Recently, deep learning has achieved impressive results in medical image tasks. However, this method usually requires large-scale annotated data, and medical images are expensive to annotate, so it is a challenge to learn efficiently from the limited annotated data. Currently, the two commonly used methods are transfer learning and self-supervised learning. However, these two methods have been little studied in multimodal medical images, so this study proposes a contrastive learning method for multimodal medical images. The method takes images of different modalities of the same patient as positive samples, which effectively increases the number of positive samples in the training process and helps the model to fully learn the similarities and differences of lesions on images of different modalities, thus improving the model's understanding of medical images and diagnostic accuracy. The commonly used data augmentation methods are not suitable for multimodal images, so this paper proposes a domain adaptive denormalization method to transform the source domain images with the help of statistical information of the target domain. In this study, the method is validated with two different multimodal medical image classification tasks: in the microvascular infiltration recognition task, the method achieves an accuracy of (74.79 ± 0.74)% and an F1 score of (78.37 ± 1.94)%, which are improved as compared with other conventional learning methods; for the brain tumor pathology grading task, the method also achieves significant improvements. The results show that the method achieves good results on multimodal medical images and can provide a reference solution for pre-training multimodal medical images.
Humans ; Algorithms ; Brain/diagnostic imaging* ; Brain Neoplasms/diagnostic imaging* ; Recognition, Psychology

Intracranial intradural chondroma is a rare disorder,the imaging findings of which have been rarely reported.The current study reported a case of intracranial extra-cerebral chondroma and described the detailed CT and magnetic resonance imaging findings,which would provide valuable imaging evidence for the diagnosis of intracranial extra-cerebral chondroma.
Brain Neoplasms/diagnostic imaging* ; Chondroma/diagnostic imaging* ; Humans ; Magnetic Resonance Imaging ; Tomography, X-Ray Computed

We report a case of papillary tumor in the pineal region.The imaging findings mainly included:(1)slight high density on CT images;(2)short T1 signal,cystic changes,and evident enhancement on magnetic resonance imaging.
Brain Neoplasms ; Humans ; Magnetic Resonance Imaging ; Pineal Gland/diagnostic imaging* ; Pinealoma/diagnostic imaging*

Glioma is the most common malignant brain tumor and classification of low grade glioma (LGG) and high grade glioma (HGG) is an important reference of making decisions on patient treatment options and prognosis. This work is largely done manually by pathologist based on an examination of whole slide image (WSI), which is arduous and heavily dependent on doctors' experience. In the World Health Organization (WHO) criteria, grade of glioma is closely related to hypercellularity, nuclear atypia and necrosis. Inspired by this, this paper designed and extracted cell density and atypia features to classify LGG and HGG. First, regions of interest (ROI) were located by analyzing cell density and global density features were extracted as well. Second, local density and atypia features were extracted in ROI. Third, balanced support vector machine (SVM) classifier was trained and tested using 10 selected features. The area under the curve (AUC) and accuracy (ACC) of 5-fold cross validation were 0.92 ± 0.01 and 0.82 ± 0.01 respectively. The results demonstrate that the proposed method of locating ROI is effective and the designed features of density and atypia can be used to predict glioma grade accurately, which can provide reliable basis for clinical diagnosis.
Brain Neoplasms/diagnostic imaging* ; Glioma/diagnostic imaging* ; Humans ; Magnetic Resonance Imaging ; Neoplasm Grading ; Support Vector Machine

Objective To investigate the difference in tumor conventional imaging findings and texture features on T2 weighted images between glioblastoma and primary central neural system (CNS) lymphoma.Methods The pre-operative MRI data of 81 patients with glioblastoma and 28 patients with primary CNS lymphoma admitted to the Chinese PLA General Hospital and Hainan Hospital of Chinese PLA General Hospital were retrospectively collected. All patients underwent plain MR imaging and enhanced T1 weighted imaging to visualize imaging features of lesions. Texture analysis of T2 weighted imaging (T2WI) was performed by use of GLCM texture plugin of ImageJ software, and the texture parameters including Angular Second Moment (ASM), Contrast, Correlation, Inverse Difference Moment (IDM), and Entropy were measured. Independent sample t-test and Mann-Whitney U test were performed for the between-group comparisons, regression model was established by Binary Logistic regression analysis, and receiver operating characteristic (ROC) curve was plotted to compare the diagnostic efficacy.Results The conventional imaging features including cystic and necrosis changes (P=0.000), 'Rosette' changes (P=0.000) and 'incision sign' (P=0.000), except 'flame-like edema' (P=0.635), presented significantly statistical difference between glioblastoma and primary CNS lymphoma. The texture features, ASM, Contrast, Correlation, IDM and Entropy, showed significant differences between glioblastoma and primary CNS lympoma (P=0.006, 0.000, 0.002, 0.000, and 0.015 respectively). The area under the ROC curve was 0.671, 0.752, 0.695, 0.720 and 0.646 respectively, and the area under the ROC curve was 0.917 for the combined texture variables (Contrast, cystic and necrosis, 'Rosette' changes, and 'incision sign') in the model of Logistic regression. Binary Logistic regression analysis demonstrated that cystic and necrosis changes, 'Rosette' changes and 'incision sign' and texture Contrast could be considered as the specific texture variables for the differential diagnosis of glioblastoma and primary CNS lymphoma.Conclusions The texture features of T2WI and conventional imaging findings may be used to distinguish glioblastoma from primary CNS lymphoma.
Adult ; Aged ; Brain Neoplasms ; diagnostic imaging ; Female ; Glioblastoma ; diagnostic imaging ; Humans ; Lymphoma ; diagnostic imaging ; Magnetic Resonance Imaging ; Male ; Middle Aged

Objective To evaluate the application of two-dimensional magnetization-prepared true fast imaging with steady-state precession(2D-MP-TrueFISP)sequence in brain tumor enhancement.Methods In this study,60 cases of brain tumor patients who underwent enhanced magnetic resonance imaging of brain were scanned with 2D-MP-TrueFISP/two-dimensional spoiled gradient-recalled echo(2D-SPGR)before and after enhancement.The scores of lesions on the images of 2D-MP-TrueFISP/2D-SPGR were compared.At the same level of 2D-SPGE and 2D-MP-TrueFISP,the signal intensities(SIs)of lesions,white matter,and cerebrospinal fluid were measured before and after enhancement,and the contrast ratios(CRs)of lesions were calculated.The CRs before and after 2D-SPGR/2D-MP-TrueFISP enhancement and those between 2D-SPGR and 2D-MP-TrueFISP after enhancement were compared.Results The scores of lesions after 2D-MP-TrueFISP/2D-SPGR T1WI enhancement were 9.0(9.0,9.0)and 7.0(6.0,7.0),respectively,with significant difference(
Brain ; Brain Neoplasms/diagnostic imaging* ; Humans ; Image Enhancement ; Imaging, Three-Dimensional ; Magnetic Resonance Imaging

With the evolution of immunochemical staining techniques and better imaging modalities with better image resolution and whole body coverage, gastrointestinal stromal tumor (GIST), the most common mesenchymal tumor of the gastrointestinal tract, is often encountered in clinical practice. Metastasis is common with malignant GIST and can be found in up to 50% of patients at presentation. Liver and peritoneum are the two most common sites of metastasis and accounted for 95% of cases. Lymphatics, bone and lung metastasis are rare. Malignant GIST with intracranial metastasis is even rarer, with only a few cases reported in the literature, and most of these had earlier metastasis elsewhere. Radiological features for GISTs are not specific but it does contribute to confirming early and accurate diagnosis of malignant GISTs by judging the tumor size, enhancement pattern and the invasion of adjacent structures. We report a case of a 26-year-old male with metastatic GIST to the liver and subsequently to the brain and skull vault. This is the first case reported in our locality and he is the youngest patient reported with this disease entity. The clinical progress, radiological features and the role of imaging will be discussed further in this paper. The radiological and clinical features of the primary tumor will specifically be addressed. The purpose of this paper is to enrich the current database of this rare disease entity and to alert both radiologists and clinicians about the imaging features of GIST with intracranial metastasis.
Adult ; Brain Neoplasms ; diagnostic imaging ; secondary ; Gastrointestinal Stromal Tumors ; complications ; diagnostic imaging ; Humans ; Male ; Radiography

Angiomyolipoma ; diagnostic imaging ; etiology ; Brain ; diagnostic imaging ; Female ; Humans ; Kidney Neoplasms ; diagnostic imaging ; etiology ; Lung Neoplasms ; diagnostic imaging ; etiology ; Lymphangioleiomyomatosis ; diagnostic imaging ; etiology ; Magnetic Resonance Imaging ; Middle Aged ; Pedigree ; Tomography, X-Ray Computed ; Tuberous Sclerosis ; complications ; diagnostic imaging

OBJECTIVETo investigate the clinical value of CT perfusion in diagnosing and assessing intracranial neoplasms and tumor-like lesions.

METHODS16-slice helical CT perfusion imaging was performed in 56 patients who were clinically suspected to have intracranial neoplasm or tumor-like lesion. With a GE-Light Speed 16-slice helical CT scanner, routine plain-CT scanning was performed to localize the central slice of the lesion. Perfusion imaging was then carried out using cine scan technique to maintain a slice thickness of 5-10 mm, a total dose of 50-70 ml of contrast-medium at an injection flow rate of 3-5 ml/s, a delay time of 7 s and a total scan time of 50 s. The images were processed using perfusion software in an ADW 4.0 workstation, meanwhile, time-density curves (TDC) of different kinds of lesions were also produced and analyzed.

RESULTSThe pathological types in this series included: 29 gliomas (12 low-grade and 17 high-grade), 2 ependemomas, 2 hemangioblastomas, 1 medulloblastoma, 2 metastatic tumors, 1 lymphoma, 5 meningiomas, 2 schwannomas, 1 germinoma, 1 teratoma in the pineal region, 6 cavernous hemangiomas, 2 inflammatory granulomas, 1 tuberculoma, and 1 hyperplasia of the choroid plexus. TDC of high-grade glioma, low-grade glioma and meningioma was different from each other. The cerebral blood flow (CBF), cerebral blood volume (CBV), particularly, the permeability surface (PS) value of glioma was found to increase significantly with the escalation of tumor differentiation grade. In PS map, margin of the tumor could be clearly showed, which was very useful when hemorrhaging within the tumor occurred. CBF in meningioma was lower than that in high-grade glioma, but there was no statistical difference in CBV, MTT and PS between these two types of tumor. The features of intracranial cavernous hemangioma such as significant prolongation of MTT, different TDCs, and zero perfused areas were diverse on CTP image, which was helpful in differentiating it from the other lesions. The germinoma and teratoma had rather low CBF and CBV value, but a remarkably high PS value, furthermore, they showed a rapid escalated TDC with a slowly and continuously elevated platform. The perfusion features of schwannoma was concordant with its pathological findings. However, no visible specific feature of inflammatory lesion was found on CTP image in this series.

CONCLUSIONMulti-slice helical CT perfusion imaging may be helpful in revealing histopathological features and hemodynamic changes as well as differential diagnosis of intracranial neoplasms and tumor-like lesions. When combined with other image and clinical information, CTP can play an important role in pre-operative diagnosis and treatment planning for intracranial neoplasms and tumor-like lesions.

Brain ; blood supply ; Brain Neoplasms ; diagnosis ; diagnostic imaging ; Cerebrovascular Circulation ; Diagnosis, Differential ; Glioma ; diagnosis ; diagnostic imaging ; Hemangioma, Cavernous ; diagnosis ; diagnostic imaging ; Humans ; Meningeal Neoplasms ; diagnosis ; diagnostic imaging ; Meningioma ; diagnosis ; diagnostic imaging ; Reproducibility of Results ; Sensitivity and Specificity ; Tomography, Spiral Computed ; methods

Cerebral metastases are the most common intracranial tumors in adults,with an increasing incidence in recent years.Radiomics can quantitatively analyze and process medical images to guide clinical practice.In recent years,CT and MRI-based radiomics has been gradually applied to the precise diagnosis and treatment of cerebral metastases,such as the precise detection and segmentation of tumors,the differential diagnosis with other cerebral tumors,the identification of primary tumors,the evaluation of treatment efficacy,and the prediction of prognosis.This article reviews the advances in radiomics of cerebral metastases.
Brain Neoplasms/diagnostic imaging* ; Diagnosis, Differential ; Humans ; Magnetic Resonance Imaging ; Prognosis ; Supratentorial Neoplasms