The generation of ground truth maps from digital whole slide image subject matter remains a labour-intensive and technically challenging task, with the net effect being that the curation of large libraries of consistently and accurately tagged features remains a daunting prospect for most histology-based machine vision research teams.  To address this need, we have developed separate assisted and autonomous image segmentation computational pipelines, which both exhibit the property of converging on a highly generalizable classifier with a high area under the curve (AUC) solution, utilizing far fewer training image set tiles than typically required for deep learning schema. Initial histology feature segmentation and classification efforts with these tools have demonstrated compelling sensitivity and specificity, when compared against pixel-level ground truth maps, as generated by a panel of subject matter experts. Typical AUC values exceed 0.98 and the use of GPU-based computational clusters allows for segmentation activities to be carried out in real time, facilitating the discovery process. Interactive application demonstrations will be available as a component of the showcasing of this abstract.

Introduction of advanced diagnostics modalities has become an imperative for many hospital -based laboratories in the era of precision medicine. Yet, building a robust advanced laboratory diagnostics program poses significant challenges from the perspective of ensuring adequate human resources, access to technology and appropriate space. In this workshop, I will share our experience with strategic planning and implementation of key laboratory diagnostic initiatives such as advanced molecular diagnostics, histocompatibility, LC/MS, molecular microbiology and total laboratory automation. I will describe several frameworks for competitive positioning for modern diagnostic laboratories and describe some of the key factors for their ongoing success and sustainability. Finally, I will go over some important financial and regulatory challenges confronting clinical pathology programs. 

In recent years, convolutional neural networks (CNN)  have revolutionized the field of computer aided digital image analysis due to their accuracy in classifying and recognizing objects /patterns from different subject matters, including histopathological images. Aside from object classification, CNN is also useful for object detection/tracking and semantic segmentation. There is a lot of potential for deep learning to change and improve the practice of pathology due to the highly visual nature of the field, especially in tasks that pathologists find boring and tedious such as finding mitosis and counting cells. Other example applications of CNN in pathology include classification of lesions (e.g. benign vs. malignant), cancer localization, nuclei identification, and segmentation of regions of interests in an image. In the image below, a CNN model based on U-Net, together with a ground truth map, was able to accurately highlight regions of glomeruli in a kidney section. Running CNN experiments used to require a significant amount of programming expertise. Fortunately, open-source tools that need minimal or no programming knowledge such as Tensorflow and Orange (Biolab) are now available, making deep learning accessible to a wider audience, including Pathologists.

Biological products contain active substances coming from living cells and are usually large, complex proteins. They are used to treat many diseases such as cancer, rheumatoid arthritis, anaemia, renal failure and autoimmune diseases. However, due to their high cost, patient access is restricted, thus biosimilars came to the market. A biosimilar is defined by the United States Food and Drug Administration (FDA) as ‘biological product that is highly similar to and has no clinically meaningful differences from an existing FDA-approved reference product in terms of safety, purity and potency1’. They increase treatment options, decrease healthcare costs and improve patients’ access to very expensive therapies. Studies have proven that biosimilars offer significant cost savings to governments, which are greatly needed in the healthcare sectors. Only minor differences are acceptable between biologics and their respective biosimilars. Currently, there are few biosimilars approved for cancer treatment, but as the patents of many biologics are expiring, many more are coming to the market. These include rituximab, bevacizumab, trastuzumab, marketed for indications such as lymphomas, leukaemia, lung or breast cancer. Erythropoiesis-Stimulating agents (ESAs) are widely used for chemotherapy-induced anaemia2 and filgrastims for neutropenia respectively. Progressionfree survival (PFS) and overall survival (OS) are usually used to measure the efficacy of biosimilars used in oncology3. The aim of this study is to provide a brief review of biosimilars, their perspectives in medical oncology and the current status of some clinical trials.

In the following is described the combination of straight biochemical and organic routes to graft nucleotide sequences to a chitosan backbone. The resulting chitosan-g-ssDNA hybrid self-assembles into submicrometer size structures in dilute aqueous solution as assessed by atomic force and electron microscopy imaging. The hypothesis of self-assembly driven by chemical incompatibility between the amphiphilic chitosan and nucleic acid grafts is supported further by stability of the self-assembly against ionic strength and pH variations.

The present study is focused for the development of nutritional formulations from Moringa leaf and other traditional food regularly used in India. The study is also focused to understand the food habits and actual requirements of different societies with different geographical region. Initially Moringa leaves have been taken for the fermentation process to evaluate the value of phytates in processed products. Different procedures have been adapted for processing and fermentation of leaves. Along with some already processed food has been evaluated for phytates level. Viz. fresh wheat dough and fresh roties (Indian Bread) and marketed breads has been evaluated for the presence of phytates level. Similarly some more Indian bread made up of fresh dough of maize, barley, qunoa, bajara and jwar (Indian Millets) has been evaluated for phytates levels. The study concluded that there is different type of processing of food which is responsible for the breakdown of phytates (Phytic acid polymer). The more the phytates level in food the less will be its nutritional value but on the other hand as phytates are high in food they do chelation of many toxic compounds and minerals which may trigger mutation in cells and may lead for the development of cancer.

With its principle of non-centralized data collection and non-central database, but sharing and distributing data across networks by credentialed users with the possibility to add and at the same time avoiding data alteration, Blockchain becomes a player in the digital healthcare. From the early buzz on healthcare, it has become lately a promising technology that is able to satisfy digital healthcare interoperability. Given the review of more studies in the Biobanks creation process and the classification of biosamples data, most stakeholders note possible obstacles in the digitization process such: data collection, who handles the data, sharing principle and data owning. At this point the new, common digital form denominator shall be introduced – Datafication. This process represents: Collecting and analyzing acguizied bio data, Deploying derived intelligence, Generate and improve immaculate client experience, products, processes and operations, Together with interoperability gives an answer to question: who owns all the data, Giving people ownership of their personal data through Blockchain, Datafication based on Blockchain, adopting data interoperability inside the flow of the Biobanks creation process with notes of fine refinement and preparation for the end users. Such data are also verified and secured and no alteration of themselves is possible inside the interoperable block-chained cycle. Blockchain-based technologies will become the foundation for digital innovation in digital pathology. A unique combination of artificial intelligence, smart contracts and the Blockchain will become the nervous system of the future Biobank modelling, helping us live longer and healthier lives.

For diagnostic purposes, it’s important that microscopy images are not just images, diagnosis reports are not just unstructured information, and molecular data are not just separated from results of image analysis. Doctors and pathologists would be supported best, if suspicious or malicious structures of tissue samples are identified at the early stages. In that case the doctors be able to apply their expert knowledge more efficiently and to focus on the illness itself. This is exactly, what the HS Analysis GmbH does, when it comes to automated image analysis, structure reports and bring them with knowledge from molecular data. HS Analysis is working closely with different partners together, when digitization, digitalization and automation in pathology is going to be a part of daily routine for pathologists. With the help of modern AI and Deep Learning supported methods, Sergey Biniaminov, CEO of HS Analysis, believes to seriously inspire diagnosis and research areas such as the early detection and therapy of cancer.

Introduction: This was a descriptive retrospective study done to analyze, compare and contrast the demographic, clinical and pathological data of odontogenic tumors, cysts and maxillofacial bone tumors seen at Tikur Anbesa Hospital, Pathology department from sept.2013-oct.2018. These were analyzed for age, gender, site of tumor as well as histopathologic type using the 2017 World Health Organization classification system. From a total of 132 cases reviewed, only 107 were having complete records suitable for the study. 59 of the study subjects were males while remaining 48 were female. 60(56.1%) of cases were Benign, 16 were Malignant and the rest 31 were non-neoplastic .From the Non-neoplastic cases,(87%) of the cases were Odontogenic cysts most commonly occurring on Maxilla (63%) . The commonest benign Odontogenic tumor was Ameloblastoma (25%) with mean age of occurrence being 28.8years and M: F ratio of 1.14:1. Majority occurred on the mandible 14(93.3%). Ossifying fibroma (20%) was the 2 nd commonest benign lesion. 8 cases (50%) from the total malignant lesions were of Osteosarcoma and Primary intraosseous squamous cell carcinoma.
Conclusion: Odontogenic tumors, cysts and maxillofacial bone lesions show a definite geographic variation. In our study, Ameloblastomas were the most frequent Odontogenic tumor similar to other African studies but with a slightly younger age of presentation followed by Benign fibroosseous lesions which was in contrary to most literatures.

Objective: Evaluation of the method and outcomes of experimental myocardial infarction in rabbit as an animal model for human and veterinary studies design: Experimental procedure case review study.
Animals: Six male New Zealand rabbit (body weight 2.3 kg) were used in this study.
Methods: Left lateral thoracotomy was performed in all cases. The LAD was ligated and gross changes were recorded. Post-operative echocardiography and measurement of blood level troponin was performed in all rabbits. All cases were kept under similar condition for one month. Before euthanasia a final echocardiography was performed. All cases were euthanized by standard methods and their heart completely harvested. Measurement of infarct size by planimetry and by the use of image software was done. All hearts were submitted for histopathologic evaluation and electronic microscopic studies. An in-depth study of all data was performed.
Results: Histopathologic and gross myocardial changes in all cases were report. Echocardiographic changes were recorded at two distinct times; exactly after surgery and one month later before euthanasia. All echocardiographic   measurements were done in both series of echocardiography. Conclusion and clinical relevance: A thorough evaluation and study of histopathologic and echocardiographic changes of experimental myocardial infarction was performed and a detail explanation of procedure and surgical techniques was done.

Approximately 70% of women with epithelial ovarian cancer (EOC) are diagnosed with advanced stage disease, which is associated with high morbidity and mortality. The standard of care in advanced stage ovarian cancer is still primary debulking surgery and optimal debulking surgery should be defined as no residual tumor load. Recently, and after been widely used in Europe for more than 10 years, neoadjuvant chemotherapy followed by interval debulking surgery (defined as debulking surgery after 3 to 4 months of induction of chemotherapy) has been gaining momentum of being considered as the standard of care in numerous cancer centers throughout the US. Retrospective studies showed that neoadjuvant therapy seemed to be as good as the standard primary tumor debulking surgery for advanced stage ovarian cancer. New clinical trials using immunotherapy have been conducted on naive ovarian cancer as well as chemotherapy ovarian cancer. However, the role of pathology in handling and reporting the histologic findings in debulking surgery specimen is still widely variable. The histologic features can vary and reporting them can be very crucial and important in patient care and management.

To improve education of diabetics & prediabetics and preventative measures along with providing health care & treatment, we need to conduct screening & e-registering. Diversity of effective factors causing the disease such as age, gender, weight, sedentary life, smoking, diet, hyperlipidemia, blood pressure,blood type must be taken seriously.
The reasearch was based on sceening of 7000 people out of whom 1300 cases were diagnosed as being diadetics & prediabetics including tables, charts, and diagrams. The task was done by e-registration of people and tracking them over the period of 5 years recording medical history, vital signs, physical examination, lab results, health care and treatment.

To preserve test quality while increasing volume in a small facility. With the increase in the United States real estate values, and decrease in buildings size due to the limited available land, with decrease payments from insurance companies and with the government pressure through many complex venues to produce and maintain quality for medical patient testing, building small space laboratories is a unique strategy. Large specialty groups benefit with the construction or acquisition of small size pathology testing laboratories that will cater to their unique patient population. The objective is to build small, utilizing distinctive approaches in order to maintain the highest quality, accuracy, precision, sensitivity, specificity, cost-effectiveness, low turnaround time, and increase productivity while reducing errors.  The steps require careful planning, budget evaluation and smart financial decisions, organizational skills, leadership and directorship skills while maintaining team concert efforts. User friendly laboratory information system and information technology systems are the crucial backbone to maintain a smooth operation and connectivity.
Methods:  Decisions are based on years of experience building portions of or complete medical laboratories. Needed quality measures include: total quality management, quality control, quality assurance, enrollment in proficiency testing, and acquisition of size appropriate highly productive state-of art quality instruments. Financial processes must include: instrument cost/benefit analysis, productivity per square footage against lease costs per sq foot, clinicians’ test menu limitation.
Conclusion: Multispecialty large groups will benefit in multiple ways when building small cost-effective laboratories to accommodate their unique variety of patients.