Building momentum through networks: Bioimaging across the Americas.

In September 2023, the two largest bioimaging networks in the Americas, Latin America Bioimaging (LABI) and BioImaging North America (BINA), came together during a 1-week meeting in Mexico. This meeting provided opportunities for participants to interact closely with decision-makers from imaging core facilities across the Americas. The meeting was held in a hybrid format and attended in-person by imaging scientists from across the Americas, including Canada, the United States, Mexico, Colombia, Peru, Argentina, Chile, Brazil and Uruguay. The aims of the meeting were to discuss progress achieved over the past year, to foster networking and collaborative efforts among members of both communities, to bring together key members of the international imaging community to promote the exchange of experience and expertise, to engage with industry partners, and to establish future directions within each individual network, as well as common goals. This meeting report summarises the discussions exchanged, the achievements shared, and the goals set during the LABIxBINA2023: Bioimaging across the Americas meeting.

Saccharomyces cerevisiae biofactory to produce naringenin using a systems biology approach and a bicistronic vector expression strategy in flavonoid production.

IMPORTANCE: Flavonoids are a group of compounds generally produced by plants with proven biological activity, which have recently beeen recommended for the treatment and prevention of diseases and ailments with diverse causes. In this study, naringenin was produced in adequate amounts in yeast after in silico design. The four genes of the involved enzymes from several organisms (bacteria and plants) were multi-expressed in two vectors carrying each two genes linked by a short viral peptide sequence. The batch kinetic behavior of the product, substrate, and biomass was described at lab scale. The engineered strain might be used in a more affordable and viable bioprocess for industrial naringenin procurement.

Design and Assembly of a Biofactory for (2S)-Naringenin Production in Escherichia coli: Effects of Oxygen Transfer on Yield and Gene Expression.

The molecule (2S)-naringenin is a scaffold molecule with several nutraceutical properties. Currently, (2S)-naringenin is obtained through chemical synthesis and plant isolation. However, these methods have several drawbacks. Thus, heterologous biosynthesis has emerged as a viable alternative to its production. Recently, (2S)-naringenin production studies in Escherichia coli have used different tools to increase its yield up to 588 mg/L. In this study, we designed and assembled a bio-factory for (2S)-naringenin production. Firstly, we used several parametrized algorithms to identify the shortest pathway for producing (2S)-naringenin in E. coli, selecting the genes phenylalanine ammonia lipase (pal), 4-coumarate: CoA ligase (4cl), chalcone synthase (chs), and chalcone isomerase (chi) for the biosynthetic pathway. Then, we evaluated the effect of oxygen transfer on the production of (2S)-naringenin at flask (50 mL) and bench (4 L culture) scales. At the flask scale, the agitation rate varied between 50 rpm and 250 rpm. At the bench scale, the dissolved oxygen was kept constant at 5% DO (dissolved oxygen) and 40% DO, obtaining the highest (2S)-naringenin titer (3.11 ± 0.14 g/L). Using genome-scale modeling, gene expression analysis (RT-qPCR) of oxygen-sensitive genes was obtained.

Diagnosis and treatment of benign adipocytic tumors in children.

PURPOSE: To describe demographic, clinical, diagnostic and therapeutic aspects of pediatric patients with benign adipocytic tumors admitted to a high complexity teaching hospital from 2007 to 2021. METHODS: Retrospective observational descriptive study. Patient information was retrieved from clinical records. A descriptive analysis was carried out for qualitative data and frequencies were calculated for quantitative data. RESULTS: 76 patients were included with a mean age of 7.5 years old where 60.5% were boys. The main symptom was a mass (73.7%) mostly found in the lower limbs (23.6%). Congenital birth defects were identified in 48.6% of the cases. Preoperative imaging was available in 78.9% of the patients allowing characterization of lesions or differential diagnosis. The therapeutic goal was resection with negative margins, which was feasible in all cases except for one case. The histopathological diagnosis was lipoma in 68.4% of the cases followed by lipoblastoma in 13.1%. The mean follow-up period was 17.9 months. 79.7% of the patients were asymptomatic at their last out-patient visit. CONCLUSION: Benign adipocytic tumors constitute a wide spectrum of lesions, which involve diverse anatomic segments from the neural axis to the inguinoscrotal region. The present work contributes to the general understanding of the clinical presentation and differential diagnosis for these infrequent neoplasms.

The Medical Segmentation Decathlon.

International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Although segmentation is the most widely investigated medical image processing task, the various challenges have been organized to focus only on specific clinical tasks. We organized the Medical Segmentation Decathlon (MSD)-a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities to investigate the hypothesis that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. MSD results confirmed this hypothesis, moreover, MSD winner continued generalizing well to a wide range of other clinical problems for the next two years. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to scientists that are not versed in AI model training.

Predicting target-ligand interactions with graph convolutional networks for interpretable pharmaceutical discovery.

Drug Discovery is an active research area that demands great investments and generates low returns due to its inherent complexity and great costs. To identify potential therapeutic candidates more effectively, we propose protein-ligand with adversarial augmentations network (PLA-Net), a deep learning-based approach to predict target-ligand interactions. PLA-Net consists of a two-module deep graph convolutional network that considers ligands' and targets' most relevant chemical information, successfully combining them to find their binding capability. Moreover, we generate adversarial data augmentations that preserve relevant biological backgrounds and improve the interpretability of our model, highlighting the relevant substructures of the ligands reported to interact with the protein targets. Our experiments demonstrate that the joint ligand-target information and the adversarial augmentations significantly increase the interaction prediction performance. PLA-Net achieves 86.52% in mean average precision for 102 target proteins with perfect performance for 30 of them, in a curated version of actives as decoys dataset. Lastly, we accurately predict pharmacologically-relevant molecules when screening the ligands of ChEMBL and drug repurposing Hub datasets with the perfect-scoring targets.

Central serous chorioretinopathy imaging biomarkers.

PURPOSE: To identify the factors predicting the visual and anatomical outcomes in eyes with central serous chorioretinopathy (CSCR) through 12 months. METHODS: Patients with diagnosis of CSCR, either acute or chronic, were included in this multicentric, retrospective study. Demographic factors; systemic risk factors; central macular thickness (CMT), subfoveal choroidal thickness (SFCT), linear extent of ellipsoid zone (EZ) and interdigitation zone damage on optical coherence tomography; details of leak on fluorescein angiography and indocyanine green angiography were included as predictors of anatomical and visual outcomes. Regression analysis was performed to correlate the changes in best corrected visual acuity (BCVA) and resolution of disease activity. RESULTS: A total of 231 eyes of 201 patients with a mean age (49.7±11.8 years) were analysed. A total of 97 and 134 eyes were classified as acute and chronic CSCR. BCVA (0.35±0.31 to 0.24±0.34; p<0.001), baseline optical coherence tomography (OCT) parameters including CMT (p<0.001), subretinal fluid (SRF) height (p<0.001) and SFCT (p=0.05) showed a significant change through 12 months. Multivariate regression analysis showed change in CMT (p≤0.01) and SRF height at baseline (p=0.05) as factors predictive of good visual outcome. Logistic regression analysis revealed changes in both CMT (p=0.009) and SFCT (p=0.01) through 12 months to correlate with the resolution of disease. CONCLUSION: OCT parameters such as changes in both CMT and SFCT along with subfoveal EZ damage can be predictive of disease resolution whereas changes in CMT and baseline SRF height correlate well with changes in BCVA through 12 months.

QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results.

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at https://github.com/RagMeh11/QU-BraTS.

Lung Nodule Malignancy Prediction in Sequential CT Scans: Summary of ISBI 2018 Challenge.

Lung cancer is by far the leading cause of cancer death in the US. Recent studies have demonstrated the effectiveness of screening using low dose CT (LDCT) in reducing lung cancer related mortality. While lung nodules are detected with a high rate of sensitivity, this exam has a low specificity rate and it is still difficult to separate benign and malignant lesions. The ISBI 2018 Lung Nodule Malignancy Prediction Challenge, developed by a team from the Quantitative Imaging Network of the National Cancer Institute, was focused on the prediction of lung nodule malignancy from two sequential LDCT screening exams using automated (non-manual) algorithms. We curated a cohort of 100 subjects who participated in the National Lung Screening Trial and had established pathological diagnoses. Data from 30 subjects were randomly selected for training and the remaining was used for testing. Participants were evaluated based on the area under the receiver operating characteristic curve (AUC) of nodule-wise malignancy scores generated by their algorithms on the test set. The challenge had 17 participants, with 11 teams submitting reports with method description, mandated by the challenge rules. Participants used quantitative methods, resulting in a reporting test AUC ranging from 0.698 to 0.913. The top five contestants used deep learning approaches, reporting an AUC between 0.87 - 0.91. The team's predictor did not achieve significant differences from each other nor from a volume change estimate (p =.05 with Bonferroni-Holm's correction).

PharmaNet: Pharmaceutical discovery with deep recurrent neural networks.

The discovery and development of novel pharmaceuticals is an area of active research mainly due to the large investments required and long payback times. As of 2016, the development of a novel drug candidate required up to $ USD 2.6 billion in investment for only 10% rate of approval by the FDA. To help decreasing the costs associated with the process, a number of in silico approaches have been developed with relatively low success due to limited predicting performance. Here, we introduced a machine learning-based algorithm as an alternative for a more accurate search of new pharmacological candidates, which takes advantage of Recurrent Neural Networks (RNN) for active molecule prediction within large databases. Our approach, termed PharmaNet was implemented here to search for ligands against specific cell receptors within 102 targets of the DUD-E database, which contains 22886 active molecules. PharmaNet comprises three main phases. First, a SMILES representation of the molecule is converted into a raw molecular image. Second, a convolutional encoder processes the data to obtain a fingerprint molecular image that is finally analyzed by a Recurrent Neural Network (RNN). This approach enables precise predictions of the molecules' target on the basis of the feature extraction, the sequence analysis and the relevant information filtered out throughout the process. Molecule Target prediction is a highly unbalanced detection problem and therefore, we propose that an adequate evaluation metric of performance is the area under the Normalized Average Precision (NAP) curve. PharmaNet largely surpasses the previous state-of-the-art method with 97.7% in the Receiver Operating Characteristic curve (ROC-AUC) and 65.5% in the NAP curve. We obtained a perfect performance for human farnesyl pyrophosphate synthase (FPPS), which is a potential target for antimicrobial and anticancer treatments. We decided to test PharmaNet for activity prediction against FPPS by searching in the CHEMBL data set. We obtained three (3) potential inhibitors that were further validated through both molecular docking and in silico toxicity prediction. Most importantly, one of this candidates, CHEMBL2007613, was predicted as a potential antiviral due to its involvement on the PCDH17 pathway, which has been reported to be related to viral infections.

ISLES 2016 and 2017-Benchmarking Ischemic Stroke Lesion Outcome Prediction Based on Multispectral MRI.

Performance of models highly depend not only on the used algorithm but also the data set it was applied to. This makes the comparison of newly developed tools to previously published approaches difficult. Either researchers need to implement others' algorithms first, to establish an adequate benchmark on their data, or a direct comparison of new and old techniques is infeasible. The Ischemic Stroke Lesion Segmentation (ISLES) challenge, which has ran now consecutively for 3 years, aims to address this problem of comparability. ISLES 2016 and 2017 focused on lesion outcome prediction after ischemic stroke: By providing a uniformly pre-processed data set, researchers from all over the world could apply their algorithm directly. A total of nine teams participated in ISLES 2015, and 15 teams participated in ISLES 2016. Their performance was evaluated in a fair and transparent way to identify the state-of-the-art among all submissions. Top ranked teams almost always employed deep learning tools, which were predominately convolutional neural networks (CNNs). Despite the great efforts, lesion outcome prediction persists challenging. The annotated data set remains publicly available and new approaches can be compared directly via the online evaluation system, serving as a continuing benchmark (www.isles-challenge.org).