scholarly journals NIMG-59. ADVERSE EFFECTS OF IMAGE TILING FOR AUTOMATIC DEEP LEARNING GLIOMA SEGMENTATION IN MRI

2019 ◽  
Vol 21 (Supplement_6) ◽  
pp. vi174-vi174
Author(s):  
G Anthony Reina ◽  
Siddhesh Thakur ◽  
Ravi Panchumarthy ◽  
Spyridon Bakas
Keyword(s):  
Deep Learning ◽  
Adverse Effects ◽  
Computational Analysis ◽  
Resonance Imaging ◽  
Contrast Variation ◽  
Abnormal Signal ◽  
Tile Size ◽  
Magnetic Resonance Imaging Mri ◽  
Tumor Extent ◽  
Intense Signal

Abstract BACKGROUND Application of deep learning to neuro-oncology has shown promising clinically relevant results for tumor classification, localization, and segmentation. Hardware limitations, typically memory size of graphics cards, prevent magnetic resonance imaging (MRI) volumes from being processed as a whole, and hence they are divided into smaller, overlapping tiles. Deep learning algorithms (e.g., U-Net) can then be trained and applied for predictions on such tiles, followed by their combination/stitching as the final prediction for the whole volume. We investigate the hypothesis that image tiling options, such as tile placing, size, overlap, and stitching, introduce variations with adverse effects on predictions, both in terms of inconsistency and accuracy. METHODS We utilized the publicly available BraTS 2018 dataset of 285 baseline pre-operative MRI glioma scans, with corresponding expert tumor boundary annotations. We implemented a 3D U-Net to predict boundaries of the whole tumor extent, by virtue of the abnormal hyper-intense signal of T2-FLAIR scans. RESULTS Simply flipping the tile horizontally, or translating it by one voxel, produces different predictions. Use of small tiles (64x64x64 voxels) yields substantially more false positive predictions than when using larger tile size (i.e., 128x128x128 voxels). Overlapping tiles produce conflicting predictions, leading to ambiguous interpretations upon their stitching. In areas of overlapping tiles, rounding followed by averaging the overlapping predictions produce superior results to the inverse sequence. All these are particularly noticeable in the margins of the abnormal signal and in areas of large contrast variation. CONCLUSIONS Although tiling is a workaround for hardware limitations, it introduces variations detrimental to accuracy. Tiling of neuro-oncology scans for computational analysis using deep learning leads to non-generalizable, non-reproducible results, thereby affecting the performance and potential clinical translatability of such algorithms. Careful considerations and standardization recommendations should be established and appropriately documented for performing such analyses, in order to avoid misinterpretation of results.

Comorbid Depressive Disorders in Epilepsy

CNS Spectrums ◽  
2010 ◽  
Vol 15 (S4) ◽  
pp. 3-6 ◽  
Author(s):  
Andres M. Kanner ◽  
Andrew J. Cole
Keyword(s):  
Emergency Room ◽  
Depressive Disorders ◽  
Clonic Seizure ◽  
Resonance Imaging ◽  
Abnormal Signal ◽  
The Past ◽  
History Of ◽  
Magnetic Resonance Imaging Mri ◽  
The Right ◽  
History Of Depression

A 27-year-old woman presented to the emergency room after having witnessed generalized tonic clonic seizure while asleep. Birth and development were normal. She had suffered a single febrile seizure at 13 months of age, but had no other seizure risk factors. She was otherwise well except for a history of depression for which she was taking sertraline. Depressive symptoms had been well controlled over the past 3 months, but she had been under increased stress working to finish a doctoral thesis. Neurological examination was normal. Magnetic resonance imaging (MRI) showed modest asymmetry of the hippocampi, slightly smaller on the right, but no abnormal signal and well-preserved laminar anatomy. An electroencephalogram was negative. She was discharged from the emergency room with no treatment. Three weeks later, the patient's boyfriend witnessed an episode of behavioral arrest with lip smacking and swallowing automatisms lasting 45 seconds, after which the patient was confused for 20–30 minutes. The next morning she and her boyfriend kept a previously scheduled appointment with a neurologist.

scholarly journals Diagnosa Tumor Otak Berdasarkan Citra MRI (Magnetic Resonance Imaging)

2019 ◽  
Vol 18 (2) ◽  
Author(s):  
Ida Bagus Leo Mahadya Suta ◽  
Rukmi Sari Hartati ◽  
Yoga Divayana
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Convolutional Neural Network ◽  
Resonance Imaging ◽  
Magnetic Resonance Imaging Mri

Tumor otak menjadi salah satu penyakit yang paling mematikan, salah satu jenis yang paling banyak ditemukan adalah glioma sekitar 6 dari 100.000 pasien adalah penderita glioma. Citra digital melalui Magnetic Resonance Imaging (MRI) merupakan salah satu metode untuk membantu dokter dalam menganalisa dan mengklasifikasikan jenis tumor otak. Namun, klasifikasi secara manual membutuhkan waktu yang lama dan memiliki resiko kesalahan yang tinggi, untuk itu dibutuhkan suatu cara otomatis dan akurat dalam melakukan klasifikasi citra MRI. Convolutional Neural Network (CNN) menjadi salah satu solusi dalam melakukan klasifikasi otomatis dalam citra MRI. CNN merupakan algoritma deep learning yang memiliki kemampuan untuk belajar sendiri dari kasus kasus sebelumnya. Dan dari penelitian yang telah dilakukan, diperoleh hasil bahwa CNN mampu dalam menyelesaikan klasifikasi tumor otak dengan akurasi yang tinggi. Peningkatan akurasi diperoleh dengan mengembangkan algoritma CNN baik melalui menentukan nilai kernel dan/atau fungsi aktivasi.

scholarly journals Deep Learning with Limited Data: Organ Segmentation Performance by U-Net

Electronics ◽  
2020 ◽  
Vol 9 (8) ◽  
pp. 1199
Author(s):  
Michelle Bardis ◽  
Roozbeh Houshyar ◽  
Chanon Chantaduly ◽  
Alexander Ushinsky ◽  
Justin Glavis-Bloom ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Data Availability ◽  
Resonance Imaging ◽  
Learning Network ◽  
Transrectal Biopsy ◽  
Minimum Number ◽  
Magnetic Resonance Imaging Mri ◽  
Deep Learning Network

(1) Background: The effectiveness of deep learning artificial intelligence depends on data availability, often requiring large volumes of data to effectively train an algorithm. However, few studies have explored the minimum number of images needed for optimal algorithmic performance. (2) Methods: This institutional review board (IRB)-approved retrospective review included patients who received prostate magnetic resonance imaging (MRI) between September 2014 and August 2018 and a magnetic resonance imaging (MRI) fusion transrectal biopsy. T2-weighted images were manually segmented by a board-certified abdominal radiologist. Segmented images were trained on a deep learning network with the following case numbers: 8, 16, 24, 32, 40, 80, 120, 160, 200, 240, 280, and 320. (3) Results: Our deep learning network’s performance was assessed with a Dice score, which measures overlap between the radiologist’s segmentations and deep learning-generated segmentations and ranges from 0 (no overlap) to 1 (perfect overlap). Our algorithm’s Dice score started at 0.424 with 8 cases and improved to 0.858 with 160 cases. After 160 cases, the Dice increased to 0.867 with 320 cases. (4) Conclusions: Our deep learning network for prostate segmentation produced the highest overall Dice score with 320 training cases. Performance improved notably from training sizes of 8 to 120, then plateaued with minimal improvement at training case size above 160. Other studies utilizing comparable network architectures may have similar plateaus, suggesting suitable results may be obtainable with small datasets.

scholarly journals Is there a link between COVID-19 and Creutzfeldt-Jakob Disease? a Case Report

2021 ◽  
Vol 9 (1) ◽  
pp. 26-26
Author(s):  
Ehsan Nasiri ◽  
Amirreza Naseri ◽  
Mohammad Yazdchi ◽  
Mahnaz Talebi
Keyword(s):  
Protein Detection ◽  
Behavioral Changes ◽  
Resonance Imaging ◽  
Mri Findings ◽  
Progressive Dementia ◽  
Abnormal Signal ◽  
Jakob Disease ◽  
The Central Nervous System ◽  
Abnormal Signal Intensity ◽  
Magnetic Resonance Imaging Mri

Creutzfeldt-Jakob Disease (CJD) is a rare rapidly progressive neurodegenerative disease. The diagnosis of CJD is based on magnetic resonance imaging (MRI) findings, electro-encephalography (EEG), or 14-3-3 protein detection. We report a case of a previously-healthy 72 years old woman, with evidence of coronavirus disease 2019 (COVID-19), who complained of behavioral changes and rapidly progressive dementia. While hospitalization, she didn't have orientation to time and place and repeated an irrelevant sentence in response to questions. Also, anomia and impaired comprehension was observed. Myoclonic jerks, abnormal signal intensity at bilateral parieto-occipital cortices in MRI, periodic sharp wave complexes in EEG, and increased lactate dehydrogenase in cerebrospinal fluid (CSF), highly recommended CJD for her. This is the second case of CJD after COVID-19 during this pandemic, which can be an alarm to clinicians about the silent impact of COVID-19 on the central nervous system.

scholarly journals Review and Prospect: Artificial Intelligence in Advanced Medical Imaging

2021 ◽  
Vol 1 ◽  
Author(s):  
Shanshan Wang ◽  
Guohua Cao ◽  
Yan Wang ◽  
Shu Liao ◽  
Qian Wang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Image Reconstruction ◽  
Medical Imaging ◽  
Imaging Data ◽  
Resonance Imaging ◽  
Volumetric Imaging ◽  
Positron Emission ◽  
Potential Applications ◽  
Magnetic Resonance Imaging Mri

Artificial intelligence (AI) as an emerging technology is gaining momentum in medical imaging. Recently, deep learning-based AI techniques have been actively investigated in medical imaging, and its potential applications range from data acquisition and image reconstruction to image analysis and understanding. In this review, we focus on the use of deep learning in image reconstruction for advanced medical imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET). Particularly, recent deep learning-based methods for image reconstruction will be emphasized, in accordance with their methodology designs and performances in handling volumetric imaging data. It is expected that this review can help relevant researchers understand how to adapt AI for medical imaging and which advantages can be achieved with the assistance of AI.

scholarly journals System for Automatic Assessment of Alzheimer’s Disease Diagnosis Based on Deep Learning Techniques

Proceedings ◽  
2019 ◽  
Vol 21 (1) ◽  
pp. 28
Author(s):  
Alejandro Puente-Castro ◽  
Cristian Robert Munteanu ◽  
Enrique Fernandez-Blanco
Keyword(s):  
Magnetic Resonance Imaging ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Deep Learning ◽  
Reference Data ◽  
Disease Diagnosis ◽  
Resonance Imaging ◽  
Automatic Assessment ◽  
Learning Techniques ◽  
Magnetic Resonance Imaging Mri

Automatic detection of Alzheimer’s disease is a very active area of research. This is due to its usefulness in starting the protocol to stop the inevitable progression of this neurodegenerative disease. This paper proposes a system for the detection of the disease by means of Deep Learning techniques in magnetic resonance imaging (MRI). As a solution, a model of neuronal networks (ANN) and two sets of reference data for training are proposed. Finally, the goodness of this system is verified within the domain of the application.

scholarly journals Optimizing Neuro-Oncology Imaging: A Review of Deep Learning Approaches for Glioma Imaging

Cancers ◽  
2019 ◽  
Vol 11 (6) ◽  
pp. 829 ◽  
Author(s):  
Madeleine Shaver ◽  
Paul Kohanteb ◽  
Catherine Chiou ◽  
Michelle Bardis ◽  
Chanon Chantaduly ◽  
...  
Keyword(s):  
Deep Learning ◽  
Outcome Prediction ◽  
Cellular Proliferation ◽  
Genetic Characterization ◽  
Tumor Segmentation ◽  
Learning Approaches ◽  
Resonance Imaging ◽  
Cellular Invasion ◽  
Magnetic Resonance Imaging Mri

Radiographic assessment with magnetic resonance imaging (MRI) is widely used to characterize gliomas, which represent 80% of all primary malignant brain tumors. Unfortunately, glioma biology is marked by heterogeneous angiogenesis, cellular proliferation, cellular invasion, and apoptosis. This translates into varying degrees of enhancement, edema, and necrosis, making reliable imaging assessment challenging. Deep learning, a subset of machine learning artificial intelligence, has gained traction as a method, which has seen effective employment in solving image-based problems, including those in medical imaging. This review seeks to summarize current deep learning applications used in the field of glioma detection and outcome prediction and will focus on (1) pre- and post-operative tumor segmentation, (2) genetic characterization of tissue, and (3) prognostication. We demonstrate that deep learning methods of segmenting, characterizing, grading, and predicting survival in gliomas are promising opportunities that may enhance both research and clinical activities.

scholarly journals Radiomics for Gleason Score Detection through Deep Learning

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5411
Author(s):  
Luca Brunese ◽  
Francesco Mercaldo ◽  
Alfonso Reginelli ◽  
Antonella Santone
Keyword(s):  
Magnetic Resonance Imaging ◽  
Prostate Cancer ◽  
Deep Learning ◽  
Gleason Score ◽  
Gray Level ◽  
Resonance Imaging ◽  
First Order ◽  
Deep Architecture ◽  
Magnetic Resonance Imaging Mri ◽  
Occurrence Matrix

Prostate cancer is classified into different stages, each stage is related to a different Gleason score. The labeling of a diagnosed prostate cancer is a task usually performed by radiologists. In this paper we propose a deep architecture, based on several convolutional layers, aimed to automatically assign the Gleason score to Magnetic Resonance Imaging (MRI) under analysis. We exploit a set of 71 radiomic features belonging to five categories: First Order, Shape, Gray Level Co-occurrence Matrix, Gray Level Run Length Matrix and Gray Level Size Zone Matrix. The radiomic features are gathered directly from segmented MRIs using two free-available dataset for research purpose obtained from different institutions. The results, obtained in terms of accuracy, are promising: they are ranging between 0.96 and 0.98 for Gleason score prediction.

scholarly journals Brain Tumor Classification using Deep Learning Algorithms

2021 ◽  
Vol 9 (12) ◽  
pp. 417-426
Author(s):  
Ankita Kadam
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Neural Networks ◽  
Deep Learning ◽  
Brain Tumor ◽  
Magnetic Resonance ◽  
Brain Tumors ◽  
Tumor Classification ◽  
Resonance Imaging ◽  
Magnetic Resonance Imaging Mri

Abstract: A Brain tumor is one aggressive disease. An estimated more than 84,000 people will receive a primary brain tumor diagnosis in 2021 and an estimated 18,600 people will die from a malignant brain tumor (brain cancer) in 2021.[8] The best technique to detect brain tumors is by using Magnetic Resonance Imaging (MRI). More than any other cancer, brain tumors can have lasting and life-altering physical, cognitive, and psychological impacts on a patient’s life and hence faster diagnosis and best treatment plan should be devised to improve the life expectancy and well-being of these patients. Neural networks have shown colossal accuracy in image classification and segmentation problems. In this paper, we propose comparative studies of various deep learning models based on different types of Neural Networks(ANN, CNN, TL) to firstly identify brain tumors and then classify them into Benign Tumor, Malignant Tumor or Pituitary Tumor. The data set used holds 3190 images on T1-weighted contrast-enhanced images which were cleaned and augmented. The best ANN model concluded with an accuracy of 78% and the best CNN model consisting of 3 convolution layers had an accuracy of 90%. The VGG16(retrained on the dataset) model surpasses other ANN, CNN, TL models for multi-class tumor classification. This proposed network achieves significantly better performance with a validation accuracy of 94% and an F1-Score of 91. Keywords: Artificial Neural Network(ANN), Convolution Neural Network (CNN), Transfer Learning(TL), Magnetic Resonance Imaging(MRI.)

scholarly journals Development of brain tumor segmentation of magnetic resonance imaging (MRI) using U-Net deep learning

2021 ◽  
Vol 4 (9(112)) ◽  
pp. 23-31
Author(s):  
Wasan M. Jwaid ◽  
Zainab Shaker Matar Al-Husseini ◽  
Ahmad H. Sabry
Keyword(s):  
Magnetic Resonance Imaging ◽  
Deep Learning ◽  
Brain Tumor ◽  
Magnetic Resonance ◽  
Tumor Segmentation ◽  
Resonance Imaging ◽  
Brain Tumor Segmentation ◽  
Brain Images ◽  
Magnetic Resonance Imaging Mri ◽  
The Brain

Brain tumors are the growth of abnormal cells or a mass in a brain. Numerous kinds of brain tumors were discovered, which need accurate and early detection techniques. Currently, most diagnosis and detection methods rely on the decision of neuro-specialists and radiologists to evaluate brain images, which may be time-consuming and cause human errors. This paper proposes a robust U-Net deep learning Convolutional Neural Network (CNN) model that can classify if the subject has a tumor or not based on Brain Magnetic resonance imaging (MRI) with acceptable accuracy for medical-grade application. The study built and trained the 3D U-Net CNN including encoding/decoding relationship architecture to perform the brain tumor segmentation because it requires fewer training images and provides more precise segmentation. The algorithm consists of three parts; the first part, the downsampling part, the bottleneck part, and the optimum part. The resultant semantic maps are inserted into the decoder fraction to obtain the full-resolution probability maps. The developed U-Net architecture has been applied on the MRI scan brain tumor segmentation dataset in MICCAI BraTS 2017. The results using Matlab-based toolbox indicate that the proposed architecture has been successfully evaluated and experienced for MRI datasets of brain tumor segmentation including 336 images as training data and 125 images for validation. This work demonstrated comparative performance and successful feasibility of implementing U-Net CNN architecture in an automated framework of brain tumor segmentations in Fluid-attenuated inversion recovery (FLAIR) MR Slices. The developed U-Net CNN model succeeded in performing the brain tumor segmentation task to classify the input brain images into a tumor or not based on the MRI dataset.

Sign in / Sign up

Export Citation Format

Share Document