Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy

This brief review summarizes the major applications of artificial intelligence (AI), in particular deep learning approaches, in molecular imaging and radiation therapy research. To this end, the applications of artificial intelligence in five generic fields of molecular imaging and radiation therapy, including PET instrumentation design, PET image reconstruction quantification and segmentation, image denoising (low-dose imaging), radiation dosimetry and computer-aided diagnosis, and outcome prediction are discussed. This review sets out to cover briefly the fundamental concepts of AI and deep learning followed by a presentation of seminal achievements and the challenges facing their adoption in clinical setting.

Quantification of Patient Specific Dosimetry in Radionuclide Therapy: A Phantom Study

The accuracy of patient specific dosimetry is correlated with measured organ activity by gamma camera and SPECT system. The assessment of the radiation-absorbed dose by patients undergoing nuclear medicine investigation requires accurate measurement of organ activity, biokinetics data, as well as physical data. Activities were estimated by using Ba-133 phantom with both planar and SPECT systems. The objective of the study was to measure the activities of Ba-133 from gamma camera images using both planar and SPECT studies and compare the reference values with the dose calibrator values to quantify the actual activity with gamma camera. Four Ba-133 sources of different volume and activity 379, 950, 1219 and 1150 KBq are measured by using Veenstra Instrument VDC 404 Dose Calibrator. The second smallest source was used to determine the calibration factor. Acquisition, corrections, reconstruction, quantification and measuring activity from both planar and SPECT imaging were done with all Ba-133 sources in air. The activities of the Ba-133 sources were also measured using I-131 settings of the dose calibrator. The measurement of the second smallest source was used to obtain the calibration factor. This calibration factor was used to convert the planer and SPECT image count of all the sources into activities. In case of both planar and SPECT gamma camera, the measurements showed good correlations and all the values varied within ±15%. Planer and SPECT gamma camera image counts can be used to calculate activity in the organ. This information can play a very significant role in evaluating image based patient specific dosimetry in radionuclide therapy.Bangladesh J. Nuclear Med. 17(2): 134-137, July 2014