Machine Learning Approaches for MRI Image Analysis-Based Prostate Cancer Detection

QR image feature extraction effectiveness based on metrics using spectral clustering and grey level Co-Occurrence matrix algorithm

Spinal curvature type can be detected from digital X-ray images. Experts diagnose spinal curvature for a long time to obtain accurate results. This research aims to analyze the use of image processing techniques to extract features in two types of spinal imagery, normal and abnormal (i.e., scoliosis), by applying the Gray Level Co-occurrence Matrix (GLCM) algorithm and Support Vector Machine (SVM) for the classification method. This study used 40 images divided into 4 data sets for analysis. Three distance parameters, 50, 75, and 100 pixels, and three parameters of quantization values, 8, 16, and 32, were utilized for analysis. The highest accuracy obtained from one of the specific data set was 100%, while the highest accuracy of the average of each value distance and quantization was 90%. The GLCM algorithm could differentiate the abnormality of spinal imagery.

Medical imaging is becoming indispensable for patients' healthcare. Machine learning plays an essential role in the medical imaging field, including computer-aided diagnosis, image segmentation, image registration, image fusion, image-guided therapy, image annotation, and image database retrieval. With advances in medical imaging, new imaging modalities and methodologies such as cone-beam/multislice CT, 3D ultrasound imaging, tomosynthesis, diffusion-weighted magnetic resonance imaging (MRI), positron-emission tomography (PET)/CT, electrical impedance tomography, and diffuse optical tomography, new machine-learning algorithms/applications are demanded in the medical imaging field. Because of large variations and complexityit is generally difficult to derive analytic solutions or simple equations to represent objects such as lesions and anatomy in medical images. Therefore, tasks in medical imaging require “learning from examples” for accurate representation of data and prior knowledge. Because of its essential needs, machine learning in medical imaging is one of the most promising, growing fields. The main aim of this special issue is to help advance the scientific research within the broad field of machine learning in medical imaging. The special issue was planned in conjunction with the International Workshop on Machine Learning in Medical Imaging (MLMI 2010) [1], which was the first workshop on this topic, held at the 13th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2010) in September, 2010, in Beijing, China. This special issue is one in a series of special issues of journals on this topic [2]; it focuses on major trends and challenges in this area, and it presents work aimed at identifying new cutting-edge techniques and their use in medical imaging. The quality level of the submissions for this special issue was very high. A total of 17 papers were submitted to this issue in response to the call for papers. Based on a rigorous review process, 10 papers (59%) were accepted for publication in the special issue. The special issue starts by a review of studies on a class of machine-learning techniques, called pixel/voxel-based machine learning, in medical imaging by K. Suzuki. A series of medical imaging applications of machine-learning techniques are presented. A large variety of applications are well represented here, including organ modeling by D. Wang et al. and X. Qiao and Y.-W. Chen, brain function estimation by V. Michel et al., image reconstruction by H. Shouno et al., lesion classification by P. Wighton et al., modality classification by X.-H. Han and Y.-W. Chen, lesion segmentation by M. Zortea et al., organ segmentation by S. Alzubi et al., and visualization of molecular signals by F. Mattoli et al. Also, the issue covers various biomedical imaging modalities, including MRI by D. Wang et al., CT by X. Qiao and Y.-W. Chen and H. Shouno et al., functional MRI by V. Michel et al., dermoscopy by P. Wighton et al. and M. Zortea et al., scintigraphy by X.-H. Han and Y.-W. Chen, ultrasound imaging by X.-H. Han and Y.-W. Chen, radiography by X.-H. Han and Y.-W. Chen, MR angiography by S. Alzubi et al., and microscopy by F. Mattoli et al. as well as a variety of organs, including the kidneys by D. Wang et al., liver by X. Qiao and Y.-W. Chen, brain by V. Michel et al. and F. Mattoli et al., chest by S. Alzubi et al., skin by P. Wighton et al. and M. Zortea et al., and heart by F. Mattoli et al. Various machine-learning techniques were developed/used to solve the respective problems, including structured dictionary learning by D. Wang et al., generalized N-dimensional principal component analysis by X. Qiao et al., multiclass sparse Bayesian regression by V. Michel et al., Bayesian hyperparameter inference by H. Shouno et al., supervised learning of probabilistic models based on maximum aposteriori estimation and conditional random fields by P. Wighton et al., joint kernel equal contribution in support vector classification by X.-H. Han and Y.-W. Chen, and iterative hybrid classification by M. Zortea et al. We are grateful to all authors for their excellent contributions to this special issue and to all reviewers for their reviews and constructive suggestions. We hope that this special issue will inspire further ideas for creative research, advance the field of machine learning in medical imaging, and facilitate the translation of the research from bench to bedside. Kenji Suzuki Pingkun Yan Fei Wang Dinggang Shen

The use of machine learning (ML) has been increasing rapidly in the medical imaging field, including computer-aided diagnosis (CAD), radiomics, and medical image analysis. Recently, an ML area called deep learning emerged in the computer vision field and became very popular in many fields. It started from an event in late 2012, when a deep-learning approach based on a convolutional neural network (CNN) won an overwhelming victory in the best-known worldwide computer vision competition, ImageNet Classification. Since then, researchers in virtually all fields, including medical imaging, have started actively participating in the explosively growing field of deep learning. In this paper, the area of deep learning in medical imaging is overviewed, including (1) what was changed in machine learning before and after the introduction of deep learning, (2) what is the source of the power of deep learning, (3) two major deep-learning models: a massive-training artificial neural network (MTANN) and a convolutional neural network (CNN), (4) similarities and differences between the two models, and (5) their applications to medical imaging. This review shows that ML with feature input (or feature-based ML) was dominant before the introduction of deep learning, and that the major and essential difference between ML before and after deep learning is the learning of image data directly without object segmentation or feature extraction; thus, it is the source of the power of deep learning, although the depth of the model is an important attribute. The class of ML with image input (or image-based ML) including deep learning has a long history, but recently gained popularity due to the use of the new terminology, deep learning. There are two major models in this class of ML in medical imaging, MTANN and CNN, which have similarities as well as several differences. In our experience, MTANNs were substantially more efficient in their development, had a higher performance, and required a lesser number of training cases than did CNNs. "Deep learning", or ML with image input, in medical imaging is an explosively growing, promising field. It is expected that ML with image input will be the mainstream area in the field of medical imaging in the next few decades.

Medical image segmentation is an essential process in disease analysis and diagnosis, in which medical images are divided into specific areas of anatomic or pathological structures. However, this process has challenges, such as the quality, variability, and complexity of medical images. Thus, we propose a medical image segmentation method using the Convolutional Neural Network (CNN) and the Histogram Equalization (HE) image preprocessing. We evaluated medical image segmentation using 2 secondary datasets, namely Lung CT-Scan and Chest X-Rays, with 267 and 3616 images, respectively. The HE method uses an averaging of the optimal cumulative distribution function (CDF) values with a range of 0 to 39. The experimental results show that adding the HE method can increase the accuracy of CNN on the Lung CT-Scan and Chest X-rays data sets, respectively, by 0.73 percentage points from 91.28% to 92.08 % and 1.23 percentage points from 95.56% to 96.85% for the training process. The results of the testing process (validation) have an increase in accuracy of 2.82 percentage points from 89.77% to 92.59% and 0.91 percentage points from 96.06% to 96.97%. Implementing the HE method increases accuracy in CNN medical image segmentation based on the value of dice similarity coefficient (DSC) and structural similarity index measurement (SSIM) close to 0.95.

The aim of this study is to evaluate infected leaf disease images. Precision agriculture's automatic leaf disease detection system employs image acquisition, image processing, image segmentation, feature extraction, and machine learning techniques. An automated disease detection system offers the farmer with a fast and accurate diagnosis of the plant disease. Automation of plant leaf disease detection system is essential for accelerating crop diagnosis. Using machine learning and image processing, this paper describes a framework for detecting leaf illness. An image of a leaf can be used as an input for this framework. To begin, leaf photographs are preprocessed in order to remove noise from their images. The mean filter is used to filter out background noise. Histogram equalization is used to enhance the quality of the image. The division of a single image into multiple portions or segments is referred to as segmentation in photography. It assists in establishing the boundaries of the image. Segmenting the image is accomplished using the K-Means approach. Feature extraction is carried by using the principal component analysis. Following that, images are categorized using techniques such as RBF-SVM, SVM, random forest, and ID3.

Medical imaging is a field of technology which is mainly used to get referential images of human body for medical science and research work. These images are extremely useful for us. We can detect brain tumor in a human body with the help of these MRI Images collected as Big Data. The Automation in this particular area is one of the hot topics of research in Medical Science. These images help us in determining the exact location and area of the weird tissues. Its orientation can also be found out. We can use support vector machine (SVM) for classification, for brain tumor segmentation use fuzzy c-means(FCM) and discrete wavelet transform(DWT). To detect the suspicious region in brain MRI image we need to do clustering and then the features are extracted from the brain image. Feature extraction is a method of capturing visual content of an image. The MRI Images having tumor are downloaded from the internet and the experiment is done on them. After which the SVM technique is used for the classifying the MRI images of brain, which in turn gives a more efficient result with high accuracy for brain MRI image classification and finally the accuracy of both the segmentation algorithms is compared.

This article aims to test FOS (first-order statistical) in extracting features of embryonated eggs. This test uses the initial step of image processing to get the best input image in feature extraction. The image processing method starts from the image acquisition process, then improves with image preprocessing and segmentation. Image acquisition in this study uses the concept of egg candling in a dark place captured with a smartphone camera. The acquisition results are improved by image preprocessing using gray scaling, image enhancement (by Histogram Equalization), and segmentation of chicken egg image. The segmentation results were extracted using FOS with five parameters: mean, entropy, variance, skewness, and kurtosis. Based on the calculation of these parameters, it is graphed and shows the difference in patterns between fertile and infertile eggs. However, some eggs have a similar pattern, thus affecting the identification process. The identification process used neural networks by the backpropagation method for training and testing. The training results provide an accuracy value of 100% of all training data; however, 80% of the new test data obtained test results at testing. This test is carried out with 100 data, 50 each for training and test data. Based on the test results, which significantly affect the level of accuracy is the feature extraction method. FOS pattern in detecting the fertility of chicken eggs by BP Neural Network is still categorized as low, so it is necessary to improve methods to get maximum results.

Segmentation of images is a very important and crucial process involved in the life cycle of medical image processing. It involves the segregation of image components into the desired categories for focusing on the ROI of the image. Though there are a vast amount of work has been done in segmenting the Colon, Rectum areas of MRI and CT images, it’s still a niche area due to the complexity involved in the shape of the organ and the spread of cancer. Segmentation of the rectum area still pose a big challenge. When radiological images are constructed, it’s not possible to capture only the concerned organ (Object) and so it is essential to do segmentation of the required parts for computer-assisted automated diagnosis. When rectum MRI is taken, it’s not possible to focus only on the exact rectum. The MRI scan results not only shows the rectum but also the nearby nodes and organs. Moreover, there are variations in scan report depending on the instrument used from which OEM and how much magnetic field applied in terms of Tesla value. Since MRI is the most preferred radiological report as per the radiologist’s opinion, and MRI is of black and white image with some grey elements present, the colour feature cannot be used in segmenting the region of interest (ROI) and so the features which include the unique properties of the organ under consideration can be obtained either with the shape or texture. As already pointed out, the rectum and the affected area is of irregular in shape and so the shape parameter also cannot be much used in the segmentation and further classification. Thus, the importance and the need of proper segmentation method is required for MRI images. This chapter focuses only on the segmentation of the rectum area MRI images so that it is easier to classify whether the area is benign and malign. The authors have proposed and experimented with the M-R-CNN which is a combination of CNN, ResNet, F-CNN, RPN with masking. The outcome of this research has got better results of segmentation using M-R-CNN with 96% accuracy and precision thus improving the results of the earlier methods discussed in literature survey.

A brain tumor occurs when abnormal cells form within the brain. Many people suffer from brain tumor, and it is a serious and dangerous disease. The detection and classification of brain tumor is an important and difficult task in the medical field. The brain tumor detection technique in the MRI images is very significant in many symptomatic and cure applications. But, as the data in MRI images are of highquality, tumor detection and classification are very hard in this process. Medical imaging plays a major role in properly diagnosing the disease, wherein an essential part in detecting the tumor is image segmentation. The segmentation provides an automatic brain tumor detection technique in order to increase the precision of the yields while also decreasing the diagnosis time. The goal is to detect the tumor from the MRI images and extract the features from the segmented tumor and finally classify it. The image detection and classification process includes image acquisition, image pre-processing, denoising, image segmentation, feature extraction and classification. The input image is pre-processed using Weiner and median filtering and the noise is removed using Edge Adaptive Total Variation Denoising (EATVD) technique. Once the noise is removed from the image, it is used for segmentation process, where Mean Shift Clustering is used. The segmented tumor undergoes features extraction stage, where Gray Level Co- occurrence Matrix (GLCM) features are used. In the last stage, images are classified either as tumorous or non-tumorous. Classification is done using Genetic Algorithm Support Vector Machine (GA-SVM), Deep Learning with Convolutional Neural Network (CNN). Early detection of the tumor region can be achieved without much time lapse in the calculation by using this efficient classifier model. This system presents a prototype for detecting objects based on GA-SVM that classifies images and assesses whether the image is cancerous. While comparing the accuracy and computational time of these classifiers, CNN would provide high accuracy and GASVM with lesser simulation time. The simulation results obtained for brain tumor detection and analysis are done with minimum computational time and with reasonable accuracy. This proposed system is tested using SPL dataset, which consists of 20 cases with 40 image samples of T2 FLAIR weighted MRI image and implemented using MATLAB software.

Accurate detection and classification of clinically significant prostate cancer remain critical challenges in medical imaging. Despite numerous studies focusing on feature extraction and classification, none have systematically assessed the impact of harmonization techniques on multicenter imaging data. This study aimed to improve diagnostic performance by integrating harmonization via unsupervised clustering with clinical variables into machine learning models, even when the source center is unknown. We extracted features from T2-weighted magnetic resonance images using two approaches: handcrafted radiomics and deep learning-based representations obtained via a 3D convolutional autoencoder architecture. To address inter-center variability, the data were harmonized using an unsupervised clustering approach that generated 19 distinct clusters, followed by ComBat harmonization. Machine learning classifiers were then trained with and without the inclusion of clinical variables (prostate-specific antigen levels and patient age). The models were evaluated using multiple metrics. Harmonization significantly improved classification performance. In particular, models based on 3D convolutional autoencoder-derived features achieved an accuracy of 75.33% and an area under the curve (AUC) of 0.74. The incorporation of clinical variables further enhanced model performance; the best model combining radiomics features with clinical data attained an accuracy of 77.67% and an AUC of 0.85. These performance metrics are concurrent with those reported in the literature for this challenge, demonstrating that our novel approach can effectively mitigate inter-center variability and enhance diagnostic accuracy. Our findings underscore the potential of harmonization via unsupervised clustering, combined with the inclusion of clinical variables, to significantly enhance the diagnostic performance of machine learning models for prostate cancer detection. This novel strategy not only addresses a gap in the current literature but also produces performance metrics comparable to those reported in multicenter studies, thereby supporting the development of robust, clinically applicable diagnostic tools.

The rapid development of medical practices and imaging technology tools creates substantial growth in the amount of medical image data each year in our present era. This research aims to develop a hybrid approach that integrates Machine Learning (ML) and Deep Learning (DL) techniques to enhance the accuracy and reliability of medical image classification for diagnostic purposes. Medical imaging data complexity and growing volume serve as the research motivation, which leads to an investigation of standalone ML or DL limitations and their combination into a single framework. The medical image processing starts with normalization, then noise reduction, and continues to grayscale conversion before performing histogram equalization. This research uses VGG16 and ResNet50 alongside MobileNet and InceptionV3 for feature extraction, then applies ten different ML algorithms, including SVM and MLP, and Ran-dom Forest, for classification. Five public medical image datasets from Kaggle are used: COVID-19 chest X-rays, melanoma skin lesions, pneumonia chest X-rays, acute stroke facial images, and various eye diseases. Hybrid models display superior performance compared to stand-alone ML or DL models based on accuracy, precision, recall, and F1-score evaluation measures. Multiple datasets demonstrate that the MobileNet+MLP combination de-livers the most accurate results, which demonstrates its reliable and efficient performance. The developed AI diagnostic tool presents a scalable system alongside accuracy and interpretability to enhance clinical decision outcomes.

Cardiovascular Disease (CVD) is one of the primary diseases that causes death every year. An approximation of roughly about 17.5 million people dies due to CVD, signifying about 31% of global deaths. Based on the statistics, every 34 seconds, a person dies due to heart disease. Various classification algorithms have been developed and utilized as classifiers to support doctors who are ineffectually diagnosed with heart disease. The main aim of this work is to improve the performance of the heart disease approach using image processing algorithm. To improve the effectiveness and efficiency of classification performance for heart disease diagnosis, an optimized neural network was proposed based on the feature extraction and selection approach for handling features. The objective of this investigation is to diagnose heart diseases using feature extraction, reduction based classification and image processing methods. The proposed model comprises of two subsets: Feature extraction using gray scale properties and Moth flame optimization (MFO) for effectual feature selection, followed by a classification technique using Generalized Regression Neural Network. The first system includes three stages: (i) Pre-processing of the dataset (ii) feature extraction (iii) performing MFO for efficient selection. In the second method, GRNN is proposed. The heart data set obtained from ACDC Challenge, was utilized for performing the computation. The image obtained from the MRI-scanner is in the NIfTI image format. The pre-process step used in this is to convert the image type from INT16 to uint8 to improve the quality of image viewing and for feature extraction process. In this phase, the texture properties from the pre-processed image are calculated and the value is in the numeric format. These values are the feature attributes of the dataset. The feature attributes of the image are given as input for the moth flame optimization process and output is the feature selected from the optimization process. The whole process is performed on the feature attributes of the image by determining the optimal feature for the classifier by reducing its error rate. The optimal feature from the moth flame optimization is used for training and testing the network. The classifier used in this approach is a single neural network classifier with a regression nature. Due to the regression property, the network is well trained with the feature. The Generalized regression neural network is used for classifying heart diseases. The proposed method achieves the accuracy of 96.23%, sensitivity of 95.41% and specificity of 96.75%. These values are calculated based on the confusion matrix of the classifier. In this, the feature extraction using the gray scale properties plays an important role to determine the feature attributes from the MRI heart images. The Moth flame optimization able to produce an accuracy of 97.23% using GRNN for classification with minimum single attribute mean of the image. It also outperformed the other methods, either the feature extraction based classification or the feature reduction based classification.

Background: The current standard technique for prostate cancer detection is trans-rectal ultrasound (TRUS) guided biopsy, and is renowned for its low sensitivity. Developments of multiparametric MRI techniques have increased the detection of significant prostate cancer. Currently there are three techniques utilizing MRI for targeted biopsy; MRI-TRUS fusion; ‘cognitive’ TRUS, and in-bore MRI guided biopsy. There is no consensus which should be preferred. The current study aims to compare prostate cancer detection rates of three target biopsy procedures. Methods: The FUTURE trial is a three-arm randomised controlled, multicentre trial comparing three techniques of MRI targeted biopsy of the prostate amongst subjects with one prior negative TRUS biopsy and a persisting suspicion on prostate cancer. All subjects undergo mpMRI imaging. Images will be centrally reviewed, and evaluated using the ‘Prostate imaging reporting and data system’. An estimated 69% of the subjects will demonstrate tumour suspicious findings on mpMRI, and will be randomised 1:1:1. The primary objective is to compare (significant) tumor detection rates of the three techniques. Secondary objectives include histopathological validation of mpMRI imaging and PI-RADS classification, a cost-effectiveness analysis, and follow-up after a negative mpMRI or negative target biopsy. All biopsy cores will be evaluated by one dedicated uro-pathologists per center. Two sub-investigations were based on the hypothesis that MRI-TRUS fusion and in-bore MRI biopsy demonstrate similar tumor detection, whilst MRI-TRUS fusion demonstrates increased tumor detection compared to ‘cognitive’ TRUS biopsy. A total number 466 of subjects is needed for equal randomization. Assuming that 69% of subjects have tumor suspicious findings on MRI imaging, a total of 675 subjects are required for inclusion. Discussion: For target biopsy procedures of the prostate the ultimate comparator is histopathological examination of radical prostatectomy specimens, though this leads to insurmountable ethical objections and thus to a methodological dilemma concerning validation.

Various machine learning methods have been proposed for predicting progression of patients with mild cognitive impairment (MCI) to Alzheimer's disease (AD) using neuroimaging data. Even though the vast majority of these works use the public dataset ADNI, reproducing their results is complicated because they often do not make available elements that are essential for reproducibility, such as selected participants and input data, image preprocessing and cross-validation procedures. Comparability is also an issue. Specially, the influence of different components like preprocessing, feature extraction or classification algorithms on the performance is difficult to evaluate. Finally, these studies rarely compare their results to models built from clinical data only, a critical aspect to demonstrate the utility of neuroimaging. In our previous work, 1, 2 we presented a framework for reproducible and objective classification experiments in AD, that included automatic conversion of ADNI database into the BIDS community standard, image preprocessing pipelines and machine learning evaluation. We applied this framework to perform unimodal classifications of T1 MRI and FDG-PET images. In the present paper, we extend this work to the combination of multimodal clinical and neuroimaging data. All experiments are based on standard approaches (namely SVM and random forests). In particular, we assess the added value of neuroimaging over using only clinical data. We first demonstrate that using only demographic and clinical data (gender, education level, MMSE, CDR sum of boxes, ADASCog) results in a balanced accuracy of 75% (AUC of 0.84). This performance is higher than that of standard neuroimaging-based classifiers. We then propose a simple trick to improve the performance of neuroimaging-based classifiers: training from AD patients and controls (rather than from MCI patients) improves the performance of FDG-PET classification by 5 percent points, reaching the level of the clinical classifier. Finally, combining clinical and neuroimaging data, prediction results further improved to 80% balanced accuracy and an AUC of 0.88). These prediction accuracies, obtained in a reproducible way, provide a base to develop on top of it and, to compare against, more sophisticated methods. All the code of the framework and the experiments is publicly available at https://github.com/aramis-lab/AD-ML