scholarly journals Discriminative Random Field Segmentation of Lung Nodules in CT Studies

2013 ◽  
Vol 2013 ◽  
pp. 1-9
Author(s):  
Brian Liu ◽  
Ashish Raj
Keyword(s):  
Random Fields ◽  
Ct Scans ◽  
Lung Nodules ◽  
Optimal Parameters ◽  
3D Segmentation ◽  
High Quality ◽  
Inference Problem ◽  
Seed Point ◽  
Scan Data ◽  
Ct Studies

The ability to conduct high-quality semiautomatic 3D segmentation of lung nodules in CT scans is of high value to busy radiologists. Discriminative random fields (DRFs) were used to segment 3D volumes of lung nodules in CT scan data using only one seed point per nodule. Optimal parameters for the DRF inference were first found using simulated annealing. These parameters were then used to solve the inference problem using the graph cuts algorithm. Results of the segmentation exhibited high precision and recall. The system can be adapted to facilitate the process of longitudinal studies but will still require human checking for failed cases.

scholarly journals Comparison of standardized uptake values measured on 18F-NaF PET/CT scans using three different tube current intensities

2015 ◽  
Vol 48 (1) ◽  
pp. 17-20 ◽  
Author(s):  
Agnes Araujo Valadares ◽  
Paulo Schiavom Duarte ◽  
Eduardo Bechtloff Woellner ◽  
George Barberio Coura-Filho ◽  
Marcelo Tatit Sapienza ◽  
...  
Keyword(s):  
Attenuation Correction ◽  
Lumbar Vertebra ◽  
Ct Scans ◽  
Femoral Diaphysis ◽  
Standardized Uptake Values ◽  
Pet Ct ◽  
Tube Current ◽  
The Mean ◽  
Humeral Diaphysis ◽  
Ct Studies

Objective: To analyze standardized uptake values (SUVs) using three different tube current intensities for attenuation correction on 18FNaF PET/CT scans. Materials and Methods: A total of 254 18F-NaF PET/CT studies were analyzed using 10, 20 and 30 mAs. The SUVs were calculated in volumes of interest (VOIs) drawn on three skeletal regions, namely, right proximal humeral diaphysis (RH), right proximal femoral diaphysis (RF), and first lumbar vertebra (LV1) in a total of 712 VOIs. The analyses covered 675 regions classified as normal (236 RH, 232 RF, and 207 LV1). Results: Mean SUV for each skeletal region was 3.8, 5.4 and 14.4 for RH, RF, and LV1, respectively. As the studies were grouped according to mAs value, the mean SUV values were 3.8, 3.9 and 3.7 for 10, 20 and 30 mAs, respectively, in the RH region; 5.4, 5.5 and 5.4 for 10, 20 and 30 mAs, respectively, in the RF region; 13.8, 14.9 and 14.5 for 10, 20 and 30 mAs, respectively, in the LV1 region. Conclusion: The three tube current values yielded similar results for SUV calculation.

3D U-net for registration of lung nodules in longitudinal CT scans

2021 ◽  
Author(s):  
Aryan Ghazipour ◽  
Benjamin Veasey ◽  
Albert Seow ◽  
Amir Amini
Keyword(s):  
Ct Scans ◽  
Lung Nodules

scholarly journals Automatic Pulmonary Nodule Detection Applying Deep Learning or Machine Learning Algorithms to the LIDC-IDRI Database: A Systematic Review

Diagnostics ◽  
2019 ◽  
Vol 9 (1) ◽  
pp. 29 ◽  
Author(s):  
Lea Pehrson ◽  
Michael Nielsen ◽  
Carsten Ammitzbøl Lauridsen
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Deep Learning ◽  
Machine Learning Algorithms ◽  
Ct Scans ◽  
Lung Nodules ◽  
Original Research ◽  
Feature Based ◽  
High Level ◽  
Meta Analyses

The aim of this study was to provide an overview of the literature available on machine learning (ML) algorithms applied to the Lung Image Database Consortium Image Collection (LIDC-IDRI) database as a tool for the optimization of detecting lung nodules in thoracic CT scans. This systematic review was compiled according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Only original research articles concerning algorithms applied to the LIDC-IDRI database were included. The initial search yielded 1972 publications after removing duplicates, and 41 of these articles were included in this study. The articles were divided into two subcategories describing their overall architecture. The majority of feature-based algorithms achieved an accuracy >90% compared to the deep learning (DL) algorithms that achieved an accuracy in the range of 82.2%–97.6%. In conclusion, ML and DL algorithms are able to detect lung nodules with a high level of accuracy, sensitivity, and specificity using ML, when applied to an annotated archive of CT scans of the lung. However, there is no consensus on the method applied to determine the efficiency of ML algorithms.

scholarly journals Computer-Aided Diagnosis of Lung Nodules on CT Scans:

2010 ◽  
Vol 17 (3) ◽  
pp. 323-332 ◽  
Author(s):  
Ted Way ◽  
Heang-Ping Chan ◽  
Lubomir Hadjiiski ◽  
Berkman Sahiner ◽  
Aamer Chughtai ◽  
...  
Keyword(s):  
Computer Aided Diagnosis ◽  
Ct Scans ◽  
Lung Nodules ◽  
Computer Aided ◽  
Aided Diagnosis

scholarly journals The Lung Image Database Consortium (LIDC): An Evaluation of Radiologist Variability in the Identification of Lung Nodules on CT Scans

2007 ◽  
Vol 14 (11) ◽  
pp. 1409-1421 ◽  
Author(s):  
Samuel G. Armato ◽  
Michael F. McNitt-Gray ◽  
Anthony P. Reeves ◽  
Charles R. Meyer ◽  
Geoffrey McLennan ◽  
...  
Keyword(s):  
Image Database ◽  
Ct Scans ◽  
Lung Nodules

Algorithms for automatic detection of lung nodules in CT scans

2011 ◽  
Author(s):  
Maria Evelina Fantacci ◽  
Niccolo Camarlinghi ◽  
Roberto Bellotti ◽  
Gianfranco Gargano ◽  
Rosario Megna ◽  
...  
Keyword(s):  
Automatic Detection ◽  
Ct Scans ◽  
Lung Nodules

Cochlear Implants in Children: Reliability of Computed Tomography

1992 ◽  
Vol 107 (3) ◽  
pp. 410-417 ◽  
Author(s):  
Michael A. Seicshnaydre ◽  
Michele H. Johnson ◽  
M. Suzanne Hasenstab ◽  
George H. Williams
Keyword(s):  
Computed Tomography ◽  
Hearing Loss ◽  
Cochlear Implant ◽  
Temporal Bone ◽  
Cochlear Implants ◽  
Cochlear Implantation ◽  
Ct Scans ◽  
Presurgical Evaluation ◽  
Preoperative Ct ◽  
Ct Studies

Preoperative temporal bone computed tomography (CT) can demonstrate anatomic details relevant to surgical management and is therefore essential in the presurgical evaluation of patients receiving cochlear implants. The purpose of this study was to evaluate preoperative CT studies and compare them to surgical findings in 34 children who received the Nucleus multichannel cochlear implant. The focus of this report is to discuss the dependability of CT scans in predicting surgical findings at the time of cochlear implantation. Results indicate that agreement of CT interpretations with surgical findings is partially related to the etiology of hearing loss and the experience of the surgeon and neuroradiologist. Advantages and limitations of the CT scans in predicting surgical findings are discussed.

Sign in / Sign up

Export Citation Format

Share Document