Associating Knee Osteoarthritis Progression with Temporal-Regional Graph Convolutional Network Analysis on MR Images.

BACKGROUND: Artificial intelligence shows promise in assessing knee osteoarthritis (OA) progression on MR images, but faces challenges in accuracy and interpretability. PURPOSE: To introduce a temporal-regional graph convolutional network (TRGCN) on MR images to study the association between knee OA progression status and network outcome. STUDY TYPE: Retrospective. POPULATION: 194 OA progressors (mean age, 62 ± 9 years) and 406 controls (mean age, 61 ± 9 years) from the OA Initiative were randomly divided into training (80%) and testing (20%) cohorts. FIELD STRENGTH/SEQUENCE: Sagittal 2D IW-TSE-FS (IW) and 3D-DESS-WE (DESS) at 3T. ASSESSMENT: Anatomical subregions of cartilage, subchondral bone, meniscus, and the infrapatellar fat pad at baseline, 12-month, and 24-month were automatically segmented and served as inputs to form compartment-based graphs for a TRGCN model, which containing both regional and temporal information. The performance of models based on (i) clinical variables alone, (ii) radiologist score alone, (iii) combined features (containing i and ii), (iv) composite TRGCN (combining TRGCN, i and ii), (v) radiomics features, (vi) convolutional neural network based on Densenet-169 were compared. STATISTICAL TESTS: DeLong test was performed to compare the areas under the ROC curve (AUC) of all models. Additionally, interpretability analysis was done to evaluate the contributions of individual regions. A P value <0.05 was considered significant. RESULTS: The composite TRGCN outperformed all other models with AUCs of 0.841 (DESS) and 0.856 (IW) in the testing cohort (all P < 0.05). Interpretability analysis highlighted cartilage's importance over other structures (42%-45%), tibiofemoral joint's (TFJ) dominance over patellofemoral joint (PFJ) (58%-67% vs. 12%-37%), and importance scores changes in compartments over time (TFJ vs. PFJ: baseline: 44% vs. 43%, 12-month: 52% vs. 39%, 24-month: 31% vs. 48%). DATA CONCLUSION: The composite TRGCN, capturing temporal and regional information, demonstrated superior discriminative ability compared with other methods, providing interpretable insights for identifying knee OA progression. TECHNICAL EFFICACY: Stage 2.

BAF-Net: bidirectional attention-aware fluid pyramid feature integrated multimodal fusion network for diagnosis and prognosis.

Objective. To go beyond the deficiencies of the three conventional multimodal fusion strategies (i.e. input-, feature- and output-level fusion), we propose a bidirectional attention-aware fluid pyramid feature integrated fusion network (BAF-Net) with cross-modal interactions for multimodal medical image diagnosis and prognosis.Approach. BAF-Net is composed of two identical branches to preserve the unimodal features and one bidirectional attention-aware distillation stream to progressively assimilate cross-modal complements and to learn supplementary features in both bottom-up and top-down processes. Fluid pyramid connections were adopted to integrate the hierarchical features at different levels of the network, and channel-wise attention modules were exploited to mitigate cross-modal cross-level incompatibility. Furthermore, depth-wise separable convolution was introduced to fuse the cross-modal cross-level features to alleviate the increase in parameters to a great extent. The generalization abilities of BAF-Net were evaluated in terms of two clinical tasks: (1) an in-house PET-CT dataset with 174 patients for differentiation between lung cancer and pulmonary tuberculosis. (2) A public multicenter PET-CT head and neck cancer dataset with 800 patients from nine centers for overall survival prediction.Main results. On the LC-PTB dataset, improved performance was found in BAF-Net (AUC = 0.7342) compared with input-level fusion model (AUC = 0.6825;p< 0.05), feature-level fusion model (AUC = 0.6968;p= 0.0547), output-level fusion model (AUC = 0.7011;p< 0.05). On the H&N cancer dataset, BAF-Net (C-index = 0.7241) outperformed the input-, feature-, and output-level fusion model, with 2.95%, 3.77%, and 1.52% increments of C-index (p= 0.3336, 0.0479 and 0.2911, respectively). The ablation experiments demonstrated the effectiveness of all the designed modules regarding all the evaluated metrics in both datasets.Significance. Extensive experiments on two datasets demonstrated better performance and robustness of BAF-Net than three conventional fusion strategies and PET or CT unimodal network in terms of diagnosis and prognosis.

Stress-only versus rest-stress SPECT MPI in the detection and diagnosis of myocardial ischemia and infarction by machine learning.

BACKGROUND: Rest-stress SPECT myocardial perfusion imaging (MPI) is widely used to evaluate coronary artery disease (CAD). We aim to evaluate stress-only versus rest-stress MPI in diagnosing CAD by machine learning (ML). METHODS: A total of 276 patients with suspected CAD were randomly divided into training (184 patients) and validation (92 patients) cohorts. Variables extracted from clinical, physiological, and rest-stress SPECT MPI were screened. Stress-only and rest-stress MPI using ML were established and compared using the training cohort. Then the diagnostic performance of two models in diagnosing myocardial ischemia and infarction was evaluated in the validation cohort. RESULTS: Six ML models based on stress-only MPI selected summed stress score, summed wall thickness score of stress%, and end-diastolic volume of stress as key variables and performed equally good as rest-stress MPI in detecting CAD [area under the curve (AUC): 0.863 versus 0.877, P  = 0.519]. Furthermore, stress-only MPI showed a reasonable prediction of reversible deficit, as shown by rest-stress MPI (AUC: 0.861). Subsequently, nomogram models using the above-stated stress-only MPI variables showed a good prediction of CAD and reversible perfusion deficit in training and validation cohorts. CONCLUSION: Stress-only MPI demonstrated similar diagnostic performance compared with rest-stress MPI using 6 ML algorithms. Stress-only MPI with ML models can diagnose CAD and predict ischemia from scar.

Optimal batch determination for improved harmonization and prognostication of multi-center PET/CT radiomics feature in head and neck cancer.

Objective. To determine the optimal approach for identifying and mitigating batch effects in PET/CT radiomics features, and further improve the prognosis of patients with head and neck cancer (HNC), this study investigated the performance of three batch harmonization methods.Approach. Unsupervised harmonization identified the batch labels by K-means clustering. Supervised harmonization regarding the image acquisition factors (center, manufacturer, scanner, filter kernel) as known/given batch labels, and Combat harmonization was then implemented separately and sequentially based on the batch labels, i.e. harmonizing features among batches determined by each factor individually or harmonizing features among batches determined by multiple factors successively. Extensive experiments were conducted to predict overall survival (OS) on public PET/CT datasets that contain 800 patients from 9 centers.Main results. In the external validation cohort, results show that compared to original models without harmonization, Combat harmonization would be beneficial in OS prediction with C-index of 0.687-0.740 versus 0.684-0.767. Supervised harmonization slightly outperformed unsupervised harmonization in all models (C-index: 0.692-0.767 versus 0.684-0.750). Separate harmonization outperformed sequential harmonization in CT_m+clinic and CT_cm+clinic models with C-index of 0.752 and 0.722, respectively, while sequential harmonization involved clinical features in PET_rs+clinic model further improving the performance and achieving the highest C-index of 0.767.Significance. Optimal batch determination especially sequential harmonization for Combat holds the potential to improve the prognostic power of radiomics model in multi-center HNC dataset with PET/CT imaging.

Role of Circulating Tumor DNA in Colorectal Cancer.

Colorectal cancer (CRC) is a very common gastrointestinal tumor, ranking second in the global cause of cancer death. Because of the invasive nature of biopsy and cannot reflect the heterogeneity of tumor or monitor the dynamic progress of tumor, it is necessary to induce a novel noninvasive method to improve the current treatment strategies of colorectal cancer. Among all the components of liquid biopsy, circulating tumor DNA (ctDNA) may have the best future. CtDNA maintains the same genomic characteristics as those in matched tumor tissues, so it allows quantitative evaluation and analysis of mutation load in body fluid. Furthermore, because the half-life of ctDNA is from 16 min to several hours in circulation, the circulating ctDNA can be measured repeatedly within a certain period to monitor the response of CRC to treatment, the occurrence of drug resistance, and the diagnosis of recurrence.

Functional-structural sub-region graph convolutional network (FSGCN): Application to the prognosis of head and neck cancer with PET/CT imaging.

BACKGROUND AND OBJECTIVE: Accurate risk stratification is crucial for enabling personalized treatment for head and neck cancer (HNC). Current PET/CT image-based prognostic methods include radiomics analysis and convolutional neural network (CNN), while extracting radiomics or deep features in grid Euclidean space has inherent limitations for risk stratification. Here, we propose a functional-structural sub-region graph convolutional network (FSGCN) for accurate risk stratification of HNC. METHODS: This study collected 642 patients from 8 different centers in The Cancer Imaging Archive (TCIA), 507 patients from 5 centers were used for training, and 135 patients from 3 centers were used for testing. The tumor was first clustered into multiple sub-regions by using PET and CT voxel information, and radiomics features were extracted from each sub-region to characterize its functional and structural information, a graph was then constructed to format the relationship/difference among different sub-regions in non-Euclidean space for each patient, followed by a residual gated graph convolutional network, the prognostic score was finally generated to predict the progression-free survival (PFS). RESULTS: In the testing cohort, compared with radiomics or FSGCN or clinical model alone, the model PETCTFea_CTROI + Cli that integrates FSGCN prognostic score and clinical parameter achieved the highest C-index and AUC of 0.767 (95% CI: 0.759-0.774) and 0.781 (95% CI: 0.774-0.788), respectively for PFS prediction. Besides, it also showed good prognostic performance on the secondary endpoints OS, RFS, and MFS in the testing cohort, with C-index of 0.786 (95% CI: 0.778-0.795), 0.775 (95% CI: 0.767-0.782) and 0.781 (95% CI: 0.772-0.789), respectively. CONCLUSIONS: The proposed FSGCN can better capture the metabolic or anatomic difference/interaction among sub-regions of the whole tumor imaged with PET/CT. Extensive multi-center experiments demonstrated its capability and generalization of prognosis prediction in HNC over conventional radiomics analysis.

Studies on improving semen quality and increasing pregnancy chances through the in vitro addition of L-carnitine and coenzyme Q10 to semen in patients with asthenozoospermia.

BACKGROUND: At present, L-carnitine (LC) and coenzyme Q10 (CoQ10), as used clinically to treat male infertility caused by asthenozoospermia (ASZ) is still mainly administered orally, but some patients with ASZ still show no significant improvement in sperm motility and spouse pregnancy rate. Prodom is a device used to assist reproduction, which is temporarily fitted onto the penis to facilitate conception by helping the wife inject a certain drug into the vagina. This study used Prodom-assisted LC/CoQ10 in the treatment of patients with ASZ and evaluated the effect of this method on sperm motility and clinical pregnancy, with the goal of finding a comfortable, low-cost, effective method. RESULTS: During the trial period, 232 cases completed the trial, while 25 cases did not. During in vitro testing, the progressive sperm motility in the LC group, CoQ10 group, LC combined with CoQ10 group, and the semen blank control group was 24.3 ± 4.6% and 38.1 ± 5.1%, 23.0 ± 4.8% and 36.9 ± 4.4%, 28.4 ± 5.0% and 43.8 ± 5.4%, 19.7 ± 4.4% and 26.0 ± 4.9%, respectively. There were statistically significant differences in progressive sperm motility among the groups (all P values < 0.05). The pregnancy rates of the Prodom-assisted LC treatment group, Prodom-assisted CoQ10 treatment group, Prodom-assisted LC combined with CoQ10 treatment group, and oral LC combined with CoQ10 treatment group in the clinical treatment stage were 38.2, 35.4, 57.1, and 30.3%, respectively; the time to conception was 6.1 ± 1.8, 6.2 ± 1.8, 3.4 ± 0.9, and 7.9 ± 2.0, months respectively; and the treatment costs were $2350 ± 457, $2455 ± 434, $1348 ± 411, and $2684 ± 334, respectively. The differences in pregnancy rate, time to conception, and treatment costs among the groups were statistically significant (all P values < 0.05). CONCLUSIONS: The supplementation of in vitro semen with LC/CoQ10 can improve sperm motility. LC/CoQ10 injected into the spouse's vagina with the assistance of a Prodom can increase the pregnancy rate, shorten the time to conception, and reduce the cost of treatment in patients with ASZ. TRIAL REGISTRATION: ChiCTR2000040349 (registry: http://www.chictr.org.cn/ ). Date of registration: November 28, 2020.

RéSUMé: CONTEXTE: À l'heure actuelle, la L-carnitine (LC) et le coenzyme Q10 (CoQ10), tels qu'utilisés en clinique pour traiter l'infertilité masculine due à une asthénozoospermie (AZS), sont encore principalement administrés par voie orale, mais certains patients atteints d'AZS ne montrent pas toujours d'amélioration significative de la motilité des spermatozoïdes, ni de grossesse chez la conjointe. Prodom™ est. un dispositif utilisé pour aider à la reproduction, qui est. temporairement installé sur le pénis pour faciliter la conception en aidant la femme à injecter certains médicaments dans le vagin. Cette étude a utilisé une association CL + CoQ10 assistée par Prodom™ pour traiter des patients atteints d'AZS et a évalué l'effet de cette méthode sur la mobilité des spermatozoïdes et la grossesse clinique, dans le but de trouver une méthode confortable, peu coûteuse et efficace. RéSULTATS: Au cours de cet essai thérapeutique, 232 cas sont allés au bout de l'étude, alors que 25 se sont arrêtés. Au cours des tests in vitro, la mobilité progressive des spermatozoïdes dans le groupe LC, le groupe CoQ10, le groupe CL + CoQ10 et dans le groupe témoin de sperme, était respectivement de 24,3 ± 4,6% et 38,1 ± 5,1%, de 23,0 ± 4,8% et 36,9 ± 4,4%, de 28,4 ± 5,0% et 43,8 ± 5,4%, et de 19,7 ± 4,4% et 26,0 ± 4,9%. La mobilité progressive des spermatozoïdes était significativement différentes entre les groupes (toutes les valeurs de P < 0,05). Les taux de grossesse dans le groupe traité par LC assistée par Prodom™, dans le groupe traité par CoQ10 assisté par Prodom™, dans le groupe traité par une association CL + CoQ10 assistée par Prodom™, et dans le groupe traité cliniquement par CL par voie orale associée au CoQ10, étaient respectivement de 38,2%, 35,4%, 57,1% et 30,3%; le délai de conception était respectivement de 6,1 ± 1,8, 6,2 ± 1,8, 3,4 ± 0,9 et 7,9 ± 2,0, mois; et les coûts de traitement étaient respectivement de 2350 ± 457 $, 2455 ± 434 $, 1348 ± 411 $ et 2684 ± 334 $. Les différences dans le taux de grossesse, le délai de conception et les coûts de traitement entre les groupes étaient statistiquement significatives (toutes les valeurs de P < 0,05). CONCLUSIONS: La supplémentation en LC/CoQ10 du sperme in vitro peut améliorer la mobilité des spermatozoïdes. L'association LC + CoQ10 injectée dans le vagin de la conjointe avec l'aide d'un Prodom™ peut augmenter le taux de grossesse, raccourcir le délai de conception et réduire le coût du traitement chez les patientes atteints d'AZS. Numéro d'enregistrement de l'essai ChiCTR2000040349 (registre: http://www.chictr.org.cn/ ). Date d'enregistrement: 28 novembre 2020.

Effects of unilateral/bilateral amputation of the ischiocavernosus muscle in male rats on erectile function and conception.

BACKGROUND: The ischiocavernosus muscle (ICM) encompasses a pair of short pinnate muscles attached to the pelvic ring. The ICM begins at the ischial tuberosity and ends at the crus of the penis while covering the surface of the crus. According to the traditional view, the contraction of the ICM plays an auxiliary role in penile erection. However, we have previously shown that the ICM plays an important role in penile erection through an indirect method of diagnosing erectile dysfunction (ED) caused by ICM injury by observing the infertility of paired female rats. Since intracavernosal pressure (ICP) is the current gold standard for diagnosing ED, this study aimed to amputate unilaterally/bilaterally the ICM to establish an ED model by detecting the ICP, recording the infertility of matching female rats, and comparing the two methods. RESULTS: Forty sexually mature adult male rats were selected and randomly divided into the following groups: the control group (n = 10), sham operation group (n = 10), unilateral ischiocavernosus muscle (Uni-ICM) amputation group (n = 10), and bilateral ischiocavernosus muscle (Bi-ICM) amputation group (n = 10). Eighty female reproductive rats were randomly assigned to the above groups at a ratio of 2:1. We evaluated the time to conception for the paired female rats and the effects of unilateral/bilateral severing of the ICM on erectile function. The results showed that the baseline and maximum intracavernosal pressure (ICP) in the control group, sham operation group, Uni-ICM amputation group, and Bi-ICM amputation group were 17.44±2.50 mmHg and 93.51±10.78 mmHg, 17.81±2.81 mmHg and 95.07±10.40 mmHg, 16.73±2.11 mmHg and 83.49±12.38 mmHg, and 14.78±2.78 mmHg and 33.57±6.72 mmHg, respectively, immediately postsurgery. The max ICP in the Bi-ICM amputation group was lower than that in the remaining three groups (all P<0.05). The pregnancy rates were 100, 100, 90, and 0% in the control group, sham operation group, Uni-ICM amputation group, and the Bi-ICM amputation group, respectively. The pregnancy rate in the Bi-ICM amputation group was significantly lower than that in the remaining groups (all P<0.05). The time to conception was approximately 7-10 days later in the Uni-ICM amputation group than in the control and sham groups (all P<0.05). CONCLUSIONS: Male rats undergoing Bi-ICM amputation may develop permanent ED, which affects their fertility. In contrast, rats undergoing Uni-ICM amputation may experience transient ED.

RéSUMé: INTRODUCTION: Le muscle Ischiocavernosus (MIC) est une paire de muscles courts attachés à l'anneau pelvien. Elle commence à la tubérosité ischiale et se termine au crus du pénis tout en couvrant la surface de ce dernier. Selon la vision traditionnelle, la contraction du MIC joue un rôle auxiliaire dans l'érection pénienne. Cependant, nos travaux précédents ont montré qu'il joue un rôle important dans l'érection pénienne par une méthode indirecte de diagnostic de la dysfonction érectile (DE) induite par une blessure du MIC en observant l'infertilité des rats femelles appariés. Comme la pression intracaverneuse (PIC) est actuellement l'étalon de référence pour le diagnostic, cette étude visait à amputer unilatéralement/bilatéralement l'ICM pour établir un modèle de DE par détection de l'ICP, par détection de l'infertilité de rats femelles appariés, et par comparaison des deux méthodes. RéSULTATS: Quarante rats mâles adultes sexuellement matures ont été sélectionnés et répartis aléatoirement dansquatre groupes groupe témoin (n = 10), groupe d'opération simulée (n = 10), groupe d'amputation unilatérale du MIC (Uni-MIC) (n = 10), et groupe d'amputation bilatérale du MIC (Bi-MIC) (n = 10). Quatre-vingts rats femelles en période de reproduction ont été réparties de façon aléatoire dans chacun des groupes mentionnés ci-dessus, selon un rapport de 2:1. Nous avons évalué le temps avant la conception des rats femelles appariés et les effets de l'amputation Uni /Bi-MIC sur la fonction érectile. Les résultats ont montré que la pression de base et la PIC maximale dans le groupe témoin, le groupe d'opération simulée, le groupe Uni-MIC et le groupe Bi-MIC étaient respectivement de 17.44 ± 2.50 mmHg et 93.51 ± 10.78 mmHg, 17.81 ± 2.81 mmHg et 95.07 ± 10.40 mmHg, 16.73 ± 2.11 mmHg et 83.49 ± 12.38 mmHg, et 14.78 ± 2.78 mmHg et 33.57 ± 6.72 mmHg, immédiatement après l'opération. La PIC maximale dans le groupe Bi-MIC était inférieure à celles des trois autres groupes (tous P < 0.05). Les taux de grossesse étaient de 90% dans le groupe Uni-MIC et de 0% dans le groupe Bi-MIC. Le taux de grossesse dans le groupe Bi-MIC était significativement plus faible que dans les autres groupes (tous P < 0.05). Le temps de conception a été d'environ 7 à 10 jours plus tard dans le groupe Uni-MIC que dans le groupe témoin et le groupe d'opération simulée (tous P < 0.05). CONCLUSIONS: Les rats mâles subissant une amputation Bi-MIC peuvent développer une DE permanente qui affecte leur fertilité. En revanche, ceux qui subissent une amputation Uni-MIC peuvent connaître des troubles érectiles transitoires.

Clinical Efficacy of Prodom-Assisted Urokinase in the Treatment of Male Infertility Caused by Impaired Semen Liquefaction.

PURPOSE: To evaluate the clinical efficacy of prodom in the administration of urokinase in the vagina in couples with impaired semen liquefaction. MATERIALS AND METHODS: Overall, 261 patients with impaired semen liquefaction were randomly divided into prodom-assisted urokinase treatment (PAUT) group (n = 91), syringe-assisted urokinase treatment (SAUT) group (n = 86), and traditional treatment (TT) group (n = 84) in the first stage. If the first stage of treatment failed, other treatment methods were initiated instead and the patients were grouped according to the newer treatment method in the second stage. The pregnancy rate, time-to-conception, and treatment costs were evaluated in each group. RESULTS: In the first stage, the pregnancy rate in the PAUT, SAUT, and TT groups was 69.23%, 29.07%, and 22.62%, respectively; the time-to-conception was 2.66 ± 1.44, 3.69 ± 2.61, and 3.86 ± 3.00 months, respectively; the treatment costs were 658.18 ± 398.40, 666.67 ± 507.50, and 680.56 ± 480.94 $, respectively. The pregnancy rate and time-to-conception were different in the PAUT group compared with those in SAUT and TT groups (all P < 0.05). However, the difference in treatment costs was not significant (P = 0.717). In the second stage, 154 nonpregnant patients were divided into nine treatment groups, and the effects of changing TT to PAUT on the pregnancy rate, time-to-conception, and treatment costs were observed to be different from those of other treatments (all P < 0.05). CONCLUSION: Prodom-assisted urokinase can effectively treat male infertility secondary to impaired semen liquefaction.

Can Statin Treatment Reduce the Risk of Hepatocellular Carcinoma? A Systematic Review and Meta-Analysis.

BACKGROUND: Whether statins can reduce the incidence of cancers has been an interesting topic in recent years. This meta-analysis aimed to determine the relationship between statin treatment with the risk of hepatocellular carcinoma. METHODS: Studies published up to July 2019 were screened from databases. The data from approved studies were pooled. Random-effects or fixed-effects model was used to calculate the relative risk with 95% CIs in the overall group and subgroups. Sensitivity and meta-regression analyses were performed, and publication bias was evaluated. RESULTS: A total of 18 studies involving 1 611 596 patients were included in this meta-analysis. The overall result showed a significantly reduced risk of hepatocellular carcinoma (relative risk = 0.54, 95% CI: 0.42-0.66) in statin users. In comparison to the risk in nonstatin users, the risk of hepatocellular carcinoma was reduced in all subgroups. The dose of statins and their pharmacokinetics can partly explain the heterogeneity in the overall meta-analysis (I2 = 94.6%, P = .000). A dose-dependent effect of statin use for the reduced risk of hepatocellular carcinoma was found. CONCLUSIONS: Findings from this meta-analysis support that statin use can significantly reduce the incidence of hepatocellular carcinoma.

A Rare Case of a Postoperative Submandibular Exophytic Goiter in a Patient With a Recurrent Normotopic Nodular Goiter.

A 50-year-old woman presented a painless left submandibular mass. She had history of partial thyroidectomy for nodular goiter. A radioiodine whole-body scan showed tracer accumulation in the mass, which connected with the thyroid remnant. The left submandibular mass was resected, and the pathological examination demonstrated exophytic and normotopic nodular goiter.