In Search of the Monolayer - Utilizing Deep Learning to efficiently locate the Monolayer on Peripheral Blood Films
(2025) In Master’s Theses in Mathematical Sciences FMAM05 20242Mathematics (Faculty of Engineering)
- Abstract
- A Peripheral Blood Film (PBF) examination with differential count (DIFF) is a common blood test, yielding quantitative and qualitative information about the blood cells of the patient important for diagnostics. The test relies on locating the monolayer, an area on the PBF slide where the cells are located in one layer. This masters thesis explores the possibilities of adopting Machine Learning (ML) to locate the monolayer on a PBF slide in a commercially available microscopic system for medical analysis. Over two million microscopic images from 972 PBF slides were collected through the system, to be used as data. Several deep learning models including Convolutional Neural Networks (CNNs), Long-Short-Term-Memory Networks (LSTMs) and... (More)
- A Peripheral Blood Film (PBF) examination with differential count (DIFF) is a common blood test, yielding quantitative and qualitative information about the blood cells of the patient important for diagnostics. The test relies on locating the monolayer, an area on the PBF slide where the cells are located in one layer. This masters thesis explores the possibilities of adopting Machine Learning (ML) to locate the monolayer on a PBF slide in a commercially available microscopic system for medical analysis. Over two million microscopic images from 972 PBF slides were collected through the system, to be used as data. Several deep learning models including Convolutional Neural Networks (CNNs), Long-Short-Term-Memory Networks (LSTMs) and Transformer encoders were trained to traverse the slide. A regression model constructed using classical machine learning techniques such as Support Vector Regression (SVR), Gradient Boosting (GB) and Random Forests (RF) were developed to be able to predict a good starting position for the search using overview images of the PBF slides. The results showed a great improvement in the efficiency of the search. A combination of using a SVR to find a start position and an LSTM model to traverse the slide produced the best result with a time reduction of over 50% with higher average quality of the monolayers found, compared to the current implemented solution. We also provide an in-depth analysis showing that our models remain robust with good results across a wide range of different PBF types. This study highlights a new use case of machine learning in automated hematology systems. (Less)
- Popular Abstract
- Blood tests are a cornerstone of modern healthcare, helping doctors diagnose everything from infections to chronic diseases. One important test, the Peripheral Blood Film (PBF) examination, uses a microscope to assess the size, shape, and ratio of different blood cells. However, for accurate results, the microscope must analyze a small, specific region of the slide called the monolayer, where cells are evenly spread out in a single layer.
Finding this region efficiently is a challenge as the monolayer usually only spans 3 mm out of the 35 mm slide. Traditionally, automated systems rely on pre-set scanning patterns to locate the monolayer, but this process can be slow and sometimes inaccurate. This thesis explores how to improve this... (More) - Blood tests are a cornerstone of modern healthcare, helping doctors diagnose everything from infections to chronic diseases. One important test, the Peripheral Blood Film (PBF) examination, uses a microscope to assess the size, shape, and ratio of different blood cells. However, for accurate results, the microscope must analyze a small, specific region of the slide called the monolayer, where cells are evenly spread out in a single layer.
Finding this region efficiently is a challenge as the monolayer usually only spans 3 mm out of the 35 mm slide. Traditionally, automated systems rely on pre-set scanning patterns to locate the monolayer, but this process can be slow and sometimes inaccurate. This thesis explores how to improve this search process, aiming to make it faster and more accurate through machine learning (ML).
We trained deep learning models to navigate the slide, using advanced techniques like Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. Additionally, we investigated the use of an overview camera, which captures a macroscopic image of the entire slide, and applied classical machine learning models to predict an optimal starting position before zooming in for a detailed microscopic search.
The results are highly promising. By combining a Support Vector Regression (SVR) model for predicting the best starting position with an LSTM model for guiding the search, we cut the search time in half while also improving accuracy. Our approach worked well across different types of blood samples, showing its potential for real-world medical applications.
This research highlights how AI-driven automation can enhance traditional diagnostic tools, paving the way for faster, more reliable blood analysis—helping doctors diagnose conditions more efficiently and improving patient care. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9187028
- author
- Larsson, Viktor and Nauclér, Gustav LU
- supervisor
- organization
- course
- FMAM05 20242
- year
- 2025
- type
- H2 - Master's Degree (Two Years)
- subject
- publication/series
- Master’s Theses in Mathematical Sciences
- report number
- LUTFMA-3570-2025
- ISSN
- 1404-6342
- other publication id
- 2025:E13
- language
- English
- id
- 9187028
- date added to LUP
- 2025-09-15 11:14:37
- date last changed
- 2025-09-15 11:14:37
@misc{9187028,
abstract = {{A Peripheral Blood Film (PBF) examination with differential count (DIFF) is a common blood test, yielding quantitative and qualitative information about the blood cells of the patient important for diagnostics. The test relies on locating the monolayer, an area on the PBF slide where the cells are located in one layer. This masters thesis explores the possibilities of adopting Machine Learning (ML) to locate the monolayer on a PBF slide in a commercially available microscopic system for medical analysis. Over two million microscopic images from 972 PBF slides were collected through the system, to be used as data. Several deep learning models including Convolutional Neural Networks (CNNs), Long-Short-Term-Memory Networks (LSTMs) and Transformer encoders were trained to traverse the slide. A regression model constructed using classical machine learning techniques such as Support Vector Regression (SVR), Gradient Boosting (GB) and Random Forests (RF) were developed to be able to predict a good starting position for the search using overview images of the PBF slides. The results showed a great improvement in the efficiency of the search. A combination of using a SVR to find a start position and an LSTM model to traverse the slide produced the best result with a time reduction of over 50% with higher average quality of the monolayers found, compared to the current implemented solution. We also provide an in-depth analysis showing that our models remain robust with good results across a wide range of different PBF types. This study highlights a new use case of machine learning in automated hematology systems.}},
author = {{Larsson, Viktor and Nauclér, Gustav}},
issn = {{1404-6342}},
language = {{eng}},
note = {{Student Paper}},
series = {{Master’s Theses in Mathematical Sciences}},
title = {{In Search of the Monolayer - Utilizing Deep Learning to efficiently locate the Monolayer on Peripheral Blood Films}},
year = {{2025}},
}