Computer-aided detection of pulmonary nodules: a comparative study using the public LIDC/IDRI database

Jacobs, Colin; Rikxoort, Eva M. van; Murphy, Keelin; Prokop, Mathias; Schaefer-Prokop, Cornelia; Ginneken, Bram van

doi:10.1007/s00330-015-4030-7

Cited by 94 publications

(65 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we evaluated the performance of a commercial DL‐CAD system for detecting and characterizing different types of lung nodules. Consistent with the results of most previous studies, our study showed that the DL‐CAD system could detect more nodules than double reading, regardless of nodule size . Recently, a report based on the International Early Lung Cancer Action Program (I‐ELCAP) study showed that in 75% of confirmed cancer patients, the corresponding small nodules could be detected in previous CT scans .…”

Section: Discussionsupporting

confidence: 91%

“…Until now, a large variety of studies based on LDCT using different CAD systems and data have reported a wide range of sensitivity performance from 38% to 100% and false positive rates from 1.0 per scan to 8.2 per scan . With the increasing improvement of CAD systems, the majority of studies have demonstrated that CAD systems could detect more nodules than radiologists, even after double reading . Moreover, in comparison with most CAD systems based on supervised machine learning algorithms, multiple studies have shown that deep learning‐based CAD systems (DL‐CAD) have superior detection rates and further reduce false positive rates .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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: Discussionsupporting

confidence: 91%

Section: Introductionmentioning

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

“…This shows the potential of using high quality nodule CAD systems in clinical practice. We have noticed this previously [11] and plan to release an update to the LIDC annotations with CAD marks confirmed by radiologists. Data augmentation has often been shown to improve the performance of CNNs.…”

Section: Discussionmentioning

confidence: 97%

Off-the-shelf convolutional neural network features for pulmonary nodule detection in computed tomography scans

Ginneken

Setio

Jacobs

et al. 2015

2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI)

Self Cite

210

150

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have emerged as the most powerful technique for a range of different tasks in computer vision. Recent work suggested that CNN features are generic and can be used for classification tasks outside the exact domain for which the networks were trained. In this work we use the features from one such network, OverFeat, trained for object detection in natural images, for nodule detection in computed tomography scans. We use 865 scans from the publicly available LIDC data set, read by four thoracic radiologists. Nodule candidates are generated by a state-of-theart nodule detection system. We extract 2D sagittal, coronal and axial patches for each nodule candidate and extract 4096 features from the penultimate layer of OverFeat and classify these with linear support vector machines. We show for various configurations that the off-the-shelf CNN features perform surprisingly well, but not as good as the dedicated detection system. When both approaches are combined, significantly better results are obtained than either approach alone. We conclude that CNN features have great potential to be used for detection tasks in volumetric medical data.

show abstract

“…Our results emphasize the need to specifically note the presence of pulmonary nodules with irregular and ill-defined margins in patients with metastatic RCC to the lung in CT reports as these may represent primary lung neoplasms. Computer-aided detection and characterization of pulmonary nodules with prediction models have been shown to be helpful in the diagnosis and pre-surgical evaluation of pulmonary nodules 18,19 and may help identify these lesions.…”

Section: Discussionmentioning

confidence: 99%

Renal Cell Carcinoma With Pulmonary Metastasis and Metachronous Non-Small Cell Lung Cancer

Bowman

Pedrosa²,

Kapur

et al. 2017

Clinical Genitourinary Cancer

View full text Add to dashboard Cite

Introduction The development of a second primary malignancy in a patient with a preexisting diagnosis of metastatic cancer may be easily overlooked or misattributed to progression of disease. We report 3 patients with clear cell renal cell carcinoma (ccRCC) metastatic to the lungs who were subsequently diagnosed with non-small cell lung cancer (NSCLC). We examined the frequency of this occurrence within our institution and report on the radiographic findings that may help distinguish between metastatic and primary lung cancers. Methods Patients who received systemic targeted therapy for metastatic RCC at our institution between January 2006 and October 2013 were identified and the proportion and incidence rate for developing NSCLC with pre-existing metastatic RCC were calculated. Results 2% of patients (3/151; 95% CI 0.68 – 5.68%) treated for metastatic RCC with systemic targeted therapies at our institution were subsequently diagnosed with NSCLC, increasing to 3.5% (3/85; 95% CI 1.21 – 9.87%) among patients with known RCC pulmonary metastasis. The incident rate for development of NSCLC in metastatic RCC patients was 0.87 per 100 person-years (95% CI 0.22 – 2.4). Conclusion The subsequent development of a primary lung cancer in metastatic RCC patients, which occurred in 2% of patients at our institution, appears underreported in the literature. Primary NSCLC may be underdiagnosed in patients with metastatic RCC. Both the radiographic appearance and clinical behavior of a lesion may hold clues that can help distinguish between a new primary and progression of metastatic disease.

show abstract

Computer-aided detection of pulmonary nodules: a comparative study using the public LIDC/IDRI database

Cited by 94 publications

References 22 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

Off-the-shelf convolutional neural network features for pulmonary nodule detection in computed tomography scans

Renal Cell Carcinoma With Pulmonary Metastasis and Metachronous Non-Small Cell Lung Cancer

Contact Info

Product

Resources

About