A Deep Learning Approach to Classify Fabry Cardiomyopathy from Hypertrophic Cardiomyopathy Using Cine Imaging on Cardiac Magnetic Resonance.

A challenge in accurately identifying and classifying left ventricular hypertrophy (LVH) is distinguishing it from hypertrophic cardiomyopathy (HCM) and Fabry disease. The reliance on imaging techniques often requires the expertise of multiple specialists, including cardiologists, radiologists, and geneticists. This variability in the interpretation and classification of LVH leads to inconsistent diagnoses. LVH, HCM, and Fabry cardiomyopathy can be differentiated using T1 mapping on cardiac magnetic resonance imaging (MRI). However, differentiation between HCM and Fabry cardiomyopathy using echocardiography or MRI cine images is challenging for cardiologists. Our proposed system named the MRI short-axis view left ventricular hypertrophy classifier (MSLVHC) is a high-accuracy standardized imaging classification model developed using AI and trained on MRI short-axis (SAX) view cine images to distinguish between HCM and Fabry disease. The model achieved impressive performance, with an F1-score of 0.846, an accuracy of 0.909, and an AUC of 0.914 when tested on the Taipei Veterans General Hospital (TVGH) dataset. Additionally, a single-blinding study and external testing using data from the Taichung Veterans General Hospital (TCVGH) demonstrated the reliability and effectiveness of the model, achieving an F1-score of 0.727, an accuracy of 0.806, and an AUC of 0.918, demonstrating the model's reliability and usefulness. This AI model holds promise as a valuable tool for assisting specialists in diagnosing LVH diseases.

Precision Identification of Locally Advanced Rectal Cancer in Denoised CT Scans Using EfficientNet and Voting System Algorithms.

BACKGROUND AND OBJECTIVE: Local advanced rectal cancer (LARC) poses significant treatment challenges due to its location and high recurrence rates. Accurate early detection is vital for treatment planning. With magnetic resonance imaging (MRI) being resource-intensive, this study explores using artificial intelligence (AI) to interpret computed tomography (CT) scans as an alternative, providing a quicker, more accessible diagnostic tool for LARC. METHODS: In this retrospective study, CT images of 1070 T3-4 rectal cancer patients from 2010 to 2022 were analyzed. AI models, trained on 739 cases, were validated using two test sets of 134 and 197 cases. By utilizing techniques such as nonlocal mean filtering, dynamic histogram equalization, and the EfficientNetB0 algorithm, we identified images featuring characteristics of a positive circumferential resection margin (CRM) for the diagnosis of locally advanced rectal cancer (LARC). Importantly, this study employs an innovative approach by using both hard and soft voting systems in the second stage to ascertain the LARC status of cases, thus emphasizing the novelty of the soft voting system for improved case identification accuracy. The local recurrence rates and overall survival of the cases predicted by our model were assessed to underscore its clinical value. RESULTS: The AI model exhibited high accuracy in identifying CRM-positive images, achieving an area under the curve (AUC) of 0.89 in the first test set and 0.86 in the second. In a patient-based analysis, the model reached AUCs of 0.84 and 0.79 using a hard voting system. Employing a soft voting system, the model attained AUCs of 0.93 and 0.88, respectively. Notably, AI-identified LARC cases exhibited a significantly higher five-year local recurrence rate and displayed a trend towards increased mortality across various thresholds. Furthermore, the model's capability to predict adverse clinical outcomes was superior to those of traditional assessments. CONCLUSION: AI can precisely identify CRM-positive LARC cases from CT images, signaling an increased local recurrence and mortality rate. Our study presents a swifter and more reliable method for detecting LARC compared to traditional CT or MRI techniques.

Uptake of perfluoroalkyl substances PFOS and PFOA by free-floating hydrophytes Pistia stratiotes L. and Eichhornia crassipes (Mart.) Solms.

The phytoremediation potential of floating aquatic plants to accumulate and remove two common PFAS from contaminated water was investigated. Free-floating hydrophytes Eichhornia crassipes and Pistia stratiotes were grown in water spiked with 0.5, 1, or 2 ppm perfluorooctanoic acid (PFOA) or perfluorooctanesulfonic acid (PFOS) for seven days. Both species were able to accumulate PFOA and PFOS in this time frame, with translocation factors (TF) ranging from 0.13 to 0.57 for P. stratiotes and 0.18 to 0.45 for E. stratiotes, respectively. E. crassipes accumulated a greater amount of PFOA and PFOS than P. stratiotes, with 178.9 ug PFOA and 308.5 ug PFOS removed by E. crassipes and 98.9 ug PFOA and 137.8 ug PFOS removed by P. stratiotes at the highest concentrations. Root tissue contained a higher concentration of PFOA and PFOS than shoot tissue in both species, and the concentration of PFOS was generally significantly higher than PFOA in both E. crassipes and P. stratiotes, with concentrations of 15.39 and 27.32 ppb PFOA and 17.41 and 80.62 ppb PFOS in shoots and roots of P. stratiotes and 12.59 and 37.37 ppb PFOA and 39.92 and 83.40 ppb PFOS in shoots and roots of E. crassipes, respectively. Both species may be candidates for further phytoremediation studies in aquatic ecosystems.

This study investigates the feasibility of using wetland plants for the phytoremediation of PFAS. Prior published studies examine various plant interactions with PFAS but do not evaluate remediation potential of P. stratiotes.

Dynamically Synthetic Images for Federated Learning of medical images.

BACKGROUND: To develop deep learning models for medical diagnosis, it is important to collect more medical data from several medical institutions. Due to the regulations for privacy concerns, it is infeasible to collect data from various medical institutions to one institution for centralized learning. Federated Learning (FL) provides a feasible approach to jointly train the deep learning model with data stored in various medical institutions instead of collected together. However, the resulting FL models could be biased towards institutions with larger training datasets. METHODOLOGY: In this study, we propose the applicable method of Dynamically Synthetic Images for Federated Learning (DSIFL) that aims to integrate the information of local institutions with heterogeneous types of data. The main technique of DSIFL is to develop a synthetic method that can dynamically adjust the number of synthetic images similar to local data that are misclassified by the current model. The resulting global model can handle the diversity in heterogeneous types of data collected in local medical institutions by including the training of synthetic images similar to misclassified cases in local collections. RESULTS: In model performance evaluation metrics, we focus on the accuracy of each client's dataset. Finally, the accuracy of the model of DSIFL in the experiments can achieve the higher accuracy of the FL approach. CONCLUSION: In this study, we propose the framework of DSIFL that achieves improvements over the conventional FL approach. We conduct empirical studies with two kinds of medical images. We compare the performance by variants of FL vs. DSIFL approaches. The performance by individual training is used as the baseline, whereas the performance by centralized learning is used as the target for the comparison studies. The empirical findings suggest that the DSIFL has improved performance over the FL via the technique of dynamically synthetic images in training.

Treatment Outcomes of Computer Tomography-Guided Brachytherapy in Cervical Cancer in Hong Kong: A Retrospective Review.

(1) Background: To report the long-term clinical outcomes of computer-tomography (CT)-guided brachytherapy (BT) for locally advanced cervical cancer. (2) Methods: A total of 135 patients with FIGO stage IB-IVA cervical cancer treated with definitive radiotherapy +/- chemotherapy with an IGABT boost at Queen Mary Hospital, Hong Kong, between November 2013 and December 2019 were included. Treatment included pelvic radiotherapy 40 Gy/20 Fr/4 weeks +/- chemotherapy then CT-guided BT (7 Gy × 4 Fr) and a sequential parametrial boost. The primary outcome was local control. Secondary outcomes were pelvic control, distant metastasis-free survival, overall survival (OS) and late toxicities. (3) Results: The median follow-up was 53.6 months (3.0-99.6 months). The five-year local control, pelvic control, distant metastasis-free survival and OS rates were 90.7%, 84.3%, 80.0% and 87.2%, respectively. The incidence of G3/4 long-term toxicities was 6.7%, including proctitis (2.2%), radiation cystitis (1.5%), bowel perforation (0.7%), ureteric stricture (0.7%) and vaginal stenosis and fistula (0.7%). Patients with adenocarcinomas had worse local control (HR 5.82, 95% CI 1.84-18.34, p = 0.003), pelvic control (HR 4.41, 95% CI 1.83-10.60, p = 0.001), distant metastasis-free survival (HR 2.83, 95% CI 1.17-6.84, p = 0.021) and OS (HR 4.38, 95% CI: 1.52-12.67, p = 0.003) rates. Distant metastasis-free survival was associated with HR-CTV volume ≥ 30 cm3 (HR 3.44, 95% CI 1.18-9.42, p = 0.025) and the presence of pelvic lymph node (HR 3.44, 95% CI 1.18-9.42, p = 0.025). OS was better in patients with concurrent chemotherapy (HR 4.33, 95% CI: 1.40-13.33, p = 0.011). (4) Conclusions: CT-guided BT for cervical cancer achieved excellent long-term local control and OS. Adenocarcinoma was associated with worse clinical outcomes. (4) Conclusion: CT-guided BT for cervical cancer achieved excellent long-term local control and OS. Adenocarcinoma was associated with worse clinical outcomes.

A novel group of genes that cause endocrine resistance in breast cancer identified by dynamic gene expression analysis.

Breast cancer (BC) is the most common type of cancer diagnosed in women. Among female cancer deaths, BC is the second leading cause of death worldwide. For estrogen receptor-positive (ER-positive) breast cancers, endocrine therapy is an effective therapeutic approach. However, in many cases, an ER-positive tumor becomes unresponsive to endocrine therapy, and tumor regrowth occurs after treatment. While some genetic mutations contribute to resistance in some patients, the underlying causes of resistance to endocrine therapy are mostly undetermined. In this study, we utilized a recently developed statistical approach to investigate the dynamic behavior of gene expression during the development of endocrine resistance and identified a novel group of genes whose time course expression significantly change during cell modelling of endocrine resistant BC development. Expression of a subset of these genes was also differentially expressed in microarray analysis of endocrine-resistant and endocrine-sensitive tumor samples. Surprisingly, a subset of those genes was also differentially genes expressed in triple-negative breast cancer (TNBC) as compared with ER-positive BC. The findings suggest shared genetic mechanisms may underlie the development of endocrine resistant BC and TNBC. Our findings identify 34 novel genes for further study as potential therapeutic targets for treatment of endocrine-resistant BC and TNBC.

Mechanistic studies of the cofactor assembly in class Ib ribonucleotide reductases and protein affinity for MnII and FeII.

Ribonucleotide reductase (RNR) is an essential enzyme found in all organisms. The function of RNR is to catalyze the conversion of nucleotides to deoxynucleotides. RNRs rely on metallocofactors to oxidize a conserved cysteine in the active site of the enzyme into a thiyl radical, which then initiates nucleotide reduction. The proteins required for MnIII2-Y• cluster formation in class Ib RNRs are NrdF (ß-subunit) and NrdI (flavodoxin). An oxidant is channeled from the FMN cofactor in NrdI to the dimanganese center in NrdF, where it oxidizes the dimanganese center and a tyrosyl radical (Y•) is formed. Both Streptococcus sanguinis and Escherichia coli MnII2-NrdF structures have a constriction in the channel immediately above the metal site. In E. coli, the constriction is formed by the side chain of S159, whereas in the S. sanguinis system it involves T158. This serine-to-threonine substitution was investigated using S. sanguinis and Streptococcus pneumoniae class Ib RNRs but it is also present in other pathogenic streptococci. Using stopped-flow kinetics, we investigate the role of this substitution in the mechanism of MnIII2-Y• cluster formation. In addition to different kinetics observed in the studied streptococci, we found that affinity constants of NrdF for MnII and FeII are about 1 µM and the previously reported preference for MnII could not be explained by affinity only.

Neutralizing Aptamers Block S/RBD-ACE2 Interactions and Prevent Host Cell Infection.

The receptor-binding domain (RBD) of the severe acute respiratory syndrome coronavirus 2 spike (S) protein plays a central role in mediating the first step of virus infection to cause disease: virus binding to angiotensin-converting enzyme 2 (ACE2) receptors on human host cells. Therefore, S/RBD is an ideal target for blocking and neutralization therapies to prevent and treat coronavirus disease 2019 (COVID-19). Using a target-based selection approach, we developed oligonucleotide aptamers containing a conserved sequence motif that specifically targets S/RBD. Synthetic aptamers had high binding affinity for S/RBD-coated virus mimics (K D≈7 nM) and also blocked interaction of S/RBD with ACE2 receptors (IC50≈5 nM). Importantly, aptamers were able to neutralize S protein-expressing viral particles and prevent host cell infection, suggesting a promising COVID-19 therapy strategy.

Neutralizing Aptamers Block S/RBD-ACE2 Interactions and Prevent Host Cell Infection.

The receptor-binding domain (RBD) of the severe acute respiratory syndrome coronavirus 2 spike (S) protein plays a central role in mediating the first step of virus infection to cause disease: virus binding to angiotensin-converting enzyme 2 (ACE2) receptors on human host cells. Therefore, S/RBD is an ideal target for blocking and neutralization therapies to prevent and treat coronavirus disease 2019 (COVID-19). Using a target-based selection approach, we developed oligonucleotide aptamers containing a conserved sequence motif that specifically targets S/RBD. Synthetic aptamers had high binding affinity for S/RBD-coated virus mimics (KD ≈7 nM) and also blocked interaction of S/RBD with ACE2 receptors (IC50 ≈5 nM). Importantly, aptamers were able to neutralize S protein-expressing viral particles and prevent host cell infection, suggesting a promising COVID-19 therapy strategy.