Traditional nuclear magnetic resonance technology has grayscale inhomogeneity in brain tumor detection, which directly affects the formulation of follow-up treatment plans. In order to improve the detection effect of nuclear magnetic resonance on brain tumors, this study uses a convolutional neural network as the basis algorithm to construct an algorithm model suitable for multimodal MRI image recognition. At the same time, combined with the actual case, this paper uses the model to segment and identify brain tumors, and this paper combines the principle of machine learning and collects data for data training to construct a multi-channel deep deconvolution network model. In addition, in order to explore the effectiveness of the algorithm in this study, the performance analysis was carried out by comparative experiment method, and the multi-faceted performance of the model was studied, and the corresponding test result images were obtained. Through experimental comparison, it can be seen that the algorithm model constructed in this study has certain validity, can be applied to practice, and can provide theoretical reference for subsequent related research.
MasonJ., Al-QaisiehB., BownesP., et al., Multi-parametric MRI-guided focal tumor boost using HDR prostate brachytherapy: A feasibility study, Brachytherapy13(2) (2014), 137–145.
2.
YueZ., BinZ., FeiL., et al., In vivo tomographic imaging with fluorescence and MRI using tumor-targeted dual-labelednanoparticles, International Journal of Nanomedicine9(9) (2014), 33–41.
3.
NjehI., SallemiL., AyedI.B., et al., 3D multimodal MRI brain glioma tumor and edema segmentation: A graph cut distribution matching approach, Computerized Medical Imaging & Graphics the Official Journal of the Computerized Medical Imaging Society40 (2015), 108–119.
4.
HeerkensH.D., Van VulpenM., Van d BC.A.T., et al., MRI-based tumor motion characterization and gating schemes for radiation therapy of pancreatic cancer, Radiotherapy and Oncology111(2) (2014), 252–257.
5.
ParkJ.A., LeeY.J., KoI.O., et al., Improved tumor-targeting MRI contrast agents: Gd(DOTA) conjugates of a cycloalkane-based RGD peptide, Biochemical and Biophysical Research Communications455(3–4) (2014).
6.
AlimohamadiM., SanjariR., MortazaviA., et al., Predictive value of diffusion-weighted MRI for tumor consistency and resection rate of nonfunctional pituitary macroadenomas, Acta Neurochirurgica156(12) (2014), 2245.
7.
GrossmannP., GutmanD.A., DunnW.D., et al., Imaging-genomics reveals driving pathways of MRI derived volumetric tumor phenotype features in Glioblastoma, BMC Cancer,16(1) (2016), 611.
8.
BurbachJ.P.M., KleijnenJ.P.J., ReerinkO., et al.Inter-observer agreement of MRI-based tumor delineation for preoperative radiotherapy boost in locally advanced rectal cancer, Radiotherapy and Oncology, 118(2) (2016), 399–407.
9.
MRI Tumor Volume Reduction Rate vs Tumor. Regression Grade in the pre-operative re-staging of locally advanced rectal cancer after chemo-radiotherapy, European Journal of Radiology84(12) (2015), S0720048X15300814.
10.
RamanathanR.K., KornR., RaghunandN., et al., Correlation Between Ferumoxytol Uptake in Tumor Lesions by MRI and Response to Nanoliposomal Irinotecan in Patients With Advanced Solid Tumors: A Pilot Study, Clinical Cancer Research23(14) (2017), 3638–3648.
11.
BarnesS.L., SoraceA.G., LovelessM.E., et al., Correlation of tumor characteristics derived from DCE-MRI and DW-MRI with histology in murine models of breast cancer, NMR in. Biomedicine28(10) (2015), 1345–1356.
12.
Recurrence-free survival in breast cancer is associated with MRI tumor enhancement dynamics quantified using computer algorithms, European Journal of Radiology84(11) (2015), S0720048X15300553.
13.
LopesS., JayaswalD. A.Methodical Approach for Detection and 3-D Reconstruction of Brain Tumor in MRI, International Journal of Computer Applications118(17) (2015), 37–43.
14.
SueroG.A., Abreu, Praveen RajuG, Aristizábal, Orlando, et al., In Vivo Mn-Enhanced MRI for Early Tumor Detection and Growth Rate Analysis in a Mouse Medulloblastoma Model, Neoplasia16(12) (2014), 993–1006.
15.
KimH.R., YouD.G., ParkS.J., et al., MRI monitoring of tumor-selective anticancer drug delivery with stable thermosensitive liposomes triggered by high-intensity focused ultrasound, Molecular Pharmaceutics (2016), acs.molpharmaceut.6b00013.
16.
LuhachI., IdiyatullinD., LynchC.C., et al., Rapid ex vivo imaging of PAIII prostate to bone tumor with SWIFT-MRI, Magnetic Resonance in Medicine72(3) (2014), 858–863.
17.
UsmanK., RajpootK. Brain tumor classification from multi-modality MRI using wavelets and machine learning, Pattern Analysis and Applications20(3) (2017), 871–881.
18.
Xin-XingHu, Zhao-XiaYang, He-YueLiang, et al., Whole-tumor MRI histogram analyses of hepatocellular carcinoma: Correlations with Ki-67 labeling index, Journal of Magnetic Resonance Imaging JMRI46(2) (2016).
19.
KraghaK.O.Malignant Peripheral Nerve Sheath Tumor: MRI and CT Findings, Case Reports in Radiology2015 (2015), 1–7.
20.
CanellasR., LoG., BhowmikS., et al., Pancreatic neuroendocrine tumor: Correlations between MRI features, tumor biology, and clinical outcome after surgery, Journal of Magnetic Resonance Imaging47(2) (2018).
21.
ChenW., LiuB., ChenJ., et al., Targeted tumor MRI with gadobutrol-loaded anti-HER2 immunoliposomes,, ActaRadiologica (2016), 0284185116664225.
22.
JohnsonD.R., DiehnF.E., GianniniC., et al., Genetically defined oligodendroglioma is characterized by indistinct tumor borders at MRI, AJNR American Journal of Neuroradiology38(4) (2017).
23.
NeubauerH., LiM., VerenaMüller, et al., Diagnostic Value of Diffusion-Weighted MRI for Tumor Characterization, Differentiation and Monitoring in Pediatric Patients with NeuroblasticTumors, RöFo - Fortschritte auf demGebiet der Röntgenstrahlen und der bildgebendenVerfahren189(07) (2017), 640–650.
24.
SmithH., TaplinA.L., SyedS.. et al., Correlation between intraoperative ultrasound and postoperative MRI in pediatrictumor surgery, Journal of Neurosurgery: Pediatrics (2016), 1–7.
25.
RajendranR., LiangJ, TangY.A. M, et al., Optimization of arterial spin labeling MRI for quantitative tumor perfusion in a mouse xenograft model, Nmr in Biomedicine28(8) (2015), 988–997.
