Automatic segmentation of extensor carpi ulnaris tendon and detection of tendinosis with convolutional neural networks.

Background: Extensor Carpi Ulnaris (ECU) tendinosis, a frequent cause of chronic wrist pain, requires prompt diagnosis to prevent disability. This study demonstrates the use of convolutional neural networks (CNNs) for automated detection and segmentation of the ECU tendon and tendinosis in 2D axial wrist MRI.

Purpose: To develop a CNN for the automated detection of ECU tendon and automatic delineation of tendinosis in 2D wrist MRI.

Factors influencing the reliability of a CT angiography-based deep learning method for infarct volume estimation.

Objectives: CT angiography (CTA)-based machine learning methods for infarct volume estimation have shown a tendency to overestimate infarct core and final infarct volumes (FIV). Our aim was to assess factors influencing the reliability of these methods.

Methods: The effect of collateral circulation on the correlation between convolutional neural network (CNN) estimations and FIV was assessed based on the Miteff system and hypoperfusion intensity ratio (HIR) in 121 patients with anterior circulation acute ischaemic stroke using Pearson correlation coefficients and median volumes.

Automatic chest computed tomography image noise quantification using deep learning.

Purpose: This study aimed to develop a deep learning (DL) method for noise quantification for clinical chest computed tomography (CT) images without the need for repeated scanning or homogeneous tissue regions.

Methods: A comprehensive phantom CT dataset (three dose levels, six reconstruction methods, amounting to 9240 slices) was acquired and used to train a convolutional neural network (CNN) to output an estimate of local image noise standard deviations (SD) from a single CT scan input. The CNN model consisting of seven convolutional layers was trained on the phantom image dataset representing a range of scan parameters and was tested with phantom images acquired in a variety of different scan conditions, as well as publicly available chest CT images to produce clinical noise SD maps.

Deep learning-aided extraction of outer aortic surface from CT angiography scans of patients with Stanford type B aortic dissection.

Background: Guidelines recommend that aortic dimension measurements in aortic dissection should include the aortic wall. This study aimed to evaluate two-dimensional (2D)- and three-dimensional (3D)-based deep learning approaches for extraction of outer aortic surface in computed tomography angiography (CTA) scans of Stanford type B aortic dissection (TBAD) patients and assess the speed of different whole aorta (WA) segmentation approaches.

Methods: A total of 240 patients diagnosed with TBAD between January 2007 and December 2019 were retrospectively reviewed for this study; 206 CTA scans from 206 patients with acute, subacute, or chronic TBAD acquired with various scanners in multiple different hospital units were included.

Leveraging open dataset and transfer learning for accurate recognition of chronic pulmonary embolism from CT angiogram maximum intensity projection images.

Background: Early diagnosis of the potentially fatal but curable chronic pulmonary embolism (CPE) is challenging. We have developed and investigated a novel convolutional neural network (CNN) model to recognise CPE from CT pulmonary angiograms (CTPA) based on the general vascular morphology in two-dimensional (2D) maximum intensity projection images.

Methods: A CNN model was trained on a curated subset of a public pulmonary embolism CT dataset (RSPECT) with 755 CTPA studies, including patient-level labels of CPE, acute pulmonary embolism (APE), or no pulmonary embolism.

Automatic head computed tomography image noise quantification with deep learning.

Purpose: Computed tomography (CT) image noise is usually determined by standard deviation (SD) of pixel values from uniform image regions. This study investigates how deep learning (DL) could be applied in head CT image noise estimation.

Methods: Two approaches were investigated for noise image estimation of a single acquisition image: direct noise image estimation using supervised DnCNN convolutional neural network (CNN) architecture, and subtraction of a denoised image estimated with denoising UNet-CNN experimented with supervised and unsupervised noise2noise training approaches.

A Randomized, Sham-Controlled Trial of Repetitive Transcranial Magnetic Stimulation Targeting M1 and S2 in Central Poststroke Pain: A Pilot Trial.

Objectives: Central poststroke pain (CPSP), a neuropathic pain condition, is difficult to treat. Repetitive transcranial magnetic stimulation (rTMS) targeted to the primary motor cortex (M1) can alleviate the condition, but not all patients respond. We aimed to assess a promising alternative rTMS target, the secondary somatosensory cortex (S2), for CPSP treatment.

Automatic CT Angiography Lesion Segmentation Compared to CT Perfusion in Ischemic Stroke Detection: a Feasibility Study.

In stroke imaging, CT angiography (CTA) is used for detecting arterial occlusions. These images could also provide information on the extent of ischemia. The study aim was to develop and evaluate a convolutional neural network (CNN)-based algorithm for detecting and segmenting acute ischemic lesions from CTA images of patients with suspected middle cerebral artery stroke.

Computed tomography angiography-based deep learning method for treatment selection and infarct volume prediction in anterior cerebral circulation large vessel occlusion.

Background: Computed tomography perfusion (CTP) is the mainstay to determine possible eligibility for endovascular thrombectomy (EVT), but there is still a need for alternative methods in patient triage.

Purpose: To study the ability of a computed tomography angiography (CTA)-based convolutional neural network (CNN) method in predicting final infarct volume in patients with large vessel occlusion successfully treated with endovascular therapy.

Materials And Methods: The accuracy of the CTA source image-based CNN in final infarct volume prediction was evaluated against follow-up CT or MR imaging in 89 patients with anterior circulation ischemic stroke successfully treated with EVT as defined by Thrombolysis in Cerebral Infarction category 2b or 3 using Pearson correlation coefficients and intraclass correlation coefficients.

Performance of a 3D convolutional neural network in the detection of hypoperfusion at CT pulmonary angiography in patients with chronic pulmonary embolism: a feasibility study.

Background: Chronic pulmonary embolism (CPE) is a life-threatening disease easily misdiagnosed on computed tomography. We investigated a three-dimensional convolutional neural network (CNN) algorithm for detecting hypoperfusion in CPE from computed tomography pulmonary angiography (CTPA).

Methods: Preoperative CTPA of 25 patients with CPE and 25 without pulmonary embolism were selected.

Evaluation of a CTA-based convolutional neural network for infarct volume prediction in anterior cerebral circulation ischaemic stroke.

Background: Computed tomography angiography (CTA) imaging is needed in current guideline-based stroke diagnosis, and infarct core size is one factor in guiding treatment decisions. We studied the efficacy of a convolutional neural network (CNN) in final infarct volume prediction from CTA and compared the results to a CT perfusion (CTP)-based commercially available software (RAPID, iSchemaView).

Methods: We retrospectively selected 83 consecutive stroke cases treated with thrombolytic therapy or receiving supportive care that presented to Helsinki University Hospital between January 2018 and July 2019.

3D convolutional neural networks applied to CT angiography in the detection of acute ischemic stroke.

Background: The aim of this study was to investigate the feasibility of ischemic stroke detection from computed tomography angiography source images (CTA-SI) using three-dimensional convolutional neural networks.

Methods: CTA-SI of 60 patients with a suspected acute ischemic stroke of the middle cerebral artery were randomly selected for this study; 30 patients were used in the neural network training, and the subsequent testing was performed using the remaining 30 patients. The training and testing were based on manually segmented lesions.

Headache as symptom of intracranial hemorrhage.

The most important signs of danger of a headache patient include exceptionally intense or acute headache, transient loss or progressive impairment of consciousness, and neurological deficit symptoms. These patients are referred to an urgent assessment by a physician. Computed tomography scanning of the head is carried out in the case of suspected hemorrhage of a headache patient.

Characteristics and long-term outcome of 251 patients with dural arteriovenous fistulas in a defined population.

Object: Management of dural arteriovenous fistulas (DAVFs) has changed during the last decades due to increased knowledge of their pathophysiology and natural history as well as advances in treatment modalities. The authors describe the characteristics and long-term outcome of a large consecutive series of patients with DAVFs.

Methods: Altogether 251 patients with 261 DAVFs were treated in 2 of the 5 neurosurgery departments at Helsinki and Kuopio University Hospitals between 1944 and 2006.

Oxidative stress is associated with cell death, wall degradation, and increased risk of rupture of the intracranial aneurysm wall.

Background: The cause of rupture of intracranial aneurysms (IA) is not well understood. We previously demonstrated that loss of cells from the IA wall is associated with wall degeneration and rupture.

Objective: To investigate the mechanisms mediating cell death in the IA wall.

Detection of unruptured cerebral artery aneurysms by MRA at 3.0 tesla: comparison with multislice helical computed tomographic angiography.

Background: Computed tomographic angiography (CTA) has become the primary non-invasive method for detection of cerebral artery aneurysms in many neurovascular centers.

Purpose: To compare MR-angiography at a 3.0 tesla (3T) scanner to CTA in the detection of unruptured intracranial aneurysms.

High-resolution TOF MR angiography at 4.7 Tesla for volumetric and morphologic evaluation of coiled aneurysm neck remnants in a rat model.

Background: Detection of morphologic and volumetric changes in aneurysm necks is important when evaluating the effects of endovascular devices for aneurysm occlusion.

Purpose: To optimize high-resolution 3D-TOF MRA at 4.7 T in order to achieve the best aneurysm-to-background contrast in experimental rat aneurysms, and to quantify the volume of the aneurysm neck by imaging.

Posterior fossa dural arteriovenous fistulas: diagnosis and follow-up with time-resolved imaging of contrast kinetics (TRICKS) at 1.5T.

Background: Time-of-flight MR angiography (TOF MRA) is currently the most widely used non-invasive imaging tool to diagnose dural arteriovenous fistula (DAVF). It is, however, not as sensitive as invasive digital subtraction angiography (DSA) for detecting the arteriovenous shunting inherent in DAVF. Dynamic contrast-enhanced MR angiography allows separation of arterial and venous phases of contrast passage though the brain and can thus demonstrate early venous filling through the arteriovenous shunt.

Lateral supraorbital approach applied to anterior clinoidal meningiomas: experience with 73 consecutive patients.

Background: Anterior clinoidal meningiomas (ACMs) are a subgroup of meningiomas accounting for less than 10% of supratentorial meningiomas.

Objective: To assess the reliability and safeness of the lateral supraorbital approach (LSO) to remove ACMs.

Methods: Between September 1997 and October 2009, a total of 73 ACM patients were operated on at the Department of Neurosurgery, Helsinki University Central Hospital, by the senior author (J.

Optimization of high-resolution USPIO magnetic resonance imaging at 4.7 T using novel phantom with minimal structural interference.

Purpose: To characterize the effect of ultrasmall superparamagnetic iron oxides (USPIOs) on magnetic resonance imaging (MRI) signal at 4.7 T, and to find the highest sensitivity pulse sequence for high-resolution USPIO MRI.

Materials And Methods: A novel phantom was constructed for optimization of sequence parameters for neuroradiological MR applications, and a wide range of dilutions of the USPIO ferumoxtran-10 was imaged using T(2)/T(1)-, T(1)-, T(2)-, T* (2)-, and PD-weighted sequences.

Complement system becomes activated by the classical pathway in intracranial aneurysm walls.

Inflammation and activation of the complement system in the intracranial aneurysm (IA) wall predispose to IA rupture. We have previously shown that increased C5b-9 accumulation correlates with IA rupture and wall degeneration. To elucidate the underlying mechanisms, we investigated initiators and the pathway of complement activation in unruptured and ruptured IAs.

Occlusion of neck remnant in experimental rat aneurysms after treatment with platinum- or polyglycolic-polylactic acid-coated coils.

Background: Neck remnants and aneurysm recurrences are marked limitations of endovascular treatment of cerebral artery aneurysms. We compared the evolution of neck remnants of experimental arterial rat aneurysms after treatment with either platinum- or PGLA-coated coils.

Methods: We created 20 standard-size aneurysms in the abdominal aortas of male Wistar rats.