A simplified cluster model and a tool adapted for collaborative labeling of lung cancer CT scans

Морозов, С. П.; Gombolevskiy, Victor A.; Elizarov, A.B.; Gusev, Maxim; Novik, Vladimir P.; Prokudaylo, Sergey B.; Bardin, A.S.; Popov, E.V.; Ледихова, Н. В.; Chernina, Valeria; Blokhin, Ivan; Николаев, А. Е.; Reshetnikov, Roman V.; Vladzymyrskyy, Anton; Kulberg, N. S.

doi:10.1016/j.cmpb.2021.106111

Cited by 20 publications

(25 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Reading of CT scans was performed by ten radiologists with 3-25 years' experience, and trained in COVID-19 pneumonia interpretation. The FAnTom software version 1.2 (Moscow, Russia) [28,29] was modified to assess disease severity according to the CT0-4 scoring scheme (Figure 1); it was also used to facilitate annotation and provide the radiologists with online access to a randomly selected set of anonymized studies. Each series was independently evaluated by two raters (Reader A and Reader B) blinded to the protocol used (standard-or low-dose CT, sharp or soft kernel) through the FAnTom interface.…”

Section: Image Analysismentioning

confidence: 99%

Inter-Observer Agreement between Low-Dose and Standard-Dose CT with Soft and Sharp Convolution Kernels in COVID-19 Pneumonia

Blokhin¹,

Gombolevskiy²,

Chernina³

et al. 2022

JCM

Self Cite

View full text Add to dashboard Cite

Computed tomography (CT) has been an essential diagnostic tool during the COVID-19 pandemic. The study aimed to develop an optimal CT protocol in terms of safety and reliability. For this, we assessed the inter-observer agreement between CT and low-dose CT (LDCT) with soft and sharp kernels using a semi-quantitative severity scale in a prospective study (Moscow, Russia). Two consecutive scans with CT and LDCT were performed in a single visit. Reading was performed by ten radiologists with 3-25 years’ experience. The study included 230 patients, and statistical analysis showed LDCT with a sharp kernel as the most reliable protocol (percentage agreement 74.35 ± 43.77%), but its advantage was marginal. There was no significant correlation between radiologists’ experience and average percentage agreement for all four evaluated protocols. Regarding the radiation exposure, CTDIvol was 3.6 ± 0.64 times lower for LDCT. In conclusion, CT and LDCT with soft and sharp reconstructions are equally reliable for COVID-19 reporting using the “CT 0-4” scale. The LDCT protocol allows for a significant decrease in radiation exposure but may be restricted by body mass index.

show abstract

Section: Image Analysismentioning

confidence: 99%

Inter-Observer Agreement between Low-Dose and Standard-Dose CT with Soft and Sharp Convolution Kernels in COVID-19 Pneumonia

Blokhin¹,

Gombolevskiy²,

Chernina³

et al. 2022

JCM

Self Cite

View full text Add to dashboard Cite

show abstract

“…To train and evaluate the consistency of the segmentation algorithms, we use two sources of paired data. The first source is a publicly available dataset Cancer-500 (Morozov et al, 2021). However, the Cancer-500 dataset does not contain COVID-19 cases.…”

Section: Paired Images Datamentioning

confidence: 99%

“…We build the Paired-public dataset using a publicly available dataset, Cancer-500 (Morozov et al, 2021). The data was collected from 536 randomly selected patients of Moscow clinics in 2018.…”

Section: Paired-publicmentioning

confidence: 99%

“…Although the augmentation can work only with the source data, the adver-sarial and consistency-based methods require additional unlabeled data from the target domain. In this task, a large pool of unlabeled chest CT image pairs which differ only in reconstruction kernels within every pair is publicly available, e.g., (Morozov et al, 2021). The intuition here is that the adaptation methods should outperform the augmentation one when a broader range of real-world data is available.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptation to CT Reconstruction Kernels by Enforcing Cross-domain Feature Maps Consistency

Shimovolos¹,

Shushko²,

Belyaev³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep learning methods provide significant assistance in analyzing coronavirus disease in chest computed tomography (CT) images, including identification, severity assessment, and segmentation. Although the earlier developed methods address the lack of data and specific annotations, the current goal is to build a robust algorithm for clinical use, having a larger pool of available data. With the larger datasets, the domain shift problem arises, affecting the performance of methods on the unseen data. One of the critical sources of domain shift in CT images is the difference in reconstruction kernels used to generate images from the raw data (sinograms). In this paper, we show a decrease in the COVID-19 segmentation quality of the model trained on the smooth and tested on the sharp reconstruction kernels. Furthermore, we compare several domain adaptation approaches to tackle the problem, such as task-specific augmentation and unsupervised adversarial learning. Finally, we propose the unsupervised adaptation method, called F-Consistency, that outperforms the previous approaches. Our method exploits a set of unlabeled CT image pairs which differ only in reconstruction kernels within every pair. It enforces the similarity of the network's hidden representations (feature maps) by minimizing mean squared error (MSE) between paired feature maps. We show our method achieving 0.64 Dice Score on the test dataset with unseen sharp kernels, compared to the 0.56 Dice Score of the baseline model. Moreover, F-Consistency scores 0.80 Dice Score between predictions on the paired images, which almost doubles the baseline score of 0.46 and surpasses the other methods. We also show F-Consistency to better generalize on the unseen kernels and without the specific semantic content, e.g., presence of the COVID-19 lesions.

show abstract

“…The diagnosis and treatment of early stage lung cancer remains challenging. Chest CT is still the main tool used to diagnose lung cancer 3 . Using chest CT scans to identify lung nodules may help physicians find early lung cancer.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-based Artificial Intelligence Improves Accuracy of Error-prone Lung Nodules

et al. 2022

View full text Add to dashboard Cite

Introduction: Early detection of lung cancer is one way to improve outcomes. Improving the detection of nodules on chest CT scans is important. Previous artificial intelligence (AI) modules show rapid advantages, which improves the performance of detecting lung nodules in some datasets. However, they have a high false-positive (FP) rate. Its effectiveness in clinical practice has not yet been fully proven. We aimed to use AI assistance in CT scans to decrease FP. Materials and methods: CT images of 60 patients were obtained. Five senior doctors who were blinded to these cases participated in this study for the detection of lung nodules. Two doctors performed manual detection and labeling of lung nodules without AI assistance. Another three doctors used AI assistance to detect and label lung nodules before manual interpretation. The AI program is based on a deep learning framework. Results: In total, 266 nodules were identified. For doctors without AI assistance, the FP was 0.617-0.650/scan and the sensitivity was 59.2-67.0%. For doctors with AI assistance, the FP was 0.067 to 0.2/scan and the sensitivity was 59.2-77.3% This AI-assisted program significantly reduced FP. The error-prone characteristics of lung nodules were central locations, ground-glass appearances, and small sizes. The AI-assisted program improved the detection of error-prone nodules. Conclusions: Detection of lung nodules is important for lung cancer treatment. When facing a large number of CT scans, error-prone nodules are a great challenge for doctors. The AI-assisted program improved the performance of detecting lung nodules, especially for error-prone nodules.

show abstract

A simplified cluster model and a tool adapted for collaborative labeling of lung cancer CT scans

Cited by 20 publications

References 40 publications

Inter-Observer Agreement between Low-Dose and Standard-Dose CT with Soft and Sharp Convolution Kernels in COVID-19 Pneumonia

Inter-Observer Agreement between Low-Dose and Standard-Dose CT with Soft and Sharp Convolution Kernels in COVID-19 Pneumonia

Adaptation to CT Reconstruction Kernels by Enforcing Cross-domain Feature Maps Consistency

Deep Learning-based Artificial Intelligence Improves Accuracy of Error-prone Lung Nodules

Contact Info

Product

Resources

About