Deep Learning Fusion for COVID-19 Diagnosis

The outbreak of the novel coronavirus (COVID-19) disease has spurred a tremendous research boost aiming at controlling it. Under this scope, deep learning techniques have received even more attention as an asset to automatically detect patients infected by COVID-19 and reduce the doctor’s burden to manually assess medical imagery. Thus, this work considers a deep learning architecture that fuses the layers of current-state-of-the-art deep networks to produce a new structure-fused deep network. The advantages of our deep network fusion scheme are multifold, and ultimately afford an appealing COVID-19 automatic diagnosis that outbalances current deep learning methods. Indeed, evaluation on Computer Tomography (CT) and X-ray imagery considering a two-class (COVID-19/ non-COVID-19) and a four-class (COVID-19/ non-COVID-19/ Pneumonia bacterial / Pneumonia virus) classification problem, highlights the classification capabilities of our method attaining 99.3% and 100%, respectively.

Benchmarking Differentially Private Residual Networks for Medical Imagery

In this paper we measure the effectiveness of ϵ-Differential Privacy (DP) when applied to medical imaging. We compare two robust differential privacy mechanisms: Local-DP and DP-SGD and benchmark their performance when analyzing medical imagery records. We analyze the trade-off between the model's accuracy and the level of privacy it guarantees, and also take a closer look to evaluate how useful these theoretical privacy guarantees actually prove to be in the real world medical setting.

Healing the State with Violence

Chapter 2 examines imagery of medicine and disease in late-republican oratory and their use as a means of conceptualizing disorder and persuading and justifying a range of actions. After a brief overview of medical imagery in republican politics, including in earlier periods, the chapter turns to a consideration of Roman preconceptions about medical knowledge and practice. Republic images of disease are also distinguished from similar Greek imagery. Commonplace appeals to salus rei publicae, “the health or wellbeing of the state,” as justifications for violent interventions are also read through the lens of medical necessity. It is argued that imagery involving medicine was useful in part for its capacity to characterize disparate courses of action, no matter what they actually were, as salutary for the republic, while enabling the interests of one’s political enemies to be written off as causes of harmful disease. A close reading of the arguments of Cicero and his opponents in the Pro Sestio shows these tendencies in action.

Spinal Cord Segmentation in Ultrasound Medical Imagery

In this paper, we study and evaluate the task of semantic segmentation of the spinal cord in ultrasound medical imagery. This task is useful for neurosurgeons to analyze the spinal cord movement during and after the laminectomy surgical operation. Laminectomy is performed on patients that suffer from an abnormal pressure made on the spinal cord. The surgeon operates by cutting the bones of the laminae and the intervening ligaments to relieve this pressure. During the surgery, ultrasound waves can pass through the laminectomy area to give real-time exploitable images of the spinal cord. The surgeon uses them to confirm spinal cord decompression or, occasionally, to assess a tumor adjacent to the spinal cord. The Freely pulsating spinal cord is a sign of adequate decompression. To evaluate the semantic segmentation approaches chosen in this study, we constructed two datasets using images collected from 10 different patients performing the laminectomy surgery. We found that the best solution for this task is Fully Convolutional DenseNets if the spinal cord is already in the train set. If the spinal cord does not exist in the train set, U-Net is the best. We also studied the effect of integrating inside both models some deep learning components like Atrous Spatial Pyramid Pooling (ASPP) and Depthwise Separable Convolution (DSC). We added a post-processing step and detailed the configurations to set for both models.

Edge Enhancing Accelerated Diffusion Model for Speckle Denoising in Medical Imagery

Speckle noise occurs in a wide range of medical images due to sampling and digital degradation. Removing speckle noise from medical images is the key for further automated processing techniques like segmentation, and can help the clinicians with better diagnosis and therapy. We consider partial differential equation (PDE)-based denoising model which is a modified Euler-Lagrange equation derived from the total variation minimization functional with additional speckle noise constraints. The new PDE model is designed and optimized to rectify speckle noise and enhance edges present in medical imagery. Wealso develop the efficicient and stable discretization techniques for the corresponding speckle denoising model. The method is tested for several types of images including ultrasound images, and it is compared favorably to the conventional denoising model.

The Vaccine and Its Simulacra: Agnotology, Ontology and Biopolitics in France, 1800–1865

The advent of smallpox vaccine in France in 1800 inaugurates a new relationship between administration, public health and the definition of medical facts. As Napoleon himself refused to establish compulsory vaccination, a Comité de vaccine was established so as to impose the idea of a riskless vaccine protecting forever from smallpox. This article studies how human experimentation, clinical experience, medical imagery and statistics maintained the idea of a perfect vaccine for six decades, despite the multiplication of cases of post-vaccination smallpox and vaccine contaminations.

Classifying the body in Marlene Dumas' The Image as Burden

Medical photography, and in particular dermatological imagery, is often assumed to provide an objective, and functional, representation of disease and that it can act as a diagnostic aid. By contrast, artistic conceptions of the images of the body tend to focus on interpretative heterogeneity and ambiguity, aiming to create or explore meaning rather than enact a particular function. In her 2015 retrospective exhibition at the Tate Modern, South African artist Marlene Dumas questions these disciplinary divides by using medical imagery (among other photographic sources) as the basis for her portraits. Her portrait ‘The White Disease’ draws on an unidentified photograph taken from a medical journal, but obscures the original image to such a degree that any representation of a particular disease is highly questionable. The title creates a new classification, which reflects on disease and on the racial politics of South Africa during apartheid. Though, on the one hand, these techniques are seemingly disparate from the methods of medical understanding, features such as reliance on classification, and attempts at dispelling ambiguity, bring Dumas’ work closer to the history of dermatological portraits than would usually be perceived to be the case. In considering the continuities and disparities between conceptualisations of skin in dermatology and Dumas’ art, this paper questions assumptions of photographic objectivity to suggest that there is greater complexity and interpretative scope in medical dermatological images than might initially be assumed.