Texture and moments-based classification of the acrosome integrity of boar spermatozoa images

On The Potential of Image Moments for Medical Diagnosis

Medical imaging is widely used for diagnosis and postoperative or post-therapy monitoring. The ever-increasing number of images produced has encouraged the introduction of automated methods to assist doctors or pathologists. In recent years, especially after the advent of convolutional neural networks, many researchers have focused on this approach, considering it to be the only method for diagnosis since it can perform a direct classification of images. However, many diagnostic systems still rely on handcrafted features to improve interpretability and limit resource consumption. In this work, we focused our efforts on orthogonal moments, first by providing an overview and taxonomy of their macrocategories and then by analysing their classification performance on very different medical tasks represented by four public benchmark data sets. The results confirmed that convolutional neural networks achieved excellent performance on all tasks. Despite being composed of much fewer features than those extracted by the networks, orthogonal moments proved to be competitive with them, showing comparable and, in some cases, better performance. In addition, Cartesian and harmonic categories provided a very low standard deviation, proving their robustness in medical diagnostic tasks. We strongly believe that the integration of the studied orthogonal moments can lead to more robust and reliable diagnostic systems, considering the performance obtained and the low variation of the results. Finally, since they have been shown to be effective on both magnetic resonance and computed tomography images, they can be easily extended to other imaging techniques.

CT Radiomics in Colorectal Cancer: Detection of KRAS Mutation Using Texture Analysis and Machine Learning

In this work, by using descriptive techniques, the characteristics of the texture of the CT (computed tomography) image of patients with colorectal cancer were extracted and, subsequently, classified in KRAS+ or KRAS-. This was accomplished by using different classifiers, such as Support Vector Machine (SVM), Grading Boosting Machine (GBM), Neural Networks (NNET), and Random Forest (RF). Texture analysis can provide a quantitative assessment of tumour heterogeneity by analysing both the distribution and relationship between the pixels in the image. The objective of this research is to demonstrate that CT-based Radiomics can predict the presence of mutation in the KRAS gene in colorectal cancer. This is a retrospective study, with 47 patients from the University Hospital, with a confirmatory pathological analysis of KRAS mutation. The highest accuracy and kappa achieved were 83% and 64.7%, respectively, with a sensitivity of 88.9% and a specificity of 75.0%, achieved by the NNET classifier using the texture feature vectors combining wavelet transform and Haralick coefficients. The fact of being able to identify the genetic expression of a tumour without having to perform either a biopsy or a genetic test is a great advantage, because it prevents invasive procedures that involve complications and may present biases in the sample. As well, it leads towards a more personalized and effective treatment.

Identification of the presence of ischaemic stroke lesions by means of texture analysis on brain magnetic resonance images

•

Radiomics in conventionally segmented tissues can identify MRI scans that had a stroke.

•

Patient’s advanced age can negatively influence classification results.

•

Feature selection and stroke subtype influence but do not determine accuracy.

•

Stroke subtype cannot be ascertained from texture analysis in brain tissues.

Background

The differential quantification of brain atrophy, white matter hyperintensities (WMH) and stroke lesions is important in studies of stroke and dementia. However, the presence of stroke lesions is usually overlooked by automatic neuroimage processing methods and the-state-of-the-art deep learning schemes, which lack sufficient annotated data. We explore the use of radiomics in identifying whether a brain magnetic resonance imaging (MRI) scan belongs to an individual that had a stroke or not.

Materials and methods

We used 1800 3D sets of MRI data from three prospective studies: one of stroke mechanisms and two of cognitive ageing, evaluated 114 textural features in WMH, cerebrospinal fluid, deep grey and normal-appearing white matter, and attempted to classify the scans using a random forest and support vector machine classifiers with and without feature selection. We evaluated the discriminatory power of each feature independently in each population and corrected the result against Type 1 errors. We also evaluated the influence of clinical parameters in the classification results.

Results

Subtypes of ischaemic strokes (i.e. lacunar vs. cortical) cannot be discerned using radiomics, but the presence of a stroke-type lesion can be ascertained with accuracies ranging from 0.7 < AUC < 0.83. Feature selection, tissue type, stroke subtype and MRI sequence did not seem to determine the classification results. From all clinical variables evaluated, age correlated with the proportion of images classified correctly using either different or the same descriptors (Pearson r = 0.31 and 0.39 respectively, p < 0.001).

Conclusions

Texture features in conventionally automatically segmented tissues may help in the identification of the presence of previous stroke lesions on an MRI scan, and should be taken into account in transfer learning strategies of the-state-of-the-art deep learning schemes.

Reliability of an automatic classifier for brain enlarged perivascular spaces burden and comparison with human performance

In the brain, enlarged perivascular spaces (PVS) relate to cerebral small vessel disease (SVD), poor cognition, inflammation and hypertension. We propose a fully automatic scheme that uses a support vector machine (SVM) to classify the burden of PVS in the basal ganglia (BG) region as low or high. We assess the performance of three different types of descriptors extracted from the BG region in T2-weighted MRI images: (i) statistics obtained from Wavelet transform's coefficients, (ii) local binary patterns and (iii) bag of visual words (BoW) based descriptors characterizing local keypoints obtained from a dense grid with the scale-invariant feature transform (SIFT) characteristics. When the latter were used, the SVM classifier achieved the best accuracy (81.16%). The output from the classifier using the BoW descriptors was compared with visual ratings done by an experienced neuroradiologist (Observer 1) and by a trained image analyst (Observer 2). The agreement and cross-correlation between the classifier and Observer 2 (κ = 0.67 (0.58-0.76)) were slightly higher than between the classifier and Observer 1 (κ = 0.62 (0.53-0.72)) and comparable between both the observers (κ = 0.68 (0.61-0.75)). Finally, three logistic regression models using clinical variables as independent variable and each of the PVS ratings as dependent variable were built to assess how clinically meaningful were the predictions of the classifier. The goodness-of-fit of the model for the classifier was good (area under the curve (AUC) values: 0.93 (model 1), 0.90 (model 2) and 0.92 (model 3)) and slightly better (i.e. AUC values: 0.02 units higher) than that of the model for Observer 2. These results suggest that, although it can be improved, an automatic classifier to assess PVS burden from brain MRI can provide clinically meaningful results close to those from a trained observer.

Automatic classification of human sperm head morphology

BACKGROUND AND OBJECTIVE

Infertility is a problem that affects up to 15% of couples worldwide with emotional and physiological implications and semen analysis is the first step in the evaluation of an infertile couple. Indeed the morphology of human sperm cells is considered to be a clinical tool dedicated to the fertility prognosis and serves, mainly, for making decisions regarding the options of assisted reproduction technologies. Therefore, a complete analysis of not only normal sperm but also abnormal sperm turns out to be critical in this context. This paper sets out to develop, implement and calibrate a novel methodology to characterize and classify sperm heads towards morphological sperm analysis. Our work is aimed at focusing on a depth analysis of abnormal sperm heads for fertility diagnosis, prognosis, reproductive toxicology, basic research or public health studies.

METHODS

We introduce a morphological characterization for human sperm heads based on shape measures. We also present a pipeline for sperm head classification, according to the last Laboratory Manual for the Examination and Processing of Human Semen of the World Health Organization (WHO). In this sense, we propose a two-stage classification scheme that permits to classify sperm heads among five different classes (one class for normal sperm heads and four classes for abnormal sperm heads) combining an ensemble strategy for feature selection and a cascade approach with several support vector machines dedicated to the verification of each class. We use Fisher's exact test to demonstrate that there is no statistically significant differences between our results and those achieved by domain experts.

RESULTS

Experimental evaluation shows that our two-stage classification scheme outperforms some state-of-the-art monolithic classifiers, exhibiting 58% of average accuracy. More interestingly, on the subset of data for which there is a total agreement between experts for the label of the samples, our system is able to provide 73% of average classification accuracy.

CONCLUSIONS

We show that our system behaves like a human expert; therefore it can be used as a supplementary source for labeling new unknown data. However, as sperm head classification is still a challenging issue due to the uncertainty on the class label of each sperm head, with the consequent high degree of variability among domain experts, we conclude that there are still opportunities for further improvement in designing a more accurate system by investigating other feature extraction methods and classification schemes.

Acrosome integrity assessment of boar spermatozoa images using an early fusion of texture and contour descriptors

The assessment of the state of the acrosome is a priority in artificial insemination centres since it is one of the main causes of function loss. In this work, boar spermatozoa present in gray scale images acquired with a phase-contrast microscope have been classified as acrosome-intact or acrosome-damaged, after using fluorescent images for creating the ground truth. Based on shape prior criteria combined with Otsu's thresholding, regional minima and watershed transform, the spermatozoa heads were segmented and registered. One of the main novelties of this proposal is that, unlike what previous works stated, the obtained results show that the contour information of the spermatozoon head is important for improving description and classification. Other of this work novelties is that it confirms that combining different texture descriptors and contour descriptors yield the best classification rates for this problem up to date. The classification was performed with a Support Vector Machine backed by a Least Squares training algorithm and a linear kernel. Using the biggest acrosome intact-damaged dataset ever created, the early fusion approach followed provides a 0.9913 F-Score, outperforming all previous related works.

Gold-standard and improved framework for sperm head segmentation

Semen analysis is the first step in the evaluation of an infertile couple. Within this process, an accurate and objective morphological analysis becomes more critical as it is based on the correct detection and segmentation of human sperm components. In this paper, we present an improved two-stage framework for detection and segmentation of human sperm head characteristics (including acrosome and nucleus) that uses three different color spaces. The first stage detects regions of interest that define sperm heads, using k-means, then candidate heads are refined using mathematical morphology. In the second stage, we work on each region of interest to segment accurately the sperm head as well as nucleus and acrosome, using clustering and histogram statistical analysis techniques. Our proposal is also characterized by being fully automatic, where a user intervention is not required. Our experimental evaluation shows that our proposed method outperforms the state-of-the-art. This is supported by the results of different evaluation metrics. In addition, we propose a gold-standard built with the cooperation of a referent expert in the field, aiming to compare methods for detecting and segmenting sperm cells. Our results achieve notable improvement getting above 98% in the sperm head detection process at the expense of having significantly fewer false positives obtained by the state-of-the-art method. Our results also show an accurate head, acrosome and nucleus segmentation achieving over 80% overlapping against hand-segmented gold-standard. Our method achieves higher Dice coefficient, lower Hausdorff distance and less dispersion with respect to the results achieved by the state-of-the-art method.

Preparation of 2D sequences of corneal images for 3D model building

A confocal microscope provides a sequence of images, at incremental depths, of the various corneal layers and structures. From these, medical practioners can extract clinical information on the state of health of the patient's cornea. In this work we are addressing problems associated with capturing and processing these images including blurring, non-uniform illumination and noise, as well as the displacement of images laterally and in the anterior-posterior direction caused by subject movement. The latter may cause some of the captured images to be out of sequence in terms of depth. In this paper we introduce automated algorithms for classification, reordering, registration and segmentation to solve these problems. The successful implementation of these algorithms could open the door for another interesting development, which is the 3D modelling of these sequences.

Assessment of acrosome state in boar spermatozoa heads using n-contours descriptor and RLVQ

This paper proposes a method for assessing the acrosome state of boar spermatozoa heads using digital image processing. We use gray level images in which spermatozoa have been labeled as acrosome-intact or acrosome damaged using the information of a coupled fluorescent image. The heads are segmented obtaining the outer head contour. A set of "n" inner contours separated by a logarithmic distance function is calculated later. For each point of the, in this case, seven contours a number of local texture features are computed. We have compared the classification performance of Relevance Learning Vector Quantization, class conditional means and KNN, employing cross-validation for the evaluation. Gradient magnitude data offer the best result with an overall test error of only 1%. This result outperforms previously applied methods and suggests this approach as an interesting automatized approach to this veterinarian problem.