WE-B-201B-02: The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Public Database of CT Scans for Lung Nodule Analysis

Armato, Samuel G.; McLennan, Geoffrey; McNitt‐Gray, M; Meyer, Charles R.; Reeves, Anthony P.; Bidaut, Luc; Zhao, Binsheng; Croft, Barbara Y.; Clarke, Laurence P.

doi:10.1118/1.3469350

Cited by 153 publications

(164 citation statements)

References 0 publications

Supporting

Mentioning

163

Contrasting

Unclassified

Order By: Relevance

“…A commercial CAD system (σ‐Discover/Lung, 12 Sigma Technologies Co. Ltd., Beijing, China) based on deep convolutional neural networks (DL‐CAD) was used to process the LDCT images to identify and characterize lung nodules (nodule by nodule). The training data used to build this DL‐CAD system included public databases, such as the Lung Image Database Consortium Image Collection from Cancer Imaging Archive (LIDC/IDRI) and the National Cancer Institute NLST . The DL‐CAD system is designed to detect nodules ≥ 3 mm and can calculate three dimensional (3D) quantitative measurements, such as the largest 3D diameter (the largest diameter in any plane of nodules), average 3D diameter (the diameter of a sphere equivalent to the volume of a nodule), 3D mass, and 3D volume.…”

Section: Methodsmentioning

confidence: 99%

Evaluating the performance of a deep learning‐based computer‐aided diagnosis (DL‐CAD) system for detecting and characterizing lung nodules: Comparison with the performance of double reading by radiologists

Liu

Huang

et al. 2018

Thoracic Cancer

View full text Add to dashboard Cite

BackgroundThe study was conducted to evaluate the performance of a state‐of‐the‐art commercial deep learning‐based computer‐aided diagnosis (DL‐CAD) system for detecting and characterizing pulmonary nodules.MethodsPulmonary nodules in 346 healthy subjects (male: female = 221:125, mean age 51 years) from a lung cancer screening program conducted from March to November 2017 were screened using a DL‐CAD system and double reading independently, and their performance in nodule detection and characterization were evaluated. An expert panel combined the results of the DL‐CAD system and double reading as the reference standard.ResultsThe DL‐CAD system showed a higher detection rate than double reading, regardless of nodule size (86.2% vs. 79.2%; P < 0.001): nodules ≥ 5 mm (96.5% vs. 88.0%; P = 0.008); nodules < 5 mm (84.3% vs. 77.5%; P < 0.001). However, the false positive rate (per computed tomography scan) of the DL‐CAD system (1.53, 529/346) was considerably higher than that of double reading (0.13, 44/346; P < 0.001). Regarding nodule characterization, the sensitivity and specificity of the DL‐CAD system for distinguishing solid nodules > 5 mm (90.3% and 100.0%, respectively) and ground‐glass nodules (100.0% and 96.1%, respectively) were close to that of double reading, but dropped to 55.5% and 93%, respectively, when discriminating part solid nodules.ConclusionOur DL‐CAD system detected significantly more nodules than double reading. In the future, false positive findings should be further reduced and characterization accuracy improved.

show abstract

Section: Methodsmentioning

confidence: 99%

Evaluating the performance of a deep learning‐based computer‐aided diagnosis (DL‐CAD) system for detecting and characterizing lung nodules: Comparison with the performance of double reading by radiologists

Liu

Huang

et al. 2018

Thoracic Cancer

View full text Add to dashboard Cite

show abstract

“…Ten clinical CT datasets were randomly selected from The Cancer Imaging Archive (TCIA) provided by National Cancer Institute (Armato et al, 2011) as illustrated in figure 3. Details pertaining to each image along with the hardware specifications and optimization parameters used in the experiments are summarized in table 1.…”

Section: Methodsmentioning

confidence: 99%

Automatic localization of vertebral levels in x-ray fluoroscopy using 3D-2D registration: a tool to reduce wrong-site surgery

Otake¹,

Schäfer²,

Stayman³

et al. 2012

Phys. Med. Biol.

View full text Add to dashboard Cite

Surgical targeting of the incorrect vertebral level (“wrong-level” surgery) is among the more common wrong-site surgical errors, attributed primarily to a lack of uniquely identifiable radiographic landmarks in the mid-thoracic spine. Conventional localization method involves manual counting of vertebral bodies under fluoroscopy, is prone to human error, and carries additional time and dose. We propose an image registration and visualization system (referred to as LevelCheck), for decision support in spine surgery by automatically labeling vertebral levels in fluoroscopy using a GPU-accelerated, intensity-based 3D-2D (viz., CT-to-fluoroscopy) registration. A gradient information (GI) similarity metric and CMA-ES optimizer were chosen due to their robustness and inherent suitability for parallelization. Simulation studies involved 10 patient CT datasets from which 50,000 simulated fluoroscopic images were generated from C-arm poses selected to approximate C-arm operator and positioning variability. Physical experiments used an anthropomorphic chest phantom imaged under real fluoroscopy. The registration accuracy was evaluated as the mean projection distance (mPD) between the estimated and true center of vertebral levels. Trials were defined as successful if the estimated position was within the projection of the vertebral body (viz., mPD < 5mm). Simulation studies showed a success rate of 99.998% (1 failure in 50,000 trials) and computation time of 4.7 sec on a midrange GPU. Analysis of failure modes identified cases of false local optima in the search space arising from longitudinal periodicity in vertebral structures. Physical experiments demonstrated robustness of the algorithm against quantum noise and x-ray scatter. The ability to automatically localize target anatomy in fluoroscopy in near-real-time could be valuable in reducing the occurrence of wrong-site surgery while helping to reduce radiation exposure. The method is applicable beyond the specific case of vertebral labeling, since any structure defined in pre-operative (or intra-operative) CT or cone-beam CT can be automatically registered to the fluoroscopic scene.

show abstract

“…The 3D CNN networks were initially trained using 888 cases with 1186 nodules ≥3 mm in size from the LUNA16 dataset. 16 To facilitate the training of the 3D CNNs, input images were normalized to have a zero mean and unit variance. The mean, µ, and the standard deviation, σ, of all training samples were first computed and then were used to normalize each pixel by subtracting µ and dividing by σ.…”

Section: Pre-processingmentioning

confidence: 99%

<p>Deep Learning in CT Images: Automated Pulmonary Nodule Detection for Subsequent Management Using Convolutional Neural Network</p>

Zhang

et al. 2020

CMAR

View full text Add to dashboard Cite

The purpose of this study is to compare the detection performance of the 3-dimensional convolutional neural network (3D CNN)-based computer-aided detection (CAD) models with radiologists of different levels of experience in detecting pulmonary nodules on thin-section computed tomography (CT). Patients and Methods: We retrospectively reviewed 1109 consecutive patients who underwent follow-up thin-section CT at our institution. The 3D CNN model for nodule detection was retrained and complemented by expert augmentation. The annotations of a consensus panel consisting of two expert radiologists determined the ground truth. The detection performance of the retrained CAD model and three other radiologists at different levels of experience were tested using a free-response receiver operating characteristic (FROC) analysis in the test group. Results: The detection performance of the retrained CAD model was significantly better than that of the pre-trained network (sensitivity: 93.09% vs 38.44%). The retrained CAD model had a significantly better detection performance than radiologists (average sensitivity: 93.09% vs 50.22%), without significantly increasing the number of false positives per scan (1.64 vs 0.68). In the training set, 922 nodules less than 3 mm in size in 211 patients at high risk were recommended for follow-up CT according to the Fleischner Society Guidelines. Fifteen of 101 solid nodules were confirmed to be lung cancer. Conclusion: The retrained 3D CNN-based CAD model, complemented by expert augmentation, was an accurate and efficient tool in identifying incidental pulmonary nodules for subsequent management.

show abstract

WE-B-201B-02: The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Public Database of CT Scans for Lung Nodule Analysis

Cited by 153 publications

References 0 publications

Evaluating the performance of a deep learning‐based computer‐aided diagnosis (DL‐CAD) system for detecting and characterizing lung nodules: Comparison with the performance of double reading by radiologists

Evaluating the performance of a deep learning‐based computer‐aided diagnosis (DL‐CAD) system for detecting and characterizing lung nodules: Comparison with the performance of double reading by radiologists

Automatic localization of vertebral levels in x-ray fluoroscopy using 3D-2D registration: a tool to reduce wrong-site surgery

<p>Deep Learning in CT Images: Automated Pulmonary Nodule Detection for Subsequent Management Using Convolutional Neural Network</p>

Contact Info

Product

Resources

About