Toward the determination of sensitive and reliable whole-lung computed tomography features for robust standard radiomics and delta-radiomics analysis in a nonhuman primate model of coronavirus disease 2019

Castro, Marcelo; Reza, Syed M. S.; Chu, Winston T.; Bradley, Dara; Lee, Ji Hyun; Crozier, Ian; Sayre, Philip J.; Lee, Byeong Y.; Mani, Venkatesh; Friedrich, Thomas C.; O’Connor, David H.; Finch, Courtney; Worwa, Gabriella; Kuhn, Jens H.; Solomon, Jeffrey

doi:10.1117/1.jmi.9.6.066003

Cited by 4 publications

(7 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The NHP dataset consisted of 92 longitudinal CT scans from 18 SARS-CoV-2-exposed crab-eating macaques (Macaca fascicularis Raffles, 1821) 4 . All scans had ground truth annotations for whole lungs and lung lesions.…”

Section: Nhp Ct Data Collectionmentioning

confidence: 99%

Lung lesion segmentation of CT scans after SARS-CoV-2 infection: combining nonhuman primate with human data for inter-species transfer learning

Shinguyen,

Chu,

Rustad

et al. 2024

Medical Imaging 2024: Clinical and Biomedical Imaging

View full text Add to dashboard Cite

Agile development of reliable and accurate segmentation models during an infectious disease outbreak has the potential to reduce the need for already-strained human expertise. Global research and data-sharing efforts during the COVID-19 pandemic have shown how rapidly deep-learning (DL) models can be developed when public datasets are available for training. However, these efforts have been rare, usually limited by the unavailability of computed tomography (CT) imaging datasets from patients in the clinical setting. In the absence of human data, animal models faithful to human disease are used to investigate the imaging phenotype of high-consequence and emerging pathogens.As simultaneous access to both human and nonhuman primate (NHP) data for the same respiratory infection is unusual, we were interested in whether the inclusion of NHP data might enhance DL image segmentation of lung lesions associated with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. Thus, we set out to evaluate DL performance and generalizability to a human test set. We found that combining human and NHP data and utilizing pretrained NHP models to initialize model training outperformed a model trained solely on human CT data.By studying the interaction between human and NHP CT imaging in developing these models, we can assess the potential value of NHP datasets for known or novel viruses that emerge in settings where medical imaging capacity is limited. Understanding and leveraging NHP datasets to improve the agility and quality of model development capabilities could better prepare us to respond to disease outbreaks in the human population.

show abstract

Section: Nhp Ct Data Collectionmentioning

confidence: 99%

Lung lesion segmentation of CT scans after SARS-CoV-2 infection: combining nonhuman primate with human data for inter-species transfer learning

Shinguyen,

Chu,

Rustad

et al. 2024

Medical Imaging 2024: Clinical and Biomedical Imaging

View full text Add to dashboard Cite

show abstract

“…Early detection and accurate identification of lung lesions by medical imaging are central to characterizing disease and its progression over time. Deep-learning methods applied to computed tomography (CT) images have proven valuable for automated lung lesion segmentation and other foundational diagnostic tasks but require substantial efforts to generate large enough ground-truth training data [1]. Manual lesion segmentation of ground-truth images by expert radiologists is timeconsuming and labor-intensive.…”

Section: Introductionmentioning

confidence: 99%

Active learning applied to selection of diverse training data using radiomic features for optimal lung lesion segmentation in nonhuman primates

Rustad,

Chu,

Reza

et al. 2024

Medical Imaging 2024: Clinical and Biomedical Imaging

View full text Add to dashboard Cite

In response to the critical need for timely and precise detection of lung lesions, we explored an innovative active learning approach for optimally selecting training data for deep-learning segmentation of computed tomography scans from nonhuman primates. Our guiding hypothesis was that by maximizing the information within a training set-accomplished by choosing images uniformly distributed in n-dimensional radiomic feature space-we may attain similar or superior segmentation results to random dataset selection, despite the use of fewer labeled images. To test this hypothesis, we compared segmentation models trained on different subsets of the available training data. Subsets that maximized the diversity among datasets (i.e., diverse data) were compared with subsets that minimized diversity among datasets (i.e., concentrated data) and randomly chosen subsets (i.e., random data). A two-tiered feature-selection technique was used to reduce the radiomic feature space to reliable, relevant, and non-redundant features. We generated learning curves to assess the model performance as a function of the number of training dataset samples. We found that models trained on uniformly distributed data consistently outperformed those trained on concentrated data, achieving higher median test Dice scores with less variance. These results suggest that active learning and intelligent selection of data that are diverse and uniformly distributed within a radiomic feature space can significantly enhance segmentation model performance. This improvement has substantial implications for optimizing lung lesion characterization, disease management, and evaluation of treatments and underscores the potential benefit of active learning and intelligent data selection in medical imaging segmentation tasks.

show abstract

“…While changes in subject conditions may mainly affect repeatability, with the use of identical scanners, acquisition parameters, and software, the main source of reduced reproducibility has become the location of regions of interest within the organ. Therefore, the evaluation of repeatability and reproducibility is pivotal but challenging because it requires multiple replicate measurements, typically lacking in the clinical setting [7]. The accuracy of radiomicsbased models may be potentially affected by the inclusion of non-reproducible radiomic features.…”

Section: Introductionmentioning

confidence: 99%

Determination of reproducible radiomic features for diagnosis of fatty liver disease in a crab-eating macaque model

Wang¹,

Solomon

Syed

et al. 2023

Medical Imaging 2023: Biomedical Applications in Molecular, Structural, and Functional Imaging

View full text Add to dashboard Cite

Evaluation of the intra-subject reproducibility of radiomic features is pivotal but challenging because it requires multiple replicate measurements, typically lacking in the clinical setting. Radiomics analysis based on computed tomography (CT) has been increasingly used to characterize liver malignancies and liver diffusive diseases. However, radiomic features are greatly affected by scanning parameters and reconstruction kernels, among other factors. In this study, we examined the effects of diets, reconstruction kernels, and liver-to-spleen normalization on the intra-subject reproducibility of radiomic features. The final goal of this work is to create a framework that may help identify reproducible radiomics features suitable for further diagnosis and grading of fatty liver disease in nonhuman primates using radiomics analysis. As a first step, the identification of reproducible features is essential. To accomplish this aim, we retrospectively analyzed serial CT images from two groups of crab-eating macaques, fed a normal or atherogenic diet. Serial CT examinations resulted in 45 highresolution scans. From each scan, two CT images were reconstructed using a standard B kernel and a bone-enhanced D kernel, with and without normalization relative to the spleen. Radiomic features were extracted from six regions in the liver parenchyma. Intra-subject variability showed that many features are fully reproducible regardless of liver disease status whereas others are significantly different in a limited number of tests. Features significantly different between the normal and atherogenic diet groups were also investigated. Reproducible features were listed, with normalized images having more reproducible features.

show abstract

Toward the determination of sensitive and reliable whole-lung computed tomography features for robust standard radiomics and delta-radiomics analysis in a nonhuman primate model of coronavirus disease 2019

Cited by 4 publications

References 64 publications

Lung lesion segmentation of CT scans after SARS-CoV-2 infection: combining nonhuman primate with human data for inter-species transfer learning

Lung lesion segmentation of CT scans after SARS-CoV-2 infection: combining nonhuman primate with human data for inter-species transfer learning

Active learning applied to selection of diverse training data using radiomic features for optimal lung lesion segmentation in nonhuman primates

Determination of reproducible radiomic features for diagnosis of fatty liver disease in a crab-eating macaque model

Contact Info

Product

Resources

About