Evaluation of an anatomic definition of non-aneurysmal perimesencephalic subarachnhoid hemorrhage

Development of a deep-learning algorithm for etiological classification of subarachnoid hemorrhage using non-contrast CT scans

OBJECTIVES

This study aims to develop a deep learning algorithm for differentiating aneurysmal subarachnoid hemorrhage (aSAH) from non-aneurysmal subarachnoid hemorrhage (naSAH) using non-contrast computed tomography (NCCT) scans.

METHODS

This retrospective study included 618 patients diagnosed with SAH. The dataset was divided into a training and internal validation cohort (533 cases: aSAH = 305, naSAH = 228) and an external test cohort (85 cases: aSAH = 55, naSAH = 30). Hemorrhage regions were automatically segmented using a U-Net + + architecture. A ResNet-based deep learning model was trained to classify the etiology of SAH.

RESULTS

The model achieved robust performance in distinguishing aSAH from naSAH. In the internal validation cohort, it yielded an average sensitivity of 0.898, specificity of 0.877, accuracy of 0.889, Matthews correlation coefficient (MCC) of 0.777, and an area under the curve (AUC) of 0.948 (95% CI: 0.929-0.967). In the external test cohort, the model demonstrated an average sensitivity of 0.891, specificity of 0.880, accuracy of 0.887, MCC of 0.761, and AUC of 0.914 (95% CI: 0.889-0.940), outperforming junior radiologists (average accuracy: 0.836; MCC: 0.660).

CONCLUSION

The study presents a deep learning architecture capable of accurately identifying SAH etiology from NCCT scans. The model's high diagnostic performance highlights its potential to support rapid and precise clinical decision-making in emergency settings.

KEY POINTS

Question Differentiating aneurysmal from naSAH is crucial for timely treatment, yet existing imaging modalities are not universally accessible or convenient for rapid diagnosis. Findings A ResNet-variant-based deep learning model utilizing non-contrast CT scans demonstrated high accuracy in classifying SAH etiology and enhanced junior radiologists' diagnostic performance. Clinical relevance AI-driven analysis of non-contrast CT scans provides a fast, cost-effective, and non-invasive solution for preoperative SAH diagnosis. This approach facilitates early identification of patients needing aneurysm surgery while minimizing unnecessary angiography in non-aneurysmal cases, enhancing clinical workflow efficiency.

Benign versus sinister aetiologies underlying basal cistern subarachnoid haemorrhage: a case series

BACKGROUND

Subarachnoid hemorrhage in the basal cisterns is usually identified on an unenhanced computed tomography scan of the head in patients presenting acutely with a characteristic sudden onset headache.

CASE PRESENTATION

Using imaging examples from our tertiary neurosciences center, we present six cases demonstrating a variety of causes for subarachnoid hemorrhage in the basal cisterns, ranging from benign to sinister causes. These include a venous perimesencephalic hemorrhage (35 years, female), pontine perforator aneurysm (54 years, male), vertebral artery dissection (69 years, male), cervical dural arteriovenous fistula (65 years, male), posterior fossa arteriovenous malformation (45 years, male), and vertebral artery aneurysm (78 years, female). Ethnically, all these patients were white. Specific imaging features are described and demonstrated.

CONCLUSION

A balance between avoiding excessive investigation and overlooking what may be a mimic of a venous perimesencephalic hemorrhage is important. To refine and establish more definitive indications on when to perform computed tomography angiogram, digital subtraction angiography, delayed angiography and magnetic resonance imaging in this context requires future research to focus on large-scale prospective multicenter studies with robust data.

Nonaneurysmal perimesencephalic subarachnoid hemorrhage on noncontrast head CT: An accuracy, inter-rater, and intra-rater reliability study

BACKGROUND AND PURPOSE

To evaluate the reliability and accuracy of nonaneurysmal perimesencephalic subarachnoid hemorrhage (NAPSAH) on Noncontrast Head CT (NCCT) between numerous raters.

MATERIALS AND METHODS

45 NCCT of adult patients with SAH who also had a catheter angiography (CA) were independently evaluated by 48 diverse raters; 45 raters performed a second assessment one month later. For each case, raters were asked: 1) whether they judged the bleeding pattern to be perimesencephalic; 2) whether there was blood anterior to brainstem; 3) complete filling of the anterior interhemispheric fissure (AIF); 4) extension to the lateral part of the sylvian fissure (LSF); 5) frank intraventricular hemorrhage; 6) whether in the hypothetical presence of a negative CT angiogram they would still recommend CA. An automatic NAPSAH diagnosis was also generated by combining responses to questions 2-5. Reliability was estimated using Gwet's AC1 (κG), and the relationship between the NCCT diagnosis of NAPSAH and the recommendation to perform CA using Cramer's V test. Multi-rater accuracy of NCCT in predicting negative CA was explored.

RESULTS

Inter-rater reliability for the presence of NAPSAH was moderate (κG = 0.58; 95%CI: 0.47, 0.69), but improved to substantial when automatically generated (κG = 0.70; 95%CI: 0.59, 0.81). The most reliable criteria were the absence of AIF filling (κG = 0.79) and extension to LSF (κG = 0.79). Mean intra-rater reliability was substantial (κG = 0.65). NAPSAH weakly correlated with CA decision (V = 0.50). Mean sensitivity and specificity were 58% (95%CI: 44%, 71%) and 83 % (95%CI: 72 %, 94%), respectively.

CONCLUSION

NAPSAH remains a diagnosis of exclusion. The NCCT diagnosis was moderately reliable and its impact on clinical decisions modest.

Current status of perimesencephalic non-aneurysmal subarachnoid hemorrhage

Perimesencephalic nonaneurysmal subarachnoid hemorrhage (PNSAH) is a distinctive disease, representing SAH centered in perimesencephalic cisterns, with negative angiography findings. In recent years, the number of patients with PNSAH has increased significantly; however, the knowledge of PNSAH is insufficient. Therefore, we performed a review of the literature from a PubMed search and recounted our understanding of PNSAH. In this review, we summarized that current high-resolution computed tomography angiography is an acceptable replacement for digital subtraction angiography to rule out aneurysms in PNSAH with strict criteria. The current hypothesis about the etiology of PNSAH is that there is deep vein rupture from aberrant venous anatomy and increased intracranial venous pressure. PNSAH is associated with mild symptoms and lower rates of hydrocephalus and symptomatic vasospasm. For PNSAH, conservative treatment has been the mainstream treatment. PNSAH has a benign clinical course and an excellent prognosis; in long-term follow-up, re-bleeding and death were uncommon.

Multiplanar CT evaluation of aneurysm rupture signs in subarachnoid hemorrhage

PURPOSE

In subarachnoid hemorrhage, noncontrast CT features are used to guide the localization of ruptured aneurysms on CT angiography and DSA. Multiplanar CT may improve the localization of aneurysm rupture sites over axial plane CT alone.

METHODS

Multiplanar CT in three orthogonal planes was used to evaluate 94 cases of SAH. Two investigators independently evaluated each imaging plane for focal thick SAH with mass effect, intracerebral hemorrhage, focal edema, filling defect, subdural hemorrhage, and dominant intraventricular hemorrhage. Also, rupture site was qualitatively identified by combining these variables in each plane and combination of three planes. DSA served as the gold standard to locate the rupture sites.

RESULTS

Interobserver agreement was k 0.60 to 0.79 for axial, k 0.43 to 0.86 for coronal and k 0.43 to 0.74 for sagittal planes. Good to substantial agreement was observed for the localization of rupture site in three planes (focal SAH with mass effect - k 0.78 to 0.85; filling defect - k 0.95 to 1.0; intracerebral hemorrhage - k 1.0; focal edema k 1.0; subdural hemorrhage - k 0.61 to 0.83). Dominant intraventricular hemorrhage revealed significant association with DSA to locate ruptured aneurysms (Fisher's exact test - Pr <  = P (< 0.001)). With non-missing data, frequency of correct ratings to locate rupture site was 66/67 (99%) in axial plane, 59/66 (89%) in coronal plane, 64/67 (96%) in sagittal plane and 77/77 (100%) in combined 3 planes.

CONCLUSIONS

Multiplanar CT head is more successful than axial plane CT alone for the localization of aneurysm rupture sites in SAH.

Subarachnoid Hemorrhage of Unknown Cause: Distribution and Role of Imaging

Subarachnoid hemorrhage of unknown cause represents approximately 10% to 15% of nontraumatic subarachnoid hemorrhages. The key factors in determining the management strategy for a presumed nonaneurysmal subarachnoid hemorrhage are the distribution, location, and amount of subarachnoid blood. Hemorrhage distribution on computed tomography can be categorized as follows: perimesencephalic, diffuse, sulcal, and primary intraventricular. The extent of the workup required in determining the cause of hemorrhage depends on the distribution of blood. The authors review the potential causes, differential diagnoses, and acute and long-term follow-up strategies in patients with subarachnoid hemorrhage of unknown cause.

Nontraumatic Nonaneurysmal Subarachnoid Hemorrhage: Risk Factors, Complications, and Clinical Outcomes

Background The present study aimed to investigate the risk factors, complications, and clinical outcomes of patients with nontraumatic, nonaneurysmal subarachnoid hemorrhage (NNSAH).

Methods We retrospectively evaluated 78 consecutive patients with NNSAH admitted to our center between April 2009 and April 2019. Patients were divided into two groups based on the distribution of blood in the CT scan, perimesencephalic subarachnoid hemorrhage ( PM-SAH) and nonperimesencephalic subarachnoid hemorrhage (nPM-SAH) groups. The outcome was assessed according to the Glasgow outcome scale (GOS). The demographic data and clinical records including age, sex, smoking history, hypertension, diabetes, history of anticoagulant medication, Glasgow coma score (GCS), Hunt–Hess (HH) grades, and in-hospital complications and clinical outcomes were retrospectively reviewed and compared between the two groups.

Results There were 45 patients (57.69%) in the PM-SAH group and 33 cases (42.30%) in the nPM-SAH group with the mean age of 53.98 ± 7.7 years. There were no significant differences between the two groups based on age, sex, smoking history, diabetes, hypertension, anticoagulation medication history, and HH grade at admission. The nPM-SAH group was significantly associated with a higher incidence of radiological and clinical vasospasm (p < 0.05). Moreover, the need for external ventricular drainage (EVD) placement because of the development of hydrocephalus was significantly higher in the nPM group (p < 0.05). Patients with PM-SAH had better clinical outcomes than those with nPM-SAH (p = 0.037).

Conclusions Our results showed that patients with nonaneurysmal subarachnoid hemorrhage (NSAH) had favorable clinical outcomes. The PM group had better clinical outcomes and lower complication rates in comparison with the nPM group. Repeated digital subtraction angiography (DSA) examinations are strongly recommended for patients with nPM-SAH.

Perimesencephalic Nonaneurysmal Subarachnoid Hemorrhage After Clipping of an Unruptured Aneurysm

BACKGROUND

Perimesencephalic nonaneurysmal subarachnoid hemorrhage (PNSAH) is a benign form of subarachnoid hemorrhage with an excellent clinical outcome. The cause of PNSAH remains unknown. We report a case of PNSAH in a patient with a history of clipping of an unruptured aneurysm. PNSAH after clipping of an unruptured aneurysm is extremely rare.

CASE DESCRIPTION

A 56-year-old man with a history of clipping surgery for an unruptured aneurysm 10 months previously presented with severe headache. No precipitating causes were shown; however, the patient had been engaged in an exertional activity before the event. After conservative treatment, he was discharged home without any complication from the hemorrhage.

CONCLUSIONS

On the basis of this case report, clinicians should consider the possibility of PNSAH in a patient who had an unruptured aneurysm previously treated with clipping. Nevertheless, diagnostic workup can be more important than keeping in mind that a subarachnoid hemorrhage might be a PNSAH.

Quadrigeminal perimesencephalic subarachnoid hemorrhage

OBJECTIVE

A variant of perimesencephalic subarachnoid hemorrhage (PSAH) has been described characterized by blood centered in the quadrigeminal cistern and limited to the superior vermian and perimesencephalic cisterns. Herein, three cases of quadrigeminal PSAH are presented.

MATERIALS AND METHODS

Medical records of all patients who underwent digital subtraction angiography for evaluation of non-traumatic SAH between July 2002 and April 2012 were reviewed. Patients with anterior circulation aneurysms were excluded. Two blinded reviewers identified admission noncontrast CT scans with pretruncal and quadrigeminal patterns of PSAH.

RESULTS

The total cohort included 106 patients: 53% (56/106) with one or more negative digital subtraction angiograms and 47% (50/106) with posterior circulation or posterior communicating artery aneurysms. Three patients with quadrigeminal PSAH were identified, two with nonaneurysmal SAH and one with a posterior circulation aneurysm. Seventeen patients (16%; 17/106) with pretruncal PSAH were identified, none of whom were found to have an aneurysm. The quadrigeminal pattern comprised 11% (2/19) of cases of pretruncal or quadrigeminal nonaneurysmal PSAH.

CONCLUSION

A small subset of patients with nonaneurysmal PSAH present with blood centered in the quadrigeminal cistern, and the etiology of this pattern may be similar to that of the classic pretruncal variant. However, patients with quadrigeminal PSAH must still undergo thorough vascular imaging, including at least two digital subtraction angiograms, to exclude a ruptured aneurysm.

The negative predictive value of CT angiography in the setting of perimesencephalic subarachnoid hemorrhage

Background

Perimesencephalic subarachnoid hemorrhage (PMSAH) is only rarely associated with a ruptured cerebral aneurysm and CT angiography (CTA) has very good sensitivity and specificity for aneurysm detection. The necessity for invasive imaging with digital subtraction angiography (DSA) is therefore debatable. We chose to assess the negative predictive value (NPV) of CTA in a series of patients with PMSAH treated at our institution over a 9-year period.

Methods

We retrospectively assessed the diagnostic yield of DSA after initial negative CTA in patients with a PMSAH pattern defined as blood centered anterior to the midbrain and/or pons within the pre-pontine or interpeduncular cistern with possible quadrigeminal or ambient cistern extension; possible extension into the basal parts of the sylvian fissures but not the lateral sylvian fissures; possible extension to the cisterna magna but not centered on the cisterna magna; and possible extension into the fourth ventricle and occipital horns of the lateral ventricles.

Results

Using this definition of PMSAH, of 72 patients, one patient showed a potentially significant finding on DSA that was not demonstrated on initial CTA (NPV 98.61% (95% CI 92.47% to 99.77%)). However, when cisterna magna extension was excluded from the definition of PMSAH, no false negative CTAs in 56 patients were encountered (NPV 100% (95% CI 93.56% to 100.00%)).

Conclusions

The NPV of normal CTA for an arterial abnormality in patients with PMSAH is high and our results therefore question the role of invasive imaging. The findings also suggest that a prospective study designed to clarify the necessity of performing DSA in this population would be feasible.