Deep learning-based image quality assessment: impact on detection accuracy of prostate cancer extraprostatic extension on MRI.

OBJECTIVE: To assess impact of image quality on prostate cancer extraprostatic extension (EPE) detection on MRI using a deep learning-based AI algorithm. MATERIALS AND METHODS: This retrospective, single institution study included patients who were imaged with mpMRI and subsequently underwent radical prostatectomy from June 2007 to August 2022. One genitourinary radiologist prospectively evaluated each patient using the NCI EPE grading system. Each T2WI was classified as low- or high-quality by a previously developed AI algorithm. Fisher's exact tests were performed to compare EPE detection metrics between low- and high-quality images. Univariable and multivariable analyses were conducted to assess the predictive value of image quality for pathological EPE. RESULTS: A total of 773 consecutive patients (median age 61 [IQR 56-67] years) were evaluated. At radical prostatectomy, 23% (180/773) of patients had EPE at pathology, and 41% (131/318) of positive EPE calls on mpMRI were confirmed to have EPE. The AI algorithm classified 36% (280/773) of T2WIs as low-quality and 64% (493/773) as high-quality. For EPE grade ≥ 1, high-quality T2WI significantly improved specificity for EPE detection (72% [95% CI 67-76%] vs. 63% [95% CI 56-69%], P = 0.03), but did not significantly affect sensitivity (72% [95% CI 62-80%] vs. 75% [95% CI 63-85%]), positive predictive value (44% [95% CI 39-49%] vs. 38% [95% CI 32-43%]), or negative predictive value (89% [95% CI 86-92%] vs. 89% [95% CI 85-93%]). Sensitivity, specificity, PPV, and NPV for EPE grades ≥ 2 and ≥ 3 did not show significant differences attributable to imaging quality. For NCI EPE grade 1, high-quality images (OR 3.05, 95% CI 1.54-5.86; P < 0.001) demonstrated a stronger association with pathologic EPE than low-quality images (OR 1.76, 95% CI 0.63-4.24; P = 0.24). CONCLUSION: Our study successfully employed a deep learning-based AI algorithm to classify image quality of prostate MRI and demonstrated that better quality T2WI was associated with more accurate prediction of EPE at final pathology.

Supine Position Popliteal Vein Puncture Under Ultrasound Guidance Is a Feasible and Effective Strategy to Establish Venous Access.

BACKGROUND: This study aims to introduce the clinical application value of popliteal vein puncture in the supine position under ultrasound guidance and compare this method with popliteal vein puncture in the prone position. METHODS: Endovascular operations for nonthrombotic iliac vein lesion patients using popliteal vein access were performed during the period from July 2019 to August 2022 at the Zhongshan Hospital (Xiamen), Fudan University, and Shanghai Xuhui District Central Hospital. Patients were randomly divided into supine position group and prone position group. All of the patients were punctured under ultrasound guidance. The procedure duration time for popliteal vein puncture, visual analog scale (VAS) scores, and postoperative complications were recorded and compared between the 2 groups. RESULTS: Totally 120 patients were included in this study, in which 60 patients were enrolled in the supine position group and 60 patients were enrolled in the prone position group. The median procedure time from puncture to iliofemoral venography was 5.97 min (interquartile range 5.78 min-6.03 min) and 28.76 min (interquartile range 26.84 min-29.83 min; P < 0.01 (in the supine position and prone position group, respectively. The median time from puncture to access sheath insertion was 5.05 min (interquartile range 4.88 min-5.13 min) and 5.03 min (interquartile range 4.93 min-5.12 min; P = 0.607) in the supine position and prone position groups, respectively. The median VAS value was 3 (interquartile range 2-3) and 8 (interquartile range 7-9, P < 0.01) in the supine position and prone position groups, respectively. In the supine position group, one case of arterial branch injury was observed after operation and was successfully managed by ultrasound-guided compression. CONCLUSIONS: Popliteal vein puncture in the supine position under ultrasound guidance is safe, significantly reduces the overall operation time without changing position, and relieves the discomfort of patients.

Effects of Remifentanil Pretreatment on Sufentanil-induced Cough Suppression During the Induction of General Anesthesia.

PURPOSE: The aim of this study was to evaluate the effect of remifentanil pretreatment on sufentanil-induced cough during general anesthesia induction. DESIGN: This experimental research was conducted as a single-center, randomized, parallel-group trial. METHODS: A total of 120 patients scheduled for elective surgery were equally randomized into two groups (remifentanil and control). The incidence and severity of coughing in both groups were recorded after sufentanil administration during general anesthesia induction. The mean arterial pressure, heart rate, and pulse oxygen saturation were recorded at T1 (before the injection of remifentanil or normal saline), T2 (1 minute after remifentanil administration), T3 (before intubation), and T4 (1 minute after intubation). Additionally, the incidences of adverse events, including dizziness, nausea, apnea, truncal rigidity, bradycardia, or other adverse effects were also recorded. FINDINGS: The incidence of sufentanil-induced cough in the remifentanil group was significantly decreased when compared with the control group (5.0% vs 35.0%, respectively; P < .001). No statistical differences were found in mean arterial pressure, heart rate, pulse oxygen saturation, and the incidences of other side effects between the two groups at T1, T2, T3, and T4 (P > .05). CONCLUSIONS: Pretreatment with remifentanil at a dose of 0.5 mcg/kg can effectively and safely suppress the incidence and severity of sufentanil-induced coughing, providing a reference for medication during general anesthesia induction.

Bio-accessibility and bio-availability evaluation of each arsenic species existing in various edible seaweeds in vitro and in vivo for arsenic risk assessment.

Seaweeds consumption is one of main internal exposure sources of arsenic for human. However, the absence of representative bio-availabilities of arsenic species makes the accurate assessment of arsenic health risk originating from seaweeds consumption impossible. Herein, the arsenic species in various seaweeds collected from Fujian of China were investigated, and the bio-accessibilities/bio-availabilities of arsenic species existing in seaweeds were evaluated in vitro and in vivo. Results revealed that in vitro bio-availabilities of arsenic species presenting in seaweeds, which obtained with Caco-2 cells, were lower than those of pure arsenic standards, and varied with order of inorganic arsenic (iAs) > dimethylarsinic acid (DMA) ≈ arsenobetaine (AsB) > arsenosugars. During gastrointestinal digestion of mice, As5+ was partly methylated into monomethylarsonic acid (MMA) and DMA, which makes the in vivo bioavailability of iAs (⁓31.8 %) obtained with mouse metabolic experiment is much higher than its in vitro bio-availability (⁓10.3 %). The in vivo bio-availabilities of DMA and total arsenic (tAs) are similar to their in vitro bio-availabilities. As the dominant arsenic species in most seaweeds, arsenosugars have an ⁓0.0 % of in vivo bioavailability and only a ⁓3.7 % of in vitro bioavailability. The simulated calculation of target hazard quotient (THQ) and target cancer risk (TR) revealed that the arsenic risk originating from seaweeds was greatly degraded by taking into consideration of arsenic species and bio-availabilities, and all seaweeds collected from Fujian are safety for consumption. The simulated calculation also revealed that arsenic risk of seaweeds can be also more accurately assessed based on tAs together with bioavailability, which provides a simple but accurate and protective method for the risk assessment of arsenic originating from seaweeds. Our work provides the possible representative bio-availabilities of arsenic species presenting in seaweeds for accurately assessing arsenic risk of seaweeds, and novel insights into the bio-availabilities of arsenic in animal.

Telephone follow-up based on empowerment theory to improve resilience and quality of life among patients after coronary artery stent implantation: a randomized controlled trial.

Background: Coronary heart disease has a high incidence rate, a high mortality rate, a high recurrence rate, and a high medical cost. In addition, some patients need to undergo percutaneous coronary artery stent implantation (CASI), which is a kind of traumatic treatment. Patients can easily experience negative emotions such as anxiety and depression after surgery, which seriously affects quality of life. Objectives: The aim of this study was to evaluate the effectiveness of an empowerment-based telephone follow-up intervention on resilience and quality of life in patients who underwent CASI. Design: The design of the study is a randomized controlled trial. Methods: A total of 92 patients were recruited after CASI from the Internal Medicine Cardiovascular Department of a Grade A tertiary hospital in Xi'an, China. The patients were randomly divided into a control group and an intervention group. The control group performed routine care, whereas the intervention group developed a telephone follow-up program based on empowerment theory while carrying out routine care. Patients were investigated using the coronary heart disease-related knowledge questionnaire, the Connor-Davidson Resilience Scale (CD-RISC), and the 36-Item Short-Form Health Survey (SF-36) to compare the effects of the intervention before and after 1 month of intervention. Results: After a 1-month telephone follow-up intervention based on the empowerment theory for patients after CASI, the variations in knowledge related to coronary heart disease and all of its subscale scores were greater in the intervention group than in the control group. Except for the three dimensions of risk factor, induction factor, and rehabilitation-related knowledge, the variations in knowledge related to coronary heart disease and the other subscale scores were significantly different between the two groups (p < 0.05). The variations in resilience and scores on the three subscales in the intervention group were greater than those in the control group, and the difference between the two groups was statistically significant (p < 0.05). The variations in the quality of life and overall health, emotional functions, and social functions were significantly greater in the intervention group than in the control group (p < 0.05). Conclusions: A telephone follow-up intervention based on the empowerment theory can effectively improve the resilience and quality of life of patients after CASI. This follow-up approach can provide a theoretical basis and practical reference for hospitals and communities to carry out targeted continuing nursing for patients after CASI. The long-term effects of the intervention and its underlying mechanisms require further study. Clinical trial registration: http://www.chictr.org.cn/showproj.aspx?proj=173682, identifier ChiCTR2200064950.

Personalized prediction of diabetic foot ulcer recurrence in elderly individuals using machine learning paradigms.

BACKGROUND: This study utilizes machine learning to analyze the recurrence risk of diabetic foot ulcers (DFUs) in elderly diabetic patients, aiming to enhance prevention and intervention efforts. OBJECTIVE: The goal is to construct accurate predictive models for assessing the recurrence risk of DFUs based on high-risk factors, such as age, blood sugar control, alcohol consumption, and smoking, in elderly diabetic patients. METHODS: Data from 138 elderly diabetic patients were collected, and after data cleaning, outlier screening, and feature integration, machine learning models were constructed. Support Vector Machine (SVM) was employed, achieving an accuracy rate of 93%. RESULTS: Experimental results demonstrate the effectiveness of SVM in predicting the recurrence risk of DFUs in elderly diabetic patients, providing clinicians with a more accurate tool for assessment. CONCLUSIONS: The study highlights the significance of machine learning in managing foot ulcers in elderly diabetic patients, particularly in predicting recurrence risk. This approach facilitates timely intervention, reducing the likelihood of patient recurrence, and introduces computer-assisted medical strategies in elderly diabetes management.

Evaluation of a Cascaded Deep Learning-based Algorithm for Prostate Lesion Detection at Biparametric MRI.

Background Multiparametric MRI (mpMRI) improves prostate cancer (PCa) detection compared with systematic biopsy, but its interpretation is prone to interreader variation, which results in performance inconsistency. Artificial intelligence (AI) models can assist in mpMRI interpretation, but large training data sets and extensive model testing are required. Purpose To evaluate a biparametric MRI AI algorithm for intraprostatic lesion detection and segmentation and to compare its performance with radiologist readings and biopsy results. Materials and Methods This secondary analysis of a prospective registry included consecutive patients with suspected or known PCa who underwent mpMRI, US-guided systematic biopsy, or combined systematic and MRI/US fusion-guided biopsy between April 2019 and September 2022. All lesions were prospectively evaluated using Prostate Imaging Reporting and Data System version 2.1. The lesion- and participant-level performance of a previously developed cascaded deep learning algorithm was compared with histopathologic outcomes and radiologist readings using sensitivity, positive predictive value (PPV), and Dice similarity coefficient (DSC). Results A total of 658 male participants (median age, 67 years [IQR, 61-71 years]) with 1029 MRI-visible lesions were included. At histopathologic analysis, 45% (294 of 658) of participants had lesions of International Society of Urological Pathology (ISUP) grade group (GG) 2 or higher. The algorithm identified 96% (282 of 294; 95% CI: 94%, 98%) of all participants with clinically significant PCa, whereas the radiologist identified 98% (287 of 294; 95% CI: 96%, 99%; P = .23). The algorithm identified 84% (103 of 122), 96% (152 of 159), 96% (47 of 49), 95% (38 of 40), and 98% (45 of 46) of participants with ISUP GG 1, 2, 3, 4, and 5 lesions, respectively. In the lesion-level analysis using radiologist ground truth, the detection sensitivity was 55% (569 of 1029; 95% CI: 52%, 58%), and the PPV was 57% (535 of 934; 95% CI: 54%, 61%). The mean number of false-positive lesions per participant was 0.61 (range, 0-3). The lesion segmentation DSC was 0.29. Conclusion The AI algorithm detected cancer-suspicious lesions on biparametric MRI scans with a performance comparable to that of an experienced radiologist. Moreover, the algorithm reliably predicted clinically significant lesions at histopathologic examination. ClinicalTrials.gov Identifier: NCT03354416 © RSNA, 2024 Supplemental material is available for this article.

SHARPIN contributes to sevoflurane-induced neonatal neurotoxicity through up-regulating HMGB1 to repress M2 like-macrophage polarization.

Sevoflurane exposure can result in neurotoxicity especially among children, which remains an important complication after surgery. However, its related mechanisms remain unclear. Here, we investigated the biological roles of SHARPIN in sevoflurane-induced neurotoxicity. As detected by qPCR, Western blotting and immunohistochemical staining, SHARPIN and HMGB1 expression was elevated in sevoflurane-stimulated mice as compared with the control mice. SHARPIN depletion attenuated hippocampus injury, repressed the expression of HMGB1 and M1-like macrophage markers (iNOS, TNF-α, IL-1ß, IL-6), but enhanced the expression of M2-like macrophage markers (ARG-1, IL-10). GST pull-down and Co-IP assays demonstrated that SHARPIN directly interacted with HMGB1 to enhance HMGB1 expression in SH-SY5Y cells. The inhibitory effects of SHARPIN silencing on inflammatory reaction and M1-like macrophages were counteracted by HMGB1 overexpression. Finally, SHARPIN-HMGB1 pathway affected neuroinflammation triggered by sevoflurane via modulating macrophage polarization. Collectively, our data suggested that SHARPIN stimulated sevoflurane-induced neurotoxicity via converting M2-like macrophages to M1-like macrophages by enhancing HMGB1 expression. SHARPIN intervention may be a promising therapeutic method to relieve sevoflurane-induced neurotoxicity.

Network-based analysis identifies potential therapeutic ingredients of Chinese medicines and their mechanisms toward lung cancer.

Lung cancer is one of the most common malignant tumors around the world, which has the highest mortality rate among all cancers. Traditional Chinese medicine (TCM) has attracted increased attention in the field of lung cancer treatment. However, the abundance of ingredients in Chinese medicines presents a challenge in identifying promising ingredient candidates and exploring their mechanisms for lung cancer treatment. In this work, two network-based algorithms were combined to calculate the network relationships between ingredient targets and lung cancer targets in the human interactome. Based on the enrichment analysis of the constructed disease module, key targets of lung cancer were identified. In addition, molecular docking and enrichment analysis of the overlapping targets between lung cancer and ingredients were performed to investigate the potential mechanisms of ingredient candidates against lung cancer. Ten potential ingredients against lung cancer were identified and they may have similar effect on the development of lung cancer. The results obtained from this study offered valuable insights and provided potential avenues for the development of novel drugs aimed at treating lung cancer.

Biopsy or Follow-up: AI Improves the Clinical Strategy of US BI-RADS 4A Breast Nodules Using a Convolutional Neural Network.

OBJECTIVES: To develop predictive nomograms based on clinical and ultrasound features and to improve the clinical strategy for US BI-RADS 4A lesions. METHODS: Patients with US BI-RADS 4A lesions from 3 hospitals between January 2016 and June 2020 were retrospectively included. Clinical and ultrasound features were extracted to establish nomograms CE (based on clinical experience) and DL (based on deep-learning algorithm). The performances of nomograms were evaluated by receiver operator characteristic curves, calibration curves and decision curves. Diagnostic performances with DL of radiologists were analyzed. RESULTS: 1616 patients from 2 hospitals were randomly divided into training and internal validation cohorts at a ratio of 7:3. Hundred patients from another hospital made up external validation cohort. DL achieved more optimized AUCs than CE (internal validation: 0.916 vs. 0.863, P < .01; external validation: 0.884 vs. 0.776, P = .05). The sensitivities of DL were higher than CE (internal validation: 81.03% vs. 72.41%, P = .044; external validation: 93.75% vs. 81.25%, P = .4795) without losing specificity (internal validation: 84.91% vs. 86.47%, P = .353; external validation: 69.14% vs. 71.60%, P = .789). Decision curves indicated DL adds more clinical net benefit. With DL's assistance, both radiologists achieved higher AUCs (0.712 vs. 0.801; 0.547 vs. 0.800), improved specificities (70.93% vs. 74.42%, P < .001; 59.3% vs. 81.4%, P = .004), and decreased unnecessary biopsy rates by 6.7% and 24%. CONCLUSION: DL was developed to discriminate US BI-RADS 4A lesions with a higher diagnostic power and more clinical net benefit than CE. Using DL may guide clinicians to make precise clinical decisions and avoid overtreatment of benign lesions.

Automated prostate gland segmentation in challenging clinical cases: comparison of three artificial intelligence methods.

OBJECTIVE: Automated methods for prostate segmentation on MRI are typically developed under ideal scanning and anatomical conditions. This study evaluates three different prostate segmentation AI algorithms in a challenging population of patients with prior treatments, variable anatomic characteristics, complex clinical history, or atypical MRI acquisition parameters. MATERIALS AND METHODS: A single institution retrospective database was queried for the following conditions at prostate MRI: prior prostate-specific oncologic treatment, transurethral resection of the prostate (TURP), abdominal perineal resection (APR), hip prosthesis (HP), diversity of prostate volumes (large ≥ 150 cc, small ≤ 25 cc), whole gland tumor burden, magnet strength, noted poor quality, and various scanners (outside/vendors). Final inclusion criteria required availability of axial T2-weighted (T2W) sequence and corresponding prostate organ segmentation from an expert radiologist. Three previously developed algorithms were evaluated: (1) deep learning (DL)-based model, (2) commercially available shape-based model, and (3) federated DL-based model. Dice Similarity Coefficient (DSC) was calculated compared to expert. DSC by model and scan factors were evaluated with Wilcox signed-rank test and linear mixed effects (LMER) model. RESULTS: 683 scans (651 patients) met inclusion criteria (mean prostate volume 60.1 cc [9.05-329 cc]). Overall DSC scores for models 1, 2, and 3 were 0.916 (0.707-0.971), 0.873 (0-0.997), and 0.894 (0.025-0.961), respectively, with DL-based models demonstrating significantly higher performance (p < 0.01). In sub-group analysis by factors, Model 1 outperformed Model 2 (all p < 0.05) and Model 3 (all p < 0.001). Performance of all models was negatively impacted by prostate volume and poor signal quality (p < 0.01). Shape-based factors influenced DL models (p < 0.001) while signal factors influenced all (p < 0.001). CONCLUSION: Factors affecting anatomical and signal conditions of the prostate gland can adversely impact both DL and non-deep learning-based segmentation models.

The interaction of lipocalin-2 and astrocytes in neuroinflammation: mechanisms and therapeutic application.

Neuroinflammation is a common pathological process in various neurological disorders, including stroke, Alzheimer's disease, Parkinson's disease, and others. It involves the activation of glial cells, particularly astrocytes, and the release of inflammatory mediators. Lipocalin-2 (Lcn-2) is a secretory protein mainly secreted by activated astrocytes, which can affect neuroinflammation through various pathways. It can also act as a pro-inflammatory factor by modulating astrocyte activation and polarization through different signaling pathways, such as NF-κB, and JAK-STAT, amplifying the inflammatory response and aggravating neural injury. Consequently, Lcn-2 and astrocytes may be potential therapeutic targets for neuroinflammation and related diseases. This review summarizes the current knowledge on the role mechanisms, interactions, and therapeutic implications of Lcn-2 and astrocytes in neuroinflammation.

Highly Crystalline Iridium-Nickel Nanocages with Subnanopores for Acidic Bifunctional Water Splitting Electrolysis.

Developing efficient bifunctional materials is highly desirable for overall proton membrane water splitting. However, the design of iridium materials with high overall acidic water splitting activity and durability, as well as an in-depth understanding of the catalytic mechanism, is challenging. Herein, we successfully developed subnanoporous Ir3Ni ultrathin nanocages with high crystallinity as bifunctional materials for acidic water splitting. The subnanoporous shell enables Ir3Ni NCs optimized exposure of active sites. Importantly, the nickel incorporation contributes to the favorable thermodynamics of the electrocatalysis of the OER after surface reconstruction and optimized hydrogen adsorption free energy in HER electrocatalysis, which induce enhanced intrinsic activity of the acidic oxygen evolution reaction (OER) and hydrogen evolution reaction (HER). Together, the Ir3Ni nanocages achieve 3.72 A/mgIr(η=350 mV) and 4.47 A/mgIr(η=40 mV) OER and HER mass activity, which are 18.8 times and 3.3 times higher than that of commercial IrO2 and Pt, respectively. In addition, their highly crystalline identity ensures a robust nanostructure, enabling good catalytic durability during the oxygen evolution reaction after surface oxidation. This work provides a new revenue toward the structural design and insightful understanding of metal alloy catalytic mechanisms for the bifunctional acidic water splitting electrocatalysis.

Forcefully engaging rods into tulips with gap discrepancy leading to pedicle screw loosening-a biomechanical analysis using long porcine spine segments.

BACKGROUND CONTEXT: Long-segment pedicle screw instrumentation is widely used to treat complex spinal disorders. Rods are routinely precontoured to maximize assistance on the correcting side of the deformity, but there often exists a residual gap discrepancy between the precontoured rods and screw tulips. No previous research has investigated the diminished pullout strength of the most proximal or distal pedicle screw resulting from a mismatched rod in long-segment pedicle screw instrumentation. PURPOSE: The present study aimed to investigate the decreased pullout force of pedicle screws affected by the gap discrepancy when forcefully engaging a mismatched rod into a tulip in a normal-density porcine spine. STUDY DESIGN: The pedicle screw fixation strength under axial pullout force was compared among three different gap discrepancies between rods and tulips using long porcine spine segments. METHODS: Twelve porcine lumbar vertebrae (L3-L6) were implanted with pedicle screws and rods. Screws on one side had no gap between the tulip and rod (0-mm group), while the most proximal screw on the other side had an intentional gap of 3 mm (3-mm group) or 6 mm (6-mm group). Three hours after forcefully engaging the rod into the tulips at room temperature, the set screws in all specimens were loosened, and each specimen was dissected into individual vertebrae for subsequent pullout testing. RESULTS: The control group exhibited significantly greater pullout strength (1987.68 ± 126.80 N) than the groups from different rod-tulip configurations (p<.05), with significantly greater strength in the 3-mm group (945.62 ± 97.43 N) than the 6-mm group (655.30 ± 194.49 N) (p<.05). Only 47.6% and 33.0% of the pullout strength was retained in the 3-mm and 6-mm groups, respectively, compared to the control group. CONCLUSIONS: Gap discrepancies between rods and tulips can significantly reduce pedicle screw pullout strength, with a correlation between decreased strength and increased gaps. Surgeons should avoid forcefully engaging mismatched rods and consider well-fitted contoured rods in spinal surgery to minimize the risk of screw loosening. CLINICAL SIGNIFICANCE: The gap discrepancy between rod and tulip significantly affected pullout strength, with greater gaps leading to reduced strength. Forcefully engaging mismatched rods into tulips in degenerative spinal surgery should be avoided to minimize the risk of early screw pullout.

Cardiovascular Mortality and Duration of Androgen Deprivation in Locally Advanced Prostate Cancer: Long-term Update of NRG/RTOG 9202.

BACKGROUND: Androgen deprivation therapy (ADT) has been associated with coronary heart disease and myocardial infarction (MI) in prostate cancer patients, but controversy persists regarding its effects on cardiovascular mortality (CVM). OBJECTIVE: We assessed the long-term relationship between ADT and CVM in a prostate cancer randomized trial (NRG Oncology/Radiation Therapy Oncology Group 9202). DESIGN, SETTING, AND PARTICIPANTS: From 1992 to 1995, 1554 men with locally advanced prostate cancer (T2c-T4, prostate-specific antigen <150 ng/ml) received radiotherapy with 4 mo (short-term [STADT]) versus 28 mo (longer-term [LTADT]) of ADT. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Using the Fine-Gray and Cox regression models, the relationship between ADT and mortality was evaluated. RESULTS AND LIMITATIONS: With a median follow-up of 19.6 yr, LTADT was associated with improved overall survival (OS) versus STADT (adjusted hazard ratio [HR] 0.88; p = 0.03) and prostate cancer survival (subdistribution HR [sHR] 0.70, p = 0.003). Comparing LTADT with STADT, prostate cancer mortality improved by 6.0% (15.6% [95% confidence interval 13.0-18.3%] vs 21.6% [18.6-24.7%]) at 15 yr, while CVM increased by 2.2% (14.9% [12.4-17.6%] vs 12.7% [10.4-15.3%]). In multivariable analyses, LTADT was not associated with increased CVM versus STADT (sHR 1.22 [0.93-1.59]; p = 0.15). An association between LTADT and MI death was detected (sHR 1.58 [1.00-2.50]; p = 0.05), particularly in patients with prevalent cardiovascular disease (CVD; sHR 2.54 [1.16-5.58]; p = 0.02). CONCLUSIONS: With 19.6 yr of follow-up, LTADT was not significantly associated with increased CVM in men with locally advanced prostate cancer. Patients may have increased MI mortality with LTADT, particularly those with baseline CVD. Overall, there remained a prostate cancer mortality benefit and no OS detriment with LTADT. PATIENT SUMMARY: In a long-term analysis of a large randomized prostate cancer trial, radiation with 28 mo of hormone therapy did not increase the risk of cardiovascular death significantly versus 4 mo of hormone therapy. Future studies are needed for patients with pre-existing heart disease, who may have an increased risk of myocardial infarction death with longer hormone use.

Porous Flower-Like Nanoarchitectures Derived from Nickel Phosphide Nanocrystals Anchored on Amorphous Vanadium Phosphate Nanosheet Nanohybrids for Superior Overall Water Splitting.

Transition metal phosphides (TMPs) and phosphates (TM-Pis) nanostructures are promising functional materials for energy storage and conversion. Nonetheless, controllable synthesis of crystalline/amorphous heterogeneous TMPs/TM-Pis nanohybrids or related nanoarchitectures remains challenging, and their electrocatalytic applications toward overall water splitting (OWS) are not fully explored. Herein, the Ni2P nanocrystals anchored on amorphous V-Pi nanosheet based porous flower-like nanohybrid architectures that are self-supported on carbon cloth (CC) substrate (Ni2P/V-Pi/CC) are fabricated by conformal oxidation and phosphorization of pre-synthesized NiV-LDH/CC. Due to the unique microstructures and strong synergistic effects of crystalline Ni2P and amorphous V-Pi components, the obtained Ni2P/V-Pi/CC owns abundant active sites, suitable surface/interface electronic structure and optimized adsorption-desorption of reaction intermediates, resulting in outstanding electrocatalytic performances toward hydrogen and oxygen evolution reactions in alkaline media. Correspondingly, the assembled Ni2P/V-Pi/CC||Ni2P/V-Pi/CC electrolyzer only needs an ultralow cell voltage (1.44 V) to deliver 10 mA cm-2 water-splitting currents, exceeding its counterparts, recently reported bifunctional catalysts-based devices, and Pt/C/CC||IrO2/CC pairs. Moreover, the Ni2P/V-Pi/CC||Ni2P/V-Pi/CC manifests remarkable stability. Also, such device shows a certain prospect for OWS in acidic media. This work may spur the development of TMPs/TMPis-based nanohybrid architectures by combining structure and phase engineering, and push their applications in OWS or other clean energy options.

An integrated model incorporating deep learning, hand-crafted radiomics and clinical and US features to diagnose central lymph node metastasis in patients with papillary thyroid cancer.

OBJECTIVE: To evaluate the value of an integrated model incorporating deep learning (DL), hand-crafted radiomics and clinical and US imaging features for diagnosing central lymph node metastasis (CLNM) in patients with papillary thyroid cancer (PTC). METHODS: This retrospective study reviewed 613 patients with clinicopathologically confirmed PTC from two institutions. The DL model and hand-crafted radiomics model were developed using primary lesion images and then integrated with clinical and US features selected by multivariate analysis to generate an integrated model. The performance was compared with junior and senior radiologists on the independent test set. SHapley Additive exPlanations (SHAP) plot and Gradient-weighted Class Activation Mapping (Grad-CAM) were used for the visualized explanation of the model. RESULTS: The integrated model yielded the best performance with an AUC of 0.841. surpassing that of the hand-crafted radiomics model (0.706, p < 0.001) and the DL model (0.819, p = 0.26). Compared to junior and senior radiologists, the integrated model reduced the missed CLNM rate from 57.89% and 44.74-27.63%, and decreased the rate of unnecessary central lymph node dissection (CLND) from 29.87% and 27.27-18.18%, respectively. SHAP analysis revealed that the DL features played a primary role in the diagnosis of CLNM, while clinical and US features (such as extrathyroidal extension, tumour size, age, gender, and multifocality) provided additional support. Grad-CAM indicated that the model exhibited a stronger focus on thyroid capsule in patients with CLNM. CONCLUSION: Integrated model can effectively decrease the incidence of missed CLNM and unnecessary CLND. The application of the integrated model can help improve the acceptance of AI-assisted US diagnosis among radiologists.

Deep Learning-Based Interpretable AI for Prostate T2W MRI Quality Evaluation.

RATIONALE AND OBJECTIVES: Prostate MRI quality is essential in guiding prostate biopsies. However, assessment of MRI quality is subjective with variation. Quality degradation sources exert varying impacts based on the sequence under consideration, such as T2W versus DWI. As a result, employing sequence-specific techniques for quality assessment could yield more advantageous outcomes. This study aims to develop an AI tool that offers a more consistent evaluation of T2W prostate MRI quality, efficiently identifying suboptimal scans while minimizing user bias. MATERIALS AND METHODS: This retrospective study included 1046 patients from three cohorts (ProstateX [n = 347], All-comer in-house [n = 602], enriched bad-quality MRI in-house [n = 97]) scanned between January 2011 and May 2022. An expert reader assigned T2W MRIs a quality score. A train-validation-test split of 70:15:15 was applied, ensuring equal distribution of MRI scanners and protocols across all partitions. T2W quality AI classification model was based on 3D DenseNet121 architecture using MONAI framework. In addition to multiclassification, binary classification was utilized (Classes 0/1 vs. 2). A score of 0 was given to scans considered non-diagnostic or unusable, a score of 1 was given to those with acceptable diagnostic quality with some usability but with some quality distortions present, and a score of 2 was given to those considered optimal diagnostic quality and usability. Partial occlusion sensitivity maps were generated for anatomical correlation. Three body radiologists assessed reproducibility within a subgroup of 60 test cases using weighted Cohen Kappa. RESULTS: The best validation multiclass accuracy of 77.1% (121/157) was achieved during training. In the test dataset, multiclassification accuracy was 73.9% (116/157), whereas binary accuracy was 84.7% (133/157). Sub-class sensitivity for binary quality distortion classification for class 0 was 100% (18/18), and sub-class specificity for T2W classification of absence/minimal quality distortions for class 2 was 90.5% (95/105). All three readers showed moderate to substantial agreement with ground truth (R1-R3 κ = 0.588, κ = 0.649, κ = 0.487, respectively), moderate to substantial agreement with each other (R1-R2 κ = 0.599, R1-R3 κ = 0.612, R2-R3 κ = 0.685), fair to moderate agreement with AI (R1-R3 κ = 0.445, κ = 0.410, κ = 0.292, respectively). AI showed substantial agreement with ground truth (κ = 0.704). 3D quality heatmap evaluation revealed that the most critical non-diagnostic quality imaging features from an AI perspective related to obscuration of the rectoprostatic space (94.4%, 17/18). CONCLUSION: The 3D AI model can assess T2W prostate MRI quality with moderate accuracy and translate whole sequence-level classification labels into 3D voxel-level quality heatmaps for interpretation. Image quality has a significant downstream impact on ruling out clinically significant cancers. AI may be able to help with reproducible identification of MRI sequences requiring re-acquisition with explainability.