Hematology is the study and practice of treating diseases of the blood, including sickle cell anemia, leukemia, lymphoma, myeloma, and many types of hemophilia. The physiology, pathology, etiology, diagnosis, treatment, prognosis, and prevention of blood-related illnesses are all covered under the field of internal medicine known as hematology. Hematologists identify blood count or platelet anomalies and concentrate mostly on the lymphatic and bone marrow systems. The lymph nodes, spleen, thymus, and lymphoid tissue are among the organs that hematologists treat
Blood is made up of several parts, Red blood cells, white blood cells, and platelets make up about 45% of the volume of blood collectively, and plasma makes up about 55% of the volume. Red blood cells, also referred to as RBCs or erythrocytes, account for around 45% of total blood volume and transport oxygen from the lungs to body tissue. Additionally, they transport carbon dioxide back to the lungs for exhalation. They are made in the bone marrow and are disc-shaped
Hematologists use various diagnostic tools, including blood tests, bone marrow biopsies, and genetic testing, to identify and understand these disorders. Treatment options may include medication, transfusions, chemotherapy, stem cell transplants, and other specialized therapies.
Advancements in hematology have led to improved treatments and outcomes for many blood-related conditions.
Basic Of Hematology Lab
The blood count is one of the most frequently requested laboratory tests. Abnormal blood counts are often incidental findings and are not necessarily associated with clinical symptoms. Many are temporarily irrelevant. Separating the abnormalities with pathological value from these is a core task in hematology. Beyond the blood count, the hematology laboratory offers a wide range of diagnostic options. It ranges from standard biochemical tests and special methods
The HSA KIT software ensures accuracy down to the last pixel with a user-friendly interface and top-notch professional annotation features. This can improve the overall analysis process by standardising procedures, preserving consistency, and fostering reproducibility
It has never been simpler to analyse samples and digitise slides Customers who want to keep up with today’s “better” alternatives and increase the efficiency of their workflow can receive an unparalleled experience from HSA KIT The HSA team goes above and beyond to satisfy its clients, from the software integration and installation to the unending support and upgrade
Whole slide imaging, also referred to as virtual microscopy, is the process of fully scanning a microscope slide and producing a single high-resolution digital file. This is often done by taking lots of tiny, high-resolution picture tiles or strips, montaging them together, and then creating a complete image of a histological slice. The processes of many laboratories are changing as a result of whole slide imaging. With the use of slide management tools, specimens on glass slides may now be converted into high-resolution digital files that can be effectively kept, retrieved, analysed, and shared with scientists from across the world.
Key features of Whole Slide Images include:
- High Resolution: WSI captures extremely detailed images at high resolutions, enabling pathologists to zoom in and examine cellular and tissue structures in depth.
- Digital Manipulation: With WSI, pathologists can adjust focus, lighting, and other parameters digitally, enhancing the ability to identify and analyze specific features.
- Remote Access and Collaboration: WSI technology enables pathologists to review and collaborate on cases remotely, which is especially useful for consultations and research involving experts in different locations.
- Archiving and Storage: Digital storage of WSI eliminates the need for physical slides, reducing storage space requirements and enabling easier archiving and retrieval of images.
- Education and Training: WSI can be used for educational purposes, allowing students and trainees to learn and practice with a variety of samples.
- Quantitative Analysis: WSI can support quantitative analysis techniques, such as image analysis algorithms, to quantify specific features within tissue samples.
- Time Efficiency: Reviewing digital images can potentially be faster and more efficient than manually scanning through physical slides.
Scanning in HSA KIT
The blood smears are scanned with the HSA SCAN software. This offers the possibility to automatically scan slides with the scan function. The digitization of the sample requires an interaction between software, hardware and user. In order to create a WSI of a sample, the microscope and the software must first be set up correctly. To do this, the user controls the motors via a user interface in the software.The user has to move the sample to the correct starting position. The scan starts at the left edge of the sample in the top corner. In addition, the sample should first be focused. When the correct start position is reached, the user starts the scan. The sample is now automatically scanned. As soon as the sample has been completely acquired, the scan is stopped and then saved.
Creating digital ready slides
Adoption of digital pathology is a multifaceted project involving many stakeholders across the pathology department. The impact on the laboratory is not isolated to simply installing a scanner, but rather affects the whole workflow to generate optimized Digital Ready Slides. Standardization of histological slide preparation requires focus on both optimization of individual workflow steps as well as a holistic overview of the complete process from sample acquisition right through to diagnosis. Knowing this in advance and taking appropriate steps to effectively support change management can promote engagement and pave a path to success
Digitalization of the specimens
The specimen collection (in this context: microscopic slides) forms the basis for a system for virtual microscopy, and is available for learning purposes at all universities and most institutes. It is important to pay attention to quality when selecting the slides, as much effort is put into scanning the slides and processing them, for example, the effortful writing and placing of annotations. In return for the efforts, a virtual specimen is created that, once perfectly selected, never again has to be edited or replaced. At first, it needs to be made clear what the outcome is, when speaking about the digitalization of a slide. The result of scanning a slide is a digital image similar to those taken with today’s digital cameras or smart phones. The difference between a microscopical slide scan and a photograph is the resolution: today’s digital cameras achieve a resolution of up to 36 mega pixel (MP), while a microscopically scanned slide using a 40x objective (400x magnification) easily reaches 10 giga pixel (GP).
A subset of machine learning, a more general category of artificial intelligence (AI), is deep learning. To learn from data and make predictions, it entails training artificial neural networks, in particular deep neural networks. Due to its impressive performance in a variety of tasks, including image recognition, natural language processing, speech recognition, and more, deep learning has attracted a great deal of attention and popularity in recent years.
An example of Annotating
Deep Learning Model can be integrated into the Laboratory Information System
Large amounts of data produced in medical and research laboratories must be managed and organised, and this is where Laboratory Information Systems (LIS) come in. These systems facilitate data analysis, streamlined laboratory workflows, and effective interprofessional communication. In order to further improve LIS’s capabilities, there is growing interest in integrating deep learning models. This is due to the rapid advancements in AI and deep learning. In this article, we examine the potential advantages and difficulties of incorporating deep learning models into LIS and talk about the important factors involved.
Ground Truth Data (GTD)
A set of precisely labelled or annotated data that is used as a standard for developing and testing machine learning models is referred to as “ground truth data.” Ground truth data is essential for creating and validating algorithms in a variety of fields, including computer vision, natural language processing, and medical imaging.
Workflow In Hematology Lab
A hematology laboratory’s workflow consists of several steps that are carried out to analyse and identify blood-related disorders. Red blood cells, white blood cells, platelets, and other blood components, as well as other relevant parameters, are all evaluated by hematology labs.
At HS Analysis, we take a comprehensive approach to slide analysis. We don’t just analyze the slides themselves, but we also integrate our solutions within the existing infrastructure. This includes connecting to LIS (Laboratory Information System) and naming the slides in a way that makes them easy to save, search, and use for medical purposes. Our goal is to provide a seamless experience for our clients, allowing them to access and utilize the data they need quickly and efficiently.
How can HSA KIT contribute to optimize your workflow even further
Before the integration of artificial intelligence (AI) in the medical workflow, doctors faced challenges in analyzing medical images manually and achieving accurate diagnoses. However, with the expertise of HS Analysis (HSA), a healthcare company, and their utilization of AI, specifically Deep Learning, in hospitals, laboratories, and research centers, the process of diagnosing various diseases, including hematology diseases, has significantly improved. The implementation of AI has particularly aided oncologists in identifying diseases more effectively.
Most laboratories use CellaVision for hematology diagnostics. To further improve and perfect the evaluation of CellaVision, the HSA KIT is perfect. By connecting HSA KIT to CellaVision or to your workflow, it is possible to automate the scanning of smears that still have to be manually microscoped by an employee and to evaluate them in real time using a deep learning model (e.g. HyperHaemaNet). This ability to easily integrate HSA KIT into your existing workflow can further save time and improve results even more.
AI based analyses using HSA KIT would provide:
- Standardised process with subjective/objective analysis
- Extraction of relevant features from raw data and create meaningful representations for training AI models
- Module selection and configuration without excessive coding
- Easy to learn software: Annotate , Train and Automate
- Quick and efficient analysis of multiple medical images which cuts down time for diagnosis or treament
- Automated report generation to boost productivity and help physicians or radiologists in evaluation process
How HSA KIT Facilitates the Transition from Microscopically Identified Cells to IHC and Flow Cytometry
The transition from microscopic identification to more advanced techniques like immunohistochemistry (IHC) and flow cytometry marks a pivotal juncture in the diagnostic process. HSA KIT acts as an exquisite bridge, seamlessly facilitating this transition with a blend of finesse and precision.
HSA KIT paves the way for IHC profiling by identifying cell populations of interest with laser-like precision. Laboratory specialists can initiate IHC analysis on these earmarked populations, applying specific antibodies to elucidate cellular markers and characteristics. This refined level of analysis augments cell classification, providing essential information on protein expression and localization, often pivotal in diagnosing hematological malignancies.
Flow cytometry, a bedrock of hematological diagnosis, finds its perfect complement in HSA KIT. The system simplifies the selection of cells for flow cytometric analysis based on the preliminary classifications. It streamlines the process of antibody staining and data acquisition, ensuring that the data acquired through flow cytometry seamlessly aligns with the microscopic findings, thus enabling a comprehensive characterization of unhealthy cell populations across multiple dimensions
Possibility to analyze further disease patterns with the HSA KIT
Nowadays, immunohematological markers are used to distinguish between blood leukemias.
There are various immunohematological markers used for the classification of leukemias. Here are some of the key markers:
- CD34: CD34 is a surface marker found on stem cells in the bone marrow and peripheral blood. High CD34 expression may indicate acute leukemia.
- CD13 and CD33: These markers are used in the diagnosis and classification of myeloid leukemias. CD13 and CD33 are myeloid antigens and are often analyzed in combination with other markers such as CD14, CD15, and CD64.
- CD19 and CD20: These markers are used in the classification of lymphocytic leukemias, especially B-cell leukemias. CD19 and CD20 are B-cell antigens and can help determine the type of leukemia.
- CD3, CD4, and CD8: These markers are used to differentiate between T-cell leukemias and B-cell leukemias. CD3 is a T-cell antigen, while CD4 and CD8 represent different subsets of T-cells.
- TdT: Terminal Deoxynucleotidyl Transferase (TdT) is a marker for immature precursor cells used in the diagnosis of acute lymphoblastic leukemias (ALL). High TdT expression indicates a tumor population composed of immature lymphoblasts.
These markers are analyzed in immunophenotyping using flow cytometry or immunohistochemistry to obtain information about the cell marker expression in leukemia cells and support the classification of leukemia. However, it is important to note that the specific selection of markers may vary depending on the individual case and the diagnostic criteria of the treating physician.