Hyperspectral Imaging System for Tissue Classification in H&amp;E-Stained Histological Slides

Souza, Mateus Martelini; Carvalho, Felipe Alvarenga; Sverzut, Enzo Fabro Vanzela; Requena, Michelle Barreto; Garcia, Marlon Rodrigues; Pratavieira, Sebastião

doi:10.1109/sbfotoniopc50774.2021.9461972

Cited by 3 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…21 This method has shown great promise, in comparison with others, in the classification of histological image data in recent papers, including blood smears. 14,[22][23][24] After classification, the resulting binary image was submitted to a morphological opening (an erosion followed by dilation) by a (5, 5) kernel of ellipsoidal format, followed by a connected components analysis (CCA) with statistics, both functions available on OpenCV library. The opening kernel was an ellipsoidal one, with a size of (5,5), and the parameters of connectivity and ltype, for CCA, as being to 8 and CV 32S, respectively.…”

Section: Image Segmentationmentioning

confidence: 99%

White blood cells segmentation and classification using a random forest and residual networks implementation

Rodrigues Garcia,

Ponce Ayala,

Pratavieira

et al. 2024

Computational Optical Imaging and Artificial Intelligence in Biomedical Sciences

View full text Add to dashboard Cite

Artificial intelligence algorithms are interesting solutions to automate the tedious manual counting of white blood cells by a specialist. Although interesting machine learning algorithms have been proposed for this task, there is a lack in the literature for high-accuracy methods (more than 99%) tested on larger datasets (more than 10 thousand images). This paper presents a segmentation and classification methodology, based on Random Forest and ResNet50, along with a comparison between ResNet models with different numbers of layers. The segmentation was tested in microscope-like images mounted using multiple single-cell images, widely available in online datasets, yielding 300×300 images to be classified by the residual network. For image classification, ResNet50 reached higher accuracies (99.3%, to the best of our knowledge, the higher accuracy for models with more than 1000 images), with the model size comparison pointing to model overfitting for larger models.

show abstract

Section: Image Segmentationmentioning

confidence: 99%

White blood cells segmentation and classification using a random forest and residual networks implementation

Rodrigues Garcia,

Ponce Ayala,

Pratavieira

et al. 2024

Computational Optical Imaging and Artificial Intelligence in Biomedical Sciences

View full text Add to dashboard Cite

show abstract

“…Hyperspectral imaging (HSI) is a method for capturing images of an object at many wavelengths and getting spectral data for each pixel [Wei, et al (2019)]. It has many applications in agriculture, environment, food detection, and medical field etc., in the medical field like digital pathology, surgery visualization, tissue condition diagnosis, brain cancer detection, and skin cancer detection [Souza, et al (2021)]. In medical imaging, in recent years hyperspectral images are giving the best results.…”

Section: Introductionmentioning

confidence: 99%

Gradient Boosting Ensembled Method for in-Vivo Brain Tumour Classification Using Hyperspectral Images

Tejasree¹,

Agilandeeswari²

2022

INDJCSE

View full text Add to dashboard Cite

In the past few years, the use of hyperspectral imaging for medicinal purposes has increased. Hyperspectral imaging is a trending topic in the remote sensing field. It is used to collect the spectral information present in the scene. Additionally, the combination of spectral and spatial data offers valuable data for classifying brain tumours. When combined with Machine Learning (ML) algorithms, HSI (Hyperspectral Imaging) can be utilised as a non-intrusive medical diagnosis tool. By using hyperspectral images in the medical field, we can classify cancers, tissues, blood vessels etc. This paper offers a gradient boosting based ensembled classification (MCGC) scheme for In-Vivo brain cancer classification. And also, a multi-scale CNN method feature extraction and graph-based clustering method for feature selection are applied to get accurate classification results. The dataset used for brain cancer classification is the In-Vivo brain cancer dataset. These dataset images are captured when the real-time brain tumour surgery was going on. Finally, we performed the experiment results of gradient boosting ensembled classification methods. Support vector machine (SVM) and Random Forest (RF) classification methods were used to compare the outcomes of classification. And in comparison, with the other existing methods, we got good outcomes.

show abstract

Lightweight Deep Learning Model Optimization for Medical Image Analysis

Al‐Milaji,

Yousif

2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Medical image labeling requires specialized knowledge; hence, the solution to the challenge of medical image classification lies in efficiently utilizing the few labeled samples to create a high‐performance model. Building a high‐performance model requires a complicated convolutional neural network (CNN) model with numerous parameters to be trained which makes the test quite expensive. In this paper, we propose optimizing a lightweight deep learning model with only five convolutional layers using the particle swarm optimization (PSO) algorithm to find the best number of kernel filters for each convolutional layer. For colored red, green, and blue (RGB) images acquired from different data sources, we suggest using stain separation using color deconvolution and horizontal and vertical flipping to produce new versions that can concentrate the representation of the images on structures and patterns. To mitigate the effect of training with incorrectly or uncertainly labeled images, grades of disease could have small variances, we apply a second‐pass training excluding uncertain data. With a small number of parameters and higher accuracy, the proposed lightweight deep learning model optimization (LDLMO) algorithm shows strong resilience and generalization ability compared with most recent research on four MedMNIST datasets (RetinaMNIST, BreastMNIST, DermMNIST, and OCTMNIST), Medical‐MNIST, and brain tumor MRI datasets.

show abstract

Hyperspectral Imaging System for Tissue Classification in H&E-Stained Histological Slides

Cited by 3 publications

References 9 publications

White blood cells segmentation and classification using a random forest and residual networks implementation

White blood cells segmentation and classification using a random forest and residual networks implementation

Gradient Boosting Ensembled Method for in-Vivo Brain Tumour Classification Using Hyperspectral Images

Lightweight Deep Learning Model Optimization for Medical Image Analysis

Contact Info

Product

Resources

About