This study aims to investigate the maximum achievable dose reduction for applying a new deep learning-based reconstruction algorithm, namely the artificial intelligence iterative reconstruction (AIIR), in computed tomography (CT) for hepatic lesion detection. A total of 40 patients with 98 clinically confirmed hepatic lesions were retrospectively included. The mean volume CT dose index was 13.66 ± 1.73 mGy in routine-dose portal venous CT examinations, where the images were originally obtained with hybrid iterative reconstruction (HIR). Low-dose simulations were performed in projection domain for 40%-, 20%-, and 10%-dose levels, followed by reconstruction using both HIR and AIIR. Two radiologists were asked to detect hepatic lesion on each set of low-dose image in separate sessions. Qualitative metrics including lesion conspicuity, diagnostic confidence, and overall image quality were evaluated using a 5-point scale. The contrast-to-noise ratio (CNR) for lesion was also calculated for quantitative assessment. The lesion CNR on AIIR at reduced doses were significantly higher than that on routine-dose HIR (all p < 0.05). Lower qualitative image quality was observed as the radiation dose reduced, while there were no significant differences between 40%-dose AIIR and routine-dose HIR images. The lesion detection rate was 100%, 98% (96/98), and 73.5% (72/98) on 40%-, 20%-, and 10%-dose AIIR, respectively, whereas it was 98% (96/98), 73.5% (72/98), and 40% (39/98) on the corresponding low-dose HIR, respectively. AIIR outperformed HIR in simulated low-dose CT examinations of the liver. The use of AIIR allows up to 60% dose reduction for lesion detection while maintaining comparable image quality to routine-dose HIR.

To explore the cycle characteristics and pregnancy outcomes of progestin-primed ovarian stimulation (PPOS) using fixed versus degressive doses of medroxyprogesterone acetate (MPA) in conjunction with letrozole (LE) in infertile women by propensity score matching (PSM) analysis.
A retrospective cohort study.
Tertiary-care academic medical center.
A total of 3173 infertile women undergoing their first in vitro fertilization/intracytoplasmic sperm injection (IVF/ICSI) treatment within the period from January 2017 to December 2020.
A total of 1068 and 783 patients who underwent a fixed dose of MPA combined with LE and a degressive dose of MPA combined with LE protocols, respectively, were enrolled in this study. The freeze-all approach and later frozen-thawed embryo transfer (FET) were performed in both groups. Propensity score matching (1:1) was performed.
The primary outcomes were the dosage of MPA and the incidence of premature luteinizing hormone (LH) surges. The secondary outcomes were the number of oocytes retrieved, the cumulative live birth rate (CLBR) and the fetal malformation rate.
We created a perfect match of 478 patients in each group. The dosage of MPA, the LH serum level on the eighth day of stimulation, progesterone (P) level and LH level on the hCG trigger day were significantly higher in the LE + fixed MPA group than in the LE + degressive MPA group (52.1 ± 13.1 mg vs. 44.9 ± 12.5 mg; 5.0 ± 2.7 IU/L vs. 3.7 ± 1.7 IU/L; 0.9 ± 0.5 ng/ml vs. 0.8 ± 0.5 ng/ml; 3.3 ± 2.4 IU/L vs. 2.8 ± 1.9 IU/L; P < 0.01). The duration of Gn, the number of follicles with diameter more than 16 mm on trigger day, the estradiol (E2) level on the hCG trigger day were lower in the LE + fixed MPA group than in the LE + degressive MPA group (9.7 ± 1.7 days vs. 10.3 ± 1.5 days; 5.6 ± 3.0 vs. 6.3 ± 3.0; 1752.5 ± 1120.8 pg/ml vs. 1997.2 ± 1108.5 pg/ml; P < 0.001). No significant difference was found in the incidence of premature LH surge, the number of oocytes retrieved, the number of top-quality embryos, clinical pregnancy rate (CPR), CLBR or fetal malformation rate between the two groups.
The combination of a degressive MPA dose with LE proved effective in reducing the total MPA dosage with comparable premature LH surge and pregnancy outcomes in women undergoing the PPOS protocol.

The aim of this phantom study was to assess the detectability and volumetric accuracy of pulmonary nodules on photon-counting detector CT (PCD-CT) at different low-dose levels compared to conventional energy-integrating detector CT (EID-CT). In-house fabricated artificial nodules of different shapes (spherical, lobulated, spiculated), sizes (2.5-10 mm and 5-1222 mm3), and densities (-330 HU and 100 HU) were randomly inserted into an anthropomorphic thorax phantom. The phantom was scanned with a low-dose chest protocol with PCD-CT and EID-CT, in which the dose with PCD-CT was lowered from 100% to 10% with respect to the EID-CT reference dose. Two blinded observers independently assessed the CT examinations of the nodules. A third observer measured the nodule volumes using commercial software. The influence of the scanner type, dose, observer, physical nodule volume, shape, and density on the detectability and volumetric accuracy was assessed by a multivariable regression analysis. In 120 CT examinations, 642 nodules were present. Observer 1 and 2 detected 367 (57%) and 289 nodules (45%), respectively. With PCD-CT and EID-CT, the nodule detectability was similar. The physical nodule volumes were underestimated by 20% (range 8-52%) with PCD-CT and 24% (range 9-52%) with EID-CT. With PCD-CT, no significant decrease in the detectability and volumetric accuracy was found at dose reductions down to 10% of the reference dose (p > 0.05). The detectability and volumetric accuracy were significantly influenced by the observer, nodule volume, and a spiculated nodule shape (p < 0.05), but not by dose, CT scanner type, and nodule density (p > 0.05). Low-dose PCD-CT demonstrates potential to detect and assess the volumes of pulmonary nodules, even with a radiation dose reduction of up to 90%.

The benefits of TDM-guided TNFi therapy in patients with rheumatic disease was still controversial. This systematic review and meta-analysis was conducted to explore if the TDM-guided TNFi therapy is superior to empirical-guided therapy.
We systematically searched PubMed, Web of Science, Cochrane Library, and EMBASE databases for articles published between database inception and October 05, 2023. Studies reporting endpoints in TDM-guided TNFi therapy and empirical therapy were included. Results would be presented in risk ratio (RR) and mean difference, with 95 % confidence interval (CI) reported. This study is registered with PROSPERO (CRD42022353956).
A total of 14 studies (eight RCTs and six cohort studies) involving 2427 patients were included in this meta-analysis. In the scenario of response prediction, compared with empirical-guided therapy, TDM-guided TNFi therapy had association with higher treat-to-target rates (RR 1.30, 95 % CI 1.02-1.65, P=0.03, I2=79 %), more specifically, higher low disease activity rates (RR 2.11, 95 % CI 1.22-3.66, P=0.007, I2=61 %), but no difference in clinical remission rates (RR 0.98,95 % CI 0.87-1.11, P=0.75, I2=0 %). In the scenario of dose reduction prediction, lower relapse rates (RR 0.73, 95 % CI 0.65-0.82, P <0.00001, I2=0 %) were observed compared with empirical-guided dose reduction strategy, but no difference (RR 1.24, 95 % CI 0.85-1.80, P=0.27, I2=57 %) between TDM-guided dose reduction and standard-dosing therapy. No significant difference was observed in change of disease activity score, mean disease activity score, radiographic progression, and safety. And TDM-guided therapy was associated with reduced cost per patient per year calculated as the total accumulated sum of therapy cost.
TDM-guided TNFi therapy was associated with increased rates of low disease activity and decreased risks of relapse, and may save cost compared with empirical-guided therapy in patients with rheumatic disease. But this does not mean that the use of TDM-guided TNFi therapy can be advocated, because there is no difference in clinical remission rates and many other outcomes. More researches, especially randomized clinical trials are needed to verify this conclusion in the future.

Objective. Reducing dose in positron emission tomography (PET) imaging increases noise in reconstructed dynamic frames, which inevitably results in higher noise and possible bias in subsequently estimated images of kinetic parameters than those estimated in the standard dose case. We report the development of a spatiotemporal denoising technique for reduced-count dynamic frames through integrating a cascade artificial neural network (ANN) with the highly constrained back-projection (HYPR) scheme to improve low-dose parametric imaging.Approach. We implemented and assessed the proposed method using imaging data acquired with11C-UCB-J, a PET radioligand bound to synaptic vesicle glycoprotein 2A (SV2A) in the human brain. The patch-based ANN was trained with a reduced-count frame and its full-count correspondence of a subject and was used in cascade to process dynamic frames of other subjects to further take advantage of its denoising capability. The HYPR strategy was then applied to the spatial ANN processed image frames to make use of the temporal information from the entire dynamic scan.Main results. In all the testing subjects including healthy volunteers and Parkinson\'s disease patients, the proposed method reduced more noise while introducing minimal bias in dynamic frames and the resulting parametric images, as compared with conventional denoising methods.Significance. Achieving 80% noise reduction with a bias of -2% in dynamic frames, which translates into 75% and 70% of noise reduction in the tracer uptake (bias, -2%) and distribution volume (bias, -5%) images, the proposed ANN+HYPR technique demonstrates the denoising capability equivalent to a 11-fold dose increase for dynamic SV2A PET imaging with11C-UCB-J.

To determine the relationship between chemotherapy dose delay/reduction with progression-free survival (PFS) and overall survival (OS) in colorectal cancer patients treated with FOLFIRI based first-line chemotherapy in real-world retrospectively study.
We identified 144 eligible patients with advanced CRC who received FOLFIRI as first-line based treatment. The study protocol was submitted to the institutional review board and was exempted. Dose delay was defined as an average delay of more than 3 days (>3 days vs. ≤3 days) from the intended date. Dose reduction (actual dose/standard dose * 100%) ≤85% was considered as chemotherapy reduction in the chemotherapy dose relative to the standard (mg/m2) regimen for all cycles. Relative dose intensity (RDI) ≤80% was described as chemotherapy reduction. OS and PFS were measured using Kaplan-Meier and Cox proportional hazard models.
There were 114 patients with chemotherapy dose delay (dose delay >3 days). PFS of patients without dose delay had better survival than patients with dose delay (p = 0.002). There were 28.47% patients treated with dose reduction of 5-Fu. PFS and OS were better in patients without 5-Fu dose reduction than in patients with 5-Fu dose reduction with p values of 0.024 and <0.001, respectively. Patients with high 5-FU RDI had better PFS than patients with low 5-FU RDI (p < 0.001). While, there was no statistical difference in OS between the two groups. Then we stratified the analysis by age. In <65 years cohort, both PFS and OS were better in patients with high 5-Fu RDI than in those with low 5-Fu RDI (p < 0.001, p = 0.005, respectively). But, in ≥65 years cohort, OS were better in patients with low 5-Fu RDI than in those with high 5-Fu RDI (p = 0.025). Moreover, both dose reduction and RDI of irinotecan had no statistically significant difference in both PFS and OS.
In the advanced colorectal cancer patients who received FOLFIRI based treatment as first-line regimen, chemotherapy dose delay and reduction dose of 5-Fu were associated with worse survival, especially among patients younger than 65 years.

A body of studies has proposed to obtain high-quality images from low-dose and noisy Computed Tomography (CT) scans for radiation reduction. However, these studies are designed for population-level data without considering the variation in CT devices and individuals, limiting the current approaches\' performance, especially for ultra-low-dose CT imaging. Here, we proposed PIMA-CT, a physical anthropomorphic phantom model integrating an unsupervised learning framework, using a novel deep learning technique called Cyclic Simulation and Denoising (CSD), to address these limitations. We first acquired paired low-dose and standard-dose CT scans of the phantom and then developed two generative neural networks: noise simulator and denoiser. The simulator extracts real low-dose noise and tissue features from two separate image spaces (e.g., low-dose phantom model scans and standard-dose patient scans) into a unified feature space. Meanwhile, the denoiser provides feedback to the simulator on the quality of the generated noise. In this way, the simulator and denoiser cyclically interact to optimize network learning and ease the denoiser to simultaneously remove noise and restore tissue features. We thoroughly evaluate our method for removing both real low-dose noise and Gaussian simulated low-dose noise. The results show that CSD outperforms one of the state-of-the-art denoising algorithms without using any labeled data (actual patients\' low-dose CT scans) nor simulated low-dose CT scans. This study may shed light on incorporating physical models in medical imaging, especially for ultra-low level dose CT scans restoration.

UNASSIGNED: To develop a deep learning approach that enables ultra-low-dose, 1% of the standard clinical dosage (3 MBq/kg), ultrafast whole-body PET reconstruction in cancer imaging.
UNASSIGNED: In this Health Insurance Portability and Accountability Act-compliant study, serial fluorine 18-labeled fluorodeoxyglucose PET/MRI scans of pediatric patients with lymphoma were retrospectively collected from two cross-continental medical centers between July 2015 and March 2020. Global similarity between baseline and follow-up scans was used to develop Masked-LMCTrans, a longitudinal multimodality coattentional convolutional neural network (CNN) transformer that provides interaction and joint reasoning between serial PET/MRI scans from the same patient. Image quality of the reconstructed ultra-low-dose PET was evaluated in comparison with a simulated standard 1% PET image. The performance of Masked-LMCTrans was compared with that of CNNs with pure convolution operations (classic U-Net family), and the effect of different CNN encoders on feature representation was assessed. Statistical differences in the structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and visual information fidelity (VIF) were assessed by two-sample testing with the Wilcoxon signed rank t test.
UNASSIGNED: The study included 21 patients (mean age, 15 years ± 7 [SD]; 12 female) in the primary cohort and 10 patients (mean age, 13 years ± 4; six female) in the external test cohort. Masked-LMCTrans-reconstructed follow-up PET images demonstrated significantly less noise and more detailed structure compared with simulated 1% extremely ultra-low-dose PET images. SSIM, PSNR, and VIF were significantly higher for Masked-LMCTrans-reconstructed PET (P < .001), with improvements of 15.8%, 23.4%, and 186%, respectively.
UNASSIGNED: Masked-LMCTrans achieved high image quality reconstruction of 1% low-dose whole-body PET images.Keywords: Pediatrics, PET, Convolutional Neural Network (CNN), Dose Reduction Supplemental material is available for this article. © RSNA, 2023.

With the advent of tyrosine kinase inhibitors (TKIs), the treatment prospects of chronic myeloid leukemia (CML) have changed markedly. This innovation can lengthen the long-term survival of patients suffering from CML. However, long-term exposure to TKIs is accompanied by various adverse events (AEs). The latter affect the quality of life and compliance of patients with CML, and may lead to serious disease progression (and even death). Recently, increasing numbers of patients with CML have begun to pursue a dose optimization strategy. Dose optimization may be considered at all stages of the entire treatment, which includes dose reduction and discontinuation of TKIs therapy. In general, reduction of the TKI dose is considered to be an important measure to reduce AEs and improve quality of life on the premise of maintaining molecular responses. Furthermore, discontinuation of TKIs therapy has been demonstrated to be feasible and safe for about half of patients with a stable optimal response and a longer duration of TKI treatment. This review focuses mainly on the latest research of dose optimization of imatinib, dasatinib, and nilotinib in CML clinical trials and real-life settings. We consider dose reduction in newly diagnosed patients, or in optimal response, or for improving AEs, either as a prelude to treatment-free remission (TFR) or as maintenance therapy in those patients unable to discontinue TKIs therapy. In addition, we also focus on discontinuation of TKIs therapy and second attempts to achieve TFR.

Glucocorticoid (GC) remains the mainstay of treatment for cutaneous adverse drug reactions (cADRs) but has been associated with side effects, emphasizing the importance of precisely managing the duration of high-dose GC treatment. Although the platelet-to-lymphocyte ratio (PLR) has been proven to be closely related to inflammatory disorders, its ability to predict the timing of GC dose reduction (Tr) during cADRs treatment remains obscure.
Hospitalized patients diagnosed with cADRs treated with glucocorticoids were analyzed in the present study to evaluate the association between PLR values and Tr values using linear, locally weighted scatter plot smoothing (LOWESS) and Poisson regression. Subgroup and ROC curve analyses were conducted to identify confounding variables and assess the predictive performance, respectively.
A total of 308 patients were included in the study, with a median age of 47.0 (31.0-62.0) years old and a median incubation period of 4 days. Antibiotics (n = 113, 36.7%) were the most common cause of cADRs, followed by Chinese herbs (n = 76, 24.7%). PLR values were positively correlated with Tr values during linear regression (P < 0.001, r = 0.414) and LOWESS regression analyses. Poisson regression showed PLR was an independent risk factor for higher Tr values (the incidence rate ratio ranged from 1.016 to 1.070 and P < 0.05 for all). The area under the curve of PLR for predicting Tr < 7 days was 0.917.
PLR is a simple and convenient parameter with huge prospects for application as a biomarker to assist clinicians in optimally managing patients treated with glucocorticoid therapy for cADRs.