Glioblastoma multiforme hiding behind the intracerebral hematoma

Machine learning based classification of spontaneous intracranial hemorrhages using radiomics features

PURPOSE

To assess the efficacy of radiomics features extracted from non-contrast computed tomography (NCCT) scans in differentiating multiple etiologies of spontaneous intracerebral hemorrhage (ICH).

METHODS

CT images and clinical data from 141 ICH patients from 2010 to 2022 were collected. The cohort comprised primary (n = 57), tumorous (n = 46), and vascular malformation-related ICH (n = 38). Radiomics features were extracted from the initial brain NCCT scans and identified potential features using mutual information. A hierarchical classification with AdaBoost classifiers was employed to classify the multiple etiologies of ICH. Age of the patient and ICH's location were examined alongside radiomics features. The accuracy, area under the curve (AUC), sensitivity, and specificity were used to evaluate classification performance.

RESULTS

The proposed method achieved an accuracy of 0.79. For identifying primary ICH, the model achieved a sensitivity of 0.86 and specificity of 0.87. Meanwhile, the sensitivity and specificity for identifying tumoral causes were 0.78 and 0.93, respectively. For vascular malformation, the model reached a sensitivity and specificity of 0.72 and 0.89, respectively. The AUCs for primary, tumorous, and vascular malformation were 0.86, 0.85, and 0.82, respectively. The findings further highlight the importance of texture-based variables in ICH classification. The age and location of the ICH can enhance the classification performance.

CONCLUSION

The use of a machine learning model with radiomics features has the potential in classifying the three types of non-traumatic ICH. It may help the radiologist decide on an appropriate further examination plan to arrive at a correct diagnosis.

Biopsy During Minimally Invasive Intracerebral Hemorrhage Clot Evacuation

BACKGROUND

The safety and efficacy of brain parenchyma biopsy during minimally invasive (MIS) intracerebral hemorrhage (ICH) clot evacuation has not been previously reported. The objective of this study was to establish the safety and diagnostic efficacy of brain biopsy during MIS ICH clot evacuation and to validate the modified Boston criteria as a predictor of cerebral amyloid angiopathy (CAA) in this cohort.

METHODS

From October 2016 to March 2018, superficial and perihematomal biopsies were collected for 40 patients undergoing MIS ICH clot evacuation and analyzed by the pathology department to assess for various ICH etiologies. Additionally, the admission magnetic resonance imaging or computed tomography scan of each patient was analyzed and evaluated for the likelihood of a CAA etiology based on the modified Boston criteria. Student t test was used to analyze intergroup differences in continuous variables, and a 2-tailed Fisher exact test was used to determine intergroup differences of categorical variables, with significance set at P < 0.05.

RESULTS

Two of the 40 patients (5%) experienced postoperative rebleed. Four of the 40 patients (10%) had evidence of CAA on biopsy. Patients with CAA on biopsy were older (P = 0.005) and had a higher prevalence of parietal lobe (P = 0.02) and occipital lobe (P = 0.001) hemorrhage. The modified Boston criteria had a sensitivity of 100% (95% confidence interval [CI], 39.6%-100%) and a specificity of 72.2% (95% CI, 54.6%-84.2%) for predicting CAA on biopsy.

CONCLUSIONS

Brain biopsy in MIS ICH clot evacuation is safe and allows for the diagnosis of various ICH etiologies.

Glioblastoma presenting as spontaneous intracranial haemorrhage: Case report and review of the literature

Glioblastoma (GB) classically presents with symptoms of raised intracranial pressure and gradual progressive neurological deficits. An acute presentation, with intracerebral haemorrhage (ICH) and rapid clinical deterioration, occurs infrequently. Contemporary imaging modalities do not reliably reflect underlying mass lesions in parenchymal brain haemorrhage at first presentation. We report a delayed diagnosis of GB in a 21-year-old patient presenting with spontaneous ICH and a negative initial neurovascular workup. A comprehensive literature review was performed to investigate the incidence of malignant aetiology for spontaneous ICH in young adults, and to underscore the importance of early utilisation of diagnostic magnetic resonance imaging (MRI) in such cases.