Spect perfusion imaging versus CT for predicting radiation injury to normal lung in lung cancer patients

Weller, Alex; Dunlop, A.; Oxer, Adam; Gunapala, R.; Murray, Iain; Gray, Matthew J.; Flux, Glenn; deSouza, Nandita M.; Ahmed, Merina

doi:10.1259/bjr.20190184

Cited by 12 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SPECT ( x,y,z ) ' is the processed SPECT value. HIR is the high-intensity region value, which was set as the 75 th percentile of the pixel values in this study since this is close to the normal lung perfusion ( 25 ). discretize indicates the above described SPECT discretization.…”

Section: Methodsmentioning

confidence: 99%

Investigation of a Novel Deep Learning-Based Computed Tomography Perfusion Mapping Framework for Functional Lung Avoidance Radiotherapy

et al. 2021

View full text Add to dashboard Cite

Functional lung avoidance radiation therapy aims to minimize dose delivery to the normal lung tissue while favoring dose deposition in the defective lung tissue based on the regional function information. However, the clinical acquisition of pulmonary functional images is resource-demanding, inconvenient, and technically challenging. This study aims to investigate the deep learning-based lung functional image synthesis from the CT domain. Forty-two pulmonary macro-aggregated albumin SPECT/CT perfusion scans were retrospectively collected from the hospital. A deep learning-based framework (including image preparation, image processing, and proposed convolutional neural network) was adopted to extract features from 3D CT images and synthesize perfusion as estimations of regional lung function. Ablation experiments were performed to assess the effects of each framework component by removing each element of the framework and analyzing the testing performances. Major results showed that the removal of the CT contrast enhancement component in the image processing resulted in the largest drop in framework performance, compared to the optimal performance (~12%). In the CNN part, all the three components (residual module, ROI attention, and skip attention) were approximately equally important to the framework performance; removing one of them resulted in a 3–5% decline in performance. The proposed CNN improved ~4% overall performance and ~350% computational efficiency, compared to the U-Net model. The deep convolutional neural network, in conjunction with image processing for feature enhancement, is capable of feature extraction from CT images for pulmonary perfusion synthesis. In the proposed framework, image processing, especially CT contrast enhancement, plays a crucial role in the perfusion synthesis. This CTPM framework provides insights for relevant research studies in the future and enables other researchers to leverage for the development of optimized CNN models for functional lung avoidance radiation therapy.

show abstract

Section: Methodsmentioning

confidence: 99%

Investigation of a Novel Deep Learning-Based Computed Tomography Perfusion Mapping Framework for Functional Lung Avoidance Radiotherapy

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The signal intensity of a lung SPECT image is strongly affected by the patient's condition, such as the respiratory capacity, frequency, diseases, etc. To ensure the perfusion value is comparable between patients, the SPECT perfusion was normalized to the 75th percentile value for each image, as this is close to the perfusion value of normal-functioning lung tissue (25). The CT-based perfusion images were then compared with the SPECT perfusion images via multi-level evaluations, including voxel-wise correlation, function-wise similarity, and lobe-wise agreement.…”

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

confidence: 99%

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

Ren

Lam

et al. 2022

Front. Oncol.

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

“…Q SPECT is performed with 99m Tc-MAA [77][78][79]. Studies have shown that local changes in Q scans correlate with radiation-induced lung damage from EBRT [80][81][82][83][84], and have noted the value of pre-treatment Q scans in the radiotherapy planning and the prediction of lung injury [85][86][87][88], with efforts made to also incorporate V scan data [89]. Recently, with the advent of V/Q PET, using 6 8 Ga-tagged Fig.…”

Section: Lungsmentioning

confidence: 99%

The increasing potential of nuclear medicine imaging for the evaluation and reduction of normal tissue toxicity from radiation treatments

Mohan

Bruin

Kamer

et al. 2021

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

Radiation therapy is an effective treatment modality for a variety of cancers. Despite several advances in delivery techniques, its main drawback remains the deposition of dose in normal tissues which can result in toxicity. Common practices of evaluating toxicity, using questionnaires and grading systems, provide little underlying information beyond subjective scores, and this can limit further optimization of treatment strategies. Nuclear medicine imaging techniques can be utilised to directly measure regional baseline function and function loss from internal/external radiation therapy within normal tissues in an in vivo setting with high spatial resolution. This can be correlated with dose delivered by radiotherapy techniques to establish objective dose-effect relationships, and can also be used in the treatment planning step to spare normal tissues more efficiently. Toxicity in radionuclide therapy typically occurs due to undesired off-target uptake in normal tissues. Molecular imaging using diagnostic analogues of therapeutic radionuclides can be used to test various interventional protective strategies that can potentially reduce this normal tissue uptake without compromising tumour uptake. We provide an overview of the existing literature on these applications of nuclear medicine imaging in diverse normal tissue types utilising various tracers, and discuss its future potential.

show abstract

Spect perfusion imaging versus CT for predicting radiation injury to normal lung in lung cancer patients

Cited by 12 publications

References 30 publications

Investigation of a Novel Deep Learning-Based Computed Tomography Perfusion Mapping Framework for Functional Lung Avoidance Radiotherapy

Investigation of a Novel Deep Learning-Based Computed Tomography Perfusion Mapping Framework for Functional Lung Avoidance Radiotherapy

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

The increasing potential of nuclear medicine imaging for the evaluation and reduction of normal tissue toxicity from radiation treatments

Contact Info

Product

Resources

About