Introduction Bladder cancer assessment with non-invasive gene expression signatures facilitates the detection of patients at risk and surveillance of their status, bypassing the discomforts given by cystoscopy. To achieve accurate cancer estimation, analysis pipelines for gene expression data (GED) may integrate a sequence of several machine learning and bio-statistical techniques to model complex characteristics of pathological patterns. Methods Numerical experiments tested the combination of GED preprocessing by discretization with tree ensemble embeddings and nonlinear dimensionality reductions to categorize oncological patients comprehensively. Modeling aimed to identify tumor stage and distinguish survival outcomes in two situations: complete and partial data embedding. This latter experimental condition simulates the addition of new patients to an existing model for rapid monitoring of disease progression. Machine learning procedures were employed to identify the most relevant genes involved in patient prognosis and test the performance of preprocessed GED compared to untransformed data in predicting patient conditions. Results Data embedding paired with dimensionality reduction produced prognostic maps with well-defined clusters of patients, suitable for medical decision support. A second experiment simulated the addition of new patients to an existing model (partial data embedding): Uniform Manifold Approximation and Projection (UMAP) methodology with uniform data discretization led to better outcomes than other analyzed pipelines. Further exploration of parameter space for UMAP and t-distributed stochastic neighbor embedding (t-SNE) underlined the importance of tuning a higher number of parameters for UMAP rather than t-SNE. Moreover, two different machine learning experiments identified a group of genes valuable for partitioning patients (gene relevance analysis) and showed the higher precision obtained by preprocessed data in predicting tumor outcomes for cancer stage and survival rate (six classes prediction). Conclusions The present investigation proposed new analysis pipelines for disease outcome modeling from bladder cancer-related biomarkers. Complete and partial data embedding experiments suggested that pipelines employing UMAP had a more accurate predictive ability, supporting the recent literature trends on this methodology. However, it was also found that several UMAP parameters influence experimental results, therefore deriving a recommendation for researchers to pay attention to this aspect of the UMAP technique. Machine learning procedures further demonstrated the effectiveness of the proposed preprocessing in predicting patients’ conditions and determined a sub-group of biomarkers significant for forecasting bladder cancer prognosis.
Spiking neural networks are biologically inspired machine learning algorithms attracting researchers’ attention for their applicability to alternative energy-efficient hardware other than traditional computers. In the current work, spiking neural networks have been tested in a quantitative structure–activity analysis targeting the toxicity of molecules. Multiple public-domain databases of compounds have been evaluated with spiking neural networks, achieving accuracies compatible with high-quality frameworks presented in the previous literature. The numerical experiments also included an analysis of hyperparameters and tested the spiking neural networks on molecular fingerprints of different lengths. Proposing alternatives to traditional software and hardware for time- and resource-consuming tasks, such as those found in chemoinformatics, may open the door to new research and improvements in the field.
BACKGROUND: Breast cancer related lymphedema (BCRL) is a detrimental condition affecting a growing number of breast cancer (BC) survivors worldwide [1]. Effective screening programs and early diagnosis are mandatory in the clinical management of this disabling condition and limb volume assessment plays a crucial role [1]. However, a reproducible volumetric assessment is still challenging in clinical practice. In this scenario, augmented reality tools have been recently proposed for volumetric quantification of BCRL [2]. Despite the advantages in safety and time effectiveness, the integration of these devices in clinical practice is affected by several barriers, and free-to-use software for volume quantification are still lacking [3]. Therefore, the aim of this study was to develop and validate a free-to-use software for volume quantification of BCRL in order to overcome barriers to technology implementation in the complex management of BC patients. METHODS: A cohort of mixed-gender young adults was assessed by tridimensional laser scanning, centimetric method, and water displacement method. The upper limb volume measures were saved and processed using a software package composed of three programs (Edit 3D, Slice 3D, Cut 3D). The novel software package was specifically developed and freely released on the online site https://mn-visions.gitbook.455io/software-kit-for-3dls-limb-volume-quantification/. In addition, hand volume has been assessed two groups (experimental group and optimization group). Digital volume quantification algorithms have been specifically designed using the gift wrapping (GW) or cubic tessellation (TE) method. The novel software package was subsequently used to assess a small pilot sample of BCRL patients. The upper limb volumes were analyzed to assess linear regression and correlation, level of agreement, and consistency between the different methods. RESULTS: Fourty upper limb volumes of 20 participants were assessed in the present study. The linear regression analysis showed a statistically significant correlation between laser scanning method and centimetric method (R2= 0.99, p< 0.0001). A high level of agreement was reported (R2 interval from 0.93 to 0.97, r ranged from 0.965 to 0.984) between the centimetric method and the novel software package. Hand volume has been assessed in 5 subjects (experimental group). The optimization group (n: 4) demonstrated that the hand volumes calculated from digital method (tessellation method) show a high correlation with the values obtained with water displacement (ρ = 0.83; p < 0.05). Preliminary data from BCRL women were recently assessed (n:3) and suggested a high correlation between LS3D and centimetric method (R2= 0.96). CONCLUSION: Our data underlined promising results for the implementation in clinical setting of the three programs Edit 3D, Slice 3D, Cut 3D for the upper limb volume quantification. In addition, significant correlations between water displacement method (gold standard) and hand digital volume method were highlighted, suggesting intriguing implications in a precise quantification of hand volume in clinical setting. These findings might provide advantages in reproducibility between different operators enhancing data sharing between different centers. Future data on BCRL patients are needed to confirm the role of this novel free-to-use software in the rehabilitation management of breast cancer survivors. REFERENCES: 1. Heller DR et al. Prevention Is Key: Importance of Early Recognition and Referral in Combating Breast Cancer–Related Lymphedema. Journal of Oncology Practice 2019;15:263–4. 2. Invernizzi M et al. Integrating Augmented Reality Tools in Breast Cancer Related Lymphedema Prognostication and Diagnosis. J Vis Exp. 2020 6;(156). 3. Kassamani YW et al. Diagnostic Criteria for Breast Cancer-Related Lymphedema of the Upper Extremity: The Need for Universal Agreement. Ann Surg Oncol. 2022;29(2):989-1002 Citation Format: Lorenzo Lippi, Mauro Nascimben, Alessandro de Sire, Arianna Folli, Nicola Fusco, Lia Rimondini, Marco Invernizzi. A novel free-to-use software for upper limb volume quantification in breast cancer related lymphedema: implementing cutting-edge technology in the individualized therapeutic approaches of breast cancer survivors [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P5-08-18.
In medicine, tridimensional scanning devices produce digital surfaces that replicate the bodies of patients, facilitating anthropometric measurement and limb volume quantification in pathological conditions. Free programs that address this task are not commonly found, with doctors mainly relying on proprietary software. This aspect brings reduced reproducibility of studies and evaluation of alternative measures. A software package made up of three programs has been developed and released together with supporting materials to enhance reproducibility and comparisons between medical centers. In this article, the functions of the programs and steps for volume assessment were introduced together with a pilot study for upper limb volume quantification. This initial experiment aimed to also verify the performance of digital volumes derived from the convex-hull gift-wrapping algorithm and the alternative analysis methods enclosed in the software. Few of these digital volumes are parameter-dependent, requiring a value selection. The experiment was conducted on a small mixed-gender group of young adults without correction for factors like arm dominance or specific physical training. In the sample under investigation, the analysis confirmed the substantial agreement between the clinical and current configurations of digital volumes produced by the package (R2 interval from 0.93 to 0.97, r ranged from 0.965 to 0.984); in addition, as a general consideration, gender appears as a variable that could influence upper limb volume quantification if a single model is built.
Background: Breast cancer-related lymphedema (BCRL) could be one consequence of breast cancer (BC). Although several risk factors have been identified, a predictive algorithm still needs to be made available to determine the patient’s risk from an ensemble of clinical variables. Therefore, this study aimed to characterize the risk of BCRL by investigating the characteristics of autogenerated clusters of patients. Methods: The dataset under analysis was a multi-centric data collection of twenty-three clinical features from patients undergoing axillary dissection for BC and presenting BCRL or not. The patients’ variables were initially analyzed separately in two low-dimensional embeddings. Afterward, the two models were merged in a bi-dimensional prognostic map, with patients categorized into three clusters using a Gaussian mixture model. Results: The prognostic map represented the medical records of 294 women (mean age: 59.823±12.879 years) grouped into three clusters with a different proportion of subjects affected by BCRL (probability that a patient with BCRL belonged to Cluster A: 5.71%; Cluster B: 71.42%; Cluster C: 22.86%). The investigation evaluated intra- and inter-cluster factors and identified a subset of clinical variables meaningful in determining cluster membership and significantly associated with BCRL biological hazard. Conclusions: The results of this study provide potential insight for precise risk assessment of patients affected by BCRL, with implications in prevention strategies, for instance, focusing the resources on identifying patients at higher risk.
Bioinformatic techniques targeting gene expression data require specific analysis pipelines with the aim of studying properties, adaptation, and disease outcomes in a sample population. Present investigation compared together results of four numerical experiments modeling survival rates from bladder cancer genetic profiles. Research showed that a sequence of two discretization phases produced remarkable results compared to a classic approach employing one discretization of gene expression data. Analysis involving two discretization phases consisted of a primary discretizer followed by refinement or pre-binning input values before the main discretization scheme. Among all tests, the best model encloses a sequence of data transformation to compensate skewness, data discretization phase with class-attribute interdependence maximization algorithm, and final classification by voting feature intervals, a classifier that also provides discrete interval optimization.
BACKGROUND: Establishing baseline measurements on normative data is essential to evaluate standards of care and the impact of clinical or surgical treatments. Hand volume determination is relevant in pathological conditions where the anatomical structures might undergo modifications like post-treatment chronic edema. For example, one of the consequences of breast cancer treatment is the possibility of developing uni-lateral lymphedema on the upper limbs. OBJECTIVE: Arm and forearm volumetrics are well-studied techniques, whereas hand volumetry computation poses several challenges both from the clinical and digital perspectives. The current work has explored routine clinical and customized digital methodologies for hand volume appraisal on healthy subjects. METHODS: Clinical hand volumes computed by water displacement or circumferential measurements were compared to digital volumetry calculated from 3D laser scans. Digital volume quantification algorithms exploited the gift wrapping concept or cubic tessellation of acquired 3D shapes. This latter digital technique is parametric, and a calibration methodology to define the resolution of the tessellation has been validated. RESULTS: Results on a group of normal subjects demonstrated that the volumes computed from digital hand representations extracted by tessellation return values similar to the clinical water displacement volume assessment at low tolerances. CONCLUSIONS: The current investigation suggested that the tessellation algorithm could be considered a digital equivalent of water displacement for hand volumetrics. Future studies are needed to confirm these results in people with lymphedema.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.