The promise of artificial intelligence and deep learning in PET and SPECT imaging

Arabi, Hossein; Akhavanallaf, Azadeh; Sanaat, Amirhossein; Shiri, Isaac; Zaidi, Habib

doi:10.1016/j.ejmp.2021.03.008

Cited by 183 publications

(72 citation statements)

References 157 publications

(177 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A number of studies have demonstrated the potential of radiomic analysis in survival analysis and prediction of treatment outcome [12][13][14][15][16]. Oikonomou et al [17] investigated the predictive power of radiomic features along with maximum standardized uptake value extracted from PET/CT images of lung cancer patients treated with stereotactic body radiotherapy (SBRT).…”

Section: Introductionmentioning

confidence: 99%

Overall Survival Prediction in Renal Cell Carcinoma Patients Using Computed Tomography Radiomic and Clinical Information

et al. 2021

Self Cite

View full text Add to dashboard Cite

The aim of this work is to investigate the applicability of radiomic features alone and in combination with clinical information for the prediction of renal cell carcinoma (RCC) patients’ overall survival after partial or radical nephrectomy. Clinical studies of 210 RCC patients from The Cancer Imaging Archive (TCIA) who underwent either partial or radical nephrectomy were included in this study. Regions of interest (ROIs) were manually defined on CT images. A total of 225 radiomic features were extracted and analyzed along with the 59 clinical features. An elastic net penalized Cox regression was used for feature selection. Accelerated failure time (AFT) with the shared frailty model was used to determine the effects of the selected features on the overall survival time. Eleven radiomic and twelve clinical features were selected based on their non-zero coefficients. Tumor grade, tumor malignancy, and pathology t-stage were the most significant predictors of overall survival (OS) among the clinical features (p < 0.002, < 0.02, and < 0.018, respectively). The most significant predictors of OS among the selected radiomic features were flatness, area density, and median (p < 0.02, < 0.02, and < 0.05, respectively). Along with important clinical features, such as tumor heterogeneity and tumor grade, imaging biomarkers such as tumor flatness, area density, and median are significantly correlated with OS of RCC patients.

show abstract

Section: Introductionmentioning

confidence: 99%

Overall Survival Prediction in Renal Cell Carcinoma Patients Using Computed Tomography Radiomic and Clinical Information

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent advances in artificial intelligence, specifically deep learning (DL), have revolutionized the domain of computer vision and image processing. In the context of medical imaging, DL has been successfully deployed in challenging tasks, such as image segmentation/interpretation, cross-modality image translation, image denoising, radiotherapy treatment planning, and outcome prediction [ 11 – 13 ].…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based fully automated Z-axis coverage range definition from scout scans to eliminate overscanning in chest CT imaging

et al. 2021

Self Cite

View full text Add to dashboard Cite

Background Despite the prevalence of chest CT in the clinic, concerns about unoptimized protocols delivering high radiation doses to patients still remain. This study aimed to assess the additional radiation dose associated with overscanning in chest CT and to develop an automated deep learning-assisted scan range selection technique to reduce radiation dose to patients. Results A significant overscanning range (31 ± 24) mm was observed in clinical setting for over 95% of the cases. The average Dice coefficient for lung segmentation was 0.96 and 0.97 for anterior–posterior (AP) and lateral projections, respectively. By considering the exact lung coverage as the ground truth, and AP and lateral projections as input, The DL-based approach resulted in errors of 0.08 ± 1.46 and − 1.5 ± 4.1 mm in superior and inferior directions, respectively. In contrast, the error on external scout views was − 0.7 ± 4.08 and 0.01 ± 14.97 mm for superior and inferior directions, respectively.The ED reduction achieved by automated scan range selection was 21% in the test group. The evaluation of a large multi-centric chest CT dataset revealed unnecessary ED of more than 2 mSv per scan and 67% increase in the thyroid absorbed dose. Conclusion The proposed DL-based solution outperformed previous automatic methods with acceptable accuracy, even in complicated and challenging cases. The generizability of the model was demonstrated by fine-tuning the model on AP scout views and achieving acceptable results. The method can reduce the unoptimized dose to patients by exclunding unnecessary organs from field of view.

show abstract

“…Therefore, Debasis Mitra developed a Spline Initialized Factor Analysis of Dynamic Structures (SIFADS) algorithm ( 41 ), which performed well in animal and human experiments and significantly reduced image noise and improved image quality. In addition, deep learning technology is developing rapidly and shows excellent potential in image acquisition and processing, which may be widely used in the future ( 42 ).…”

Section: Research Progress Of Imaging Methods For Detection Of Microvascular Angina Pectorismentioning

confidence: 99%

Research Progress of Imaging Methods for Detection of Microvascular Angina Pectoris in Diabetic Patients

Feng

et al. 2021

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Diabetes is a complex metabolic disease characterized by hyperglycemia. Its complications are various, often involving the heart, brain, kidney, and other essential organs. At present, the number of diabetic patients in the world is growing day by day. The cardiovascular disease caused by diabetes has dramatically affected the quality of life of diabetic patients. It is the leading cause of death of diabetic patients. Diabetic patients often suffer from microvascular angina pectoris without obstructive coronary artery disease. Still, there are typical ECG ischemia and angina pectoris, that is, chest pain and dyspnea under exercise. Unlike obstructive coronary diseases, nitrate does not affect chest pain caused by coronary microvascular angina in most cases. With the increasing emphasis on diabetic microvascular angina, the need for accurate diagnosis of the disease is also increasing. We can use SPECT, PET, CMR, MCE, and other methods to evaluate coronary microvascular function. SPECT is commonly used in clinical practice, and PET is considered the gold standard for non-invasive detection of myocardial blood flow. This article mainly introduces the research progress of these imaging methods in detecting microvascular angina in diabetic patients.

show abstract

The promise of artificial intelligence and deep learning in PET and SPECT imaging

Cited by 183 publications

References 157 publications

Overall Survival Prediction in Renal Cell Carcinoma Patients Using Computed Tomography Radiomic and Clinical Information

Overall Survival Prediction in Renal Cell Carcinoma Patients Using Computed Tomography Radiomic and Clinical Information

Deep learning-based fully automated Z-axis coverage range definition from scout scans to eliminate overscanning in chest CT imaging

Research Progress of Imaging Methods for Detection of Microvascular Angina Pectoris in Diabetic Patients

Contact Info

Product

Resources

About