• Advances in nano research
• /
• v.12 no.2
• /
• pp.185-195
• /
• 2022

Deep learning is another field of artificial intelligence (AI) utilized for computer aided diagnosis (CAD) and image processing in scientific research. Considering numerous mechanical repetitive tasks, reading image slices need time and improper with geographical limits, so the counting of image information is hard due to its strong subjectivity that raise the error ratio in misdiagnosis. Regarding the highest mortality rate of Lung cancer, there is a need for biopsy for determining its class for additional treatment. Deep learning has recently given strong tools in diagnose of lung cancer and making therapeutic regimen. However, identifying the pathological lung cancer's class by CT images in beginning phase because of the absence of powerful AI models and public training data set is difficult. Convolutional Neural Network (CNN) was proposed with its essential function in recognizing the pathological CT images. 472 patients subjected to staging FDG-PET/CT were selected in 2 months prior to surgery or biopsy. CNN was developed and showed the accuracy of 87%, 69%, and 69% in training, validation, and test sets, respectively, for T1-T2 and T3-T4 lung cancer classification. Subsequently, CNN (or deep learning) could improve the CT images' data set, indicating that the application of classifiers is adequate to accomplish better exactness in distinguishing pathological CT images that performs better than few deep learning models, such as ResNet-34, Alex Net, and Dense Net with or without Soft max weights.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.322-323
• /
• 2002

Partial volume averaging effect of PET data influences on the accuracy of quantitative measurements of regional brain metabolism because spatial resolution of PET is limited. The purpose of this study was to evaluate the accuracy of partial volume correction carried out on $^{18}$ F-PET images using Hoffman brain phantom. $^{18}$ F-PET Hoffman phantom images were co-registered to MR slices of the same phantom. All the MR slices of the phantom were then segmented to be binary images. Each of these binary images was convolved in 2 dimensions with the spatial resolution of the PET. The original PET images were then divided by the smoothed binary images in slice-by-slice, voxel-by-voxel basis resulting in larger PET image volume in size. This enlarged partial volume corrected PET image volume was multiplied by original binary image volume to exclude extracortical region. The evaluation of partial volume corrected PET image volume was performed by region of interests (ROI) analysis applying ROIs, which were drawn on cortical regions of the original MR image slices, to corrected and original PET image volume. From the ROI analysis, range of regional mean values increases of partial volume corrected PET images was 4 to 14%, and average increase for all the ROIs was about 10% in this phantom study. Hoffman brain phantom study was useful for the objective evaluation of the partial volume correction method. This MR-based correction method would be applicable to patients in the. quantitative analysis of FDG-PET studies.

• Korean Journal of Radiology
• /
• v.22 no.9
• /
• pp.1497-1513
• /
• 2021

The diagnostic and treatment methods of multiple myeloma (MM) have been rapidly evolving owing to advances in imaging techniques and new therapeutic agents. Imaging has begun to play an important role in the management of MM, and international guidelines are frequently updated. Since the publication of 2015 International Myeloma Working Group (IMWG) criteria for the diagnosis of MM, whole-body magnetic resonance imaging (MRI) or low-dose whole-body computed tomography (CT) and ¹⁸F-fluorodeoxyglucose positron emission tomography/CT have entered the mainstream as diagnostic and treatment response assessment tools. The 2019 IMWG guidelines also provide imaging recommendations for various clinical settings. Accordingly, radiologists have become a key component of MM management. In this review, we provide an overview of updates in the MM field with an emphasis on imaging modalities.

• Korean Journal of Radiology
• /
• v.22 no.5
• /
• pp.714-724
• /
• 2021

Objective: To evaluate the value of ¹⁸F-fluorodeoxyglucose PET/MRI added to contrast-enhanced CT (CECT) in initial staging, assessment of resectability, and postoperative follow-up of biliary tract cancer. Materials and Methods: This retrospective study included 100 patients (initial workup [n = 65] and postoperative follow-up [n = 35]) who had undergone PET/MRI and CECT for bile duct or gallbladder lesions between January 2013 and March 2020. Two radiologists independently reviewed the CECT imaging set and CECT plus PET/MRI set to determine the likelihood of malignancy, local and overall resectability, and distant metastasis in the initial workup group, and local recurrence and distant metastasis in the follow-up group. Diagnostic performances of the two imaging sets were compared using clinical-surgical-pathologic findings as standards of reference. Results: The diagnostic performance of CECT significantly improved after the addition of PET/MRI for liver metastasis (area under the receiver operating characteristic curve [A_z]: 0.77 vs. 0.91 [p = 0.027] for reviewer 1; 0.76 vs. 0.92 [p = 0.021] for reviewer 2), lymph node metastasis (0.73 vs. 0.92 [p = 0.004]; 0.81 vs. 0.92 [p = 0.023]), and overall resectability (0.79 vs. 0.92 [p = 0.007]; 0.82 vs. 0.94 [p = 0.021]) in the initial workup group. In the follow-up group, the diagnostic performance of CECT plus PET/MRI was significantly higher than that of CECT imaging for local recurrence (0.81 vs. 1.00 [p = 0.029]; 0.82 vs. 0.94 [p = 0.045]). Conclusion: PET/MRI may add value to CECT in patients with biliary tract cancer both in the initial workup for staging and determination of overall resectability and in follow-up for local recurrence.

• Korean Journal of Radiology
• /
• v.24 no.6
• /
• pp.574-589
• /
• 2023

Radiopharmaceuticals targeting prostate-specific membrane antigens (PSMA) are essential for the diagnosis, evaluation, and treatment of prostate cancer (PCa), particularly metastatic castration-resistant PCa, for which conventional treatment is ineffective. These molecular probes include [⁶⁸Ga]PSMA, [¹⁸F]PSMA, [Al¹⁸F]PSMA, [^99mTc]PSMA, and [⁸⁹Zr]PSMA, which are widely used for diagnosis, and [¹⁷⁷Lu]PSMA and [²²⁵Ac]PSMA, which are used for treatment. There are also new types of radiopharmaceuticals. Due to the differentiation and heterogeneity of tumor cells, a subtype of PCa with an extremely poor prognosis, referred to as neuroendocrine prostate cancer (NEPC), has emerged, and its diagnosis and treatment present great challenges. To improve the detection rate of NEPC and prolong patient survival, many researchers have investigated the use of relevant radiopharmaceuticals as targeted molecular probes for the detection and treatment of NEPC lesions, including DOTA-TOC and DOTA-TATE for somatostatin receptors, 4A06 for CUB domain-containing protein 1, and FDG. This review focused on the specific molecular targets and various radionuclides that have been developed for PCa in recent years, including those mentioned above and several others, and aimed to provide valuable up-to-date information and research ideas for future studies.

• Journal of radiological science and technology
• /
• v.30 no.4
• /
• pp.373-379
• /
• 2007

Purpose : There is difference between PET and PET/CT method on their transmission image for attenuation correction. The CT image is used for attenuation correction on PET/CT and the parameters of CT may be affected on PET image. We performed the phantom study to evaluate whether the change of CT parameters(kilovolts peak and milliampere) affect standardized uptake value(SUV) on PET image. Material and Method: The data spectrum lung phantom containing diluted [18F]fluorodeoxyglucose ([18F]FDG) solution(1.909 mCi for phantom 1, $913\;{\mu}Ci$ for phantom 2) was used. The CT images of phantom were acquired with varying parameters (80, 100, 120, 140 for kVp, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100 for mA). The PET images were reconstructed with the each CT images and SUVs were compared. Result : The SUVs of phantom 1 reconstructed with each 80, 100, 120 and 140 kVp showed $12.26{\pm}0.009$, $12.27{\pm}0.005$, $12.27{\pm}0.006$ and $12.27{\pm}0.009$, respectively. The SUVs of phantom 2 revealed $4.52{\pm}0.043$, $4.53{\pm}0.004$, $4.52{\pm}0.007$ and $4.52{\pm}0.005$ with elevation of voltage. There was no statistically significant difference of SUVs between groups based on various kVp. Also SUVs of phantom 1 and 2 showed no significant change with elevation of milliampere in CT parameter. Conclusion : The parameters of CT did not significantly affect SUV on PET image in our study. Therefore we can apply various parameters of CT appropriated for clinical conditions without significant change of SUV on PET CT image.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.15 no.2
• /
• pp.13-20
• /
• 2011

Purpose: The limited FOV(Field of View) of CT (Computed Tomography) can cause truncation artifact at external DFOV (Display Field of View) in PET/CT image. In our study, we measured the difference of SUV and compared the influence affecting to the image reconstructed with the extended DFOV. Materials and Methods: NEMA 1994 PET Phantom was filled with $^{18}F$(FDG) of 5.3 kBq/mL and placed at the center of FOV. Phantom images were acquired through emission scan. Shift the phantom's location to the external edge of DFOV and images were acquired with same method. All of acquired data through each experiment were reconstructed with same method, DFOV was applied 50 cm and 70 cm respectively. Then ROI was set up on the emission image, performed the comparative analysis SUV. In the clinical test, patient group shown truncation artifact was selected. ROI was set up at the liver of patient's image and performed the comparative analysis SUV according to the change of DFOV. Results: The pixel size was increase from 3.91 mm to 5.47 mm according to the DFOV increment in the centered location phantom study. When extended DFOV was applied, $_{max}SUV$ of ROI was decreased from 1.49 to 1.35. In case of shifted the center of phantom location study, $_{max}SUV$ was decreased from 1.30 to 1.20. The $_{max}SUV$ was 1.51 at the truncated region in the extended DFOV. The difference of the $_{max}SUV$ was 25.9% higher at the outside of the truncated region than inside. When the extended DFOV was applied, $_{max}SUV$ was decreased from 3.38 to 3.13. Conclusion: When the extended DFOV was applied, $_{max}SUV$ decreasing phenomenon can cause pixel to pixel noise by increasing of pixel size. In this reason, $_{max}SUV$ was underestimated. Therefore, We should consider the underestimation of quantitative result in the whole image plane in case of patient study applied extended DFOV protocol. Consequently, the result of the quantitative analysis may show more higher than inside at the truncated region.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.15 no.2
• /
• pp.94-98
• /
• 2011

Purpose: The radiation exposure from radioisotope at the hands and foots of radiation workers who works in PET/CT part at the department of nuclear medicine was investigated in this study. Materials and Methods: From 4th August 2010 to 14th January 2011, 6 radio-technologists' radiation on hands and feet were measured. All radio-technologist have been examined around 8; morning, 12; afternoon, and 16 o'clock; evening, respectively. SPSS version 17 was used for statistical analysis. Results: The statistical significances were calculated in several ways. The radiation from both hands and feet in the Morning was lower than Afternoon and Evening. In some cases, the detected radiation showed extremely high values in data. In order to find the effect of the ${\gamma}$-ray on the hand, the estimated doses were presumably calculated, however, the exposure dose on feet were unmeasured. Conclusion: Even if the radiation exposure from the radioisotope at the hands and feet were under the limitations, it is definitely needs to prevent the radiation-contamination. Therefore, the radio-technologists need to have a proper radiation-dealing-procedure of their own, and must try to prevent a radiation exposure by themselves.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.15 no.2
• /
• pp.47-52
• /
• 2011

Purpose: Facilities use own sever or mini PACS system for storage and analysis of the PET/CT data. Mini PACS can storage scan data as well as measuring SUV. Therefore, the study was performed to confirm whether or not measured SUV on mini PACS is measured equally on PET/CT workstation. Materials and Methods: In February 2011, 30 patients who were performed $^{18}F$-FDG wholebody PET/CT scan in Biograph 16, Biograph 40 and Discovery Ste 8 were enrolled. First, using each workstation, SUV in liver and aorta of mediastinum level was measured. Second, using mini PACS, SUV was measured by same method. Result: The correlation coefficient of SUV in liver between PET/CT scanner and min PACS in Biograph 16, Biograph 40, Discovery Ste 8 was 0.99, 0.98, 0.64 respectably, the correlation coefficient of SUV in aorta was 0.98, 0.98, 0.66, and these were showed positive correlation coefficient. Difference of SUV between Biograph workstation and mini PACS was not showed statistical significant difference at 5% level of significance. Difference of SUV between Discovery Ste 8 workstation and mini PACS was showed statistical significant difference at 5% level of significance. Conclusion: In case that patient was scanned by the other scanner, if the correction of SUV formula in mini PACS for each scanners is performed, mini PACS will be usefully used to provide consistently quantitative assessment.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.19 no.2
• /
• pp.63-67
• /
• 2015

Purpose Among various causes that influence image quality degradation, various methods for decrease in Artifact occurred by respiration of patients are being used. Among them, this study intended to evaluate CTAC Shift correction method and additional scan compare to the Scan(Q static scan) using respiratory gated system. Materials and Methods This study was conducted on 10 patients, and used PET-CT Discovery 710 (GE Healthcare, MI, USA) and Varian's RPM system. 5.18 Mbq per kg of $^{18}F$-FDG was injected on patients, asked them to take a rest for 1 hour in the bed, and conducted test after urination. Images were visualized through Q static scan, CTAC Shift correction method, Additional scan based on the Whole body scan(WBS) with Artifact. Decrease in Artifact was compared in each image, conducted Gross Evalution, and measured changes of SUVmax. Results For image obtained through the CTAC Shift correction method through WBS with Artifact, 12~56%, Q static scan image showed 17~54% of change rate and Additional Scan showed -27~46% of change rate. In Blind Test, the CTAC Shift correction image showed the highest point with 4 points, Q static scan image showed 3.5 points, and Additional scan image showed 3.4 points. The standardized WBS scan through Oneway ANOVA and three types of Scan method showed significant difference(p<0.05), and did not show significant difference between the three Scan methods(p>0.05). However, the three Scan methods showed significant difference in Blind test. Conclusion Additional scan and Q static scan require more time than the CTAC Shift correction method, there is concern about excessive exposure to patients by CT rescan and Q static scan is difficult to apply on patients with inconsistent respiration or irregular respiration cycle due to pain. For CTAC Shift correction method, limited correction is possible and the range is limited as well. It is considered as a useful method of improving diagnostic value when hospitals use the system appropriately and develop various advantageous factors of each method.