Fairness and Ethics in Artificial Intelligence-Based Medical Imagining

Artificial intelligence has a huge array of current and potential applications in healthcare and medicine. Ethical issues arising due to algorithmic biases are one of the greatest challenges faced in the generalizability of AI models today. The authors address safety and regulatory barriers that impede data sharing in medicine as well as potential changes to existing techniques and frameworks that might allow ethical data sharing for machine learning. With these developments in view, they also present different algorithmic models that are being used to develop machine learning-based medical systems that will potentially evolve to be free of the sample, annotator, and temporal bias. These AI-based medical imaging models will then be completely implemented in healthcare facilities and institutions all around the world, even in the remotest areas, making diagnosis and patient care both cheaper and freely accessible.

5th INTERNATIONAL SYMPOSIUM “SMART LION”. MEDICAL IMAGINING AND GLOBAL HEALTH, OCTOBER 7–9, 2021

For the fifth year in a row, the international symposium SMART LION (Science Medicine Arts Research Translational Lviv International Opportunity Network) is taking place in Lviv, which has become a good tradition in scientific and practical communication. This year, the symposium is focused on the “Medical Imagining and Global Health”. The scientific event was held in Lviv on October 7–9, 2021. The format was mixed. The event was held with the support of Danylo Halytsky Lviv National Medical University, Medical Commission of the Shevchenko Scientific Society, Lviv City Council and Lviv Convention Bureau. The symposium was focused on providing a unique opportunity for young and experienced scientists and doctors working on the development of innovative technologies in medicine, to further cooperate in the field of science and integrate their knowledge and achievements into world science. The interesting and eventful agenda included over 20 lectures and poster presentations delivered by national and foreign lecturers, as well as a master class on “How to use the online Open Journal System to publish scientific articles in medical journals”. To focus the attention of young scientists, students and interns on topical issues of medicine, well-known scientists from different countries of Europe and America are annually invited to attend the symposium as speakers. During the two days of the conference, Ukrainian and foreign leading experts in the field of medicine – Leo Wolansky (USA), Sandor Szabo (USA), Vassyl Lonchyna (USA), Klaus Holzmann (Austria), Siegfried Knasmüller (Austria), Armen Gasparyan (Great Britain), Ivan Wolansky (USA), Yuriy Ivaniv (Ukraine), Nelya Oryshchyn (Ukraine), Andriy Netliukh (Ukraine), Yuriy Mylyan (Ukraine), Oksana Zayachkivska (Ukraine), Roman Plyatsko (Ukraine), Khrystyna Lishchuk-Yakymovych (Ukraine), Olena Zimba (Ukraine) – shared their experience and the latest achievements in the field of medicine. After a two-year break due to a COVID-19 pandemic, joint live discussions between young scientists – students, interns, post-graduate students – with leading scientists during poster presentations and panel discussions held at the symposium helped them rethink the need for systemic changes in medical education and the implementation of modern diagnostic methods utilizing real-time visualization with elements of artificial intelligence into curriculums. In conclusion, Oksana Zayachkivska (Professor, Chair of the Department of Normal Physiology, Danylo Halytsky Lviv National Medical University; Editor-in-Chief of the “Proceeding of the Shevchenko Scientific Society. Medical Sciences”) and Vassyl Lonchyna (Professor, University of Chicago Pritzker School of Medicine, Ukrainian Catholic University) summed up the symposium and expressed hope to meet again at SMART LION 2022.

Pancreatic pseudocyst, pancreatitis, and incomplete pancreas divisum in a child treated with endotherapy: a case report

Pancreatic divisum (PD) is caused by the lack of fusion of the pancreatic duct during the embryonic period. Considering the incidence rate of PD, clinicians lack an understanding of the disease, which is usually asymptomatic. Some patients with PD may experience recurrent pancreatitis and progress to chronic pancreatitis. Recently, a 13-year-old boy presented with pancreatic pseudocyst, recurrent pancreatitis, and incomplete PD, and we report this patient’s clinical data regarding the diagnosis, medical imagining, and treatment. The patient had a history of recurrent pancreatitis and abdominal pain. Magnetic resonance cholangiopancreatography was chosen for diagnosis of PD, pancreatitis, and pancreatic pseudocyst, followed by endoscopic retrograde cholangiopancreatography, minor papillotomy, pancreatic pseudocyst drainage, and stent implantation. In the follow-up, the pseudocyst lesions were completely resolved, and no recurrent pancreatitis has been observed.

Neuro-Imaging Machine Learning Techniques for Alzheimer's Disease Diagnosis

Alzheimer's disease (AD) is considered one of the most common dementia's forms affecting senior's age staring from 65 and over. The standard method for identifying AD are usually based on behavioral, neuropsychological and cognitive tests and sometimes followed by a brain scan. Advanced medical imagining modalities such as MRI and pattern recognition techniques are became good tools for predicting AD. In this chapter, an automatic AD diagnosis system from MRI images based on using machine learning tools is proposed. A bench mark dataset is used to evaluate the performance of the proposed system. The adopted dataset consists of 20 patients for each diagnosis case including cognitive impairment, Alzheimer's disease and normal. Several evaluation measurements are used to evaluate the robustness of the proposed diagnosis system. The experimental results reveal the good performance of the proposed system.

3D Construction of Brain using 2D MRI Slices

Medical image analysis plays a more and more major role in medicine. Detection and analysis of risks causing cancer and other medical issues in early-stage help to prevent death. PET, CT, X-ray and MRI are the medical imagining techniques used. There have been a number of researches have done on constructing the 3D model for better analysis of the structure. The paper is proposed about the construction of a 3D brain model using 2D slices of MRI. The 3 different images of the brain are considered (T1, T2 and PD). The image registration is applied to T1, T2 and PD and fusion is done. The fused image includes of the complete detail of the brain, these 2D slices are used to construct the 3D model. The 3D map is created and surface to volume construction is applied to build the 3D model.

Improving Image Segmentation by DFS Algorithm

Medical imagining has proven to be a significant field for examining human tissues non-intrusively. One of the subset of Imaging is the Image segmentation where in an image is split into significant regions which being later used for classification and performing analysis. This process is quiet complex as it involves accurately detecting and removing the affected part of the image containing abnormal tissues which are later being used for analysis. Image segmentation employs numerous techniques and approaches. Though there exist several methods and techniques for image segmentation but all of them can’t be implemented on medical images. The existing paper put forwards a complete survey and review concerning the medical image segmentation models, techniques, algorithms along with the challenges faced with the involvement of contrast filtering and large scale image processing perspectives. The technique of Discrete Feature Segmentation (DFS) is adopted for extracting the attributes related to a medical image. For improvising the contrast of an image, the popular method of Histogram equalization is utilized that basically enlarges the dynamic range of intensity. A method is recommended for defining the parameters of the Contrast-Limited Adaptive Histogram Equalization (CLAHE) by utilizing entropy of image. The CLAHE method that projects intensity levels concerning the medical images is backed up by evidence from detection trials and anecdotal evidence. For classifying the diseases in medical image, the prime emphasis is on the FCM (Fuzzy C-Means (FCM) algorithm. Present research paper compares various techniques of image enhancement considering their quality parameters (PSNR, Mean, MSE, Entropy, SN, Variance and RMS).

Neuro-Imaging Machine Learning Techniques for Alzheimer's Disease Diagnosis

Alzheimer's disease (AD) is considered one of the most common dementia's forms affecting senior's age staring from 65 and over. The standard method for identifying AD are usually based on behavioral, neuropsychological and cognitive tests and sometimes followed by a brain scan. Advanced medical imagining modalities such as MRI and pattern recognition techniques are became good tools for predicting AD. In this chapter, an automatic AD diagnosis system from MRI images based on using machine learning tools is proposed. A bench mark dataset is used to evaluate the performance of the proposed system. The adopted dataset consists of 20 patients for each diagnosis case including cognitive impairment, Alzheimer's disease and normal. Several evaluation measurements are used to evaluate the robustness of the proposed diagnosis system. The experimental results reveal the good performance of the proposed system.

Overview of Biomedical Engineering

Biomedical Engineering is a branch that unites engineering methods with biological and medical sciences in order to enhance the quality of our lives. It focuses on understanding intricate systems of living organisms, and on technology development, algorithms, methods, and advanced medical knowledge, while enhancing the conveyance and success of clinical medicine. With engineering principles, biomedical engineering improves the procedures and devices to overcome health care and medical problems by combining both biology and medicine with engineering principals. In the field of Biomedical Engineering, engineers usually need to have background knowledge from such different fields of engineering as electronics, mechanical, and chemical engineering. Specialties in this field like bioinstrumentation, biomechanics, biomaterials, medical imagining, clinical engineering, bioinformatics, telemedicine and rehabilitation engineering, which will be introduced in this chapter together with an overview of the field of biomedical engineering.