METHOD: Two large datasets, including 1110 3D CT images, were split into five segments of 20% each. Each dataset's first 20% segment was separated as a holdout test set. 3D-CNN training was performed with the remaining 80% from each dataset. Two small external datasets were also used to independently evaluate the trained models.
RESULTS: The total combination of 80% of each dataset has an accuracy of 91% on Iranmehr and 83% on Moscow holdout test datasets. Results indicated that 80% of the primary datasets are adequate for fully training a model. The additional fine-tuning using 40% of a secondary dataset helps the model generalize to a third, unseen dataset. The highest accuracy achieved through transfer learning was 85% on LDCT dataset and 83% on Iranmehr holdout test sets when retrained on 80% of Iranmehr dataset.
CONCLUSION: While the total combination of both datasets produced the best results, different combinations and transfer learning still produced generalizable results. Adopting the proposed methodology may help to obtain satisfactory results in the case of limited external datasets.
MATERIALS AND METHODS: Between March 2011 and May 2012, 20 patients were treated with 55 fractions of brachytherapy using tandem and ovoids and underwent post-implant CT scans. The external beam radiotherapy (EBRT) dose was 48.6 Gy in 27 fractions. HDR brachytherapy was delivered to a dose of 21 Gy in three fractions. The ICRU bladder and rectum point doses along with 4 additional rectal points were recorded. The maximum dose (DMax) to rectum was the highest recorded dose at one of these five points. Using the HDR plus 2.6 brachytherapy treatment planning system, the bladder and rectum were retrospectively contoured on the 55 CT datasets. The DVHs for rectum and bladder were calculated and the minimum doses to the highest irradiated 2cc area of rectum and bladder were recorded (D2cc) for all individual fractions. The mean D2cc of rectum was compared to the means of ICRU rectal point and rectal DMax using the Student's t-test. The mean D2cc of bladder was compared with the mean ICRU bladder point using the same statistical test .The total dose, combining EBRT and HDR brachytherapy, were biologically normalized to the conventional 2 Gy/fraction using the linear-quadratic model. (α/β value of 10 Gy for target, 3 Gy for organs at risk).
RESULTS: The total prescribed dose was 77.5 Gy α/β10. The mean dose to the rectum was 4.58 ± 1.22 Gy for D 2cc, 3.76 ± 0.65 Gy at D ICRU and 4.75 ± 1.01 Gy at DMax. The mean rectal D 2cc dose differed significantly from the mean dose calculated at the ICRU reference point (p<0.005); the mean difference was 0.82 Gy (0.48 -1.19 Gy). The mean EQD2 was 68.52 ± 7.24 Gy α/β3 for D 2cc, 61.71 ± 2.77 Gy α/β3 at D ICRU and 69.24 ± 6.02 Gy α/β3 at DMax. The mean ratio of D 2cc rectum to D ICRU rectum was 1.25 and the mean ratio of D 2cc rectum to DMax rectum was 0.98 for all individual fractions. The mean dose to the bladder was 6.00 ± 1.90 Gy for D 2cc and 5.10 ± 2.03 Gy at D ICRU. However, the mean D 2cc dose did not differ significantly from the mean dose calculated at the ICRU reference point (p=0.307); the mean difference was 0.90 Gy (0.49-1.25 Gy). The mean EQD2 was 81.85 ± 13.03 Gy α/β3 for D 2cc and 74.11 ± 19.39 Gy α/β3 at D ICRU. The mean ratio of D 2cc bladder to D ICRU bladder was 1.24. In the majority of applications, the maximum dose point was not the ICRU point. On average, the rectum received 77% and bladder received 92% of the prescribed dose.
CONCLUSIONS: OARs doses assessed by DVH criteria were higher than ICRU point doses. Our data suggest that the estimated dose to the ICRU bladder point may be a reasonable surrogate for the D 2cc and rectal DMax for D 2cc. However, the dose to the ICRU rectal point does not appear to be a reasonable surrogate for the D 2cc.
METHODS: This is a retrospective observational study where 25 male in-patients with laboratory-confirmed COVID-19 in Hospital Canselor Tuanku Muhriz. Demographics, clinical data and CT images of these patients were reviewed by 2 senior radiologists.
RESULTS: In total there were 25 patients (all males; mean age [±SD], 21.64±2.40 years; range, 18-27 years). Patients with abnormal chest CT showed a relatively low normal absolute lymphocytes count (median: 2.2 x 109/L) and absolute monocyte count (median: 0.5 x 109/L). Lactate dehydrogenase was elevated in 5 (20%) of the patients. The procalcitonin level was normal while elevated levels of alanine aminotransferase, total bilirubin, platelet and C-reactive protein were common. Baseline chest CT showed abnormalities in 6 patients. The distribution of the lesions were; upper lobe 3 (12%) lower lobe 3 (12%) with peripheral distribution 4 (16%). Of the 25 patients included, 4 (16%) had ground glass opacification (GGO), 1 (4%) had a small peripheral subpleural nodule, and 1 (4%) had a dense solitary granuloma. Four patients had typical CT features of COVID-19.
CONCLUSION: We found that the CT imaging showed peripheral GGO in our patients. They remained clinically stable with no deterioration of their respiratory symptoms suggesting stability in lung involvement. We postulate that rapid changes in CT imaging may not be present in young, asymptomatic, non-smoking COVID-19 patients. Thus the use of CT thoraxfor early diagnosis may be reserved for patients in the older agegroups, and not in younger patients.
METHODS: We reviewed children aged
METHODS: In total, 154 patients (wild-type EGFR, 72 patients; Del19 mutation, 45 patients; and L858R mutation, 37 patients) were retrospectively enrolled and randomly divided into 92 training and 62 test cases. Two support vector machine (SVM) models to distinguish between wild-type and mutant EGFR (mutation [M] classification) as well as between the Del19 and L858R subtypes (subtype [S] classification) were trained using 3DBN features. These features were computed from 3DBN maps by using histogram and texture analyses. The 3DBN maps were generated using computed tomography (CT) images based on the Čech complex constructed on sets of points in the images. These points were defined by coordinates of voxels with CT values higher than several threshold values. The M classification model was built using image features and demographic parameters of sex and smoking status. The SVM models were evaluated by determining their classification accuracies. The feasibility of the 3DBN model was compared with those of conventional radiomic models based on pseudo-3D BN (p3DBN), two-dimensional BN (2DBN), and CT and wavelet-decomposition (WD) images. The validation of the model was repeated with 100 times random sampling.
RESULTS: The mean test accuracies for M classification with 3DBN, p3DBN, 2DBN, CT, and WD images were 0.810, 0.733, 0.838, 0.782, and 0.799, respectively. The mean test accuracies for S classification with 3DBN, p3DBN, 2DBN, CT, and WD images were 0.773, 0.694, 0.657, 0.581, and 0.696, respectively.
CONCLUSION: 3DBN features, which showed a radiogenomic association with the characteristics of the EGFR Del19/L858R mutation subtypes, yielded higher accuracy for subtype classifications in comparison with conventional features.