Mining textural knowledge in biological images: Applications, methods and trends

Cataldo, Santa Di; Ficarra, Elisa

doi:10.1016/j.csbj.2016.11.002

Cited by 54 publications

(49 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…More specifically, we implemented a Bag Of Features (BOF) framework leveraging SURF, a scale-and rotation-invariant keypoint detector and descriptor [6,31], and a support vector machine classifier. This is a consolidated approach to histological image classification [4,5].…”

Section: Traditional Machine Learning Approachmentioning

confidence: 99%

“…Image texture provides information about the spatial arrangement of color or intensities in an image. Hence, when applied to histological images, it can be used to characterize the spatial arrangement of the cells or in general the architecture of a tissue [5]. Systems based on texture analysis, as the name suggests, leverage the extraction of a limited set of texture and morphometric descriptors from the histological images; for example, statistic descriptors based on the Grey-Level Co-occurrence Matrices (GLCM), Local Binary Patterns (LBPs) and its variants, features based on Gabor or wavelet transform, and key-point detectors and descriptors such as Speeded-Up Robust Features (SURF) [6,7].…”

Section: Introductionmentioning

confidence: 99%

“…The major issue of all the classical texture-analysis approaches is typically the dependency on a fixed set of handcrafted features for the image representation [4,5]. Indeed, pre-designing the features based on a priori assumptions on the patterns that are most important for the classification intrinsically limits the robustness and generalization capabilities of a system.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dealing with Lack of Training Data for Convolutional Neural Networks: The Case of Digital Pathology

et al. 2019

Self Cite

View full text Add to dashboard Cite

Thanks to their capability to learn generalizable descriptors directly from images, deep Convolutional Neural Networks (CNNs) seem the ideal solution to most pattern recognition problems. On the other hand, to learn the image representation, CNNs need huge sets of annotated samples that are unfeasible in many every-day scenarios. This is the case, for example, of Computer-Aided Diagnosis (CAD) systems for digital pathology, where additional challenges are posed by the high variability of the cancerous tissue characteristics. In our experiments, state-of-the-art CNNs trained from scratch on histological images were less accurate and less robust to variability than a traditional machine learning framework, highlighting all the issues of fully training deep networks with limited data from real patients. To solve this problem, we designed and compared three transfer learning frameworks, leveraging CNNs pre-trained on non-medical images. This approach obtained very high accuracy, requiring much less computational resource for the training. Our findings demonstrate that transfer learning is a solution to the automated classification of histological samples and solves the problem of designing accurate and computationally-efficient CAD systems with limited training data.

show abstract

Section: Traditional Machine Learning Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dealing with Lack of Training Data for Convolutional Neural Networks: The Case of Digital Pathology

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…The prime focus of this method is to detect, isolate distinct portions and features of images. The features extracted are then fed into machine learning algorithm for classification [23] [24].…”

Section: Feature Extractionmentioning

confidence: 99%

TADOC : Tool for Automated Detection of Oral Cancer

Sattar¹

2020

IJACSA

View full text Add to dashboard Cite

Cancer is a group of related diseases and it is necessary to classify the type and its impact. In this paper an automated learning-based system for detection of oral cancer from Whole Slide Images (WSI) has been designed. The main challenges of the system were to handle the huge dataset and to train the machine learning model as it consumed more time for each iteration involved. This further increased the time consumed to get a proper model and decrease of freedom for experimentation. Other important key features of the system were to implement a futuristic deep learning architecture to classify small patches from the large whole slide images and use of carefully designed post-processing methods for the slide-based classification.

show abstract

“…Thus, the texture brings important information about the meat. Texture within the context of this review is defined as non-random arrangement of entities with given distribution of intensities and shapes, see Figure 2b,c for example, (Di Cataldo & Ficarra, 2017).…”

Section: Assessment Of Meat Textural Characteristicsmentioning

confidence: 99%

Chemometrics and hyperspectral imaging applied to assessment of chemical, textural and structural characteristics of meat

et al. 2018

View full text Add to dashboard Cite

Spectroscopy in the visible near-infrared spectral (Vis-NIRS) range combined with imaging techniques (hyperspectral imaging, HSI) allows assessment of chemical composition, texture, and meat structure. The use of HSI in the meat and food industry has observed a significant growth in the last decade, yet its use for assessment of meat it is not optimal yet. The application of HSI for assessment of meat is reviewed with focus on its ability to capture meat unique chemical and structural characteristics. While HSI is widely used for assessment of chemical composition, a limited number of evidences on its ability to handle the effect of different sources of variation on the assessment is found. The use of spatially resolved spectroscopy has been able to detect structural information related to animal background, muscle type, rigor process and ageing. Similarly the use of texture features seem to capture unique characteristics of meat.

show abstract

Mining textural knowledge in biological images: Applications, methods and trends

Cited by 54 publications

References 87 publications

Dealing with Lack of Training Data for Convolutional Neural Networks: The Case of Digital Pathology

Dealing with Lack of Training Data for Convolutional Neural Networks: The Case of Digital Pathology

TADOC : Tool for Automated Detection of Oral Cancer

Chemometrics and hyperspectral imaging applied to assessment of chemical, textural and structural characteristics of meat

Contact Info

Product

Resources

About