI, pre-operative SF-12 physical component scale (PCS), and extent of cerebellar ectopia performed best with an area under the curve (AUC) of 0.71 and an F1 score of 0.74. Conclusion This is the first study to our knowledge to explore the prediction of postoperative recurrence of symptoms in CM1 patients using machine learning methods and represents the first step toward developing a clinically useful prognostication machine learning model. Further studies utilizing a similar deep learning approach with a larger sample size are needed to improve the performance.
Aggressive pituitary adenomas have a high risk of recurrence, a lack of therapeutic response, and resistance to conventional treatment. So far, no satisfactory biomarkers are available for predicting ...their behavior. Some specific pituitary adenoma histotypes are more prone to follow an aggressive behavior. Pituitary carcinomas are rare and show cerebrospinal and/or systemic metastasis. They have worse prognosis than aggressive adenomas, and radiation is of limited use in their treatment.
G-quadruplex stabilizers are an established opportunity in anticancer chemotherapy. To circumvent the antiproliferative effects of G4 ligands, cancer cells recruit PARP enzymes at telomeres. Herein, ...starting from the structural similarity of a potent G4 ligand previously discovered by our group and a congeneric PARP inhibitor, a library of derivatives was synthesized to discover the first dual G4/PARP ligand. We demonstrate that a properly decorated thieno3,2-cquinolin-4(5H)-one stabilizes the G4 fold in vitro and in cells, induces a DNA damage response localized to telomeres, inhibits PARylation in cells, and has an antiproliferative effect in BRCA2 deficient tumor cells.