Explaining Bounding Boxes in Deep Object Detectors Using Post Hoc Methods for Autonomous Driving Systems.

Deep learning has rapidly increased in popularity, leading to the development of perception solutions for autonomous driving. The latter field leverages techniques developed for computer vision in other domains for accomplishing perception tasks such as object detection. However, the black-box nature of deep neural models and the complexity of the autonomous driving context motivates the study of explainability in these models that perform perception tasks. Moreover, this work explores explainable AI techniques for the object detection task in the context of autonomous driving. An extensive and detailed comparison is carried out between gradient-based and perturbation-based methods (e.g., D-RISE). Moreover, several experimental setups are used with different backbone architectures and different datasets to observe the influence of these aspects in the explanations. All the techniques explored consist of saliency methods, making their interpretation and evaluation primarily visual. Nevertheless, numerical assessment methods are also used. Overall, D-RISE and guided backpropagation obtain more localized explanations. However, D-RISE highlights more meaningful regions, providing more human-understandable explanations. To the best of our knowledge, this is the first approach to obtaining explanations focusing on the regression of the bounding box coordinates.

Annotating for Artificial Intelligence Applications in Digital Pathology: A Practical Guide for Pathologists and Researchers.

Training machine learning models for artificial intelligence (AI) applications in pathology often requires extensive annotation by human experts, but there is little guidance on the subject. In this work, we aimed to describe our experience and provide a simple, useful, and practical guide addressing annotation strategies for AI development in computational pathology. Annotation methodology will vary significantly depending on the specific study's objectives, but common difficulties will be present across different settings. We summarize key aspects and issue guiding principles regarding team interaction, ground-truth quality assessment, different annotation types, and available software and hardware options and address common difficulties while annotating. This guide was specifically designed for pathology annotation, intending to help pathologists, other researchers, and AI developers with this process.

Two-Stage Framework for Faster Semantic Segmentation.

Semantic segmentation consists of classifying each pixel according to a set of classes. Conventional models spend as much effort classifying easy-to-segment pixels as they do classifying hard-to-segment pixels. This is inefficient, especially when deploying to situations with computational constraints. In this work, we propose a framework wherein the model first produces a rough segmentation of the image, and then patches of the image estimated as hard to segment are refined. The framework is evaluated in four datasets (autonomous driving and biomedical), across four state-of-the-art architectures. Our method accelerates inference time by four, with additional gains for training time, at the cost of some output quality.

3D Breast Volume Estimation.

INTRODUCTION: Breast volume estimation is considered crucial for breast cancer surgery planning. A single, easy, and reproducible method to estimate breast volume is not available. This study aims to evaluate, in patients proposed for mastectomy, the accuracy of the calculation of breast volume from a low-cost 3D surface scan (Microsoft Kinect) compared to the breast MRI and water displacement technique. MATERIAL AND METHODS: Patients with a Tis/T1-T3 breast cancer proposed for mastectomy between July 2015 and March 2017 were assessed for inclusion in the study. Breast volume calculations were performed using a 3D surface scan and the breast MRI and water displacement technique. Agreement between volumes obtained with both methods was assessed with the Spearman and Pearson correlation coefficients. RESULTS: Eighteen patients with invasive breast cancer were included in the study and submitted to mastectomy. The level of agreement of the 3D breast volume compared to surgical specimens and breast MRI volumes was evaluated. For mastectomy specimen volume, an average (standard deviation) of 0.823 (0.027) and 0.875 (0.026) was obtained for the Pearson and Spearman correlations, respectively. With respect to MRI annotation, we obtained 0.828 (0.038) and 0.715 (0.018). DISCUSSION: Although values obtained by both methodologies still differ, the strong linear correlation coefficient suggests that 3D breast volume measurement using a low-cost surface scan device is feasible and can approximate both the MRI breast volume and mastectomy specimen with sufficient accuracy. CONCLUSION: 3D breast volume measurement using a depth-sensor low-cost surface scan device is feasible and can parallel MRI breast and mastectomy specimen volumes with enough accuracy. Differences between methods need further development to reach clinical applicability. A possible approach could be the fusion of breast MRI and the 3D surface scan to harmonize anatomic limits and improve volume delimitation.

Electrocardiogram lead conversion from single-lead blindly-segmented signals.

BACKGROUND: The standard configuration's set of twelve electrocardiogram (ECG) leads is optimal for the medical diagnosis of diverse cardiac conditions. However, it requires ten electrodes on the patient's limbs and chest, which is uncomfortable and cumbersome. Interlead conversion methods can reconstruct missing leads and enable more comfortable acquisitions, including in wearable devices, while still allowing for adequate diagnoses. Currently, methodologies for interlead ECG conversion either require multiple reference (input) leads and/or require input signals to be temporally aligned considering the ECG landmarks. METHODS: Unlike the methods in the literature, this paper studies the possibility of converting ECG signals into all twelve standard configuration leads using signal segments from only one reference lead, without temporal alignment (blindly-segmented). The proposed methodology is based on a deep learning encoder-decoder U-Net architecture, which is compared with adaptations based on convolutional autoencoders and label refinement networks. Moreover, the method is explored for conversion with one single shared encoder or multiple individual encoders for each lead. RESULTS: Despite the more challenging settings, the proposed methodology was able to attain state-of-the-art level performance in multiple target leads, and both lead I and lead II seem especially suitable to convert certain sets of leads. In cross-database tests, the methodology offered promising results despite acquisition setup differences. Furthermore, results show that the presence of medical conditions does not have a considerable effect on the method's performance. CONCLUSIONS: This study shows the feasibility of converting ECG signals using single-lead blindly-segmented inputs. Although the results are promising, further efforts should be devoted towards the improvement of the methodologies, especially the robustness to diverse acquisition setups, in order to be applicable to cardiac health monitoring in wearable devices and less obtrusive clinical scenarios.

Maximum Relevance Minimum Redundancy Dropout with Informative Kernel Determinantal Point Process.

In recent years, deep neural networks have shown significant progress in computer vision due to their large generalization capacity; however, the overfitting problem ubiquitously threatens the learning process of these highly nonlinear architectures. Dropout is a recent solution to mitigate overfitting that has witnessed significant success in various classification applications. Recently, many efforts have been made to improve the Standard dropout using an unsupervised merit-based semantic selection of neurons in the latent space. However, these studies do not consider the task-relevant information quality and quantity and the diversity of the latent kernels. To solve the challenge of dropping less informative neurons in deep learning, we propose an efficient end-to-end dropout algorithm that selects the most informative neurons with the highest correlation with the target output considering the sparsity in its selection procedure. First, to promote activation diversity, we devise an approach to select the most diverse set of neurons by making use of determinantal point process (DPP) sampling. Furthermore, to incorporate task specificity into deep latent features, a mutual information (MI)-based merit function is developed. Leveraging the proposed MI with DPP sampling, we introduce the novel DPPMI dropout that adaptively adjusts the retention rate of neurons based on their contribution to the neural network task. Empirical studies on real-world classification benchmarks including, MNIST, SVHN, CIFAR10, CIFAR100, demonstrate the superiority of our proposed method over recent state-of-the-art dropout algorithms in the literature.

Machine Learning Improvements to Human Motion Tracking with IMUs.

Inertial Measurement Units (IMUs) have become a popular solution for tracking human motion. The main problem of using IMU data for deriving the position of different body segments throughout time is related to the accumulation of the errors in the inertial data. The solution to this problem is necessary to improve the use of IMUs for position tracking. In this work, we present several Machine Learning (ML) methods to improve the position tracking of various body segments when performing different movements. Firstly, classifiers were used to identify the periods in which the IMUs were stopped (zero-velocity detection). The models Random Forest, Support Vector Machine (SVM) and neural networks based on Long-Short-Term Memory (LSTM) layers were capable of identifying those periods independently of the motion and body segment with a substantially higher performance than the traditional fixed-threshold zero-velocity detectors. Afterwards, these techniques were combined with ML regression models based on LSTMs capable of estimating the displacement of the sensors during periods of movement. These models did not show significant improvements when compared with the more straightforward double integration of the linear acceleration data with drift removal for translational motion estimate. Finally, we present a model based on LSTMs that combined simultaneously zero-velocity detection with the translational motion of sensors estimate. This model revealed a lower average error for position tracking than the combination of the previously referred methodologies.

A Regression Model for Predicting Shape Deformation after Breast Conserving Surgery.

Breast cancer treatments can have a negative impact on breast aesthetics, in case when surgery is intended to intersect tumor. For many years mastectomy was the only surgical option, but more recently breast conserving surgery (BCS) has been promoted as a liable alternative to treat cancer while preserving most part of the breast. However, there is still a significant number of BCS intervened patients who are unpleasant with the result of the treatment, which leads to self-image issues and emotional overloads. Surgeons recognize the value of a tool to predict the breast shape after BCS to facilitate surgeon/patient communication and allow more educated decisions; however, no such tool is available that is suited for clinical usage. These tools could serve as a way of visually sensing the aesthetic consequences of the treatment. In this research, it is intended to propose a methodology for predict the deformation after BCS by using machine learning techniques. Nonetheless, there is no appropriate dataset containing breast data before and after surgery in order to train a learning model. Therefore, an in-house semi-synthetic dataset is proposed to fulfill the requirement of this research. Using the proposed dataset, several learning methodologies were investigated, and promising outcomes are obtained.

Towards a Continuous Biometric System Based on ECG Signals Acquired on the Steering Wheel.

Electrocardiogram signals acquired through a steering wheel could be the key to seamless, highly comfortable, and continuous human recognition in driving settings. This paper focuses on the enhancement of the unprecedented lesser quality of such signals, through the combination of Savitzky-Golay and moving average filters, followed by outlier detection and removal based on normalised cross-correlation and clustering, which was able to render ensemble heartbeats of significantly higher quality. Discrete Cosine Transform (DCT) and Haar transform features were extracted and fed to decision methods based on Support Vector Machines (SVM), k-Nearest Neighbours (kNN), Multilayer Perceptrons (MLP), and Gaussian Mixture Models - Universal Background Models (GMM-UBM) classifiers, for both identification and authentication tasks. Additional techniques of user-tuned authentication and past score weighting were also studied. The method's performance was comparable to some of the best recent state-of-the-art methods (94.9% identification rate (IDR) and 2.66% authentication equal error rate (EER)), despite lesser results with scarce train data (70.9% IDR and 11.8% EER). It was concluded that the method was suitable for biometric recognition with driving electrocardiogram signals, and could, with future developments, be used on a continuous system in seamless and highly noisy settings.

Mobile-Based Analysis of Malaria-Infected Thin Blood Smears: Automated Species and Life Cycle Stage Determination.

Microscopy examination has been the pillar of malaria diagnosis, being the recommended procedure when its quality can be maintained. However, the need for trained personnel and adequate equipment limits its availability and accessibility in malaria-endemic areas. Rapid, accurate, accessible diagnostic tools are increasingly required, as malaria control programs extend parasite-based diagnosis and the prevalence decreases. This paper presents an image processing and analysis methodology using supervised classification to assess the presence of malaria parasites and determine the species and life cycle stage in Giemsa-stained thin blood smears. The main differentiation factor is the usage of microscopic images exclusively acquired with low cost and accessible tools such as smartphones, a dataset of 566 images manually annotated by an experienced parasilogist being used. Eight different species-stage combinations were considered in this work, with an automatic detection performance ranging from 73.9% to 96.2% in terms of sensitivity and from 92.6% to 99.3% in terms of specificity. These promising results attest to the potential of using this approach as a valid alternative to conventional microscopy examination, with comparable detection performances and acceptable computational times.

Fingerprint Liveness Detection in the Presence of Capable Intruders.

Fingerprint liveness detection methods have been developed as an attempt to overcome the vulnerability of fingerprint biometric systems to spoofing attacks. Traditional approaches have been quite optimistic about the behavior of the intruder assuming the use of a previously known material. This assumption has led to the use of supervised techniques to estimate the performance of the methods, using both live and spoof samples to train the predictive models and evaluate each type of fake samples individually. Additionally, the background was often included in the sample representation, completely distorting the decision process. Therefore, we propose that an automatic segmentation step should be performed to isolate the fingerprint from the background and truly decide on the liveness of the fingerprint and not on the characteristics of the background. Also, we argue that one cannot aim to model the fake samples completely since the material used by the intruder is unknown beforehand. We approach the design by modeling the distribution of the live samples and predicting as fake the samples very unlikely according to that model. Our experiments compare the performance of the supervised approaches with the semi-supervised ones that rely solely on the live samples. The results obtained differ from the ones obtained by the more standard approaches which reinforces our conviction that the results in the literature are misleadingly estimating the true vulnerability of the biometric system.

A cognitively-motivated framework for partial face recognition in unconstrained scenarios.

Humans perform and rely on face recognition routinely and effortlessly throughout their daily lives. Multiple works in recent years have sought to replicate this process in a robust and automatic way. However, it is known that the performance of face recognition algorithms is severely compromised in non-ideal image acquisition scenarios. In an attempt to deal with conditions, such as occlusion and heterogeneous illumination, we propose a new approach motivated by the global precedent hypothesis of the human brain's cognitive mechanisms of perception. An automatic modeling of SIFT keypoint descriptors using a Gaussian mixture model (GMM)-based universal background model method is proposed. A decision is, then, made in an innovative hierarchical sense, with holistic information gaining precedence over a more detailed local analysis. The algorithm was tested on the ORL, ARand Extended Yale B Face databases and presented state-of-the-art performance for a variety of experimental setups.

Anonymizing medical case-based explanations through disentanglement.

Case-based explanations are an intuitive method to gain insight into the decision-making process of deep learning models in clinical contexts. However, medical images cannot be shared as explanations due to privacy concerns. To address this problem, we propose a novel method for disentangling identity and medical characteristics of images and apply it to anonymize medical images. The disentanglement mechanism replaces some feature vectors in an image while ensuring that the remaining features are preserved, obtaining independent feature vectors that encode the images' identity and medical characteristics. We also propose a model to manufacture synthetic privacy-preserving identities to replace the original image's identity and achieve anonymization. The models are applied to medical and biometric datasets, demonstrating their capacity to generate realistic-looking anonymized images that preserve their original medical content. Additionally, the experiments show the network's inherent capacity to generate counterfactual images through the replacement of medical features.

An interpretable machine learning system for colorectal cancer diagnosis from pathology slides.

Considering the profound transformation affecting pathology practice, we aimed to develop a scalable artificial intelligence (AI) system to diagnose colorectal cancer from whole-slide images (WSI). For this, we propose a deep learning (DL) system that learns from weak labels, a sampling strategy that reduces the number of training samples by a factor of six without compromising performance, an approach to leverage a small subset of fully annotated samples, and a prototype with explainable predictions, active learning features and parallelisation. Noting some problems in the literature, this study is conducted with one of the largest WSI colorectal samples dataset with approximately 10,500 WSIs. Of these samples, 900 are testing samples. Furthermore, the robustness of the proposed method is assessed with two additional external datasets (TCGA and PAIP) and a dataset of samples collected directly from the proposed prototype. Our proposed method predicts, for the patch-based tiles, a class based on the severity of the dysplasia and uses that information to classify the whole slide. It is trained with an interpretable mixed-supervision scheme to leverage the domain knowledge introduced by pathologists through spatial annotations. The mixed-supervision scheme allowed for an intelligent sampling strategy effectively evaluated in several different scenarios without compromising the performance. On the internal dataset, the method shows an accuracy of 93.44% and a sensitivity between positive (low-grade and high-grade dysplasia) and non-neoplastic samples of 0.996. On the external test samples varied with TCGA being the most challenging dataset with an overall accuracy of 84.91% and a sensitivity of 0.996.

Objective assessment of cosmetic outcome after targeted intraoperative radiotherapy in breast cancer: results from a randomised controlled trial.

The international randomised targeted intraoperative radiotherapy (TARGIT) trial has demonstrated evidence of non-inferiority between the novel technique of TARGIT (intra-operative radiotherapy with Intrabeam(®)) and conventional external beam radiotherapy (EBRT) in women with early breast cancer in terms of the primary outcome measure of risk of local relapse within the treated breast. Cosmesis is an increasingly important outcome of breast conserving treatment with both surgery and radiotherapy contributing to this. It was unknown if the single high dose of TARGIT may lead to damaging fibrosis and thus impair cosmesis further, so we objectively evaluated the aesthetic outcome of patients within the TARGIT randomised controlled trial. We have used an objective assessment tool for evaluation of cosmetic outcome. Frontal digital photographs were taken at baseline (before TARGIT or EBRT) and yearly thereafter for up to 5 years. The photographs were analysed by BCCT.core, a validated software which produces a composite score based on symmetry, colour and scar. 342 patients were assessed, median age at baseline 64 years (IQR 59-68). The scores were dichotomised into Excellent and Good (EG), and Fair and Poor (FP). There were statistically significant increases in the odds of having an outcome of EG for patients in the TARGIT group relative to the EBRT group at year 1 (OR 2.07, 95 % CI 1.12-3.85, p = 0.021) and year 2 (OR 2.11, 95 % CI 1.0-4.45, p = 0.05). Following a totally objective assessment in a randomised setting, the aesthetic outcome of patients demonstrates that those treated with TARGIT have a superior cosmetic result to those patients who received conventional external beam radiotherapy.

Symmetry-based regularization in deep breast cancer screening.

Breast cancer is the most common and lethal form of cancer in women. Recent efforts have focused on developing accurate neural network-based computer-aided diagnosis systems for screening to help anticipate this disease. The ultimate goal is to reduce mortality and improve quality of life after treatment. Due to the difficulty in collecting and annotating data in this domain, data scarcity is - and will continue to be - a limiting factor. In this work, we present a unified view of different regularization methods that incorporate domain-known symmetries in the model. Three general strategies were followed: (i) data augmentation, (ii) invariance promotion in the loss function, and (iii) the use of equivariant architectures. Each of these strategies encodes different priors on the functions learned by the model and can be readily introduced in most settings. Empirically we show that the proposed symmetry-based regularization procedures improve generalization to unseen examples. This advantage is verified in different scenarios, datasets and model architectures. We hope that both the principle of symmetry-based regularization and the concrete methods presented can guide development towards more data-efficient methods for breast cancer screening as well as other medical imaging domains.

Deep Edge Detection Methods for the Automatic Calculation of the Breast Contour.

Breast cancer conservative treatment (BCCT) is a form of treatment commonly used for patients with early breast cancer. This procedure consists of removing the cancer and a small margin of surrounding tissue, while leaving the healthy tissue intact. In recent years, this procedure has become increasingly common due to identical survival rates and better cosmetic outcomes than other alternatives. Although significant research has been conducted on BCCT, there is no gold-standard for evaluating the aesthetic results of the treatment. Recent works have proposed the automatic classification of cosmetic results based on breast features extracted from digital photographs. The computation of most of these features requires the representation of the breast contour, which becomes key to the aesthetic evaluation of BCCT. State-of-the-art methods use conventional image processing tools that automatically detect breast contours based on the shortest path applied to the Sobel filter result in a 2D digital photograph of the patient. However, because the Sobel filter is a general edge detector, it treats edges indistinguishably, i.e., it detects too many edges that are not relevant to breast contour detection and too few weak breast contours. In this paper, we propose an improvement to this method that replaces the Sobel filter with a novel neural network solution to improve breast contour detection based on the shortest path. The proposed solution learns effective representations for the edges between the breasts and the torso wall. We obtain state of the art results on a dataset that was used for developing previous models. Furthermore, we tested these models on a new dataset that contains more variable photographs and show that this new approach shows better generalization capabilities as the previously developed deep models do not perform so well when faced with a different dataset for testing. The main contribution of this paper is to further improve the capabilities of models that perform the objective classification of BCCT aesthetic results automatically by improving upon the current standard technique for detecting breast contours in digital photographs. To that end, the models introduced are simple to train and test on new datasets which makes this approach easily reproducible.

A CAD system for automatic dysplasia grading on H&E cervical whole-slide images.

Cervical cancer is the fourth most common female cancer worldwide and the fourth leading cause of cancer-related death in women. Nonetheless, it is also among the most successfully preventable and treatable types of cancer, provided it is early identified and properly managed. As such, the detection of pre-cancerous lesions is crucial. These lesions are detected in the squamous epithelium of the uterine cervix and are graded as low- or high-grade intraepithelial squamous lesions, known as LSIL and HSIL, respectively. Due to their complex nature, this classification can become very subjective. Therefore, the development of machine learning models, particularly directly on whole-slide images (WSI), can assist pathologists in this task. In this work, we propose a weakly-supervised methodology for grading cervical dysplasia, using different levels of training supervision, in an effort to gather a bigger dataset without the need of having all samples fully annotated. The framework comprises an epithelium segmentation step followed by a dysplasia classifier (non-neoplastic, LSIL, HSIL), making the slide assessment completely automatic, without the need for manual identification of epithelial areas. The proposed classification approach achieved a balanced accuracy of 71.07% and sensitivity of 72.18%, at the slide-level testing on 600 independent samples, which are publicly available upon reasonable request.

BOLD: Blood-gas and Oximetry Linked Dataset - Open Source Research.

Pulse oximeters measure peripheral arterial oxygen saturation (SpO 2 ) noninvasively, while the gold standard (SaO 2 ) involves arterial blood gas measurement. There are known racial and ethnic disparities in their performance. BOLD is a new comprehensive dataset that aims to underscore the importance of addressing biases in pulse oximetry accuracy, which disproportionately affect darker-skinned patients. The dataset was created by harmonizing three Electronic Health Record databases (MIMIC-III, MIMIC-IV, eICU-CRD) comprising Intensive Care Unit stays of US patients. Paired SpO 2 and SaO 2 measurements were time-aligned and combined with various other sociodemographic and parameters to provide a detailed representation of each patient. BOLD includes 49,099 paired measurements, within a 5-minute window and with oxygen saturation levels between 70-100%. Minority racial and ethnic groups account for ∼25% of the data - a proportion seldom achieved in previous studies. The codebase is publicly available. Given the prevalent use of pulse oximeters in the hospital and at home, we hope that BOLD will be leveraged to develop debiasing algorithms that can result in more equitable healthcare solutions.

Evaluating the ability of an artificial-intelligence cloud-based platform designed to provide information prior to locoregional therapy for breast cancer in improving patient's satisfaction with therapy: The CINDERELLA trial.

BACKGROUND: Breast cancer therapy improved significantly, allowing for different surgical approaches for the same disease stage, therefore offering patients different aesthetic outcomes with similar locoregional control. The purpose of the CINDERELLA trial is to evaluate an artificial-intelligence (AI) cloud-based platform (CINDERELLA platform) vs the standard approach for patient education prior to therapy. METHODS: A prospective randomized international multicentre trial comparing two methods for patient education prior to therapy. After institutional ethics approval and a written informed consent, patients planned for locoregional treatment will be randomized to the intervention (CINDERELLA platform) or controls. The patients in the intervention arm will use the newly designed web-application (CINDERELLA platform, CINDERELLA APProach) to access the information related to surgery and/or radiotherapy. Using an AI system, the platform will provide the patient with a picture of her own aesthetic outcome resulting from the surgical procedure she chooses, and an objective evaluation of this aesthetic outcome (e.g., good/fair). The control group will have access to the standard approach. The primary objectives of the trial will be i) to examine the differences between the treatment arms with regards to patients' pre-treatment expectations and the final aesthetic outcomes and ii) in the experimental arm only, the agreement of the pre-treatment AI-evaluation (output) and patient's post-therapy self-evaluation. DISCUSSION: The project aims to develop an easy-to-use cost-effective AI-powered tool that improves shared decision-making processes. We assume that the CINDERELLA APProach will lead to higher satisfaction, better psychosocial status, and wellbeing of breast cancer patients, and reduce the need for additional surgeries to improve aesthetic outcome.