scholarly journals A Fully Automated Deep Learning-based Network For Detecting COVID-19 from a New And Large Lung CT Scan Dataset

2020 ◽  
Author(s):  
Mohammad Rahimzadeh ◽  
Abolfazl Attar ◽  
Seyed Mohammad Sakhaei
Keyword(s):  
Ct Scan ◽  
High Speed ◽  
Early Stage ◽  
Proper Time ◽  
Ct Images ◽  
Automated System ◽  
Image Processing Algorithm ◽  
Convolutional Network ◽  
Automated Method ◽  
Feature Pyramid

COVID-19 is a severe global problem, and one of the primary ways to decrease its casualties is the infected person's identification at the proper time. AI can play a significant role in these cases by monitoring and detecting infected persons in early-stage. In this paper, we aim to propose a high- speed and accurate fully-automated method to detect COVID-19 from the patient's CT scan. We introduce a new dataset that contains 48260 CT scan images from 282 normal persons and 15589 images from 95 patients with COVID-19 infection. Our proposed automated system takes all the CT scan image sequences of a patient as the input and determines if the patient is infected with COVID-19. At the first stage, this system runs the proposed image processing algorithm to discard those CT images that inside the lung is not properly visible in them. This helps to reduce the number of images that shall be processed, so it reduces the processing time. Also, running this algorithm makes the deep network at the next stage to analyze only the proper images and thus reduces false detections. At the next stage, we propose a new modified deep convolutional network that is based on ResNet50V2 and is enhanced by the feature pyramid network for classifying the selected CT images into COVID-19 or normal. After running these two phases, if enough number of chosen CT scan images of a patient be identified as COVID-19, the system considers that patient, infected to this disease. In the single image classification stage, the ResNet50V2 with feature pyramid network achieved 98.49% accuracy on more than 7996 validation images. At the fully automated phase, the automated system correctly identified almost 237 patients from 245 patients on average between five-folds with high speed. In the end, we also investigate the classified images with a feature visualization algorithm to indicate the area of infections in each image. We are implementing these materials on some medical centers in Iran, and we hope that it would be a great help in Intelligence disease detection anywhere.

scholarly journals A Fully Automated Deep Learning-based Network For Detecting COVID-19 from a New And Large Lung CT Scan Dataset

2020 ◽  
Author(s):  
Mohammad Rahimzadeh ◽  
Abolfazl Attar ◽  
Mohammad Sakhaei
Keyword(s):  
Ct Scan ◽  
Early Stage ◽  
Proper Time ◽  
Ct Images ◽  
Image Sequences ◽  
Image Processing Algorithm ◽  
Automated Method ◽  
The World ◽  
Feature Pyramid ◽  
Lung Ct

COVID-19 is a severe global problem that has crippled many industries and killed many people around the world. One of the primary ways to decrease the casualties is the infected person's identification at the proper time. AI can play a significant role in these cases by monitoring and detecting infected persons in early-stage so that it can help many organizations. In this paper, we aim to propose a fully-automated method to detect COVID-19 from the patient's CT scan without needing a clinical technician. We introduce a new dataset that contains 48260 CT scan images from 282 normal persons and 15589 images from 95 patients with COVID-19 infection. Our proposed network takes all the CT scan image sequences of a patient as the input and determines if the patient is infected with COVID-19. At the first stage, this network runs an image processing algorithm to discard those CT images that inside the lung is not properly visible in them. This helps to reduce the number of images that shall be identified as normal or COVID-19, so it reduces the processing time. Also, running this algorithm makes the deep network at the next stage to analyze only the proper images and thus reduces false detections. At the next stage, we propose a modified version of ResNet50V2 that is enhanced by a feature pyramid network for classifying the selected CT images into COVID-19 or normal. If enough number of chosen CT scan images of a patient be identified as COVID-19, the network considers that patient, infected to this disease. The ResNet50V2 with feature pyramid network achieved 98.49% accuracy on more than 7996 validation images and correctly identified almost 237 patients from 245 patients.

scholarly journals A Fully Automated Deep Learning-based Network For Detecting COVID-19 from a New And Large Lung CT Scan Dataset

2020 ◽  
Author(s):  
Mohammad Rahimzadeh ◽  
Abolfazl Attar ◽  
Seyed Mohammad Sakhaei
Keyword(s):  
Ct Scan ◽  
Early Stage ◽  
Proper Time ◽  
Ct Images ◽  
Image Sequences ◽  
Image Processing Algorithm ◽  
Automated Method ◽  
The World ◽  
Feature Pyramid ◽  
Lung Ct

AbstractCOVID-19 is a severe global problem that has crippled many industries and killed many people around the world. One of the primary ways to decrease the casualties is the infected person’s identification at the proper time. AI can play a significant role in these cases by monitoring and detecting infected persons in early-stage so that it can help many organizations. In this paper, we aim to propose a fully-automated method to detect COVID-19 from the patient’s CT scan without needing a clinical technician. We introduce a new dataset that contains 48260 CT scan images from 282 normal persons and 15589 images from 95 patients with COVID-19 infection. Our proposed network takes all the CT scan image sequences of a patient as the input and determines if the patient is infected with COVID-19. At the first stage, this network runs an image processing algorithm to discard those CT images that inside the lung is not properly visible in them. This helps to reduce the number of images that shall be identified as normal or COVID-19, so it reduces the processing time. Also, running this algorithm makes the deep network at the next stage to analyze only the proper images and thus reduces false detections. At the next stage, we propose a modified version of ResNet50V2 that is enhanced by a feature pyramid network for classifying the selected CT images into COVID-19 or normal. If enough number of chosen CT scan images of a patient be identified as COVID-19, the network considers that patient, infected to this disease. The ResNet50V2 with feature pyramid network achieved 98.49% accuracy on more than 7996 validation images and correctly identified almost 237 patients from 245 patients.

scholarly journals A Fully Automated Deep Learning-based Network For Detecting COVID-19 from a New And Large Lung CT Scan Dataset

2020 ◽  
Author(s):  
Mohammad Rahimzadeh ◽  
Abolfazl Attar ◽  
Seyed Mohammad Sakhaei
Keyword(s):  
Ct Scan ◽  
High Speed ◽  
Early Stage ◽  
Ct Images ◽  
Patient Identification ◽  
Image Processing Algorithm ◽  
Convolutional Networks ◽  
Model Classification ◽  
Automated Method ◽  
Two Phases

COVID-19 is a severe global problem, and AI can play a significant role in preventing losses by monitoring and detecting infected persons in early-stage. This paper aims to propose a high-speed and accurate fully-automated method to detect COVID-19 from the patient's CT scan images. We introduce a new dataset that contains 48260 CT scan images from 282 normal persons and 15589 images from 95 patients with COVID-19 infections. At the first stage, this system runs our proposed image processing algorithm to discard those CT images that inside the lung is not properly visible in them. This action helps to reduce the processing time and false detections. At the next stage, we introduce a novel method for increasing the classification accuracy of convolutional networks. We implemented our method using the ResNet50V2 network and a modified feature pyramid network alongside our designed architecture for classifying the selected CT images into COVID-19 or normal with higher accuracy than other models. After running these two phases, the system determines the condition of the patient using a selected threshold. We are the first to evaluate our system in two different ways. In the single image classification stage, our model achieved 98.49% accuracy on more than 7996 test images. At the patient identification phase, the system correctly identified almost 234 of 245 patients with high speed. We also investigate the classified images with the Grad-CAM algorithm to indicate the area of infections in images and evaluate our model classification correctness.

scholarly journals Region Detection and Segmentation of Brain Hemorrhage using Algorithmic Approach of Image Processing

2022 ◽  
Vol 2161 (1) ◽  
pp. 012070
Author(s):  
Krithika M Pai
Keyword(s):  
Ct Scan ◽  
Early Stage ◽  
The Body ◽  
Automated System ◽  
Brain Hemorrhage ◽  
Cross Sectional ◽  
Region Detection ◽  
Computer Tomography Scan ◽  
And Function ◽  
The Brain

Abstract Brain is one of the most important part of the body. Brain Hemorrhage is a severe head injury that deteriorates the performance and function of an individual. Brain Hemorrhage can be detected through CT (Computer Tomography) scan of the brain. CT scan uses narrow X-ray beam which rotates around the part of the body and provides a set of images from different angles and the computer creates a cross-sectional view. It is challenging to detect and segment the region of the brain having Hemorrhage. Hence an automated system would be handy at those times. In the proposed work an attempt has been made to segment and identify the hemorrhaged region of the brain in the CT scan slices of the image. Brain hemorrhage segmentation helps to identify the region of brain hemorrhage which in turn helps to treat the patients at an early stage. The region of brain hemorrhage is appropriately identified from the proposed algorithm.

scholarly journals Improved Imaging and Image Analysis System for Application to Measurement of Small Ice Crystals

2012 ◽  
Vol 29 (12) ◽  
pp. 1811-1824 ◽  
Author(s):  
T. Kuhn ◽  
I. Grishin ◽  
J. J. Sloan
Keyword(s):  
High Resolution ◽  
High Speed ◽  
Early Stage ◽  
Resolving Power ◽  
Image Analysis System ◽  
Experimental Conditions ◽  
Pixel Resolution ◽  
Size And Shape ◽  
Automated Method ◽  
Ice Particles

Abstract Accurate knowledge of ice particle size and shape distribution is required for understanding of atmospheric microphysical processes. While larger ice particles are easily measured with a variety of sensors, the measurement of small ice particles with sizes down to a few micrometers remains challenging. Here the authors report the development of a system that measures the size and shape of small ice particles using a novel combination of high-resolution imaging and high-speed automated image classification. The optical system has a pixel resolution of 0.2 μm and a resolving power of approximately 1 μm. This imaging instrument is integrated into a cryogenic flow tube that allows precise control of experimental conditions. This study also describes an automated method for the high-speed analysis of high-resolution particle images. Each particle is located in the image using a Sobel edge detector, the border is vectorized, and a polygon representing the border is found. The vertices of this polygon are expressed in complex coordinates, and an analytic implementation of Fourier shape descriptors is used for piecewise integration along the edges of the polygon. The authors demonstrate the capabilities of this system in a study of the early-stage growth of ice particles, which are grown for approximately 1 min at fixed temperature and saturated water vapor concentrations in the cryogenic flowtube. Ice particle shapes and size distributions are reported and compared with habit diagrams found in the literature. The capability of the shape recognition system is verified by comparison with manual classification.

APPLICATION OF THE EARLY DAMAGE DIAGNOSTICS TECHNIQUE TO EXAMINATION OF THE AVIATION PANEL

2019 ◽  
Vol 85 (6) ◽  
pp. 53-63 ◽  
Author(s):  
I. E. Vasil’ev ◽  
Yu. G. Matvienko ◽  
A. V. Pankov ◽  
A. G. Kalinin
Keyword(s):  
Acoustic Emission ◽  
Damage Detection ◽  
High Speed ◽  
Early Stage ◽  
Video Data ◽  
High Speed Video ◽  
Damage Diagnostics ◽  
Subsurface Defect ◽  
Sensitive Coating ◽  
Early Damage

The results of using early damage diagnostics technique (developed in the Mechanical Engineering Research Institute of the Russian Academy of Sciences (IMASH RAN) for detecting the latent damage of an aviation panel made of composite material upon bench tensile tests are presented. We have assessed the capabilities of the developed technique and software regarding damage detection at the early stage of panel loading in conditions of elastic strain of the material using brittle strain-sensitive coating and simultaneous crack detection in the coating with a high-speed video camera “Video-print” and acoustic emission system “A-Line 32D.” When revealing a subsurface defect (a notch of the middle stringer) of the aviation panel, the general concept of damage detection at the early stage of loading in conditions of elastic behavior of the material was also tested in the course of the experiment, as well as the software specially developed for cluster analysis and classification of detected location pulses along with the equipment and software for simultaneous recording of video data flows and arrays of acoustic emission (AE) data. Synchronous recording of video images and AE pulses ensured precise control of the cracking process in the brittle strain-sensitive coating (tensocoating)at all stages of the experiment, whereas the use of structural-phenomenological approach kept track of the main trends in damage accumulation at different structural levels and identify the sources of their origin when classifying recorded AE data arrays. The combined use of oxide tensocoatings and high-speed video recording synchronized with the AE control system, provide the possibility of definite determination of the subsurface defect, reveal the maximum principal strains in the area of crack formation, quantify them and identify the main sources of AE signals upon monitoring the state of the aviation panel under loading P = 90 kN, which is about 12% of the critical load.

Connection of discontinuous segments in early functional recovery from thoracic ossification of the posterior longitudinal ligament treated with posterior instrumented surgery

2020 ◽  
Vol 32 (2) ◽  
pp. 200-206
Author(s):  
Kei Ando ◽  
Kazuyoshi Kobayashi ◽  
Masaaki Machino ◽  
Kyotaro Ota ◽  
Satoshi Tanaka ◽  
...  
Keyword(s):  
Early Stage ◽  
Morphological Changes ◽  
Japanese Orthopaedic Association ◽  
Multislice Ct ◽  
Posterior Longitudinal Ligament ◽  
Ct Images ◽  
Rigid Fixation ◽  
Disc Space ◽  
Fusion Surgery ◽  
Estimated Blood Loss

OBJECTIVEThe objective of this study was to investigate the relationship between morphological changes in thoracic ossification of the posterior longitudinal ligament (T-OPLL) and postoperative neurological recovery after thoracic posterior fusion surgery. Changes of OPLL morphology and postoperative recovery in cases with T-OPLL have not been examined.METHODSIn this prospective study, the authors evaluated data from 44 patients (23 male and 21 female) who underwent posterior decompression and fusion surgery with instrumentation for the treatment of T-OPLL at our hospital. The patients’ mean age at surgery was 50.7 years (range 38–68 years). The minimum duration of follow-up was 2 years. The location of thoracic ossification of the ligamentum flavum (T-OLF), T-OLF at the OPLL level, OPLL morphology, fusion range, estimated blood loss, operative time, pre- and postoperative Japanese Orthopaedic Association (JOA) scores, and JOA recovery rate were investigated. Reconstructed sagittal multislice CT images were obtained before and at 3 and 6 months and 1 and 2 years after surgery. The basic fusion area was 3 vertebrae above and below the OPLL lesion. All parameters were compared between patients with and without continuity across the disc space at the OPLL at 3 and 6 months after surgery.RESULTSThe preoperative morphology of OPLL was discontinuous across the disc space between the rostral and caudal ossification regions on sagittal CT images in all but one of the patients. Postoperatively, these segments became continuous in 42 patients (97.7%; occurring by 6.6 months on average) without progression of OPLL thickness. Patients with continuity at 3 months had significantly lower rates of diabetes mellitus (p < 0.05) and motor palsy in the lower extremities (p < 0.01). The group with continuity also had significantly higher mean postoperative JOA scores at 3 (p < 0.01) and 6 (p < 0.05) months and mean JOA recovery rates at 3 and 6 months (both p < 0.01) after surgery.CONCLUSIONSPreoperatively, discontinuity of rostral and caudal ossified lesions was found on CT in all patients but one of this group of 44 patients who needed surgery for T-OPLL. Rigid fixation with instrumentation may have allowed these segments to connect at the OPLL. Such OPLL continuity at an early stage after surgery may accelerate spinal cord recovery.

Automation and validation of a MALDI-TOF MS (Mass-Fix) replacement of immunofixation electrophoresis in the clinical lab

2021 ◽  
Vol 59 (1) ◽  
pp. 155-163
Author(s):  
Mindy Kohlhagen ◽  
Surendra Dasari ◽  
Maria Willrich ◽  
MeLea Hetrick ◽  
Brian Netzel ◽  
...  
Keyword(s):  
Limit Of Detection ◽  
Turnaround Time ◽  
Automated System ◽  
Serum Samples ◽  
Maldi Tof Ms ◽  
Maldi Tof ◽  
Automated Method ◽  
Positive Specimen ◽  
Specimen Identification ◽  
Tof Ms

AbstractObjectivesA matrix assisted laser desorption ionization time of flight mass spectrometry (MALDI-TOF MS) method (Mass-Fix) as a replacement for gel-based immunofixation (IFE) has been recently described. To utilize Mass-Fix clinically, a validated automated method was required. Our aim was to automate the pre-analytical processing, improve positive specimen identification and ergonomics, reduce paper data storage and increase resource utilization without increasing turnaround time.MethodsSerum samples were batched and loaded onto a liquid handler along with reagents and a barcoded sample plate. The pre-analytical steps included: (1) Plating immunopurification beads. (2) Adding 10 μl of serum. (3) Bead washing. (4) Eluting the immunoglobulins (Igs), and reducing to separate the heavy and light Ig chains. The resulting plate was transferred to a second low-volume liquid handler for MALDI plate spotting. MALDI-TOF mass spectra were collected. Integrated in-house developed software was utilized for sample tracking, driving data acquisition, data analysis, history tracking, and result reporting. A total of 1,029 residual serum samples were run using the automated system and results were compared to prior electrophoretic results.ResultsThe automated Mass-Fix method was capable of meeting the validation requirements of concordance with IFE, limit of detection (LOD), sample stability and reproducibility with a low repeat rate. Automation and integrated software allowed a single user to process 320 samples in an 8 h shift. Software display facilitated identification of monoclonal proteins. Additionally, the process maintains positive specimen identification, reduces manual pipetting, allows for paper free tracking, and does not significantly impact turnaround time (TAT).ConclusionsMass-Fix is ready for implementation in a high-throughput clinical laboratory.

scholarly journals The impact of tumour regression in locally advanced carcinoma cervix during external beam radiotherapy and the need for adaptive planning

2016 ◽  
Keyword(s):  
Ct Scan ◽  
Locally Advanced ◽  
Target Volume ◽  
Ct Images ◽  
Tumour Regression ◽  
Target Coverage ◽  
Carcinoma Cervix ◽  
Advanced Carcinoma ◽  
The Impact ◽  
Planning Ct

Aim: To study the impact of tumour regression occurring during IMRT for locally advanced carcinoma cervix and study dose distribution to target volume and OARs and hence the need for any replanning. Materials and Methods: 40 patients undergoing IM-IGRT and weekly chemotherapy were included in the study. After 36 Gy, a second planning CT-scan was done and target volume and OARs were recontoured. First plan (non-adaptive) was compared with second plan (adaptive plan) to evaluate whether it would still offer sufficient target coverage to the CTV and spare the OARs after having delivered 36 Gy. Finally new plan was created based on CT-images to investigate whether creating a new treatment plan would optimize target coverage and critical organ sparing. To measure the response of the primary tumour and pathologic nodes to EBRT, the differences in the volumes of the primary GTV and nodal GTV between the pretreatment and intratreatment CT images was calculated. Second intratreatment IMRT plans was generated, using the delineations of the intratreatment CT images. The first IMRT plan (based on the first CT-scan or non adaptive plan) was compared with second IMRT plan (based on the second CT-scan or adaptive plan). Results: 35% patients had regression in GTV in the range of 4.1% to 5%, 20% in the range of 1.1%-2%, 15% in the range of 2.1%-3% and 20% in the range of 6%-15%. There was significant mean decrease in GTV of 4.63 cc (p=0.000). There was a significant decrease in CTV on repeat CT done after 36 Gy by 23.31 cc (p=0.000) and in PTV by 23.31 cc (p=0.000). There was a statistically significant increase in CTV D98, CTV D95, CTV D50 and CTV D2 in repeat planning CT done after 36 Gy. There was no significant alteration in OARs doses. Conclusion: Despite tumour regression and increased target coverage in locally advanced carcinoma cervix after a delivery of 36 Gy there was no sparing of OARs. Primary advantage of adaptive RT seems to be in greater target coverage with non-significant normal tissue sparing.

Sign in / Sign up

Export Citation Format

Share Document