Incidental findings in research brain MRI: Definition, prevalence and ethical implications.

Radiological incidental findings (IFs) are previously undetected abnormalities which are unrelated to the original indication for imaging and are unexpectedly discovered. In brain magnetic resonance imaging (MRI), the prevalence of IFs is increasing. By reviewing the literature on IFs in brain MRI performed for research purposes and discussing ethical considerations of IFs, this paper provides an overview of brain IF research results and factors contributing to inconsistencies and considers how the consent process can be improved from an ethical perspective. We found that despite extensive literature regarding IFs in research MRI of the brain, there are major inconsistencies in the reported prevalence, ranging from 1.3% to 99%. Many factors appear to contribute to this broad range: lack of standardised definition, participant demographics variance, heterogenous MRI scanner strength and sequences, reporter variation and results classification. We also found significant discrepancies in the review, consent and clinical communication processes pertaining to the ethical nature of these studies. These findings have implications for future studies, particularly those involving artificial intelligence. Further research, particularly in relation to MRI brain IFs would be useful to explore the generalisability of study results.

Development a novel nano-platform for Thrombolysis acceleration by Thrombin sensitive polymer-peptide hybrid nancapsules.

According to the importance of time in treatment of thrombosis disorders, faster than current treatments are required. For the first time, this research discloses a novel strategy for rapid dissolution of blood clots by encapsulation of a fibrinolytic (Reteplase) into a Thrombin sensitive shell formed by polymerization of acrylamide monomers and bisacryloylated peptide as crosslinker. Degradability of the peptide units in exposure to Thrombin, creates the Thrombin-sensitive Reteplase nanocapsules (TSRNPs) as a triggered release system. Accelerated thrombolysis was achieved by combining three approaches including: deep penetration of TSRNPs into the blood clots, changing the clot dissolution mechanism by altering the distribution pattern of TSRNPs to 3D intra-clot distribution (based on the distributed intra-clot thrombolysis (DIT) model) instead of peripheral and unidirectional distribution of unencapsulated fibrinolytics and, enzyme-stimulated release of the fibrinolytic. Ex-vivo study was carried out by an occluded tube model that mimics in-vivo brain stroke as an emergency situation where faster treatment in short time is a golden key. In in vivo, efficacy of the developed formulation was confirmed by PET scan and laser Doppler flowmetry (LDF). As the most important achievements, 40.0 ± 0.7 (n = 3) % and 37.0 ± 0.4 (n = 3) % reduction in the thrombolysis time (faster reperfusion) were observed by ex-vivo and in-vivo experiments, respectively. Higher blood flow and larger digestion mass of clot at similar times in comparison to non-encapsulated Reteplase were observed that means more effective thrombolysis by the developed strategy.

Evaluation of a passive arm-support exoskeleton for surgical team members: Results from live surgeries.

BACKGROUND: Musculoskeletal symptoms and injuries adversely impact the health of surgical team members and their performance in the operating room (OR). Though ergonomic risks in surgery are well-recognized, mitigating these risks is especially difficult. In this study, we aimed to assess the impacts of an exoskeleton when used by OR team members during live surgeries. METHODS: A commercial passive arm-support exoskeleton was used. One surgical nurse, one attending surgeon, and five surgical trainees participated. Twenty-seven surgeries were completed, 12 with and 15 without the exoskeleton. Upper-body postures and muscle activation levels were measured during the surgeries using inertial measurement units and electromyography sensors, respectively. Postures, muscle activation levels, and self-report metrics were compared between the baseline and exoskeleton conditions using non-parametric tests. RESULTS: Using the exoskeleton significantly decreased the percentage of time in demanding postures (>45° shoulder elevation) for the right shoulder by 7% and decreased peak muscle activation of the left trapezius, right deltoid, and right lumbar erector spinae muscles, by 7%, 8%, and 12%, respectively. No differences were found in perceived effort, and overall scores on usability ranged from "OK" to "excellent." CONCLUSIONS: Arm-support exoskeletons have the potential to assist OR team members in reducing musculoskeletal pain and fatigue indicators. To further increase usability in the OR, however, better methods are needed to identify the surgical tasks for which an exoskeleton is effective.

High-frequency optical coherence tomography for endovascular management of cerebral aneurysms.

Endovascular management of intracranial aneurysms has become the mainstay of treatment in recent years; however, retreatment rates remain as high as 1 in 5. High-frequency optical coherence tomography (HF-OCT) is an emerging imaging modality for the assessment, treatment and follow-up of cerebral aneurysms. EMBASE and SCOPUS databases were searched for studies relating to the management of intracranial aneurysm with OCT. A combination of keywords were used including 'cerebral aneurysm', 'intracranial aneurysm', 'high-frequency optical coherence tomography', 'optical coherence tomography', and 'optical frequency domain imaging'. There were 23 papers included in this review. For the assessment of intracranial aneurysm, OCT was able to accurately assess aneurysm morphology as well as detailed analysis of arterial wall layers. During IA treatment, OCT was used to assess and troubleshoot stent placement to optimise successful isolation from the circulation. In the follow-up period, endothelial growth patterns were visualised by OCT imaging. OCT shows promise for the treatment of IAs at all stages of management. Due to the novel development of HF-OCT, there is limited longitudinal data in human studies. Further research in this area is required with a focus specifically on long-term treatment outcomes in humans.

Re-Evaluating Risk Factors, Incidence, and Outcome of Aneurysmal and Non-Aneurysmal Subarachnoid Hemorrhage.

OBJECTIVE: Subarachnoid hemorrhage (SAH) is one of the world's most life-threatening types of stroke. SAH can be classified into two main categories, aneurysmal (aSAH) and non-aneurysmal SAH (naSAH). In the present study, we aimed to prospectively evaluate SAH and its subcategories incidences, risk factors, complications, and outcomes in central Iran. METHODS: All SAH patients diagnosed between 2016 and 2020 were included in Isfahan SAH Registry. Demographic, clinical characteristics, incidence rates (based on age categories), and laboratory/imaging findings were collected and compared between aSAH and naSAH subgroups. Complications during hospital stay and outcomes were also analyzed. Binary logistic regression analysis was performed to investigate the predictors of aSAH versus naSAH. Kaplan-Meier curves and Cox regression were used to evaluate the survival probability. RESULTS: A total of 461 SAH patients were included through Isfahan SAH Registry. The SAH annual incidence rate was 3.11 per 100,000 person-years. aSAH had higher incidence rate than naSAH (2.08/100,000 vs. 0.9/100,000 person-years, respectively). In-hospital mortality was 18.2%. Hypertension (P = 0.003) and smoking (P = 0.03) were significantly associated with aSAH, whereas diabetes mellitus (P < 0.001) was more associated with naSAH. After Cox regression analysis, there were higher hazard ratios for reduced in-hospital survival in conditions including altered mental status, Glasgow Coma Scale ≤13, rebleeding, and seizures. CONCLUSIONS: This study provided an updated estimation of SAH and its subgroups incidences in central Iran. Risk factors for aSAH are comparable to the ones reported in the literature. It is noteworthy that diabetes mellitus was associated with a higher incidence of naSAH in our cohort.

Radioembolization for Treatment of Hepatocellular Carcinoma: Current Evidence and Patterns of Utilization.

Primary liver malignancy, of which hepatocellular carcinoma (HCC) is the most common type, is the second most common cause of death due to cancer worldwide. Given the historically poor prognosis of liver cancer, there has been major research on its treatment options, with significant advancements over the last decade. Transarterial radioembolization (TARE) is a locoregional treatment option for HCC that involves transarterial delivery of the ß-emitter yttrium-90 via resin or glass microspheres to arterialized tumor vasculature, delivering a tumoricidal dose to the tumor. The recent 2022 update of the Barcelona Clinic Liver Cancer (BCLC) treatment algorithm features a more prominent role for locoregional treatment, including the incorporation of radioembolization for very-early-stage (BCLC-0) and early-stage (BCLC-A) diseases. This review provides a contemporary summary of the evolving role of TARE in treatment of HCC in light of recent and upcoming trials.

Comparing treatment outcomes of various intracranial bifurcation aneurysms locations using the Woven EndoBridge (WEB) device.

BACKGROUND: The Woven EndoBridge (WEB) device has Food and Drug Administration approval for treatment of wide-necked intracranial bifurcation aneurysms. The WEB device has been shown to result in adequate occlusion in bifurcation aneurysms overall, but its usefulness in the individual bifurcation locations has been evaluated separately only in few case series, which were limited by small sample sizes. OBJECTIVE: To compare angiographic and clinical outcomes after treatment of bifurcation aneurysms at various locations, including anterior communicating artery (AComA), anterior cerebral artery (ACA) bifurcation distal to AComA, basilar tip, internal carotid artery (ICA) bifurcation, and middle cerebral artery (MCA) bifurcation aneurysms using the WEB device. METHODS: A retrospective cohort analysis was conducted at 22 academic institutions worldwide to compare treatment outcomes of patients with intracranial bifurcation aneurysms using the WEB device. Data include patient and aneurysm characteristics, procedural details, angiographic and functional outcomes, and complications. RESULTS: A total of 572 aneurysms were included. MCA (36%), AComA (35.7%), and basilar tip (18.9%) aneurysms were most common. The rate of adequate aneurysm occlusion was significantly higher for basilar tip (91.6%) and ICA bifurcation (96.7%) aneurysms and lower for ACA bifurcation (71.4%) and AComA (80.6%) aneurysms (p=0.04). CONCLUSION: To our knowledge, this is the most extensive study to date that compares the treatment of different intracranial bifurcation aneurysms using the WEB device. Basilar tip and ICA bifurcation aneurysms showed significantly higher rates of aneurysm occlusion than other locations.

Characterizing Exposure to Physical Risk Factors during Veterinary Surgery with Wearable Sensors: A Pilot Study.

OCCUPATIONAL APPLICATIONSVeterinarians provide comprehensive health services for animals, but despite exposure to similar occupational and safety hazards as medical physicians, physical risk factors for these doctors and healthcare teams have not been characterized. In this pilot study, we used wearable sensor technology and showed that veterinary surgeons commonly experience static and demanding postures while performing soft tissue and orthopedic surgeries. Observations showed that muscle activation was highest in the right trapezius. Job factors such as surgical role (attending vs. assisting) and surgical specialty (soft tissue vs. orthopedics) appeared to influence exposure to physical risk factors. These findings suggest a need to consider the unique demands of surgical specialties in order to address the key risk factors impacting injury risks among veterinarians. For example, static postures may be a priority for soft tissue surgeons, while tools that reduce force requirements are more pressing for orthopedic surgeons.

BACKGROUND: Although musculoskeletal fatigue, pain, and injuries are commonly reported among surgeons in veterinary medicine, few studies have objectively characterized the exposure to physical risk factors among veterinary surgeons. Purpose: This study aimed to characterize muscle activation and postures of the neck and shoulders during live veterinary surgeries in the soft tissue and orthopedic specialties. Methods: Forty-four ergonomic exposure assessments (exposures) were collected during 26 surgical procedures across five surgeons. Exposures were collected from both soft tissue (n = 23) and orthopedic (n = 21) specialties. Physical risk factors were characterized by: (1) directly measuring muscle activation and posture of the neck and shoulders, using surface electromyography and inertial measurement units, respectively; and (2) collecting self-reported workload, pain, and stiffness. Results: Across the 44 exposures, neck and back symptoms respectively worsened after the surgery in 27% and 14% of the exposures. Veterinary surgeons exhibited neck postures involving a mean of 17° flexion during the surgical procedures. Static postures were common, occurring during 53­80% of the procedures. Compared to soft tissue procedures (e.g., 13.2% MVC in the right trapezius), higher muscle activity was observed during orthopedic procedures (e.g., 27.6% MVC in the right trapezius). Conclusions: This pilot study showed that physical risk factors (i.e., muscle activity and posture of the neck/shoulder) can be measured using wearable sensors during live veterinary surgeries. The observed risk factors were similar to those documented for medical physicians. Further studies are needed to bring awareness to opportunities for improving workplace ergonomics in veterinary medicine and surgery.

A Systematic Review and Meta-analysis of Patient Survival and Disease Recurrence Following Percutaneous Ablation of Pulmonary Metastasis.

BACKGROUND: Pulmonary metastasectomy has been widely adopted in the treatment of metastatic disease. In recent years image guided ablation has seen increased use in the treatment of thoracic malignancies. The objective of this study was to evaluate oncological outcomes following percutaneous ablation (PA) of pulmonary metastasis. METHODS: A comprehensive search of the PubMed, MEDLINE and EMBASE databases from January 2000 to August 2021 was performed to identify studies evaluating patient survival following ablation of lung metastasis. Pooled outcomes have been presented with a random effects model to assess primary outcomes of overall survival, progression free survival and 1-year local control. Secondary outcomes included procedural mortality, major complications, and the incidence of pneumothorax. RESULTS: A total of 24 studies were identified. The pooled median overall survival was 5.13 [95% confidence interval (CI): 4.37-6.84] years, and the 1-, 3-, 5-year progression free survival rates were 53%, 26% and 20% respectively. The 1-year local control rate was 91% (95%CI: 86-95%). Periprocedural mortality was rare (0%; 95%CI: 0-1%), as were major complications excluding pneumothorax (1%; 95%CI: 1-2%). Pneumothorax developed in 44% of ablation sessions, although only half of these required chest tube placement. Most patients were able to be discharged day one post-procedurally. CONCLUSION: PA demonstrates high overall, progression free and local tumour survival in patients with lung metastasis. Complications and mortality are also rare. Consideration of its use should be made in a tumour board meeting in conjunction with surgical and radiotherapy perspectives for targeted local control of metastases.

A comparison of laparoscopic and robotic ergonomic risk.

INTRODUCTION: Work related injuries in minimally invasive surgery (MIS) are common because of the strains placed on the surgeon's or assistant's body. The objective of this study was to compare specific ergonomic risks among surgeons and surgical trainees performing robotic and laparoscopic procedures. MATERIALS AND METHODS: Ergonomic data and discomfort questionnaires were recorded from surgeons and trainees (fellows/residents) for both robotic and laparoscopic procedures. Perceived discomfort questionnaires were recorded pre/postoperatively. Intraoperatively, biomechanical loads were captured using motion tracking sensors and electromyography (EMG) sensors. Perceived discomfort, body position and muscle activity were compared between robotic and laparoscopic procedures using a linear regression model. RESULTS: Twenty surgeons and surgical trainees performed 29 robotic and 48 laparoscopic procedures. Postoperatively, increases in right finger numbness and right shoulder stiffness and surgeon irritability were noted after laparoscopy and increased back stiffness after robotic surgery. Further, the laparoscopic group saw increases in right hand/shoulder pain (OR 0.8; p = 0.032) and left hand/shoulder pain (0.22; p < 0.001) compared to robotic. Right deltoid and trapezius excessive muscle activity were significantly higher in laparoscopic operations compared to robotic. Demanding and static positioning was similar between the two groups except there was significantly more static neck position required for robotic operations. CONCLUSION: Robotic assisted surgeries led to lower postoperative discomfort and muscle strain in both upper extremities, particularly dominant side of the surgeon, but increased static neck positioning with subjective back stiffness compared with laparoscopy. These recognized ergonomic differences between the two platforms can be used to raise surgeon awareness of their intraoperative posture and to develop targeted physical and occupational therapy interventions to decrease surgeon WMSDs and increase surgeon longevity.

Association of Onset-to-Treatment Time With Discharge Destination, Mortality, and Complications Among Patients With Aneurysmal Subarachnoid Hemorrhage.

Importance: Rapid access to specialized care is recommended to improve outcomes after aneurysmal subarachnoid hemorrhage (SAH), but understanding of the optimal onset-to-treatment time for aneurysmal SAH is limited. Objective: To assess the optimal onset-to-treatment time for aneurysmal SAH that maximized patient outcomes after surgery. Design, Setting, and Participants: This cohort study assessed 575 retrospectively identified cases of first-ever aneurysmal SAH occurring within the referral networks of 2 major tertiary Australian hospitals from January 1, 2010, to December 31, 2016. Individual factors, prehospital factors, and hospital factors were extracted from the digital medical records of eligible cases. Data analysis was performed from March 1, 2020, to August 31, 2021. Exposures: Main exposure was onset-to-treatment time (time between symptom onset and aneurysm surgical treatment in hours) derived from medical records. Main Outcomes and Measures: Clinical characteristics, complications, and discharge destination were extracted from medical records and 12-month survival obtained from data linkage. The associations of onset-to-treatment time (in hours) with (1) discharge destination of survivors (home vs rehabilitation), (2) 12-month survival, and (3) neurologic complications (rebleed, delayed cerebral ischemia, meningitis, seizure, hydrocephalus, and delayed cerebral injury) were investigated using natural cubic splines in multivariable Cox proportional hazards and logistic regression models. Results: Of the 575 patients with aneurysmal SAH, 482 patients (mean [SD] age, 55.0 [14.5] years; 337 [69.9%] female) who received endovascular coiling or neurosurgical clipping were studied. A nonlinear association of treatment delay was found with the odds of being discharged home vs rehabilitation (effective df = 3.83 in the generalized additive model, χ2 test P = .002 for the 4-df cubic spline), with a similar nonlinear association remaining significant after adjustment for sex, treatment modality, severity, Charlson Comorbidity Index, history of hypertension, and hospital transfer (likelihood ratio test: df = 3, deviance = 9.57, χ2 test P = .02). Both unadjusted and adjusted cox regression models showed a nonlinear association between time to treatment and 12-month mortality with the lowest hazard of death with receipt of treatment at 12.5 hours after symptom onset, although the nonlinear term became nonsignificant upon adjustment. The odds of being discharged home were higher with treatment before 20 hours after onset, with the probability of being discharged home compared with rehabilitation or other hospital increased by approximately 10% when treatment was received within the first 12.5 hours after symptom onset and increased by an additional 5% from 12.5 to 20 hours. Time to treatment was not associated with any complications. Conclusions and Relevance: This cohort study found evidence that more favorable outcomes (discharge home and survival at 12 months) were achieved when surgical treatment occurred at approximately 12.5 hours. These findings provide more clarity around optimal timelines of treatment with people with aneurysmal SAH; however, additional studies are needed to confirm the findings.

Intracranial atherosclerotic disease and acute ischaemic stroke: A review of diagnosis and management.

Intracranial atherosclerotic disease is highly prevalent and a common cause of ischaemic stroke globally. With the increasing use of endovascular treatment for acute stroke management, computed tomography and magnetic resonance imaging have become an essential part of patient selection. In this review, we present the typical imaging findings of intracranial atherosclerosis and an overview of management as relevant to diagnostic and interventional radiologists.

Image-guided spinal injection for pain management.

Radiculopathy and spinal pain are debilitating conditions affecting millions of people worldwide each year. While most cases can be managed conservatively with physiotherapy and nonsteroidal anti-inflammatory medications, minimally invasive corticosteroid injections are the mainstay intervention for those not responsive to conservative treatment. Historically, spinal injections were performed in the absence of imaging guidance; however, imaging modalities, in particular fluoroscopy and computer tomography (CT), have become the standard of care in performing most of these procedures. Under imaging guidance, operators can accurately confirm needle placement and safely target localised pathologies.

Development of a machine learning-based real-time location system to streamline acute endovascular intervention in acute stroke: a proof-of-concept study.

BACKGROUND: Delivery of acute stroke endovascular intervention can be challenging because it requires complex coordination of patient and staff across many different locations. In this proof-of-concept paper we (a) examine whether WiFi fingerprinting is a feasible machine learning (ML)-based real-time location system (RTLS) technology that can provide accurate real-time location information within a hospital setting, and (b) hypothesize its potential application in streamlining acute stroke endovascular intervention. METHODS: We conducted our study in a comprehensive stroke care unit in Melbourne, Australia that offers a 24-hour mechanical thrombectomy service. ML algorithms including K-nearest neighbors, decision tree, random forest, support vector machine and ensemble models were trained and tested on a public WiFi dataset and the study hospital WiFi dataset. The hospital dataset was collected using the WiFi explorer software (version 3.0.2) on a MacBook Pro (AirPort Extreme, Broadcom BCM43x×1.0). Data analysis was implemented in the Python programming environment using the scikit-learn package. The primary statistical measure for algorithm performance was the accuracy of location prediction. RESULTS: ML-based WiFi fingerprinting can accurately predict the different hospital zones relevant in the acute endovascular intervention workflow such as emergency department, CT room and angiography suite. The most accurate algorithms were random forest and support vector machine, both of which were 98% accurate. The algorithms remain robust when new data points, which were distinct from the training dataset, were tested. CONCLUSIONS: ML-based RTLS technology using WiFi fingerprinting has the potential to streamline delivery of acute stroke endovascular intervention by efficiently tracking patient and staff movement during stroke calls.

Application of a computational model in simulating an endovascular clot retrieval service system within regional Australia.

INTRODUCTION: The global demand for endovascular clot retrieval (ECR) has grown rapidly in recent years creating challenges to healthcare system planning and resource allocation. This study aims to apply our established computational model to predict and optimise the performance and resource allocation of ECR services within regional Australia, and applying data from the state of South Australia as a modelling exercise. METHOD: Local geographic information obtained using the Google Maps application program interface and real-world data was input into the discrete event simulation model we previously developed. The results were obtained after the simulation was run over 5 years. We modelled and compared a single-centre and two-centre ECR service delivery system. RESULTS: Based on the input data, this model was able to simulate the ECR delivery system in the state of South Australia from the moment when emergency services were notified of a potential stroke patient to potential delivery of ECR treatment. In the model, ECR delivery improved using a two-centre system compared to a one-centre system, as the percentage of stroke patients requiring ECR was increased. When 15% of patients required ECR, the proportion of 'failure to receive ECR' cases for a single-centre system was 17.35%, compared to 3.71% for a two-centre system. CONCLUSIONS: Geolocation and resource utilisation within the ECR delivery system are crucial in optimising service delivery and patient outcome. Under the model assumptions, as the number of stroke cases requiring ECR increased, a two-centre ECR system resulted in increased timely ECR delivery, compared to a single-centre system. This study demonstrated the flexibility and the potential application of our DES model in simulating the stroke service within any location worldwide.

Artificial intelligence in clinical decision support and outcome prediction - applications in stroke.

Artificial intelligence (AI) is making a profound impact in healthcare, with the number of AI applications in medicine increasing substantially over the past five years. In acute stroke, it is playing an increasingly important role in clinical decision-making. Contemporary advances have increased the amount of information - both clinical and radiological - which clinicians must consider when managing patients. In the time-critical setting of acute stroke, AI offers the tools to rapidly evaluate and consolidate available information, extracting specific predictions from rich, noisy data. It has been applied to the automatic detection of stroke lesions on imaging and can guide treatment decisions through the prediction of tissue outcomes and long-term functional outcomes. This review examines the current state of AI applications in stroke, exploring their potential to reform stroke care through clinical decision support, as well as the challenges and limitations which must be addressed to facilitate their acceptance and adoption for clinical use.

Social media in interventional radiology.

INTRODUCTION: Social media provides opportunities for Interventional Radiologists to share research, communicate with colleagues, provide health information and advertise their clinical practice. This study aims to examine the online and social media presence of currently practicing Australian Interventional Radiologists. METHODS: Systematic Google searches were undertaken in May 2019 and updated in May 2020 to identify practicing Interventional Radiologists in Australia. Comprehensive searches of practice websites and social media platforms (Facebook, LinkedIn, Twitter, ResearchGate, YouTube) were undertaken for each Interventional Radiologist. RESULTS: There were 265 Interventional Radiologists identified as currently practising in Australia, including 209 Interventional Radiologists (excluding Interventional Neuroradiologists), 49 Interventional Neuroradiologists and 7 that practise across both Interventional Radiology and Interventional Neuroradiology. 72% of Interventional Radiologists had at least one social media account, with LinkedIn the most widely used social media platform (60%). There was a significant negative correlation between the total number of social media accounts and years in practice (P = 0.04). Across the states, a higher population per IR was positively correlated with a higher average number of social media accounts per IR (P = 0.04). Interventional Neuroradiologists had a significantly higher average number of social media accounts compared to Interventional Radiologists (1.94 vs 1.29, P < 0.01). CONCLUSIONS: Most Australian Interventional Radiologists have a readily identifiable social media presence. There is potential for further utilisation of social media for academic, educational and business purposes.

Review of deep learning algorithms for the automatic detection of intracranial hemorrhages on computed tomography head imaging.

Artificial intelligence is a rapidly evolving field, with modern technological advances and the growth of electronic health data opening new possibilities in diagnostic radiology. In recent years, the performance of deep learning (DL) algorithms on various medical image tasks have continually improved. DL algorithms have been proposed as a tool to detect various forms of intracranial hemorrhage on non-contrast computed tomography (NCCT) of the head. In subtle, acute cases, the capacity for DL algorithm image interpretation support might improve the diagnostic yield of CT for detection of this time-critical condition, potentially expediting treatment where appropriate and improving patient outcomes. However, there are multiple challenges to DL algorithm implementation, such as the relative scarcity of labeled datasets, the difficulties in developing algorithms capable of volumetric medical image analysis, and the complex practicalities of deployment into clinical practice. This review examines the literature and the approaches taken in the development of DL algorithms for the detection of intracranial hemorrhage on NCCT head studies. Considerations in crafting such algorithms will be discussed, as well as challenges which must be overcome to ensure effective, dependable implementations as automated tools in a clinical setting.