Deep Learning-Based Computed Tomography Perfusion Mapping (DL-CTPM) for Pulmonary CT-to-Perfusion Translation

Ren, Ge; Jiang, Zhang; Tian, Lu; Xiao, Haonan; Cheung, Lai Yin; Ho, Wai Yin; Qin, Jing; Cai, Jing

doi:10.1016/j.ijrobp.2021.02.032

Cited by 21 publications

(34 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CT-based perfusion images were compared with ground-truth SPECT perfusion images with voxel-wise correlation, function-wise similarity, and lobe-wise agreement in 33 lung cancer patients. In our previous work, we developed and evaluated the deep learning based CTPM method in patients with various lung diseases (22). However, the performance of the CTPM method specifically on lung cancer patients is yet to be investigated due to the limited number of lung cancer patients in our previous dataset.…”

Section: Discussionmentioning

confidence: 99%

“…The preprocessing procedures and CNN model were proposed in our previous study (22) and illustrated in Figure 1B. Briefly, the lung parenchyma region was segmented by using a pre-trained U-Net model (R231) (24), which was trained on multifarious lung CT scans.…”

Section: Transfer Learning Framework For the Generation Of Ct-based P...mentioning

confidence: 99%

“…This method synthesizes lung functional images based on the texture information provided by anatomic CT images. We previously demonstrated that the CT-based perfusion images generated by the CTPM method achieved a moderate-to-high approximation as compared with SPECT perfusion images in patients with different lung diseases (22,23). Perfusion SPECT is one of the primarily diagnostic tools for pulmonary embolism, but not for lung cancer patients.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Transfer Learning Framework for Deep Learning-Based CT-to-Perfusion Mapping on Lung Cancer Patients

Ren

Lam

et al. 2022

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

PurposeDeep learning model has shown the feasibility of providing spatial lung perfusion information based on CT images. However, the performance of this method on lung cancer patients is yet to be investigated. This study aims to develop a transfer learning framework to evaluate the deep learning based CT-to-perfusion mapping method specifically on lung cancer patients.MethodsSPECT/CT perfusion scans of 33 lung cancer patients and 137 non-cancer patients were retrospectively collected from two hospitals. To adapt the deep learning model on lung cancer patients, a transfer learning framework was developed to utilize the features learned from the non-cancer patients. These images were processed to extract features from three-dimensional CT images and synthesize the corresponding CT-based perfusion images. A pre-trained model was first developed using a dataset of patients with lung diseases other than lung cancer, and subsequently fine-tuned specifically on lung cancer patients under three-fold cross-validation. A multi-level evaluation was performed between the CT-based perfusion images and ground-truth SPECT perfusion images in aspects of voxel-wise correlation using Spearman’s correlation coefficient (R), function-wise similarity using Dice Similarity Coefficient (DSC), and lobe-wise agreement using mean perfusion value for each lobe of the lungs.ResultsThe fine-tuned model yielded a high voxel-wise correlation (0.8142 ± 0.0669) and outperformed the pre-trained model by approximately 8%. Evaluation of function-wise similarity indicated an average DSC value of 0.8112 ± 0.0484 (range: 0.6460-0.8984) for high-functional lungs and 0.8137 ± 0.0414 (range: 0.6743-0.8902) for low-functional lungs. Among the 33 lung cancer patients, high DSC values of greater than 0.7 were achieved for high functional volumes in 32 patients and low functional volumes in all patients. The correlations of the mean perfusion value on the left upper lobe, left lower lobe, right upper lobe, right middle lobe, and right lower lobe were 0.7314, 0.7134, 0.5108, 0.4765, and 0.7618, respectively.ConclusionFor lung cancer patients, the CT-based perfusion images synthesized by the transfer learning framework indicated a strong voxel-wise correlation and function-wise similarity with the SPECT perfusion images. This suggests the great potential of the deep learning method in providing regional-based functional information for functional lung avoidance radiation therapy.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Transfer Learning Framework For the Generation Of Ct-based P...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Transfer Learning Framework for Deep Learning-Based CT-to-Perfusion Mapping on Lung Cancer Patients

Ren

Lam

et al. 2022

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ren et al implemented the DL-based approach to transform 3DCT to SPECT perfusion images and investigated the influence of different model architectures and preprocessing. 24,25 They reported that there were some cases in which the lowfunctional region was predicted to be a high-functional region, which can be partly attributed to the low occurrence and small volume of the low-functional regions compared with high-functional regions. Our results showed similar trends (Figures 3 and 4).…”

Section: Discussionmentioning

confidence: 99%

A deep learning method for translating 3DCT to SPECT ventilation imaging: First comparison with ^81mKr‐gas SPECT ventilation imaging

et al. 2022

View full text Add to dashboard Cite

Purpose This study aimed to evaluate the accuracy of deep learning (DL)‐based computed tomography (CT) ventilation imaging (CTVI). Methods A total of 71 cases that underwent single‐photon emission CT 81mKr‐gas ventilation (SPECT V) and CT imaging were included. Sixty cases were assigned to the training and validation sets, and the remaining 11 cases were assigned to the test set. To directly transform three‐dimensional (3D) CT (free‐breathing CT) images to SPECT V images, a DL‐based model was implemented based on the U‐Net architecture. The input and output data were 3DCT‐ and SPECT V‐masked, respectively, except for whole‐lung volumes. These data were rearranged in voxel size, registered rigidly, cropped, and normalized in preprocessing. In addition to a standard estimation method (i.e., without dropout during the estimation process), a Monte Carlo dropout (MCD) method (i.e., with dropout during the estimation process) was used to calculate prediction uncertainty. To evaluate the two models’ (CTVIMCD U‐Net, CTVIU‐Net) performance, we used fivefold cross‐validation for the training and validation sets. To test the final model performances for both approaches, we applied the test set to each trained model and averaged the test prediction results from the five trained models to acquire the mean test result (bagging) for each approach. For the MCD method, the models were predicted repeatedly (sample size = 200), and the average and standard deviation (SD) maps were calculated in each voxel from the predicted results: The average maps were defined as test prediction results in each fold. As an evaluation index, the voxel‐wise Spearman rank correlation coefficient (Spearman rs) and Dice similarity coefficient (DSC) were calculated. The DSC was calculated for three functional regions (high, moderate, and low) separated by an almost equal volume. The coefficient of variation was defined as prediction uncertainty, and these average values were calculated within three functional regions. The Wilcoxon signed‐rank test was used to test for a significant difference between the two DL‐based approaches. Results The average indexes with one SD (1SD) between CTVIMCD U‐Net and SPECT V were 0.76 ± 0.06, 0.69 ± 0.07, 0.51 ± 0.06, and 0.75 ± 0.04 for Spearman rs, DSChigh, DSCmoderate, and DSClow, respectively. The average indexes with 1SD between CTVIU‐Net and SPECT V were 0.72 ± 0.05, 0.66 ± 0.04, 0.48 ± 0.04, and 0.74 ± 0.06 for Spearman rs, DSChigh, DSCmoderate, and DSClow, respectively. These indexes between CTVIMCD U‐Net and CTVIU‐Net showed no significance difference (Spearman rs, p = 0.175; DSChigh, p = 0.123; DSCmoderate, p = 0.278; DSClow, p = 0.520). The average coefficient of variations with 1SD were 0.27 ± 0.00, 0.27 ± 0.01, and 0.36 ± 0.03 for the high‐, moderate‐, and low‐functional regions, respectively, and the low‐functional region showed a tendency to exhibit larger uncertainties than the others. Conclusion We evaluated DL‐based framework for estimating lung‐functional ventilation images only from CT image...

show abstract

“…Subsequent layers combine these extracted features for advanced object detection. This property makes DL a suitable tool for image-related tasks, such as computer-aided diagnosis (27,28), image enhancement (29), image synthesis (30,31), and functional information derivation (32,33).…”

Section: DLmentioning

confidence: 99%

A review of deep learning-based three-dimensional medical image registration methods

Xiao¹,

Teng²,

Liu³

et al. 2021

Quant Imaging Med Surg

Self Cite

View full text Add to dashboard Cite

Medical image registration is a vital component of many medical procedures, such as imageguided radiotherapy (IGRT), as it allows for more accurate dose-delivery and better management of side effects. Recently, the successful implementation of deep learning (DL) in various fields has prompted many research groups to apply DL to three-dimensional (3D) medical image registration. Several of these efforts have led to promising results. This review summarized the progress made in DL-based 3D image registration over the past 5 years and identify existing challenges and potential avenues for further research.The collected studies were statistically analyzed based on the region of interest (ROI), image modality, supervision method, and registration evaluation metrics. The studies were classified into three categories: deep iterative registration, supervised registration, and unsupervised registration. The studies are thoroughly reviewed and their unique contributions are highlighted. A summary is presented following a review of each category of study, discussing its advantages, challenges, and trends. Finally, the common challenges for all categories are discussed, and potential future research topics are identified.

show abstract

Deep Learning-Based Computed Tomography Perfusion Mapping (DL-CTPM) for Pulmonary CT-to-Perfusion Translation

Cited by 21 publications

References 44 publications

A Transfer Learning Framework for Deep Learning-Based CT-to-Perfusion Mapping on Lung Cancer Patients

A Transfer Learning Framework for Deep Learning-Based CT-to-Perfusion Mapping on Lung Cancer Patients

A deep learning method for translating 3DCT to SPECT ventilation imaging: First comparison with ^81mKr‐gas SPECT ventilation imaging

A review of deep learning-based three-dimensional medical image registration methods

Contact Info

Product

Resources

About

Deep Learning-Based Computed Tomography Perfusion Mapping (DL-CTPM) for Pulmonary CT-to-Perfusion Translation

Cited by 21 publications

References 44 publications

A Transfer Learning Framework for Deep Learning-Based CT-to-Perfusion Mapping on Lung Cancer Patients

A Transfer Learning Framework for Deep Learning-Based CT-to-Perfusion Mapping on Lung Cancer Patients

A deep learning method for translating 3DCT to SPECT ventilation imaging: First comparison with 81mKr‐gas SPECT ventilation imaging

A review of deep learning-based three-dimensional medical image registration methods

Contact Info

Product

Resources

About

A deep learning method for translating 3DCT to SPECT ventilation imaging: First comparison with ^81mKr‐gas SPECT ventilation imaging