Despite the advances in automated medical image segmentation, AI models still underperform in various clinical settings, posing challenges for integration into real-world workflows. In this pre-registered prospective multicenter evaluation, we analyzed 20 state-of-the-art mandibular segmentation models across 19,218 segmentations of 1,000 clinically resampled CT/CBCT scans. Our results suggest that for a given model, segmentation accuracy can vary by up to 25% in Dice score as socio-technical factors such as voxel size, bone orientation, and patient conditions (e.g., osteosynthesis or pathology) shift from favorable to adverse. Higher sharpness, isotropic smaller voxels, and neutral orientation significantly improved results, while metallic osteosynthesis and anatomical complexity led to significant degradation. Our findings challenge the common view of AI models as “plug-and-play” tools and suggest evidence-based optimization recommendations for both clinicians and developers. This will in turn boost the integration of AI segmentation tools in routine healthcare.

Abstract Object detection is one of the most fundamental problems to tackle in the computer vision research area. Recent advances in multimodal data streams and deep learning architectures have prompted a fast growth in the field of multimodal learning, which brings several advantages over single-modality approaches for object detection, such as improved accuracy, robustness to noise and ambiguity, handling of complex scenarios and adaptability to diverse data. Some of the biggest challenges when implementing a multimodal learning approach are the selection of the fusion strategy, design of processing architecture, modality alignment/synchronization and interpretability of such high-dimensional representations. To address this challenge, we propose a feature-level fusion architecture for object detection based on extracting YOLO features from images, spectral and rhythm features from sound using Mel-frequency cepstral coefficients, and general descriptors from radar modalities that, after timestamp and homography transformation matrix alignment, are combined with an attention mechanism into a single classification network. Preliminary experiments indicate that the proposed architecture can constitute itself as a base pipeline for several different multimodal object detection tasks in real-world applications.

With the massive proliferation of data-driven algorithms, such as deep learning-based approaches, the availability of high-quality data is of great interest. Volumetric data is very important in medicine, as it ranges from disease diagnoses to therapy monitoring. When the dataset is sufficient, models can be trained to help doctors with these tasks. Unfortunately, there are scenarios where large amounts of data is unavailable. For example, rare diseases and privacy issues can lead to restricted data availability. In non-medical fields, the high cost of obtaining enough high-quality data can also be a concern. A solution to these problems can be the generation of realistic synthetic data using Generative Adversarial Networks (GANs). The existence of these mechanisms is a good asset, especially in healthcare, as the data must be of good quality, realistic, and without privacy issues. Therefore, most of the publications on volumetric GANs are within the medical domain. In this review, we provide a summary of works that generate realistic volumetric synthetic data using GANs. We therefore outline GAN-based methods in these areas with common architectures, loss functions and evaluation metrics, including their advantages and disadvantages. We present a novel taxonomy, evaluations, challenges, and research opportunities to provide a holistic overview of the current state of volumetric GANs.

In the last years, the number of machine learning algorithms and their parameters has increased significantly. On the one hand, this increases the chances of finding better models. On the other hand, it increases the complexity of the task of training a model, as the search space expands significantly. As the size of datasets also grows, traditional approaches based on extensive search start to become prohibitively expensive in terms of computational resources and time, especially in data streaming scenarios. This paper describes an approach based on meta-learning that tackles two main challenges. The first is to predict key performance indicators of machine learning models. The second is to recommend the best algorithm/configuration for training a model for a given machine learning problem. When compared to a state-of-the-art method (AutoML), the proposed approach is up to 130x faster and only 4% worse in terms of average model quality. Hence, it is especially suited for scenarios in which models need to be updated regularly, such as in streaming scenarios with big data, in which some accuracy can be traded for a much shorter model training time.

This paper presents an approach on entrepreneurship education which helps to turn ideas into Minimum Viable Products (MVP) and to capacitate students to become entrepreneurs. In this approach, we integrate development and management project to different business models. Students acquire, in addition to technical competencies, skills on market knowledge and business modeling. This approach has been applied for several years in an informatics engineering course and suggests a set of activities on 18 weeks. Teachers’ perceptions and students’ opinions were collected through direct observations and using a questionnaire in order to evaluate the process behind this pedagogical project which goes beyond the walls of the university. Most of the students are satisfied with the process since they develop projects that have a good fit with the market needs and opportunities and some of them are close to creating a startup.

The aim of this paper is to provide a comprehensive overview of the MICCAI 2020 AutoImplant Challenge. The approaches and publications submitted and accepted within the challenge will be summarized and reported, highlighting common algorithmic trends and algorithmic diversity. Furthermore, the evaluation results will be presented, compared and discussed in regard to the challenge aim: seeking for low cost, fast and fully automated solutions for cranial implant design. Based on feedback from collaborating neurosurgeons, this paper concludes by stating open issues and post-challenge requirements for intra-operative use. The codes can be found at https://github.com/Jianningli/tmi.

Fully convolutional networks have been achieving remarkable results in image semantic segmentation, while being efficient. Such efficiency results from the capability of segmenting several voxels in a single forward pass. So, there is a direct spatial correspondence between a unit in a feature map and the voxel in the same location. In a convolutional layer, the kernel spans over all channels and extracts information from them. We observe that linear recombination of feature maps by increasing the number of channels followed by compression may enhance their discriminative power. Moreover, not all feature maps have the same relevance for the classes being predicted. In order to learn the inter-channel relationships and recalibrate the channels to suppress the less relevant ones, squeeze and excitation blocks were proposed in the context of image classification with convolutional neural networks. However, this is not well adapted for segmentation with fully convolutional networks since they segment several objects simultaneously, hence a feature map may contain relevant information only in some locations. In this paper, we propose recombination of features and a spatially adaptive recalibration block that is adapted for semantic segmentation with fully convolutional networks- the SegSE block. Feature maps are recalibrated by considering the cross-channel information together with spatial relevance. The experimental results indicate that recombination and recalibration improve the results of a competitive baseline, and generalize across three different problems: brain tumor segmentation, stroke penumbra estimation, and ischemic stroke lesion outcome prediction. The obtained results are competitive or outperform the state of the art in the three applications.

Cardio Vascular Disease (CVD) also known as heart and circulatory disease comprises all the illnesses of the heart and the circulatory system, namely coronary heart disease, angina, heart attack, congenital heart disease or stroke. CVDs are, nowadays, one of the main causes of death. Indeed, this fact reveals the centrality of prevention and how important is to be aware on these kind of situations. Thus, this work will focus on the development of a decision support system to help to prevent these events from happening, centred on a formal framework based on Mathematical Logic and Logic Programming for Knowledge Representation and Reasoning, complemented with a Case Based Reasoning approach to computing that caters to the handling of incomplete, unknown or even self-contradictory information or knowledge.

Among brain tumors, gliomas are the most common and aggressive, leading to a very short life expectancy in their highest grade. Thus, treatment planning is a key stage to improve the quality of life of oncological patients. Magnetic resonance imaging (MRI) is a widely used imaging technique to assess these tumors, but the large amount of data produced by MRI prevents manual segmentation in a reasonable time, limiting the use of precise quantitative measurements in the clinical practice. So, automatic and reliable segmentation methods are required; however, the large spatial and structural variability among brain tumors make automatic segmentation a challenging problem. In this paper, we propose an automatic segmentation method based on Convolutional Neural Networks (CNN), exploring small 3 ×3 kernels. The use of small kernels allows designing a deeper architecture, besides having a positive effect against overfitting, given the fewer number of weights in the network. We also investigated the use of intensity normalization as a pre-processing step, which though not common in CNN-based segmentation methods, proved together with data augmentation to be very effective for brain tumor segmentation in MRI images. Our proposal was validated in the Brain Tumor Segmentation Challenge 2013 database (BRATS 2013), obtaining simultaneously the first position for the complete, core, and enhancing regions in Dice Similarity Coefficient metric (0.88, 0.83, 0.77) for the Challenge data set. Also, it obtained the overall first position by the online evaluation platform. We also participated in the on-site BRATS 2015 Challenge using the same model, obtaining the second place, with Dice Similarity Coefficient metric of 0.78, 0.65, and 0.75 for the complete, core, and enhancing regions, respectively.