Background: Accurate localization and classification of intracerebral hemorrhage (ICH) lesions are of great significance for the treatment and prognosis of patients with ICH. The purpose of this study is to develop a symmetric prior knowledge based deep learning model to segment ICH lesions in computed tomography (CT).Methods: A novel symmetric Transformer network (Sym-TransNet) is designed to segment ICH lesions in CT images. A cohort of 1,157 patients diagnosed with ICH is established to train (n = 857), validate (n = 100), and test (n = 200) the Sym-TransNet. A healthy cohort of 200 subjects is added, establishing a test set with balanced positive and negative cases (n = 400), to further evaluate the accuracy, sensitivity, and specificity of the diagnosis of ICH. The segmentation results are obtained after data pre-processing and Sym-TransNet. The DICE coefficient is used to evaluate the similarity between the segmentation results and the segmentation gold standard. Furthermore, some recent deep learning methods are reproduced to compare with Sym-TransNet, and statistical analysis is performed to prove the statistical significance of the proposed method. Ablation experiments are conducted to prove that each component in Sym-TransNet could effectively improve the DICE coefficient of ICH lesions.Results: For the segmentation of ICH lesions, the DICE coefficient of Sym-TransNet is 0.716 ± 0.031 in the test set which contains 200 CT images of ICH. The DICE coefficients of five subtypes of ICH, including intraparenchymal hemorrhage (IPH), intraventricular hemorrhage (IVH), extradural hemorrhage (EDH), subdural hemorrhage (SDH), and subarachnoid hemorrhage (SAH), are 0.784 ± 0.039, 0.680 ± 0.049, 0.359 ± 0.186, 0.534 ± 0.455, and 0.337 ± 0.044, respectively. Statistical results show that the proposed Sym-TransNet can significantly improve the DICE coefficient of ICH lesions in most cases. In addition, the accuracy, sensitivity, and specificity of Sym-TransNet in the diagnosis of ICH in 400 CT images are 91.25%, 98.50%, and 84.00%, respectively.Conclusion: Compared with recent mainstream deep learning methods, the proposed Sym-TransNet can segment and identify different types of lesions from CT images of ICH patients more effectively. Moreover, the Sym-TransNet can diagnose ICH more stably and efficiently, which has clinical application prospects.

Background: Cerebral cryptococcomas is a rare form of central nervous system cryptococcosis. Most previous cases were mistaken for neoplasm before surgery. We present a case of cerebral cryptococcomas whose radiological profiles resembled demyelinating disease, especially tumefactive demyelinating lesion. Case presentation: A 40-year-old male was admitted for 1-week-long unconsciousness. Brain MRI revealed a rim-enhanced mass within the corpus callosum body. Central nervous system demyelinating disease was suspected. Empirical corticosteroid treatment led to some improvement, but his condition deteriorated 2 months later. Brain MRI revealed punctate new foci. Cryptococcus neoformans was detected in cerebrospinal fluid. Cryptococcus antigen test was positive in his current and previous cerebrospinal fluid samples. The patient died despite standard antifungal treatment. Conclusion: Diagnosis of cerebral cryptococcomas is challenging. It may mimic demyelinating diseases.

Background: Hemichorea is usually caused by contralateral deep structures of brain. It rarely results from acute cortical ischemic stroke and that caused by ipsilateral brain lesions is even rarer. Case presentation: A 64-year-old female presented with acute obtuseness and left-sided hemichorea. She had a history of right frontal lobe surgery and radiotherapy due to brain metastasis from lung cancer 8 years ago. MRI revealed acute left frontal lobe infarction in addition to an old right frontal lobe lesion. 18FDG PET-CT showed hypometabolism in the left frontal lobe and hypermetabolism in the right basal ganglia region and central sulcus. The choreatic movement remitted after antipsychotic treatment. Conclusion: The mechanism of hemichorea after ipsilateral cortical infarction is poorly understood. We assume both previous contralateral brain lesion and recent ipsilateral ischemic stroke contributed to the strange manifestation in this case.

Hypoglycemia, which is characterized mainly by palpitations, dizziness, and sweating, is common and easy to identify. However, some other symptoms, such as mental disorder or abnormal behavior, are atypical, which may lead to a misdiagnosis of epilepsy, sleepwalking, infarction, or mental disorder, among others. We report a case of a patient with type 2 diabetes who presented with abnormal nocturnal behavior due to hypoglycemia. Hypoglycemia was diagnosed based on a blood glucose level of 2.1 mmol/L when the patient turned up disoriented unresponsive, unable to understand what was said to him, and producing nonsensical speech. After the patient ate a piece of chocolate, his consciousness returned to normal and all mental symptoms disappeared. Polysomnography (PSG) was synchronously performed. The results of the PSG did not show any signs of abnormality during nonrapid eye movement (NREM) or rapid eye movement (REM) sleep. We regulated his dose of insulin. No additional episodes occurred during the 3-month follow-up. Therefore, the abnormal nocturnal behavior of this patient was determined to be due to hypoglycemia, while the cause of the hypoglycemia was insulin overuse. For physicians, if the cause of abnormal behavior cannot be detected, hypoglycemia should be suspected. Long-term persistent hypoglycemia may cause brain dysfunction and even result in permanent brain damage.