SlideTiler: A dataset creator software for boosting deep learning on histological whole slide images.

The introduction of deep learning caused a significant breakthrough in digital pathology. Thanks to its capability of mining hidden data patterns in digitised histological slides to resolve diagnostic tasks and extract prognostic and predictive information. However, the high performance achieved in classification tasks depends on the availability of large datasets, whose collection and preprocessing are still time-consuming processes.

Comparison of Different Convolutional Neural Network Activation Functions and Methods for Building Ensembles for Small to Midsize Medical Data Sets.

CNNs and other deep learners are now state-of-the-art in medical imaging research. However, the small sample size of many medical data sets dampens performance and results in overfitting. In some medical areas, it is simply too labor-intensive and expensive to amass images numbering in the hundreds of thousands.

Deep Features for Training Support Vector Machines.

Features play a crucial role in computer vision. Initially designed to detect salient elements by means of handcrafted algorithms, features now are often learned using different layers in convolutional neural networks (CNNs). This paper develops a generic computer vision system based on features extracted from trained CNNs.

Deep learning-based BCI for gait decoding from EEG with LSTM recurrent neural network.

Objective: Mobile Brain/Body Imaging (MoBI) frameworks allowed the research community to find evidence of cortical involvement at walking initiation and during locomotion. However, the decoding of gait patterns from brain signals remains an open challenge. The aim of this work is to propose and validate a deep learning model to decode gait phases from Electroenchephalography (EEG).

Stochastic Selection of Activation Layers for Convolutional Neural Networks.

In recent years, the field of deep learning has achieved considerable success in pattern recognition, image segmentation, and many other classification fields. There are many studies and practical applications of deep learning on images, video, or text classification. Activation functions play a crucial role in discriminative capabilities of the deep neural networks and the design of new "static" or "dynamic" activation functions is an active area of research.

Bioimage Classification with Handcrafted and Learned Features.

Bioimage classification is increasingly becoming more important in many biological studies including those that require accurate cell phenotype recognition, subcellular localization, and histopathological classification. In this paper, we present a new General Purpose (GenP) bioimage classification method that can be applied to a large range of classification problems. The GenP system we propose is an ensemble that combines multiple texture features (both handcrafted and learned descriptors) for superior and generalizable discriminative power.

Risk factors for three-month mortality after discharge in a cohort of non-oncologic hospitalized elderly patients: Results from the REPOSI study.

Background: Short-term prognosis, e.g. mortality at three months, has many important implications in planning the overall management of patients, particularly non-oncologic patients in order to avoid futile practices.

Toward a General-Purpose Heterogeneous Ensemble for Pattern Classification.

We perform an extensive study of the performance of different classification approaches on twenty-five datasets (fourteen image datasets and eleven UCI data mining datasets). The aim is to find General-Purpose (GP) heterogeneous ensembles (requiring little to no parameter tuning) that perform competitively across multiple datasets. The state-of-the-art classifiers examined in this study include the support vector machine, Gaussian process classifiers, random subspace of adaboost, random subspace of rotation boosting, and deep learning classifiers.

Texture Descriptors Based on Dijkstra's Algorithm for Medical Image Analysis.

In this paper we investigate a new approach for extracting features from a texture using Dijkstra's algorithm. The method maps images into graphs and gray level differences into transition costs. Texture is measured over the whole image comparing the costs found by Dijkstra's algorithm with the geometric distance of the pixels.

Inappropriate prescription of allopurinol and febuxostat and risk of adverse events in the elderly: results from the REPOSI registry.

Purpose: To investigate the prevalence of xanthine oxidase (XO) inhibitors prescription at admission and discharge in elderly hospital in-patients, to analyze the appropriateness of their use in relation to evidence-based indications, to evaluate the predictors of inappropriate prescription at discharge and the association with adverse events 3 months after hospital discharge.

Methods: This cross-sectional study, based upon a prospective registry, was held in 95 Italian internal medicine and geriatric hospital wards. The sample included 4035 patients aged 65 years or older at admission and 3502 at discharge.

Different approaches for extracting information from the co-occurrence matrix.

In 1979 Haralick famously introduced a method for analyzing the texture of an image: a set of statistics extracted from the co-occurrence matrix. In this paper we investigate novel sets of texture descriptors extracted from the co-occurrence matrix; in addition, we compare and combine different strategies for extending these descriptors. The following approaches are compared: the standard approach proposed by Haralick, two methods that consider the co-occurrence matrix as a three-dimensional shape, a gray-level run-length set of features and the direct use of the co-occurrence matrix projected onto a lower dimensional subspace by principal component analysis.

Recurrent pericarditis: autoimmune or autoinflammatory?

Idiopathic recurrent acute pericarditis (IRAP) represents the most troublesome complication of acute pericarditis and occurs in up to 20-50% of patients. It is generally idiopathic or postcardiac injury. IRAP is a disease of suspected immune-mediated pathogenesis.

Arrhythmias presenting in neonatal lupus.

Perfusion of human foetal heart with anti-Ro/SSA antibodies induces transient heart block. Anti-Ro/SSA antibodies may cross-react with T- and L-type calcium channels, and anti-p200 antibodies may cause calcium to accumulate in rat heart cells. These actions may explain a direct electrophysiological effect of these antibodies.

[Splenic artero-venous fistula and portal hypertension. A case report with review of the literature].

Splenic artero-venous fistula (SAVF) is a rare but potentially curable cause of pre-hepatic portal hypertension. About 100 cases have been reported in the world medical literature. The Authors report a case of 46-year-old man with a splenic artery aneurysm and a large SAVF treated by surgical resection of splenic vessels and splenectomy.

Early and late recurrence after liver resection for hepatocellular carcinoma: prognostic and therapeutic implications.

Objective: To evaluate the predictive factors, the therapy, and the prognosis of intrahepatic recurrence (IR) after surgery for hepatocellular carcinoma (HCC).

Summary Background Data: The predictive factors of IR are debated. To class the recurrence according to the modality of presentation may help to find a correlation and to select the right therapy for the recurrence.

Aggressive recurrence after radiofrequency ablation of liver neoplasms.

Radiofrequency ablation is considered safe for inoperable liver neoplasms; with small lesions the rate of success is very high, the local recurrence is marginal and generally suitable for a retreatment. We have little information about the possibility of rapid regrowth of the tumor after a response judged as complete. We present four patients, affected by primary (3 patients) and metastatic (1 patient) uninodular cancer.

Early and long-term prognostic factors after liver resection for HCC.

The Authors discuss the principal early and long term predictive factors after liver resection in patients with hepatocellular carcinoma (HCC). The Authors report (131 cases) early mortality as 7.6%, entirely confined in the group, numerically prevalent and affected by cirrhosis.

[Resection surgery in malignant neoplasms of the exocrine pancreas: our experience, 1987-1994].

From 1987 to 1994, 24 patients underwent resection for pancreatic cancer; they represented 24% of all patients observed in that period. Surgical procedures were a pancreatoduodenectomy (PD) in 20 cases, a distal pancreatectomy in 4 cases, a palliative intervention in 61 cases, an exploratory laparotomy in 13 cases and a video laparoscopy in 2 cases. Adjuvant treatments were given in addition to resection in 20 patients.