Segment Aneurysms Research Articles

Integrated Deep Learning Model for the Detection, Segmentation, and Morphologic Analysis of Intracranial Aneurysms Using CT Angiography.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop a deep learning model for the morphologic measurement of unruptured intracranial aneurysms (UIAs) based on CT angiography (CTA) data and validate its performance using a multicenter dataset. Materials and Methods In this retrospective study, patients with CTA examinations, including those with and without UIAs, in a tertiary referral hospital from February 2018 to February 2021 were included as the training dataset. Patients with UIAs who underwent CTA at multiple centers between April 2021 to December 2022 were included as the multicenter external testing set. An integrated deep-learning (IDL) model was developed for UIA detection, segmentation and morphologic measurement using an nnU-net algorithm. Model performance was evaluated using the Dice similarity coefficient (DSC) and intraclass correlation coefficient (ICC), with measurements by senior radiologists serving as the reference standard. The ability of the IDL model to improve performance of junior radiologists in measuring morphologic UIA features was assessed. Results The study included 1182 patients with UIAs and 578 controls without UIAs as the training dataset (55 years [IQR, 47-62], 1,012 [57.5%] females) and 535 patients with UIAs as the multicenter external testing set (57 years [IQR, 50-63], 353 [66.0%] females). The IDL model achieved 97% accuracy in detecting UIAs and achieved a DSC of 0.90 (95%CI, 0.88-0.92) for UIA segmentation. Model-based morphologic measurements showed good agreement with reference standard measurements (all ICCs > 0.85). Within the multicenter external testing set, the IDL model also showed agreement with reference standard measurements (all ICCs > 0.80). Junior radiologists assisted by the IDL model showed significantly improved performance in measuring UIA size (ICC improved from 0.88 [0.80-0.92] to 0.96 [0.92-0.97], P < .001). Conclusion The developed integrated deep learning model using CTA data showed good performance in UIA detection, segmentation and morphologic measurement and may be used to assist less experienced radiologists in morphologic analysis of UIAs. ©RSNA, 2024.

A School-Goer’s Nightmare: Case Report of CABG in an 8 Year-Old with Kawasaki Disease

Introduction: Kawasaki disease (KD) is an acute vasculitis primarily affecting medium-sized arteries, particularly the coronary arteries (CA). Its impact varies, with some patients developing transient dilation while others experience severe coronary artery aneurysms (CAA), leading to complications such as thrombosis, stenosis, and myocardial ischemia. Male gender, delayed diagnosis, incomplete presentation of KD, and resistance to Intravenous Immunoglobulin (IVIG) therapy are risk factors for CAA. The Japanese Ministry of Health classifies CAAs by size, with giant aneurysms (&gt;8 mm) carrying significant long-term risks, including coronary thrombosis and acute coronary syndrome. Case Report: We report the case of an 8-year-old Malay boy with giant CAA secondary to KD. The patient presented with classical KD symptoms and inflammatory markers, with echocardiography revealing a giant aneurysm (8.7 mm) in the left anterior descending artery (LAD), alongside smaller aneurysms in the left circumflex and right coronary arteries (RCA). Initial management included IVIG, aspirin, and heparin, with warfarin and clopidogrel added subsequently. Coronary angiography indicated severe LAD stenosis (95%) with total occlusion and an aneurysmal segment distal to the occlusion. A multidisciplinary team determined that coronary artery bypass grafting (CABG) using bilateral internal mammary arteries was the optimal intervention. The patient had a favourable recovery and was stable at discharge. Discussion: CABG is recognized as a preferred treatment for severe or multivessel coronary involvement in KD, offering lower reintervention rates compared to percutaneous coronary intervention (PCI). Studies support CABG’s efficacy in managing coronary complications in KD, especially for complex or multivessel cases. Conclusion: This case illustrates the complexities of managing giant CAAs in paediatric KD and underscores the necessity of a multidisciplinary approach and long-term monitoring to

Deep learning-based segmentation of abdominal aortic aneurysms and intraluminal thrombus in 3D ultrasound images.

Ultrasound (US)-based patient-specific rupture risk analysis of abdominal aortic aneurysms (AAAs) has shown promising results. Input for these models is the patient-specific geometry of the AAA. However, segmentation of the intraluminal thrombus (ILT) remains challenging in US images due to the low ILT-blood contrast. This study aims to improve AAA and ILT segmentation in time-resolved three-dimensional (3D + t) US images using a deep learning approach. In this study a "no new net" (nnU-Net) model was trained on 3D + t US data using either US-based or (co-registered) computed tomography (CT)-based annotations. The optimal training strategy for this low-contrast data was determined for a limited dataset. The merit of augmentation was investigated, as well as the inclusion of low-contrast areas. Segmentation results were validated with CT-based geometries as the ground truth. The model trained on CT-based masks showed the best performance in terms of DICE index, Hausdorff distance, and diameter differences, covering a larger part of the AAA. With a higher accuracy and less manual input the model outperforms conventional methods, with a mean Hausdorff distance of 4.4mm for the vessel and 7.8mm for the lumen. However, visibility of the lumen-ILT interface remains the limiting factor, necessitating improvements in image acquisition to ensure broader patient inclusion and enable rupture risk assessment of AAAs in the future.

Extracranial internal carotid artery aneurysm: Surgical approach to a rare entity.

Extracranial internal carotid artery aneurysms are rare entities that arise within the carotid triangle. Although rare, they are clinically significant due to the risk of neurologic thromboembolic events, compression of cranial nerves and vasculature, rupture, and ischemia. Surgery is the gold-standard treatment for symptomatic patients of all ages with extracranial internal carotid artery aneurysm. A 26-year-old female patient was admitted to our institution with complaints of left auricular pain, hoarseness, and uncontrollable hypertension. She had a pulsatile mass located at the left cervical region. After diagnosing the extracranial internal carotid artery aneurysm, it was decided that surgery was necessary to relieve the patient's discomfort and prevent possible complications from the aneurysm in the left carotid artery. In the operation, the aneurysmatic segment was resected and sent for histopathological evaluation. Saphenous vein graft was interposed as end to end anastomosis to the proximal and distal healthy segments of the internal carotid artery. This case report highlights the surgical management of a 26-year-old female patient who presented to our institution with complaints of left auricular pain, hoarseness, uncontrolled hypertension, and a pulsatile mass localized at the left cervical region and diagnosed extracranial internal carotid artery aneurysm.

BIF-Net: Boundary information fusion network for abdominal aortic aneurysm segmentation

The accurate abdominal aortic aneurysm (AAA) segmentation is significant for assisting clinicians in diagnosis and treatment planning. However, existing segmentation methods exhibit a low utilization rate for the semantic information of vessel boundaries, which is disadvantageous for segmenting AAA with significant scale variability of vessel diameter (diameter ranges from 4 mm to 85 mm). To tackle this problem, we introduce a boundary information fusion network (BIF-Net) specially designed for AAA segmentation. BIF-Net initially constructs convolutional kernel functions based on Gabor and Sobel operators, enriching the global semantic features and localization information through the Gabor and Sobel dilated convolution (GSDC) module. Additionally, BIF-Net supplements lost boundary feature information during the sampling process through the guided filtering feature supplementation (GFFS) module and the channel-spatial attention module (CSAM), enhancing the ability to capture targets with shape diversity and boundary features. Finally, we introduce a boundary feature loss function to alleviate the impact of the imbalance between positive and negative samples. The results demonstrate that BIF-Net outperforms current state-of-the-art methods across multiple evaluation metrics, achieving the highest Dice similarity coefficient (DSC) accuracies of 93.29 % and 91.01 % on the preoperative and postoperative datasets, respectively. Compared to the state-of-the-art methods, BIF-Net improves DSC by 6.86 % and 3.85 %. Due to the powerful boundary feature extraction ability, the proposed BIF-Net is a competitive AAA segmentation method exhibiting significant potential for application in diagnosis and treatment processes of AAA.

Morphology and Texture-Guided Deep Neural Network for Intracranial Aneurysm Segmentation in 3D TOF-MRA.

This study concentrates on the segmentation of intracranial aneurysms, a pivotal aspect of diagnosis and treatment planning. We aim to overcome the inherent instance imbalance and morphological variability by introducing a novel morphology and texture loss reweighting approach.Our innovative method involves the incorporation of tailored weights within the loss function of deep neural networks. Specifically designed to account for aneurysm size, shape, and texture, this approach strategically guides the model to focus on capturing discriminative information from imbalanced features. The study conducted extensive experimentation utilizing ADAM and RENJI TOF-MRA datasets to validate the proposed approach.The results of our experimentation demonstrate the remarkable effectiveness of the introduced methodology in improving aneurysm segmentation accuracy. By dynamically adapting to the variances present in aneurysm features, our model showcases promising outcomes for accurate diagnostic insights. The nuanced consideration of morphological and textural nuances within the loss function proves instrumental in overcoming the challenge posed by instance imbalance.In conclusion, our study presents a nuanced solution to the intricate challenge of intracranial aneurysm segmentation. The proposed morphology and texture loss reweighting approach, with its tailored weights and dynamic adaptability, proves to be instrumental in enhancing segmentation precision. The promising outcomes from our experimentation suggest the potential for accurate diagnostic insights and informed treatment strategies, marking a significant advancement in this critical domain of medical imaging.

Computer tomography-based assessment of perivascular adipose tissue in patients with abdominal aortic aneurysms

This retrospective study investigates perivascular adipose tissue (PVAT) alterations in CT as a marker of inflammation in patients with abdominal aortic aneurysms (AAA). 100 abdominal CT scans of patients with abdominal aortic aneurysms and 100 age and sex matched controls without underlying aortic disease were included. Artificial Intelligence (AI) assisted segmentation of the aorta and the surrounding adipose tissue was performed. Adipose tissue density was measured in Hounsfield units (HU) close (2-5mm, HUclose) and distant (10-12mm, HUdistant) to the aortic wall. To investigate alterations in adipose tissue density close to the aorta (HUclose) as a potential marker of inflammation, we calculated the difference HUΔ = HUclose-HUdistant and the fat attenuation ratio HUratio = HUclose/HUdistant as normalized attenuation measures. These two markers were compared i) inter-individually between AAA patients and controls and ii) intra-individually between the aneurysmal and non-aneurysmal segments in AAA patients. Since most AAAs are generally observed infrarenal, the aneurysmal section of the AAA patients was compared with the infrarenal section of the aorta of the control patients. In inter-individual comparisons, higher HUΔ and a lower HUratio were observed (aneurysmal: 8.9 ± 5.1 HU vs. control: 6.9 ± 4.8 HU, p-value = 0.006; aneurysmal: 89.8 ± 5.7% vs. control: 92.1 ± 5.5% p-value = 0.004). In intra-individual comparisons, higher HUΔ and lower HUratio were observed (aneurysmal: 8.9 ± 5.1 HU vs. non-aneurysmal: 5.5 ± 4.1 HU, p-value < 0.001; aneurysmal: 89.8 ± 5.7% vs. non-aneurysmal 93.3 ± 4.9%, p-value < 0.001). The results indicate PVAT density alterations in AAA patients. This motivates further research to establish non-invasive imaging markers for vascular and perivascular inflammation in AAA.

Reproducibility and across-site transferability of an improved deep learning approach for aneurysm detection and segmentation in time-of-flight MR-angiograms

This study aimed to (1) replicate a deep-learning-based model for cerebral aneurysm segmentation in TOF-MRAs, (2) improve the approach by testing various fully automatic pre-processing pipelines, and (3) rigorously validate the model’s transferability on independent, external test-datasets. A convolutional neural network was trained on 235 TOF-MRAs acquired on local scanners from a single vendor to segment intracranial aneurysms. Different pre-processing pipelines including bias field correction, resampling, cropping and intensity-normalization were compared regarding their effect on model performance. The models were tested on independent, external same-vendor and other-vendor test-datasets, each comprised of 70 TOF-MRAs, including patients with and without aneurysms. The best-performing model achieved excellent results on the external same-vendor test-dataset, surpassing the results of the previous publication with an improved sensitivity (0.97 vs. ~ 0.86), a higher Dice score coefficient (DSC, 0.60 ± 0.25 vs. 0.53 ± 0.31), and an improved false-positive rate (0.87 ± 1.35 vs. ~ 2.7 FPs/case). The model further showed excellent performance in the external other-vendor test-datasets (DSC 0.65 ± 0.26; sensitivity 0.92, 0.96 ± 2.38 FPs/case). Specificity was 0.38 and 0.53, respectively. Raising the voxel-size from 0.5 × 0.5×0.5 mm to 1 × 1×1 mm reduced the false-positive rate seven-fold. This study successfully replicated core principles of a previous approach for detecting and segmenting cerebral aneurysms in TOF-MRAs with a robust, fully automatable pre-processing pipeline. The model demonstrated robust transferability on two independent external datasets using TOF-MRAs from the same scanner vendor as the training dataset and from other vendors. These findings are very encouraging regarding the clinical application of such an approach.

Knowledge-Augmented Deep Learning for Segmenting and Detecting Cerebral Aneurysms With CT Angiography: A Multicenter Study.

Background Deep learning (DL) could improve the labor-intensive, challenging processes of diagnosing cerebral aneurysms but requires large multicenter data sets. Purpose To construct a DL model using a multicenter data set for accurate cerebral aneurysm segmentation and detection on CT angiography (CTA) images and to compare its performance with radiology reports. Materials and Methods Consecutive head or head and neck CTA images of suspected unruptured cerebral aneurysms were gathered retrospectively from eight hospitals between February 2018 and October 2021 for model development. An external test set with reference standard digital subtraction angiography (DSA) scans was obtained retrospectively from one of the eight hospitals between February 2022 and February 2023. Radiologists (reference standard) assessed aneurysm segmentation, while model performance was evaluated using the Dice similarity coefficient (DSC). The model's aneurysm detection performance was assessed by sensitivity and comparing areas under the receiver operating characteristic curves (AUCs) between the model and radiology reports in the DSA data set with use of the DeLong test. Results Images from 6060 patients (mean age, 56 years ± 12 [SD]; 3375 [55.7%] female) were included for model development (training: 4342; validation: 1086; and internal test set: 632). Another 118 patients (mean age, 59 years ± 14; 79 [66.9%] female) were included in an external test set to evaluate performance based on DSA. The model achieved a DSC of 0.87 for aneurysm segmentation performance in the internal test set. Using DSA, the model achieved 85.7% (108 of 126 aneurysms [95% CI: 78.1, 90.1]) sensitivity in detecting aneurysms on per-vessel analysis, with no evidence of a difference versus radiology reports (AUC, 0.93 [95% CI: 0.90, 0.95] vs 0.91 [95% CI: 0.87, 0.94]; P = .67). Model processing time from reconstruction to detection was 1.76 minutes ± 0.32 per scan. Conclusion The proposed DL model could accurately segment and detect cerebral aneurysms at CTA with no evidence of a significant difference in diagnostic performance compared with radiology reports. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Payabvash in this issue.

Management of Proximal (A1 Segment) Anterior Cerebral Artery Aneurysms: A Literature Review

AbstractProximal or A1 segment anterior cerebral artery (ACA) aneurysms are rare aneurysms. They have certain unique properties when compared to all other intracranial aneurysms. They are smaller and prone to an early rupture. Thus, they need an aggressive intervention even when they are less than 7 mm in size. The technical difficulties that arise in their management are based on their location along the length and circumference of the ACA. Accordingly, they have been variously classified in literature. Their intimate relationship to the medial lenticulostriate perforators and the recurrent artery of Heubner is the prime factor in determining the surgical or endovascular strategy and outcome. These aneurysms are commonly associated with vascular anomalies, needing a thorough interpretation of preoperative angiograms. Though there are many series reporting the clinical features and management outcome of proximal ACA aneurysms, all are limited by a small sample size due to the rarity of the pathology. In this article, the pertinent literature related to the surgical nuances associated with dealing with A1 segment aneurysms is reviewed. The clinical presentation, associated anatomical characteristics, microsurgical management, role of endovascular therapy, and outcome are discussed.

Deep learning for intracranial aneurysm segmentation using CT angiography

Objective. This study aimed to employ a two-stage deep learning method to accurately detect small aneurysms (4–10 mm in size) in computed tomography angiography images. Approach. This study included 956 patients from 6 hospitals and a public dataset obtained with 6 CT scanners from different manufacturers. The proposed method consists of two components: a lightweight and fast head region selection (HRS) algorithm and an adaptive 3D nnU-Net network, which is used as the main architecture for segmenting aneurysms. Segments generated by the deep neural network were compared with expert-generated manual segmentation results and assessed using Dice scores. Main Results. The area under the curve (AUC) exceeded 79% across all datasets. In particular, the precision and AUC reached 85.2% and 87.6%, respectively, on certain datasets. The experimental results demonstrated the promising performance of this approach, which reduced the inference time by more than 50% compared to direct inference without HRS. Significance. Compared with a model without HRS, the deep learning approach we developed can accurately segment aneurysms by automatically localizing brain regions and can accelerate aneurysm inference by more than 50%.

Pipeline versus non-pipeline flow diverter treatment for M1 aneurysms: A systematic review and meta-analysis.

The flow diversion treatment of aneurysms located distal to the Circle of Willis has recently increased in frequency. We conducted a systematic review and meta-analysis of the clinical and radiological outcomes of flow diverter (FD) embolization in treating M1 aneurysms. PubMed, Web of Science, Ovid Medline, Ovid Embase, and Scopus were searched up to May 2024 using the Nested Knowledge platform. We included studies assessing the long-term clinical and radiological outcomes for M1 aneurysms. Results of FDs classified as Pipeline Embolization Devices (PED) versus other types of FDs. Angiographic occlusion rates, ischemic and hemorrhagic complications, and favorable clinic outcomes were included. All data were analyzed using R software version 4.2.2. Thirteen studies with 112 total patients (58 patients for PED and 54 patients for other FD devices) were included in our meta-analysis. The overall adequate (complete + near-complete) occlusion rates were 85.1%. The complete occlusion rate was higher with PED than with other FD devices (72.9% PED and 41.6% for non-PED FDs, respectively, p-value <.01). The ischemic complications were 9.9% and 9.0% for the PED and non-PED groups, respectively (p-value = .89). The overall modified Rankin Scale 0-2 was 100% for the non-PED and 97.1% for the PED group (p-value = .51). In-stent stenosis rate was 7.5% for PED devices compared to 2.6% in the non-PED group (p-value = .35). This relatively small meta-analysis showed high rates of adequate and complete occlusion in FD treatment of M1 segment aneurysms, with favorable safety profiles. PEDs were associated with higher rates of complete aneurysm occlusion compared to other types of FDs.

The Importance of Aneurysm Morphology and Perianeurysmal Environment in Aneurysmal Subdural Hematomas

Aim: Aneurysmal subdural hematoma (anSDH) is an uncommon condition associated with significant mortality risk. This study focused on the relationship between morphology and the perianeurysmal environment by comparing aneurysm location and clinical outcomes. Material and Methods: A total of 486 patients with aneurysmal subarachnoid hemorrhage were retrospectively analyzed for accompanying subdural hematoma (SDH) cases. Demographic information, rebleeding, discharge, and 6 months of the modified Rankin scale scores (favorable and unfavorable) were recorded. The aneurysms were divided into 3 groups: internal carotid artery (ICA), anterior cerebral artery (ACA), and middle cerebral artery (MCA). Other parameters included aneurysm morphology, SDH width, intracerebral hematoma (ICH) volume, the presence of intraventricular hematoma, and distance to the subdural space. Results: Concomitant SDH was detected in 19 (3.9%) patients. Aneurysms were located in the ICA, 10 (52.6%); MCA, 8 (42.1%); and ACA, one (5.3%). The mean size was 9.5±4.3 mm, and there was a significant difference in aneurysm size between the ICA and MCA (p=0.025). In six supraclinoid aneurysms (posterior communicating and anterior choroidal arteries), the aneurysm dome was in the inferior lateral projection. No significant differences were observed between patients with favorable and unfavorable modified Rankin scale in terms of clinical and aneurysm morphological characteristics, except for increased ICH volume (p=0.020) and shift effects (p=0.030). Conclusion: The size and dome projection of ICA supraclinoid segment aneurysms may be important risk factors for SDH. We also believe that aneurysm localization may have a limited impact on clinical outcomes in the context of SDH.

Review: Flow Diversion for the Treatment of Middle Cerebral Artery Aneurysms.

The invention of flow diverting stents (FDS) is a novel milestone in the field of endovascular aneurysm therapy, promoting physiological healing of the vessel segment contrary to prior deconstructive treatment strategies, such as coiling. The effects of FDS are based on changes in flow patterns, segmental wall stabilization, and the growth of a neointima. Although flow diversion is already well established for cerebral aneurysms in proximal segments, peripheral locations remain challenging. Especially the middle cerebral artery (MCA) with its predominance of non-collateralized perforators and functional end arteries that supply the eloquent areas of the brain is of major concern.The literature was reviewed for flow diversion of the MCA and antiplatelet therapy.Resulting from the special anatomical characteristics of the MCA, FDS implantation in this territory is completely different from the proximal vessel segments. Still, flow diversion represents an effective endovascular strategy, especially in otherwise non-accessible or sufficiently treatable lesions. However, the risk of ischemic adverse events might be increased. Special attention to the individual decision regarding device selection, antiplatelet regimen, and exact definition of the proximal and distal landing zone considering the jailed side branches is essential for a good angiographic and clinical outcome. · MCA aneurysms can be sufficiently treated by FDS.. · The anatomic and hemodynamic characteristics of the MCA result in an increased risk of thromboembolism.. · Individual device selection and antiplatelet regimen are essential for treatment success.. · Schüngel M, Wohlgemuth WA, Elolf E et al. Review: Flow Diversion for the Treatment of Middle Cerebral Artery Aneurysms. Fortschr Röntgenstr 2024; DOI 10.1055/a-2343-0046.

The role of preoperative D-dimer blood level in assessing the risk of open abdominal aortic surgery (statistical study)

Introduction. Changes in the hemostasis and fibrinolysis system in patients with aortoiliac segment lesion can cause the development of specific thromboembolic and hemorrhagic complications, accompanied by a high level of mortality. Preoperative laboratory analysis of the D-dimer blood level may help to objectify the risk assessment of open surgery in this category of patients. Objective. Assessment of the significance of preoperative blood D-dimer level in predicting the development of morbidity and mortality after open surgery on the aortoiliac segment. Materials and methods. The study included 108 patients who were determined the D-dimer blood level before planned reconstructive intervention on the aortoiliac segment at the Pavlov University from 2013 to 2021. The first group consisted of 56 patients with aneurysmal aortoiliac segment lesions, and the second group included 52 patients with occlusive-stenotic lesions of the aortoiliac segment. Results. 92 (85%) patients had an increase of D-dimer level above 500 μg/L, among them 18 patients developed early postoperative complications, and 4 cases were fatal. In 16 (15%) patients with normal D-dimer levels, the postoperative the period was uneventful. Both groups showed statistically significant differences in preoperative blood D-dimer levels depending on the presence or absence of early postoperative complications. In the first group, the median of D-dimer level in the smooth course of the postoperative period was 2035 μg/L, and in patients with complicated course – 3770 μg/L (p=0.04), in the second group these indicators were 635 μg/L and 1231.5 μg/L (p=0.02), respectively. The threshold value of D-dimer level in predicting the risk of death in the first group was 4150 μg/L (p=0.001). Conclusion. The blood D-dimer level may be an additional laboratory risk factor for adverse outcome of open surgery in patients with aortoiliac occlusive disease.

Aneurysm in the first segment of the superior cerebellar artery: Case report

Introduction: Superior cerebellar artery aneurysms are rare lesions. This location comprises 0.2 % of all intracranial aneurysms, around 60 % debut with subarachnoid hemorrhage, frecuently from small aneurysms.Case report: A 54- year- old famale patient who began with a sudden headache and loss of consciousness that caused her to fall to the ground. She is diagnosed with spontaneous subarachnoid hemorrhage. Angiography was performed, which showed an aneurysm of the left superior cerebellar artery.Conclusion: The diagnosis of subarachnoid hemorrhage secondary to an aneurysm of the anterior pontomesencephalic segment of the superior cerebellar artery is an unusual finding.

Automatic exudate and aneurysm segmentation in OCT images using UNET++ and hyperreflective-foci feature based bagged tree ensemble.

Diabetic retinopathy's signs, such as exudates (EXs) and aneurysms (ANs), initially develop from under the retinal surface detectable from optical coherence tomography (OCT) images. Detecting these signs helps ophthalmologists diagnose DR sooner. Detecting and segmenting exudates (EXs) and aneurysms (ANs) in medical images is challenging due to their small size, similarity to other hyperreflective regions, noise presence, and low background contrast. Furthermore, the scarcity of public OCT images featuring these abnormalities has limited the number of studies related to the automatic segmentation of EXs and ANs, and the reported performance of such studies has not been satisfactory. This work proposes an efficient algorithm that can automatically segment these anomalies by improving key steps in the process. The potential area where these hyper-reflective EXs and ANs occur was scoped by our method using a deep-learning U-Net++ program. From this area, the candidates for EX-AN were segmented using the adaptive thresholding method. Nine features based on appearances, locations, and shadow markers were extracted from these candidates. They were trained and tested using bagged tree ensemble classifiers to obtain only EX-AN blobs. The proposed method was tested on a collection of a public dataset comprising 80 images with hand-drawn ground truths. The experimental results showed that our method could segment EX-AN blobs with average recall, precision, and F1-measure as 87.9%, 86.1%, and 87.0%, respectively. Its F1-measure drastically outperformed two comparative methods, binary thresholding and watershed (BT-WS) and adaptive thresholding with shadow tracking (AT-ST), by 78.0% and 82.1%, respectively.

Fungal carotiditis with aneurysm - a rare complication of mucormycosis: presentation and management

During the COVID-19 pandemic, cases of mucormycosis (ROCM) had increased drastically, especially in the second wave. Most of these cases involved the paranasal sinuses, orbit and occasionally brain. This case report presents a rare case of mucormycosis complicated with a mycotic aneurysm of the petrous part of the internal carotid artery (ICA). A 43-year-old man presented with left-sided facial weakness for which high resolution computed tomography scan of the Temporal bones was done. A scrutiny of the computed tomography temporal bone showed evidence of osteomyelitis extending to the petrous apex around the foramen Lacerum. Computed tomography and magnetic resonance imaging of the paranasal sinus done later confirmed the diagnosis of mucormycosis. The patient underwent endoscopic surgical debridement of the nose and sinuses, with post-operative amphotericin B. After 3 weeks, the patient presented with bouts of profuse nasal bleed. Computed tomography angiogram showed an aneurysm in the petrous segment of the ICA suggestive of mycotic carotiditis complicated from mucormycosis spread along the skull base. It was successfully managed neurosurgically by a bypass shunting procedure. Mucormycosis is a disease that typically has an aggressive and startling fatality rate. ICA aneurysm is an uncommon occurrence in mucormycosis. Subjects with ROCM should be examined for brain and vascular involvement. Computed tomography angiogram should be performed as soon as possible if the skull base is involved in the ICA area. Morbidity and mortality can often be reduced by early diagnosis and interventions by a multidisciplinary team.

CORONARY ARTERY ANEURYSM IN IGG4–RELATED DISEASE

Abstract Introduction Coronary artery ectasia is a rare disease defined as a local or diffuse dilatation of the coronary artery more than 1.5 times the diameter of the adiacent normal segment. The etiology is diverse and can be rarely associated with immunoglobulin G4 (IgG4)–related disease. The high levels of serum IgG4 may promote the development of low–density plaques, intimal thickening due to pericoronitis and subsequent coronary ectasia. Case Report We present the case of a 72–year–old male patient with arterial hypertension, dyslipidemia, chronic renal insufficiency, and a family history of cardiovascular diseases. In the previous year, he suffered a cerebral hemorrhage attributed to an unspecified cerebral vascular malformation, which was managed with an endovascular approach. The patient was admitted for Non–ST–segment Elevation Myocardial Infarction (NSTEMI). Coronary angiography revealed widespread ectasia of the coronary vessels, a chronically occluded marginal branch, and an aneurysmatic proximal right coronary artery with the presence of a thrombus on the aneurysmal segment, dissolved following administration of intracoronaric heparin. Furthermore a critical stenosis at the crux involving the posterior interventricular branch was detected and angioplasty with drug–eluting stent implantation was performed on the affected vessel. Given the coronary artery ectasia, aortic ectasia revealed by echocardiography, renal insufficiency and persistently elevated amylase and lipase levels, further diagnostic investigation was conducted suspecting IgG4–related disease. Hematological tests revealed elevated IgG and IgG4 subclass levels (882 mg/dL and 1438 mg/L, respectively), C3 117 mg/dL, C4 30 mg/dL, and total IgE 130 KU/L. The diagnosis of IgG4–related disease was confirmed and the patient was advised to continue cardiological and rheumatological follow–up. Conclusion When the coronary arteries are involved in the IgG4–related disease, risk of acute events such as heart attack may increase and the prognosis is poor. Coronary thickening and ectasia, typical imaging features, other aortic involvement and inflammation indicators, like elevated serum IgG4, should be considered as red flags for an early investigation and subsequent early intervention.

DISCONTINUING DAPT: NOT JUST A MATTER OF SCORES BUT OF INTEGRATED EVALUATION? A KEY ROLE OF IMAGING IN A COMPLEX SCENARIO

Abstract The duration of the dual antiplatelet therapy (DAPT) is a widely debated topic within the scientific community. The latest guidelines on acute coronary syndromes have supported the possibility of different therapeutic approaches tailored to patient characteristics. However, the clinical cardiologist‘s decisions are not always based on certain principles. The following case report is a practical example. Discussion: A 31–years–old man came to our attention after a resuscitated cardiac arrest due to ventricular fibrillation during a motorcycle race. His history was characterized by a previous acute myocardial infarction at the age of thirteen due to a traumatic dissection of the proximal left anterior descending (LAD) coronary artery and ascending aorta treated conservatively, with residual transmural necrosis of the mid and subendocardial anterior wall on cardiac MRI. At the admission, ECG showed ST–segment elevation in the anterior leads. Coronary angiography revealed occlusion of the proximal LAD coronary artery, treated with drug–eluting stent (ONYX 5.0 mm), with evidence of dissection and aneurysmal wall of that segment. The patient started a DAPT with aspirin and prasugrel. At discharge, echocardiogram evidenced a moderate left ventricular dysfunction (ejection fraction 34%) with signs of anterior and apical necrosis. Later, the patient was admitted for a subcutaneous defibrillator implantation, due to persistent moderate ventricular dysfunction. One year after revascularization, a lifelong DAPT strategy with downgrading to clopidogrel was considered the best choice for the following considerations: the young age of the patient, the low bleeding risk (PRECISE DAPT score 8), a not elevated DAPT score (value 2), the revascularization in the aneurysmal segment without an appropriate stent apposition (due to absence of a right sizing) and the previous dissection with sign of partial thrombosis at coronary CT. Conclusions: The anatomical complexity of angioplasty procedures and the delicate balance between ischemic and thrombotic risks have led to continuously evolving therapeutic strategies. The clinical scores currently available cannot often account for complex coronary anatomy. Thus, it‘s essential to consider a personalized approach, individualized on clinical and imaging characteristics, that encompasses ischemic and bleeding risk and procedural data for the appropriate treatment for each patient.