Abstract
Lower limb amputation is a condition affecting millions of people worldwide. Patients are often prescribed with lower limb prostheses to aid their mobility, but these prostheses require frequent adjustments through an iterative and manual process, which heavily depends on patient feedback and on the prosthetist's experience. New computer-aided design and manufacturing technologies have been emerging as ways to improve the fitting process by creating virtual models of the prosthesis' interface component with the limb, the socket. Using Adversarial Autoencoders, a generative model describing both transtibial and transfemoral sockets was created. Two strategies were tested to counteract the small size of the dataset: transfer learning using the ModelNet dataset and data augmentation through a previously validated socket statistical shape model. The minimum reconstruction error was 0.00124 mm and was obtained for the model which combined the two approaches. A single-blind assessment conducted with prosthetists showed that, while generated and real shapes are distinguishable, most generated ones assume plausible shapes. Our results show that the use of transfer learning allowed for a correct training and regularization of the latent space, inducing in the model generative abilities with potential clinical applications.

Abstract
BackgroundTraumatic Brain Injury (TBI) is one of the leading causes of injury related mortality in the world, with severe cases reaching mortality rates of 30-40%. It is highly heterogeneous both in causes and consequences, complicating medical interpretation and prognosis. Gathering clinical, demographic, and laboratory data to perform a prognosis requires time and skill in several clinical specialties. Machine learning (ML) methods can take advantage of the data and guide physicians toward a better prognosis and, consequently, better healthcare. The objective of this study was to develop and test a wide range of machine learning models and evaluate their capability of predicting mortality of TBI, at hospital discharge, while assessing the similarity between the predictive value of the data and clinical significance. MethodsThe used dataset is the Hackathon Pediatric Traumatic Brain Injury (HPTBI) dataset, composed of electronic health records containing clinical annotations and demographic data of 300 patients. Four different classification models were tested, either with or without feature selection. For each combination of the classification model and feature selection method, the area under the receiver operator curve (ROC-AUC), balanced accuracy, precision, and recall were calculated. ResultsMethods based on decision trees perform better when using all features (Random Forest, AUC = 0.86 and XGBoost, AUC = 0.91) but other models require prior feature selection to obtain the best results (k-Nearest Neighbors, AUC = 0.90 and Artificial Neural Networks, AUC = 0.84). Additionally, Random Forest and XGBoost allow assessing the feature's importance, which could give insights for future strategies on the clinical routine. ConclusionPredictive capability depends greatly on the combination of model and feature selection methods used but, overall, ML models showed a very good performance in mortality prediction for TBI. The feature importance results indicate that predictive value is not directly related to clinical significance.

Abstract
The estimation of the spectral absorption coefficient of biological tissues provides valuable information that can be used in diagnostic procedures. Such estimation can be made using direct calculations from invasive spectral measurements or though machine learning algorithms based on noninvasive or minimally invasive spectral measurements. Since in a noninvasive approach, the number of measurements is limited, an exploratory study to investigate the use of artificial generated data in machine learning techniques was performed to evaluate the spectral absorption coefficient of the brain cortex. Considering the spectral absorption coefficient that was calculated directly from invasive measurements as reference, the similar spectra that were estimated through different machine learning approaches were able to provide comparable information in terms of pigment, DNA and blood contents in the cortex. The best estimated results were obtained based only on the experimental measurements, but it was also observed that artificially generated spectra can be used in the estimations to increase accuracy, provided that a significant number of experimental spectra are available both to generate the complementary artificial spectra and to estimate the resulting absorption spectrum of the tissue. © 2022 Journal of Biomedical Photonics & Engineering. © J-BPE.

Abstract
Artificial Intelligence-based tools have shown promising results to help clinicians in diagnosis tasks. Radio-genomics would aid in the genotype characterization using information from radiologic images. The prediction of the mutations status of main oncogenes associated with lung cancer will help the clinicians to have a more accurate diagnosis and a personalized treatment plan, decreasing the need to use the biopsy. In this work, novel and objective features were extracted from the lung that contained the nodule, and several machine learning methods were combined with feature selection techniques to select the best approach to predict the EGFR mutation status in lung cancer CT images. An AUC of 0.756 ± 0.055 was obtained using a logistic regression and independent component analysis as feature selector, supporting the hypothesis that CT images can capture pathophysiological information with great value for clinical assessment and personalized medicine of lung cancer. Clinical Relevance-Radiogenomic approaches could be an interesting help for lung cancer characterization. This work represents a preliminary study for the development of computer-aided decision systems to provide a more accurate and fast characterization of lung cancer which is fundamental for an adequate treatment plan for lung cancer patients.

Abstract
Neuroblastoma (NB) is the most common extracranial solid tumor in childhood. Genomic amplification of MYCN is associated with poor outcomes and is detected in 16% of all NB cases. CT scans and MRI are the imaging techniques recommended for diagnosis and disease staging. The assessment of imaging features such as tumor volume, shape, and local extension represent relevant prognostic information. Radiogenomics have shown powerful results in the assessment of the genotype based on imaging findings automatically extracted from medical images. In this work, random forest was used to classify the MYCN amplification using radiomic features extracted from CT slices in a population of 46 NB patients. The learning model showed an area under the curve (AUC) of 0.85 ± 0.13, suggesting that radiomic-based methodologies might be helpful in the extraction of information that is not accessible by human naked eyes but could aid the clinicians on the diagnosis and treatment plan definition. Clinical relevance - This approach represents a random forest-based model to predict the MYCN amplification in NB patients that could give a faster, earlier, and repeatable analysis of the tumor along the time.

Abstract
Deep Learning (DL) based classification algorithms have been shown to achieve top results in clinical diagnosis, namely with lung cancer datasets. However, the complexity and opaqueness of the models together with the still scant training datasets call for the development of explainable modeling methods enabling the interpretation of the results. To this end, in this paper we propose a novel interpretability approach and demonstrate how it can be used on a malignancy lung cancer DL classifier to assess its stability and congruence even when fed a low amount of image samples. Additionally, by disclosing the regions of the medical images most relevant to the resulting classification the approach provides important insights to the correspondent clinical meaning apprehended by the algorithm. Explanations of the results provided by ten different models against the same test sample are compared. These attest the stability of the approach and the algorithm focus on the same image regions.