Tu1040 Comparison of Different Machine Learning Systems in Classifying Focal Liver Lesions Based on Clinical and Dynamic Imaging Data

2013 ◽  
Vol 144 (5) ◽  
pp. S-1038-S-1039
Author(s):  
Costin T. Streba ◽  
Cristin C. Vere ◽  
Larisa D. Sandulescu ◽  
Adrian Saftoiu ◽  
Dan Ionut Gheonea ◽  
...  
2014 ◽  
Vol 146 (5) ◽  
pp. S-933
Author(s):  
Costin T. Streba ◽  
Cristin Constantin Vere ◽  
Larisa D. Sandulescu ◽  
Adrian Saftoiu ◽  
Dan Ionut Gheonea ◽  
...  

2021 ◽  
Vol 8 ◽  
Author(s):  
Silvia Burti ◽  
Alessandro Zotti ◽  
Federico Bonsembiante ◽  
Barbara Contiero ◽  
Tommaso Banzato

To describe the computed tomographic (CT) features of focal liver lesions (FLLs) in dogs, that could enable predicting lesion histotype. Dogs diagnosed with FLLs through both CT and cytopathology and/or histopathology were retrospectively collected. Ten qualitative and 6 quantitative CT features have been described for each case. Lastly, a machine learning-based decision tree was developed to predict the lesion histotype. Four categories of FLLs - hepatocellular carcinoma (HCC, n = 13), nodular hyperplasia (NH, n = 19), other benign lesions (OBL, n = 18), and other malignant lesions (OML, n = 19) - were evaluated in 69 dogs. Five of the observed qualitative CT features resulted to be statistically significant in the distinction between the 4 categories: surface, appearance, lymph-node appearance, capsule formation, and homogeneity of contrast medium distribution. Three of the observed quantitative CT features were significantly different between the 4 categories: the Hounsfield Units (HU) of the radiologically normal liver parenchyma during the pre-contrast scan, the maximum dimension, and the ellipsoid volume of the lesion. Using the machine learning-based decision tree, it was possible to correctly classify NHs, OBLs, HCCs, and OMLs with an accuracy of 0.74, 0.88, 0.87, and 0.75, respectively. The developed decision tree could be an easy-to-use tool to predict the histotype of different FLLs in dogs. Cytology and histology are necessary to obtain the final diagnosis of the lesions.


2018 ◽  
Vol 12 ◽  
pp. 85-98
Author(s):  
Bojan Kostadinov ◽  
Mile Jovanov ◽  
Emil STANKOV

Data collection and machine learning are changing the world. Whether it is medicine, sports or education, companies and institutions are investing a lot of time and money in systems that gather, process and analyse data. Likewise, to improve competitiveness, a lot of countries are making changes to their educational policy by supporting STEM disciplines. Therefore, it’s important to put effort into using various data sources to help students succeed in STEM. In this paper, we present a platform that can analyse student’s activity on various contest and e-learning systems, combine and process the data, and then present it in various ways that are easy to understand. This in turn enables teachers and organizers to recognize talented and hardworking students, identify issues, and/or motivate students to practice and work on areas where they’re weaker.


Processes ◽  
2020 ◽  
Vol 8 (9) ◽  
pp. 1071
Author(s):  
Lucia Billeci ◽  
Asia Badolato ◽  
Lorenzo Bachi ◽  
Alessandro Tonacci

Alzheimer’s disease is notoriously the most common cause of dementia in the elderly, affecting an increasing number of people. Although widespread, its causes and progression modalities are complex and still not fully understood. Through neuroimaging techniques, such as diffusion Magnetic Resonance (MR), more sophisticated and specific studies of the disease can be performed, offering a valuable tool for both its diagnosis and early detection. However, processing large quantities of medical images is not an easy task, and researchers have turned their attention towards machine learning, a set of computer algorithms that automatically adapt their output towards the intended goal. In this paper, a systematic review of recent machine learning applications on diffusion tensor imaging studies of Alzheimer’s disease is presented, highlighting the fundamental aspects of each work and reporting their performance score. A few examined studies also include mild cognitive impairment in the classification problem, while others combine diffusion data with other sources, like structural magnetic resonance imaging (MRI) (multimodal analysis). The findings of the retrieved works suggest a promising role for machine learning in evaluating effective classification features, like fractional anisotropy, and in possibly performing on different image modalities with higher accuracy.


Diagnostics ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 1244
Author(s):  
Sonja Schwarz ◽  
Dirk-André Clevert ◽  
Michael Ingrisch ◽  
Thomas Geyer ◽  
Vincent Schwarze ◽  
...  

Background: To evaluate the diagnostic accuracy of quantitative perfusion parameters in contrast-enhanced ultrasound to differentiate malignant from benign liver lesions. Methods: In this retrospective study 134 patients with a total of 139 focal liver lesions were included who underwent contrast enhanced ultrasound (CEUS) between 2008 and 2018. All examinations were performed by a single radiologist with more than 15 years of experience using a second-generation blood pool contrast agent. The standard of reference was histopathology (n = 60), MRI or CT (n = 75) or long-term CEUS follow up (n = 4). For post processing regions of interests were drawn both inside of target lesions and the liver background. Time–intensity curves were fitted to the CEUS DICOM dataset and the rise time (RT) of contrast enhancement until peak enhancement, and a late-phase ratio (LPR) of signal intensities within the lesion and the background tissue, were calculated and compared between malignant and benign liver lesion using Student’s t-test. Quantitative parameters were evaluated with respect to their diagnostic accuracy using receiver operator characteristic curves. Both features were then combined in a logistic regression model and the cumulated accuracy was assessed. Results: RT of benign lesions (14.8 ± 13.8 s, p = 0.005), and in a subgroup analysis, particular hemangiomas (23.4 ± 16.2 s, p < 0.001) differed significantly to malignant lesions (9.3 ± 3.8 s). The LPR was significantly different between benign (1.59 ± 1.59, p < 0.001) and malignant lesions (0.38 ± 0.23). Logistic regression analysis with RT and LPR combined showed a high diagnostic accuracy of quantitative CEUS parameters with areas under the curve of 0.923 (benign vs. malignant) and 0.929 (hemangioma vs. malignant. Conclusions: Quantified CEUS parameters are helpful to differentiate malignant from benign liver lesions, in particular in case of atypical hemangiomas.


Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2514
Author(s):  
Tharindu Kaluarachchi ◽  
Andrew Reis ◽  
Suranga Nanayakkara

After Deep Learning (DL) regained popularity recently, the Artificial Intelligence (AI) or Machine Learning (ML) field is undergoing rapid growth concerning research and real-world application development. Deep Learning has generated complexities in algorithms, and researchers and users have raised concerns regarding the usability and adoptability of Deep Learning systems. These concerns, coupled with the increasing human-AI interactions, have created the emerging field that is Human-Centered Machine Learning (HCML). We present this review paper as an overview and analysis of existing work in HCML related to DL. Firstly, we collaborated with field domain experts to develop a working definition for HCML. Secondly, through a systematic literature review, we analyze and classify 162 publications that fall within HCML. Our classification is based on aspects including contribution type, application area, and focused human categories. Finally, we analyze the topology of the HCML landscape by identifying research gaps, highlighting conflicting interpretations, addressing current challenges, and presenting future HCML research opportunities.


Entropy ◽  
2020 ◽  
Vol 23 (1) ◽  
pp. 18
Author(s):  
Pantelis Linardatos ◽  
Vasilis Papastefanopoulos ◽  
Sotiris Kotsiantis

Recent advances in artificial intelligence (AI) have led to its widespread industrial adoption, with machine learning systems demonstrating superhuman performance in a significant number of tasks. However, this surge in performance, has often been achieved through increased model complexity, turning such systems into “black box” approaches and causing uncertainty regarding the way they operate and, ultimately, the way that they come to decisions. This ambiguity has made it problematic for machine learning systems to be adopted in sensitive yet critical domains, where their value could be immense, such as healthcare. As a result, scientific interest in the field of Explainable Artificial Intelligence (XAI), a field that is concerned with the development of new methods that explain and interpret machine learning models, has been tremendously reignited over recent years. This study focuses on machine learning interpretability methods; more specifically, a literature review and taxonomy of these methods are presented, as well as links to their programming implementations, in the hope that this survey would serve as a reference point for both theorists and practitioners.


Sign in / Sign up

Export Citation Format

Share Document