KALSIMIS 2018 Abstracts

Full Papers
Paper Nr: 4

Adopting Semantic Information of Grayscale Radiographs for Image Classification and Retrieval


Obioma Pelka, Felix Nensa and Christoph M. Friedrich

Abstract: As the number of digital medical images taken daily rapidly increases, manual annotation is impractical, time-consuming and prone to errors. Hence, there is need to create systems that automatically classify and annotate medical images. The aim of this presented work is to utilize Transfer Learning to generate image keywords, which are substituted as text representation for medical image classification and retrieval tasks. Text preprocessing methods such as detection and removal of compound figure delimiters, stop-words, special characters and word stemming are applied before training the keyword generation model. All images are visually represented using Convolutional Neural Networks (CNN) and the Long Short-Term Memory (LSTM) based Recurrent Neural Network (RNN) Show-and-Tell model is adopted for keyword generation. To improve model performance, a second training phase is initiated, where parameters are fine-tuned using the pre-trained deep learning network Inception-ResNet-V2. For the image classification tasks, Random Forest models trained with Bag-of-Keypoints visual representations were adopted. Classification prediction accuracy was higher for all classification schemes and on two distinct radiology image datasets using the proposed approach.

Paper Nr: 5

Localization of Neuron Nucleuses in Microscopy Images with Convolutional Neural Networks


Arkadiusz Tomczyk, Bartłomiej Stasiak, Paweł Tarasiuk, Anna Gorzkiewicz, Anna Walczewska and Piotr S. Szczepaniak

Abstract: In this paper, an automatic method of neuron nucleuses localization in the images, taken with the fluorescent microscope, is presented. The proposed approach has two phases. During the first phase, a properly trained convolutional neural network acts as a non-linear filter which indicates regions of interest. The network architecture and specific method of its training are original concepts of the authors of this work. In the second phase, analysis of these regions allows to identify points representing positions of the nucleuses. To illustrate the method, images of neurons isolated from neonatal rat cerebral cortex were used. These images were inspected by a domain expert and all the visible nucleuses were manually annotated. This allowed not only to objectively assess the obtained detection results but it enabled the application of machine learning as well.

Short Papers
Paper Nr: 2

The Effectiveness of Data Augmentation for Detection of Gastrointestinal Diseases from Endoscopical Images


Andrea Asperti and Claudio Mastronardo

Abstract: The lack, due to privacy concerns, of large public databases of medical pathologies is a well-known and major problem, substantially hindering the application of deep learning techniques in this field. In this article, we investigate the possibility to supply to the deficiency in the number of data by means of data augmentation techniques, working on the recent Kvasir dataset (Pogorelov et al., 2017) of endoscopical images of gastrointestinal diseases. The dataset comprises 4,000 colored images labeled and verified by medical endoscopists, covering a few common pathologies at different anatomical landmarks: Z-line, pylorus and cecum. We show how the application of data augmentation techniques allows to achieve sensible improvements of the classification with respect to previous approaches, both in terms of precision and recall.