BACKGROUND Intracranial blister-like microaneurysms are an extremely rare disease.Rupture of intracranial aneurysms can lead to subarachnoid hemorrhage(SAH).Patients with SAH may experience severe neurological symptom...BACKGROUND Intracranial blister-like microaneurysms are an extremely rare disease.Rupture of intracranial aneurysms can lead to subarachnoid hemorrhage(SAH).Patients with SAH may experience severe neurological symptoms,including severe headache,nausea,vomiting,transient or persistent loss of consciousness,limb weakness,and blurred vision.Ruptured aneurysms should be surgically treated as soon as possible.Intravascular electrocoagulation is becoming a promising treatment method for intracranial blister-like microaneurysms.The short-term follow-up results demonstrated that this method is safe and effective.This article presents a case of endovascular electrocoagulation for the treatment of a blisterlike microaneurysm.CASE SUMMARY This article reports the case of 71-year-old female patient with an intracranial aneurysm.The patient experienced a sudden headache with vomiting for 3 hours.Brain computed tomography(CT)scan showed a subarachnoid hemorrhage.She was diagnosed with rupture of an aneurysm and subarachnoid hemorrhage.The aneurysm was located in the choroidal segment of the right internal carotid artery.The size of the aneurysm was 2.00 mm×1.80 mm×1.97 mm,and the neck of the aneurysm was less than 0.5 mm wide.We successfully treated this aneurysm with endovascular electrocoagulation,and the patient was safely returned to the ward and discharged after subsequent supportive treatment.CT angiography reexamination 3 months after surgery revealed no contrast agent extravasation in the original lesion,with a good prognosis.CONCLUSION Endovascular electrocoagulation is an effective and safe method for the treatment of intracranial blister-like microaneurysms.展开更多
AIM: To investigate the contribution of fluorescein angiographic leaking microaneurysms (leak-MA) versus non-leaking microaneurysms (non-leak-MA) to retinal thickening in diabetic retinopathy.METHODS: A consecutive se...AIM: To investigate the contribution of fluorescein angiographic leaking microaneurysms (leak-MA) versus non-leaking microaneurysms (non-leak-MA) to retinal thickening in diabetic retinopathy.METHODS: A consecutive series of 38 eyes from 24 patients with diabetic retinopathy was included.Leak-MA and non-leak-MA in each eye were selected in pairs at corresponding topographic location.Leaking was defined by late phase fluorescein angiograms compared to early phase.Retinal thickness was measured with Heidelberg Spectralis OCT topographically aligned on early phase angiograms at the MA site and within a 1 mm circle.RESULTS: In all eyes,significant retinal thickening at the site of leaking compared to non-leaking microaneurysms was observed (356±69μm vs 318±56μm,P <0.001),showing a mean increase in thickness in the areas of leak-MA vs non-leak-MA of 38±39μm (95% confidence interval 2551μm,P<0.001).All 1mm area measurements also showed significant (P<0.001) thickening of the leak-MA with average thickness of leak-MA vs non-leak-MA as 351±67μmvs 319±59μm;minimum thickness 311±62μm vs 284±60μm;maximum thickness 389±78μm vs 352±66μm;and retina volume 26.4±6.0mmvs 23.6±3.7mm3,respectively.CONCLUSION: Leaking of microaneurysms on fluorescein angiography appears to cause focal thickening of retina,which can be measured with high-resolution OCT.Therefore,targeting leaking microaneursyms in diabetic retinopathy has the potential to reduce retinal thickening.展开更多
This research focuses on the automatic detection and grading of microaneurysms in fundus images of diabetic retinopathy using artificial intelligence deep learning algorithms.By integrating multi-source fundus image d...This research focuses on the automatic detection and grading of microaneurysms in fundus images of diabetic retinopathy using artificial intelligence deep learning algorithms.By integrating multi-source fundus image data and undergoing a rigorous preprocessing workflow,a hybrid deep learning model architecture combining a modified U-Net and a residual neural network was adopted for the study.The experimental results show that the model achieved an accuracy of[X]%in microaneurysm detection,with a recall rate of[Y]%and a precision rate of[Z]%.In terms of grading diabetic retinopathy,the Cohen’s kappa coefficient for agreement with clinical grading was[K],and there were specific sensitivities and specificities for each grade.Compared with traditional methods,this model has significant advantages in processing speed and result consistency.However,it also has limitations such as insufficient data diversity,difficulties for the algorithm in detecting microaneurysms in severely hemorrhagic images,and high computational costs.The results of this research are of great significance for the early screening and clinical diagnosis decision support of diabetic retinopathy.In the future,it is necessary to further optimize the data and algorithms and promote clinical integration and telemedicine applications.展开更多
文摘BACKGROUND Intracranial blister-like microaneurysms are an extremely rare disease.Rupture of intracranial aneurysms can lead to subarachnoid hemorrhage(SAH).Patients with SAH may experience severe neurological symptoms,including severe headache,nausea,vomiting,transient or persistent loss of consciousness,limb weakness,and blurred vision.Ruptured aneurysms should be surgically treated as soon as possible.Intravascular electrocoagulation is becoming a promising treatment method for intracranial blister-like microaneurysms.The short-term follow-up results demonstrated that this method is safe and effective.This article presents a case of endovascular electrocoagulation for the treatment of a blisterlike microaneurysm.CASE SUMMARY This article reports the case of 71-year-old female patient with an intracranial aneurysm.The patient experienced a sudden headache with vomiting for 3 hours.Brain computed tomography(CT)scan showed a subarachnoid hemorrhage.She was diagnosed with rupture of an aneurysm and subarachnoid hemorrhage.The aneurysm was located in the choroidal segment of the right internal carotid artery.The size of the aneurysm was 2.00 mm×1.80 mm×1.97 mm,and the neck of the aneurysm was less than 0.5 mm wide.We successfully treated this aneurysm with endovascular electrocoagulation,and the patient was safely returned to the ward and discharged after subsequent supportive treatment.CT angiography reexamination 3 months after surgery revealed no contrast agent extravasation in the original lesion,with a good prognosis.CONCLUSION Endovascular electrocoagulation is an effective and safe method for the treatment of intracranial blister-like microaneurysms.
文摘AIM: To investigate the contribution of fluorescein angiographic leaking microaneurysms (leak-MA) versus non-leaking microaneurysms (non-leak-MA) to retinal thickening in diabetic retinopathy.METHODS: A consecutive series of 38 eyes from 24 patients with diabetic retinopathy was included.Leak-MA and non-leak-MA in each eye were selected in pairs at corresponding topographic location.Leaking was defined by late phase fluorescein angiograms compared to early phase.Retinal thickness was measured with Heidelberg Spectralis OCT topographically aligned on early phase angiograms at the MA site and within a 1 mm circle.RESULTS: In all eyes,significant retinal thickening at the site of leaking compared to non-leaking microaneurysms was observed (356±69μm vs 318±56μm,P <0.001),showing a mean increase in thickness in the areas of leak-MA vs non-leak-MA of 38±39μm (95% confidence interval 2551μm,P<0.001).All 1mm area measurements also showed significant (P<0.001) thickening of the leak-MA with average thickness of leak-MA vs non-leak-MA as 351±67μmvs 319±59μm;minimum thickness 311±62μm vs 284±60μm;maximum thickness 389±78μm vs 352±66μm;and retina volume 26.4±6.0mmvs 23.6±3.7mm3,respectively.CONCLUSION: Leaking of microaneurysms on fluorescein angiography appears to cause focal thickening of retina,which can be measured with high-resolution OCT.Therefore,targeting leaking microaneursyms in diabetic retinopathy has the potential to reduce retinal thickening.
文摘This research focuses on the automatic detection and grading of microaneurysms in fundus images of diabetic retinopathy using artificial intelligence deep learning algorithms.By integrating multi-source fundus image data and undergoing a rigorous preprocessing workflow,a hybrid deep learning model architecture combining a modified U-Net and a residual neural network was adopted for the study.The experimental results show that the model achieved an accuracy of[X]%in microaneurysm detection,with a recall rate of[Y]%and a precision rate of[Z]%.In terms of grading diabetic retinopathy,the Cohen’s kappa coefficient for agreement with clinical grading was[K],and there were specific sensitivities and specificities for each grade.Compared with traditional methods,this model has significant advantages in processing speed and result consistency.However,it also has limitations such as insufficient data diversity,difficulties for the algorithm in detecting microaneurysms in severely hemorrhagic images,and high computational costs.The results of this research are of great significance for the early screening and clinical diagnosis decision support of diabetic retinopathy.In the future,it is necessary to further optimize the data and algorithms and promote clinical integration and telemedicine applications.
