scholarly journals Automated Detection of Pancreatic Cystic Lesions on CT Using Deep Learning

Diagnostics ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. 901
Author(s):  
Lorraine Abel ◽  
Jakob Wasserthal ◽  
Thomas Weikert ◽  
Alexander W. Sauter ◽  
Ivan Nesic ◽  
...  
Keyword(s):  
Incidental Finding ◽  
Automated Detection ◽  
Ct Scans ◽  
Cystic Lesions ◽  
Imaging Data ◽  
Radiology Resident ◽  
Abdominal Radiology ◽  
Proposed Model ◽  
Distal Pancreas ◽  
Mean Sensitivity

Pancreatic cystic lesions (PCL) are a frequent and underreported incidental finding on CT scans and can transform into neoplasms with devastating consequences. We developed and evaluated an algorithm based on a two-step nnU-Net architecture for automated detection of PCL on CTs. A total of 543 cysts on 221 abdominal CTs were manually segmented in 3D by a radiology resident in consensus with a board-certified radiologist specialized in abdominal radiology. This information was used to train a two-step nnU-Net for detection with the performance assessed depending on lesions’ volume and location in comparison to three human readers of varying experience. Mean sensitivity was 78.8 ± 0.1%. The sensitivity was highest for large lesions with 87.8% for cysts ≥220 mm3 and for lesions in the distal pancreas with up to 96.2%. The number of false-positive detections for cysts ≥220 mm3 was 0.1 per case. The algorithm’s performance was comparable to human readers. To conclude, automated detection of PCL on CTs is feasible. The proposed model could serve radiologists as a second reading tool. All imaging data and code used in this study are freely available online.

Multiple Congenital Ocular Anomalies in a silver coat Missouri Fox Trotter stallion

2021 ◽  
Vol 49 (05) ◽  
pp. 350-354
Author(s):  
Verena Maria Herb ◽  
Verena Zehetner ◽  
Klaas-Ole Blohm
Keyword(s):  
Missense Mutation ◽  
Coat Color ◽  
Incidental Finding ◽  
Unknown Origin ◽  
Allelic Frequency ◽  
Cystic Lesions ◽  
Wild Type Allele ◽  
Wild Type ◽  
Type Allele ◽  
Phenotype Characterization

AbstractThis is the first description of Multiple Congenital Ocular Anomalies (MCOA) in a silver coat Missouri Fox Trotter determined to be heterozygous for the Silver PMEL17 missense mutation associated with MCOA and a silver coat in other breeds. The stallion was treated for meningoencephalitis and bilateral uveitis of unknown origin. A complete ophthalmic examination and ocular ultrasonography were performed. As an incidental finding, the patient exhibited bilateral cystic lesions restricted to the temporal anterior uvea consistent with the Cyst phenotype and was genotyped heterozygous for the Silver mutation. Additionally, 4 other non-silver colored Missouri Fox Trotters were genotyped homozygous for the wild-type allele. Screening for PMEL17 mutation in Missouri Fox Trotters accompanied by ophthalmic phenotype characterization is recommended to determine the allelic frequency and facilitate informed breeding decisions since the silver coat color is particularly popular.

scholarly journals Truncated Inception Net: COVID-19 Outbreak Screening using Chest X-rays

2020 ◽  
Author(s):  
Dipayan Das ◽  
KC Santosh ◽  
Umapada Pal
Keyword(s):  
Neural Network ◽  
World Wide ◽  
Imaging Techniques ◽  
Imaging Systems ◽  
Ct Scans ◽  
X Rays ◽  
X Ray ◽  
X Ray Imaging ◽  
Proposed Model ◽  
Different Types

Abstract Since December 2019, the Coronavirus Disease (COVID-19) pandemic has caused world-wide turmoil in less than a couple of months, and the infection, caused by SARS-CoV-2, is spreading at an unprecedented rate. AI-driven tools are used to identify Coronavirus outbreaks as well as forecast their nature of spread, where imaging techniques are widely used, such as CT scans and chest X-rays (CXRs). In this paper, motivated by the fact that X-ray imaging systems are more prevalent and cheaper than CT scan systems, a deep learning-based Convolutional Neural Network (CNN) model, which we call Truncated Inception Net, is proposed to screen COVID-19 positive CXRs from other non-COVID and/or healthy cases. To validate our proposal, six different types of datasets were employed by taking the following CXRs: COVID-19 positive, Pneumonia positive, Tuberculosis positive, and healthy cases into account. The proposed model achieved an accuracy of 99.96% (AUC of 1.0) in classifying COVID- 19 positive cases from combined Pneumonia and healthy cases. Similarly, it achieved an accuracy of 99.92% (AUC of 0.99) in classifying COVID-19 positive cases from combined Pneumonia, Tuberculosis and healthy CXRs. To the best of our knowledge, as of now, the achieved results outperform the existing AI-driven tools for screening COVID-19 using CXRs.

scholarly journals Deep Learning Assisted Covid-19 Detection using full CT-scans

2020 ◽  
Author(s):  
varan singhrohila ◽  
Nitin Gupta ◽  
Amit Kaul ◽  
Deepak Sharma
Keyword(s):  
Deep Learning ◽  
Ct Scans ◽  
Detection Accuracy ◽  
Residual Network ◽  
Excellent Performance ◽  
Examination Procedure ◽  
Medical Institutions ◽  
Proposed Model ◽  
Learning Technique ◽  
Intensive Approach

<div>The ongoing pandemic of COVID-19 has shown</div><div>the limitations of our current medical institutions. There</div><div>is a need for research in the field of automated diagnosis</div><div>for speeding up the process while maintaining accuracy</div><div>and reducing computational requirements. In this work, an</div><div>automatic diagnosis of COVID-19 infection from CT scans</div><div>of the patients using Deep Learning technique is proposed.</div><div>The proposed model, ReCOV-101 uses full chest CT scans to</div><div>detect varying degrees of COVID-19 infection, and requires</div><div>less computational power. Moreover, in order to improve</div><div>the detection accuracy the CT-scans were preprocessed by</div><div>employing segmentation and interpolation. The proposed</div><div>scheme is based on the residual network, taking advantage</div><div>of skip connection, allowing the model to go deeper.</div><div>Moreover, the model was trained on a single enterpriselevel</div><div>GPU such that it can easily be provided on the edge of</div><div>the network, reducing communication with the cloud often</div><div>required for processing the data. The objective of this work</div><div>is to demonstrate a less hardware-intensive approach for COVID-19 detection with excellent performance that can</div><div>be combined with medical equipment and help ease the</div><div>examination procedure. Moreover, with the proposed model</div><div>an accuracy of 94.9% was achieved.</div>

scholarly journals Multiple cystic lesions in the abdominopelvic cavity one and a half years after resection of presacral neurogenic tumor: tumor recurrence or other?

2020 ◽  
Vol 7 (12) ◽  
pp. 4180
Author(s):  
Umar Zeb Khan ◽  
Matiullah Masroor ◽  
Hai Liu
Keyword(s):  
Spontaneous Rupture ◽  
Tumor Recurrence ◽  
Tumor Resection ◽  
Abdominal Distension ◽  
Neurogenic Tumor ◽  
Ct Scans ◽  
Cystic Degeneration ◽  
Cystic Lesions ◽  
Local Hospital ◽  
Neurogenic Tumors

Cystic lesions of abdominopelvic cavity include a variety of pathologies and diagnosis can sometimes be challenging. Urinoma can be caused by iatrogenic injury, spontaneous rupture of ureters or by various causes of ureteral obstruction. It needs to be differentiated from abdominopelvic cystic diseases including tumors that can undergo cystic degeneration. Here we report a case of a 41 years old female underwent a presacral neurogenic tumor resection at a local hospital 5 years ago. The tumor recurred three and a half years after the first surgery and removed at another hospital. She experienced abdominal distension and difficulty in urination from the last 2 months and was diagnosed as having a recurrence of tumor once again at both hospitals on separate CT scans. They believed that the tumor was too large and encroaching on adjacent organs to be surgically resected, she was finally diagnosed as infected urinoma during surgery in our hospital. Even though spontaneous rupture of ureters and urinoma formation is a rare disease but it should be considered as a main differential diagnosis of recurrence of neurogenic tumors especially in post abdominopelvic surgeries patient.

Automated Detection of Small Pulmonary Nodules in Whole Lung CT Scans

2007 ◽  
Vol 14 (5) ◽  
pp. 579-593 ◽  
Author(s):  
Andinet A. Enquobahrie ◽  
Anthony P. Reeves ◽  
David F. Yankelevitz ◽  
Claudia I. Henschke
Keyword(s):  
Pulmonary Nodules ◽  
Automated Detection ◽  
Ct Scans ◽  
Small Pulmonary Nodules ◽  
Lung Ct

How much is the effective dose from medical imaging in pediatric patients in the neurosurgery department?

2021 ◽  
Author(s):  
B. Zeinali-Rafsanjani ◽  
S. Haseli ◽  
R. Jalli ◽  
M. Saeedi-Moghadam
Keyword(s):  
Medical Imaging ◽  
Ionizing Radiation ◽  
Ct Scan ◽  
Effective Dose ◽  
Pediatric Patients ◽  
Ct Scans ◽  
Imaging Data ◽  
Plain Radiographs ◽  
Brain Ct ◽  
Abdomen Ct

Medical imaging with ionizing radiation in pediatric patients is rising, and their radiation sensitivity is 2–3 times more than adults. The objective of this study was to estimate the total effective dose (ED) of all medical imaging by CT scan and plain radiography in patients in pediatric neurosurgery department. Patients with at least one brain CT scan and recorded dose length product (DLP) were included. Patients’ imaging data were collected from the picture-archiving-and-communicating system (PACS) using their national code to find all their medical imaging. Total ED (mSv) from CT scans and plain radiographs were calculated. A total of 300 patients were included, of which 129 were females and 171 males with a mean age of 5.45 ± 4.34 years. Mean DLPs of brain, abdomen, and chest CT were 329.16, 393.06, 284.46 mGy.cm. The most frequent CT scans in these children were brain CT scans with ED range of 0.09 to 47.09 mSv. Total ED due to all CT scans and plain radiographs were in the range of 0.38 to 63.41 mSv. Although the mean DLP of each brain, chest, and abdomen CT of patients was in the range of DRLs reported by previous studies, the patients with numerous CT scans received more radiation doses than mean ED (6.21 mSv between all age groups). The most frequent CT scan was the brain, and the most frequent plain radiographs were chest and lower extremities. It can be concluded that reducing the number of CT scans or plain radiographs by appropriate physical exams or replacing them with modalities that do not use ionizing radiation can reduce ED.

scholarly journals A multi-label classification model for full slice brain computerised tomography image

2020 ◽  
Vol 21 (S6) ◽  
Author(s):  
Jianqiang Li ◽  
Guanghui Fu ◽  
Yueda Chen ◽  
Pengzhi Li ◽  
Bo Liu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Ct Images ◽  
Image Features ◽  
Classification Model ◽  
Brain Diseases ◽  
Ct Scans ◽  
Computerised Tomography ◽  
Brain Ct ◽  
Proposed Model ◽  
The Brain

Abstract Background Screening of the brain computerised tomography (CT) images is a primary method currently used for initial detection of patients with brain trauma or other conditions. In recent years, deep learning technique has shown remarkable advantages in the clinical practice. Researchers have attempted to use deep learning methods to detect brain diseases from CT images. Methods often used to detect diseases choose images with visible lesions from full-slice brain CT scans, which need to be labelled by doctors. This is an inaccurate method because doctors detect brain disease from a full sequence scan of CT images and one patient may have multiple concurrent conditions in practice. The method cannot take into account the dependencies between the slices and the causal relationships among various brain diseases. Moreover, labelling images slice by slice spends much time and expense. Detecting multiple diseases from full slice brain CT images is, therefore, an important research subject with practical implications. Results In this paper, we propose a model called the slice dependencies learning model (SDLM). It learns image features from a series of variable length brain CT images and slice dependencies between different slices in a set of images to predict abnormalities. The model is necessary to only label the disease reflected in the full-slice brain scan. We use the CQ500 dataset to evaluate our proposed model, which contains 1194 full sets of CT scans from a total of 491 subjects. Each set of data from one subject contains scans with one to eight different slice thicknesses and various diseases that are captured in a range of 30 to 396 slices in a set. The evaluation results present that the precision is 67.57%, the recall is 61.04%, the F1 score is 0.6412, and the areas under the receiver operating characteristic curves (AUCs) is 0.8934. Conclusion The proposed model is a new architecture that uses a full-slice brain CT scan for multi-label classification, unlike the traditional methods which only classify the brain images at the slice level. It has great potential for application to multi-label detection problems, especially with regard to the brain CT images.

Lymphoepithelial cyst of the pancreas. A case report

2007 ◽  
Vol 52 (3) ◽  
pp. 53-53
Author(s):  
L Fraser ◽  
OO Komolafe ◽  
JR Anderson
Keyword(s):  
Case Report ◽  
Cystic Lesion ◽  
Cystic Lesions ◽  
Lymphoepithelial Cyst ◽  
Invasive Procedures ◽  
Diagnostic Challenge ◽  
Distal Pancreas ◽  
Ct And Mri ◽  
Diagnostic Investigations ◽  
The Ideal

We present the case of a 63 year-old male who presented with a cystic lesion of the distal pancreas. Excision and histology showed this to be a lymphoepithelial cyst. Cystic lesions of the pancreas represent a diagnostic challenge, especially when pseudocyst secondary to pancreatitis is excluded. These lesions can be broadly classified into benign, pre-malignant and malignant. Widely used imaging modalities such as CT and MRI are not able to categorically differentiate between these. More invasive procedures such as endoscopic US and FNA again do not give a cast-iron diagnosis. Our patient had a symptomatic cystic lesion in his pancreas which was excised after cross-specialty discussion. We advocate that this is the ideal way to treat patients with cystic lesions of the pancreas, with each case considered on its own merits as all current diagnostic investigations have their limitations.

scholarly journals A model for the effective COVID-19 identification in uncertainty environment using primary symptoms and CT scans

2020 ◽  
Vol 26 (4) ◽  
pp. 3088-3105 ◽  
Author(s):  
Mohamed Abdel-Basst ◽  
Rehab Mohamed ◽  
Mohamed Elhoseny
Keyword(s):  
Ct Scans ◽  
Detection Accuracy ◽  
Ideal Solution ◽  
Accurate Evaluation ◽  
Proposed Model ◽  
Rapid Spread ◽  
The World ◽  
Uncertainty Environment ◽  
Internet Of Things Technology ◽  
Best Worst Method

The rapid spread of the COVID-19 virus around the world poses a real threat to public safety. Some COVID-19 symptoms are similar to other viral chest diseases, which makes it challenging to develop models for effective detection of COVID-19 infection. This article advocates a model to differentiate between COVID-19 and other four viral chest diseases under uncertainty environment using the viruses primary symptoms and CT scans. The proposed model is based on a plithogenic set, which provides higher accurate evaluation results in an uncertain environment. The proposed model employs the best-worst method (BWM) and the technique in order of preference by similarity to ideal solution (TOPSIS). Besides, this study discusses how smart Internet of Things technology can assist medical staff in monitoring the spread of COVID-19. Experimental evaluation of the proposed model was conducted on five different chest diseases. Evaluation results demonstrate that the proposed model effectiveness in detecting the COVID-19 in all five cases achieving detection accuracy of up to 98%.

scholarly journals Deep Learning for Detecting Building Defects Using Convolutional Neural Networks

Sensors ◽  
2019 ◽  
Vol 19 (16) ◽  
pp. 3556 ◽  
Author(s):  
Husein Perez ◽  
Joseph H. M. Tah ◽  
Amir Mosavi
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Effective Means ◽  
Scale Up ◽  
Real Life ◽  
Health And Safety ◽  
Condition Assessment ◽  
Automated Detection ◽  
Proposed Model ◽  
Current Asset

Clients are increasingly looking for fast and effective means to quickly and frequently survey and communicate the condition of their buildings so that essential repairs and maintenance work can be done in a proactive and timely manner before it becomes too dangerous and expensive. Traditional methods for this type of work commonly comprise of engaging building surveyors to undertake a condition assessment which involves a lengthy site inspection to produce a systematic recording of the physical condition of the building elements, including cost estimates of immediate and projected long-term costs of renewal, repair and maintenance of the building. Current asset condition assessment procedures are extensively time consuming, laborious, and expensive and pose health and safety threats to surveyors, particularly at height and roof levels which are difficult to access. This paper aims at evaluating the application of convolutional neural networks (CNN) towards an automated detection and localisation of key building defects, e.g., mould, deterioration, and stain, from images. The proposed model is based on pre-trained CNN classifier of VGG-16 (later compaired with ResNet-50, and Inception models), with class activation mapping (CAM) for object localisation. The challenges and limitations of the model in real-life applications have been identified. The proposed model has proven to be robust and able to accurately detect and localise building defects. The approach is being developed with the potential to scale-up and further advance to support automated detection of defects and deterioration of buildings in real-time using mobile devices and drones.

Sign in / Sign up

Export Citation Format

Share Document