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.
Background: Minimally invasive pancreaticoduodenectomy (PD) is a feasible option for periampullary tumours. However, it remains a complex procedure with no proven advantages over open PD (OPD). The aim of the study was to compare the outcomes between laparoscopic-assisted PD (LAPD) and OPD using a propensity score-matched analysis. Methods: Retrospective review of 40 patients who underwent PD for periampullary tumours between January 2014 and December 2016 was conducted. The patients were matched 1:1 for age, gender, body mass index, Charlson comorbidty index, tumour size and haematological indices. Peri-operative outcomes were evaluated. Results: LAPD appeared to have a longer median operative time as compared to OPD (LAPD, 425 min (285-597) versus OPD, 369 min (260-500)) (P = 0.066). Intra-operative blood loss was comparable between both groups. Respiratory complications were five times higher in the OPD group (LAPD, 5% versus OPD, 25%) (P = 0.077), while LAPD patients required less time to start ambulating post-operatively (LAPD, 2 days versus OPD, 2 days) (P = 0.021). Pancreas-specific complications and morbidity/mortality rates were similar. Conclusion: LAPD is a safe alternative to OPD in a select group of patients for an institution starting out with minimally invasive PD, and can be used to bridge the learning curve required for total laparoscopic PD. © 2019 Royal Australasian College of Surgeons ANZ J Surg 89 (2019) E190-E194 ANZJSurg.com 12.0 (2.0-39.0) 13.5 (4.0-27.0) 0.480 R0 resection, n (%) 16 (80.0) 19 (95.0) 0.151 LAPD, laparoscopic-assisted pancreaticoduodenectomy; OPD, open pancreaticoduodenectomy.
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 informationboth clinical and radiologicalwhich 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.
We report a pathologically proved craniopharyngioma in the prepontine cistern. A 50-year-old woman presented with swallowing difficulty for 1 month. She underwent brain MR and CT imaging.T1-weighted, T2-weighted, and contrast-enhanced T1-weighted images showed a large peripheral enhancing cystic mass in the prepontine cistern. Inside the lesion, high signal intensity (SI) on T1 and low SI on T2-weighted imaging were noted (Fig 1). The CT scan showed features similar to those on the MR images, except for the addition of a peripheral small calcification in the cystic lesion. We could not find any connection between the mass in the prepontine cistern and the sellar or parasellar area. The mass was partially surgically removed, and histopathologic examination revealed craniopharyngioma in the prepontine cistern.Craniopharyngiomas can arise anywhere along the craniopharyngeal canal. However, there are several reports of craniopharyngiomas with unusual locations-that is, in the posterior cranial fossa, without a connection to the sellar or parasellar area. The locations were the temporal lobe, pons and fourth ventricle, and cerebellopontine angle and fourth ventricle. [1][2][3] In our case, the location was the prepontine cistern, which was not previously described, to our knowledge. Considering the location of the craniopharyngioma in our patient in contrast to the usual location, the hypothesis that most craniopharyngiomas occur along the craniopharyngeal canal could not be applied. Instead, the suggestion of Solarski et al, 4 -that is, ectopic craniopharyngiomas might origi-nate from totipotential or multipotential cells-might be applied to our case.In conclusion, although the location in our patient was very unusual, craniopharyngiomas can occur anywhere.
Background Deep learning (DL) algorithms are playing an increasing role in automatic medical image analysis. Purpose To evaluate the performance of a DL model for the automatic detection of intracranial haemorrhage and its subtypes on non-contrast CT (NCCT) head studies and to compare the effects of various preprocessing and model design implementations. Methods The DL algorithm was trained and externally validated on open-source, multi-centre retrospective data containing radiologist-annotated NCCT head studies. The training dataset was sourced from four research institutions across Canada, the USA and Brazil. The test dataset was sourced from a research centre in India. A convolutional neural network (CNN) was used, with its performance compared against similar models with additional implementations: (1) a recurrent neural network (RNN) attached to the CNN, (2) preprocessed CT image-windowed inputs and (3) preprocessed CT image-concatenated inputs. The area under the receiver operating characteristic curve (AUC-ROC) and microaveraged precision (mAP) score were used to evaluate and compare model performances. Results The training and test datasets contained 21,744 and 491 NCCT head studies, respectively, with 8,882 (40.8%) and 205 (41.8%) positive for intracranial haemorrhage. Implementation of preprocessing techniques and the CNN-RNN framework increased mAP from 0.77 to 0.93 and increased AUC-ROC [95% confidence intervals] from 0.854 [0.816–0.889] to 0.966 [0.951–0.980] (p-value = 3.91 × 10−12). Conclusions The deep learning model accurately detected intracranial haemorrhage and improved in performance following specific implementation techniques, demonstrating clinical potential as a decision support tool and an automated system to improve radiologist workflow efficiency. Key points • The deep learning model detected intracranial haemorrhages on computed tomography with high accuracy. • Image preprocessing, such as windowing, plays a large role in improving deep learning model performance. • Implementations which enable an analysis of interslice dependencies can improve deep learning model performance. • Visual saliency maps can facilitate explainable artificial intelligence systems. • Deep learning within a triage system may expedite earlier intracranial haemorrhage detection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.